- Current Issue
- Online First
- Adopt
- Most Downloaded Archive
-
Xue Yuan, Chen Zhigang, Wang Yanxue, Shi Mengyao
2024,47(9):1-7, DOI:
Abstract:
In response to the problem that rolling bearing vibration signal characteristics were difficult to be extracted in the case of strong noise, a method based on composite spectral kurtosis to optimise the variational modal decompositionwas proposed. First, the original fault signal was subjected to variational modaldecomposition, and several intrinsic mode functionswere acquired by optimizing the key parameters of VMD-modal numberand penalty factorrespectively with the principle of the maximum value of composite spectral kurtosis. Then, the kurtosis of each IMFwas calculated, and the component with the maximum kurtosis value was selected as the optimal IMF. Finally, the Hilbert transform was performed on the optimal intrinsic modal function to obtain their envelope spectra, so as to realize the extraction of the fault eigenfrequency. Through the analysis of the public dataset and the relevant data of the homemade test bed, it is shown that the proposed method can effectively extract the fault characteristics of the fault signal under the background of strong noise and realize the discrimination of the fault type.
-
Qiu Ling, Lyu Shuang, Yang Xue, Xie Xiaolin, Xiang Xiaoming
2024,47(9):8-17, DOI:
Abstract:
To fully leverage the business application capabilities of standard format radar PUP products, the visualization application system of PUP products of standard format weather radar is designed and developed. The overall architecture of the system, as well as solutions for the collection, decoding, processing, and sharing of standard format radar PUP products, were researched and designed. Considering the large volume of data characteristic of standard format radar PUP products, an improved RLE compression algorithm and an optimized radar image rendering method were proposed to effectively enhance the efficiency of product image display and achieve efficient visualization applications of standard format radar PUP products. Based on the B/S architecture, the system′s functionalities were implemented using mature technologies such as SpringMVC framework, HTML5, CSS, and WebGIS. It provides rich radar PUP product overlay display and sharing applications with GIS data for users across the province. Additionally, it offers layered overlay applications of ground observation data, lightning data, and radar PUP products. Upon deployment, it received positive feedback from meteorological business users, effectively enhancing the forecasting and warning capabilities for severe convective weather and hazardous weather events. The system has achieved early implementation of the standard format radar PUP product in the operational applications of meteorological departments nationwide, providing valuable reference for the visualization standard format radar PUP products in other provinces. It has broad application value for promotion.
-
Li Jiarun, Chen Yong, Chen Guang, Qiu Zizhen, Zhao Lei, Zhang Liming
2024,47(9):18-25, DOI:
Abstract:
A proportional resonance self immunity control strategy is proposed to solve the problem of a large number of low-frequency harmonics caused by the nonlinearity of the drive motor inverter and the non-sinusoidal waveform of the back electromotive force. This strategy can suppress the current harmonics more comprehensively, while the introduction of resonance control can provide better suppression of specific frequency harmonics. A mathematical model of the motor system is established. Based on the Maxwell tensor method, the analytical equation of the electromagnetic force is deduced. It is analyzed that the 5th and 7th harmonics will deteriorate the performance of the motor in terms of torque pulsation and electromagnetic noise. A multi-physical field co-simulation model using Simulink and Jmag is established. Simulation analysis is conducted to validate the theoretical analysis and the effectiveness of harmonic suppression in reducing torque pulsation and electromagnetic noise.An experimental platform is set up to analyze the current and electromagnetic noise results before and after applying the strategy. The results indicate that the control strategy constructed has a better suppression effect on the harmonic components of the main order of low frequency, and optimizes the low frequency noise characteristics of the motor.
-
Li Qian, Chen Fulong, Zheng Liang, Zhao Falong, Chen Zhijun
2024,47(9):26-32, DOI:
Abstract:
In various applications of mobile robotics, such as automated warehousing logistics scenarios, due to the limitation of lidar installation location. The adoption of a single LiDAR for Simultaneous Localization and Mapping (SLAM) introduces challenges pertaining to restricted field of view and complexities in achieving loop closure. In response, we proposes a multi-LiDAR localization and mapping methodology incorporating tight coupling with an Inertial Measurement Unit (IMU), building upon the FAST-LIO2 algorithm. This approach not only expands the perceptual range of the robot but also enhances localization precision and mapping effect. Through rigorous evaluation via offline tests utilizing public datasets and online experiments conducted on the experimental platform, the proposed algorithm demonstrates marked enhancements in localization accuracy and mapping effect compared to the M-LOAM and FAST-LIO2 algorithms, concurrently exhibiting reduced loop closure drift.
-
Wu Teng, Dong Minggang, Li Guanglin, Cao Jianglang, Fang Peng
2024,47(9):33-39, DOI:
Abstract:
Electrical stimulation technology has significant application value in clinical rehabilitation of motor function, and the development of advanced electrical stimulation systems is crucial for achieving precise and efficient neuromuscular electrical stimulation. This work combines digital signal synthesis and a constant current source circuit model to design a multi parameter adjustable electrical stimulation system with small output current error. The system can output three waveforms: square wave, triangular wave, and sine wave. The output current error is less than 0.5%, and the maximum output impedance is 4 000 Ω. The frequency error in the range of 10~500 Hz is less than 0.5% for square wave, less than 1% for triangular wave, and less than 3% for sine wave. Compared with KT-90A and PE1-2 medical grade electric stimulators, the system still maintains high current accuracy at a minimum output impedance of 2 000 Ω, and the waveform is not distorted. The system was applied to neuromuscular functional electrical stimulation experiments, and the effectiveness of the system in clinical rehabilitation applications was verified by analyzing the waveform and energy spectrum of EEG waves. This work is expected to provide technical support for the clinical application of electrical stimulation rehabilitation intervention.
-
Li Yumiao, Wang Huizhen, Xue Jialu, Xing Shaohua, Liu Yufeng
2024,47(9):40-45, DOI:
Abstract:
This paper presents a novel approach to the design of a 4×4 slot array antenna operating at 5.8 GHz, utilizing a slot element based on the Koch Snowflake hexagonal fractal structure. The antenna is fed by a parallel feeding network, resulting in characteristics of high directivity. The proposed design was experimentally validated through fabrication and testing. Measurement results indicate a 5.7% impedance bandwidth (5.56~5.89 GHz) with well-matched impedance. At the operating frequency, the antenna exhibits commendable directional radiation characteristics and stable gain, achieving a peak gain of 19.85 dBi and a corresponding aperture efficiency of 80.69%. Moreover, the 3.dB gain bandwidth extends to 18.40% (5.13~6.20 GHz), demonstrating the efficacy of the Koch Snowflake fractal structure in enhancing the performance of slot array antennas.
-
Liu Zhongying, Zhai Pengfei, Hou Weiyan
2024,47(9):46-51, DOI:
Abstract:
Stacked plate are counted by hand, which takes long time and has poor accuracy. Hence, the paper proposes a plate counting instrument based on embedded platform with a lightweight model. The instrument can detect in real time the number of stacked plate at production and logistics site, which deploys the improved Faster R-CNN network to the Industrial Personal Computer.In order to alleviate the difficulty of small object detection, the network algorithm by using lightweight network MobileNetv2 to integrate the efficient channel attention as the backbone network, using spatial attention and inverted residual structure module to reconstruct the FPN structure, proposing an HIOU_Loc algorithm based on on Height intersection over union to remove redundant prediction boxes. The plate counting experiment on a IPC equipped with N4100 CPU. The results show that the accuracy of the plate counting algorithm proposed in this paper reaches 98.51%, and it only takes 0.31 s to detect a high-resolution plate image. A quantitative calibration module is designed for the instrument. The instrument can reach 100% accuracy in counting stacked plate after the manual calibration module, which meets the requirements of stacked plate real-time counting in practical scenarios.
-
Guo Xinyan, Zhu Shuo, Sun Jiahao, Liang Jifeng, Wang Zongyang
2024,47(9):52-60, DOI:
Abstract:
To address the issue of low vehicle detection accuracy in road surveillance, this paper proposes an improved vehicle detection method based on YOLOv7. Firstly, we introduce the Efficient Multi-Scale Attention Mechanism (EMA) for cross-space learning to enhance attention to feature information. Secondly, we replace the SPPCSPC module in the neck network with the SPPFCSPC module, trim the CBS layer, and introduce the EMA attention mechanism to strengthen attention to small target areas, thereby obtaining more accurate vehicle features. Additionally, we incorporate the EMA attention into the MP module to fuse more important feature information. Finally, employing the MPDIoU loss function accelerates model convergence and enhances detection accuracy. Experimental results show that the improved YOLOv7 achieves a detection accuracy of 86.69%, which is a 2.83% improvement over the original YOLOv7 network. This enhancement effectively boosts the accuracy of vehicle object detection, providing assurance for applications such as road video surveillance.
-
Bai Long, Yu Bin, Gao Feng, Gu Jinhao, Xu Jie
2024,47(9):61-69, DOI:
Abstract:
The accurate prediction of PV power is very important for the safe and stable operation and real-time control of the integrated energy system. In order to solve the problems of noise interference in photovoltaic power prediction and poor prediction accuracy of traditional single prediction model, a short-term photovoltaic power prediction model based on ICEEMDAN and TCN-AM-BiGRU is proposed. Firstly, the Pearson correlation coefficient was used to screen the key meteorological factors, and the historical PV power data were divided into three similar days: sunny, cloudy and rainy by fuzzy C-means clustering. Secondly, ICEEMDAN is used to decompose the historical training set into several regular subsequences and reconstruct them according to the permutation entropy. Finally, the sequence features are extracted by TCN, the attention mechanism is introduced to assign different weights, and then the prediction is made by BiGRU to output the final prediction result. Taking the actual data of a photovoltaic power station as an example, the prediction model and other models were verified and analyzed. The results showed that in sunny, cloudy and rainy weather, compared with other comparison models, the accuracy of the proposed model increased by 1.69%, 3.58% and 4.40% on average, the MAE decreased by 57.61%, 36.83% and 40.94% on average, and the RMSE decreased by 56.90%, 34.30% and 36.63% on average, which verified the effectiveness and superiority of the proposed model.
-
Liu Hongkai, Wang Shaohong, Zuo Yunbo, Gu Yuhai
2024,47(9):70-78, DOI:
Abstract:
Lidar point cloud segmentation technology plays an important role in intelligent vehicle environment recognition. Due to the problems of near dense and far sparse point clouds, uneven distribution, and the presence of noise in LiDAR, inaccurate point cloud segmentation occurs. A self adaptation DBSCAN with Euclidean joint clustering algorithm is proposed to address the above issues. This method first preprocesses the point cloud data, using through filtering, voxel filtering, and cube filtering to extract, sparse, and denoise the point cloud. Then, it combines the adaptive DBSCAN algorithm and an improved variable threshold Euclidean clustering algorithm to cluster and segment the point cloud. Real scene data was collected for testing, and the results showed improvements in evaluation indicators such as C-H coefficient, contour coefficient, D-B coefficient, and contour coefficient. This indicates that the variable threshold joint clustering algorithm significantly improves the accuracy of point cloud segmentation, effectively improves the intra class consistency and inter class differences of clustering results, and provides a more reliable foundation for object detection and recognition.
-
2024,47(9):79-84, DOI:
Abstract:
With regard to the problem of tracking telemetry and command instruments in accuracy evaluation, put forward an adoption double the satellite navigate a measuring of receiver to control the project of equiping the accuracy acceptance, give accuracy acceptance of general process, deduced in detail a kind of differ from traditional of the true value compute a new method, and provided the concrete calculate way and model of this method.The foundation analyzed in the theory up, adoption calculate the example carry on calculation and analysis and express as a result according to the double the satellite navigates a receiver of measure to control to equip an accuracy acceptance method, can in advance according to measuring the accuracy index sign of controling the material, analysis need the satellite navigates a receiver of index sign, can also provide a metered data to prop up for route design at the same time, save to measure to control the manpower and material resources of equiping the accuracy acceptance, can be measuring to control the related realm expansion application of instruments accuracy evaluation.
-
Wang Liyong, Wang Hongxuan, Su Qinghua, Wang Shentong, Zhang Pengbo
2024,47(9):85-92, DOI:
Abstract:
With the in-depth application of mobile robot in production and life, its path planning ability also needs to develop to both rapidity and environmental adaptability. In order to solve the problems existing in the existing mobile robot path planning using reinforcement learning methods, which are easy to fall into local optimization in the early stage of exploration, repeatedly search the same area, and explore the late convergence rate and slow convergence rate, an improved Q-Learning algorithm is proposed in this study. The algorithm improves the Q matrix assignment method to make the exploration process directional in the early iteration and reduces the collision situation; the Q matrix iterative method is improved to make the Q matrix update forward-looking and avoid repeated exploration in a small area; the random exploration strategy is improved to make full use of environmental information in the early iteration and close to the target point in the later stage. The simulation results of different raster maps show that the algorithm in this paper has higher computational efficiency by reducing the path length, reducing jitter and improving the speed of convergence based on the Q-Learning algorithm.
-
Su Pengjian, Ma Haiqin, Ye Junming
2024,47(9):93-97, DOI:
Abstract:
The rapid expansion of the application range of unmanned systems makes the visual perception environment more complex and changeable, which makes it difficult for traditional visual control algorithms to effectively control visual sensors to obtain accurate visual perception images, thus affecting the stable operation of unmanned systems. Therefore, the research on intelligent visual control algorithms based on unmanned systems is proposed. The gray value of the visual perception image of unmanned system is transformed by Gamma curve nonlinear, and the contrast of the image is enhanced by the gray world method. Based on the processed image, the image moment is calculated, namely the space moment, the central moment and the normalized central moment, to describe the global and local characteristics of the image. According to the obtained visual perception information of the unmanned system, the intelligent visual control framework is built. Obtain the desired image feature matrix, extract the current moment image feature matrix, and nonlinear map the camera angle through the extreme learning machine based on the improved firefly algorithm, so as to obtain the intelligent vision control law, so as to eliminate the visual perception image error and realize the effective control of intelligent vision. The experimental results show that under the background of different experimental groups, the minimum average time of visual control obtained by the proposed algorithm reaches 1 s, and the minimum average error of visual control reaches 0.12%, which fully confirms the better application performance of the proposed algorithm.
-
Yang Tongtong, Yang Ziyun, Wang Zichi
2024,47(9):98-104, DOI:
Abstract:
Neural networks have been extensively utilized in various fields, steganography for neural network is a research emerging direction in academia in recent years. Embedding capacity and robustness are important indicators for steganography. But balancing embedding capacity and robustness is challenging. This paper proposes a robust steganography for neural network models. Embedding secret data into neural network without visibly reducing the performance of the original task. This is achieved by embedding secret data during the training process instead of modifying the network parameters after training. Receivers can obtain the secret data from data decoding networks, the parameters of data decoding networks are generated using the embedding keys. In this way, it is unnecessary to transmit the decoding networks secretly. Additionally, introducing reed-solomon codes to improve data extraction robustness. Experimental results reveal that the robust steganography for neural models improves robustness while maintaining superior embedding capacity.
-
Li Yunfei, Xu Huajie, Wei Zexian
2024,47(9):105-111, DOI:
Abstract:
Aiming at the difficulty of target matching between two kinds of sensors in the fusion of radar and video data in the process of highway vehicle tracking, a highway vehicle tracking method based on target trajectory similarity matching was proposed. Firstly, the radar data is converted to the dimension of video data by projection transformation. Secondly, curve fitting algorithm is used to interpolate discrete trajectory points into continuous trajectory curves. Finally, the similarity between the trajectory curve projected on the image of the radar detection target and the trajectory curve of the video detection target is calculated, and the matching relationship between the radar detection target and the video detection target is obtained by screening the similarity matrix. Comparative experiments were carried out with vehicle data collected in real scenarios on highways. The results show that the average success rate of target matching in the expressways is 94.71%, which is 3.01% and 3.69% higher than that of other similar methods. The proposed method can effectively filter false targets and is more suitable for vehicle tracking in highway scenarios.
-
Liang Tiantian, Yang Songqi, Qian Zhenming
2024,47(9):112-119, DOI:
Abstract:
Addressing the issues of image blurring and uneven light distribution encountered when capturing images in adverse weather conditions, which lead to decreased scene contrast and subsequently increase the difficulty of distinguishing detection targets from the background in images, this paper proposes an improved YOLOv8s algorithm to enhance the detection capability of vehicles and pedestrians in harsh weather environments. Firstly, based on the YOLOv8s algorithm, this paper optimizes the C2F module in the backbone network with an expandable residual structure, enhancing the model′s adaptability to environmental changes. At the same time, an efficient multi-scale attention mechanism is introduced before the SPPF module in the backbone network, which can more effectively capture the rich and varied multi-scale features in images. Secondly, the detection head of the YOLOv8s algorithm is redesigned to reduce the model′s complexity while maintaining accuracy. Finally, the introduction of Wise-IoU improves the regression loss function of the YOLOv8s algorithm, enhancing the algorithm′s convergence speed and detection accuracy. Experimental results show that the improved YOLOv8s algorithm achieves an mean average precision of 91.41% on datasets for vehicle and pedestrian detection under adverse weather conditions, which is a 2.56% improvement over the original algorithm, with a model parameter reduction of 8% and a computational reduction of 4.9 GFLOPs. Compared to other mainstream object detection algorithms, the significantly improved YOLOv8s algorithm not only ensures real-time performance but also effectively meets the challenging requirements for vehicle and pedestrian detection under adverse weather conditions.
-
Li Zhixing, Yang Xiaolong, Li Tianhao, Wang Ningning
2024,47(9):120-128, DOI:
Abstract:
The wire rope used in coal mine plays an important application value in mine operation, and its reliability is directly related to the operation efficiency of the mine and the life safety of the staff. Aiming at the problems of low detection accuracy and insufficient detection efficiency of existing wire rope surface defects. This paper proposes an improved YOLOv8 detection algorithm YOLO_BF. Firstly, an improved double-layer link attention mechanism (BiFormer) is introduced into the backbone network to enhance the model ′s ability to analyze images and information fusion, which significantly improves the accuracy of the model. Secondly, the repeated weighted bidirectional feature pyramid network (BiFPN) is embedded to improve the ability of network defect feature extraction. On this basis, WIoU is used to improve the convergence speed of the model. Finally, GhostConv is used to replace the traditional convolution to realize the lightweight of the model. Compared with the original basic network YOLOv8n, the accuracy, recall and average accuracy are increased by 2.3%, 3.3% and 5.2% respectively.It is more in line with the practical application requirements of wire rope damage detection.
-
Huo Aiqing, Guo Lanjie, Feng Ruoshui
2024,47(9):129-136, DOI:
Abstract:
Although object detection can provide the location, size and category of nearby targets for autonomous vehicles, there are still problems of missed detection and false detection in multi-object detection in dense scenes, so an AD-YOLOv5 vehicle detection model is proposed. Firstly, the C3 module in the feature extraction network is optimized to obtain the C-C3 module using the lightweight structure CBAM attention mechanism, which improves the ability to acquire feature information and reduces the attention to other features; secondly, in the detection head section, the classification and regression tasks are decoupled in order to achieve stronger feature representation; then, the generalized power transform is used to perform the transformation operation on the IoU, and the Alpha-IoU loss function with better robustness is proposed, which improves the detection accuracy of the model and accelerates the convergence speed of the model; finally, to add to the complexity of the sample, the GridMask data enhancement technique was used and experiments were carried out on the processed dataset. The experimental results show that the mean average accuracy of the improved target detection model reaches 72.72%, which is 2.25% higher than the original YOLOv5 model, and the model has a high convergence speed, and the visual comparison experiments intuitively show that the model of this paper can effectively avoid the phenomenon of misdetection and omission detection in dense scenes.
-
Li Meng, Huang Hongbo, Zheng Yaolin, Xu Longfei
2024,47(9):137-144, DOI:
Abstract:
In recent years, the widespread deployment of high-definition and ultra-high-definition surveillance cameras has led to a significant increase in the volume of fixed-scene video data, such as surveillance videos. This sharp rise in data has imposed tremendous pressure on video storage and transmission. To further eliminate redundancy in fixed-scene videos, this paper proposes a novel compression and reconstruction method. By employing background extraction and an inter-frame foreground difference detection-based foreground extraction and compression approach, a substantial amount of data redundancy is removed from the videos. Experimental results show that, compared to MPEG-4, the proposed method achieves higher video reconstruction performance at a higher compression ratio. Compared to H.264, H.265, and DCVC-DC, the proposed method improves compression performance by 82.75%, 76.19%, and 59.56% respectively, while maintaining a high level of video reconstruction quality. This effectively alleviates the storage and transmission pressure of fixed-scene videos.
-
Zhao Shuanfeng, Li Leping, Wang Maoquan, Li Xiaoyu, Xie Lekun
2024,47(9):145-153, DOI:
Abstract:
Driver distraction behaviour detection is of crucial significance for the development of driver-centered human-vehicle co-driving systems. Aiming at the existing convolutional neural network-based driver distraction detection models that lack global feature extraction capability, have weak generalisation performance and neglect of the importance of different regions in the driving scene, a driver distraction detection model based on deep learning is constructed to achieve accurate prediction of driver distraction behaviour. First, a residual structure based on HorNet is developed to enhance the feature representation capability through higher-order spatial interactions; second, inspired by the human attention mechanism and the existing attention mechanisms, an adaptive weighted attention strategy is designed to extract the features most relevant to the driving behaviour; and then, the model in this paper is trained on the existing categorical dataset, and the a priori knowledge is used as the initial weights to improve the training results which in turn improves the generalisation ability of the model; finally, the driving behaviour features are visualised to improve the trust in this paper′s model. The experimental results show that the model in this paper can accurately detect driver distraction behaviour, which is significantly better than existing methods in terms of accuracy, and reliability.
-
Wang Yanhai, Zhang Yuhao, Li Cheng, Chen Shuping, Gong Xinxi
2024,47(9):154-162, DOI:
Abstract:
In order to solve the problem that a large number of detail features are missing after the simplified three-dimensional grid model of transmission towers, a lightweight algorithm for the three-dimensional grid model of transmission towers is proposed based on Quadric Error Metrics algorithm. The algorithm firstly defines the detail features in the 3D grid model of the transmission tower, then proposes the detail feature extraction strategy of the transmission tower, and introduces the detail feature significance factor and vertex approximate curvature factor to optimize the folding cost in the QEM algorithm. The experimental results show that the improved algorithm can effectively retain the important geometric features and detailed features of the three-dimensional grid model of the transmission tower, avoiding the problem of large-area feature loss in the simplified model, and compared with the ordinary QEM algorithm, the maximum error, mean error and mean square error of the simplified model are reduced by at least 39.77%, 10.64% and 64.99% respectively, which realizes the high quality and lightweight of the three-dimensional grid model of the transmission tower.
-
Xiao Hengshu, Li Junying, Liang Hong, Ma Erdeng, Zhang Hong
2024,47(9):163-171, DOI:
Abstract:
Accurate plant counting is crucial in precision agriculture, forming a critical foundation for monitoring crop growth and predicting yield. To address challenges such as densely packed, overlapping, and aerial small targets of tobacco plants during the maturity stage, a lightweight GEW-YOLOv8 tobacco plant counting algorithm was proposed. The algorithm utilizes the GhostC2f module to reduce the parameters and computational workload of the model and employs an efficient multi-scale attention mechanism to discern occluded tobacco plants. Additionally, the WIoU loss function is introduced to accelerate model convergence and improve accuracy. Experimental results show a significant improvement in efficiency and accuracy compared to the original model, with a 24.7% reduction in FLOPs and a 26.7% decrease in model size. The improved model tobacco plant detection accuracy AP0.5 and AP0.5~0.95 reached 99.1% and 86.2% respectively, which were increased by 0.8% and 3.6% respectively compared with the original YOLOv8n model. The improved model can more swiftly and accurately identify field tobacco plants, providing technical support for intelligent tobacco agriculture.
-
Jin Lei, Ji Xiang, Deng Liyun, Xu Shaojie, Wang Han
2024,47(9):172-183, DOI:
Abstract:
With the development and popularity of smartphone products, a large number of bowed-head tribes have emerged who play mobile phones at any time regardless of the occasion; for the frequent occurrence of traffic accidents caused by bowed-head tribes′ dependence on mobile phones, a multimodal bowed-head tribes′ hazard perception and warning system based on mobile phones is proposed. First, gravity acceleration on the mobile phone side is used to monitor behaviors in real time based on fuzzy control rules, including Walking and looking at the mobile phone, Walking up and down stairs, Looking at the mobile phone at rest, Walking with the mobile phone in hand, Walking with the mobile phone in pocket; and then the user′s environment is described in real time using the mobile phone′s rear view camera images based on the grouping of fast spatial pyramids pooled in the lightweight YOLO network, including: stairs, crosswalks, low-light environments, puddles, and normal road surfaces. Finally, a state-environment-multimodal hazard detection model is constructed for the Android system; and based on the detection results, audible, visual, and tactile three-dimensional warning signals are given to the bowed tribe by using sound, image, and vibration signals to reduce the potential hazards of the bowed tribe such as fall injury and collision. Online experiments show that the proposed multimodal threat perception model for mobile phones is highly accurate, robust, and real-time, and is able to achieve effective proactive warning for the common threat states of bowed heads.
-
Liu Yong, Guo Kai, Liu Xueying, He Bin
2024,47(9):184-190, DOI:
Abstract:
In response to the maintenance requirements of airborne radar in field operations, this paper proposes a process-oriented automatic measurement method for the parameters of airborne radar signals based on the spectrum analysis module. The principles and steps of automatic parameter measurement for multi-system radar signals are analyzed in detail in the paper. Corresponding testing software is also developed to execute the relevant algorithms and enable streamlined measurements. Additionally, four signal simulation experiments are designed to validate the effectiveness of the proposed method. The experimental results demonstrate that this method can achieve a comprehensive measurement of multiple parameters of typical radar signals in a streamlined manner, without relying on traditional general instruments. It solely utilizes the sampling data provided by the spectrum analysis module in different working modes. The measurement results are accurate and effective, meeting the requirements of field maintenance support. Therefore, it possesses strong engineering application value.
-
Wang Shenghua, Zhao Chenbo, Deng Yukun, Xu Jianing, He Pengchao
2024,47(9):191-196, DOI:
Abstract:
For the waveform distortion of narrow pulse signal after amplification, frequency conversion and other analog devices, a waveform distortion correction method for signals based on modified frequency domain filter is proposed. Traditional distortion correction methods only use signals within the effective bandwidth. It results in poor time domain performance after waveform distortion correction. To improve the distortion correction accuracy and ensure the time domain waveform characteristics of the signal, the proposed method uses the frequency responses of the effective bandwidth and the partial high-frequency region outside the bandwidth to solve the waveform distortion correction filter. But the spectrum of the distortion correction filter fluctuates greatly and has many spikes and burrs in the high-frequency region outside the bandwidth. It can′t be directly used to solve the coefficients of the waveform distortion correction filter. The proposed method applies median filtering to the amplitude-frequency response correction curves and phase-frequency response correction curves, followed by polynomial fitting. Better waveform correction performance has been achieved by optimizing the order and coefficients of the waveform distortion correction filter. Finally, the real data processing results verified the effectiveness of the proposed method.
Volume 47, 2024 Issue 9
Research&Design
Theory and Algorithms
Information Technology & Image Processing
-
Integrating Multi-scale Features and Attention Mechanisms for Food Image Recognition
Abstract:
To address the challenges in food image recognition caused by small inter-class differences, large intra-class variations, and complex structures, this paper proposes a food image recognition method that integrates multi-scale features and an attention mechanism. First, the ConvNeXt model, which has stronger feature extraction capabilities, is used as the backbone network to better capture the detailed features of food images. Next, an improved ASPP module is introduced to expand the receptive field and utilize multi-scale information, enhancing the model"s ability to capture features at different scales. Finally, an attention mechanism is added after each convolutional block to improve feature representation and the ability to capture contextual information. Experimental results show that the proposed method achieves accuracies of 91.56% and 87.22% on the extended Vireo Food172 dataset and the ETH Food101 dataset, respectively, which represents an improvement of 2.05% and 1.66% over the original model, thus verifying the effectiveness of the proposed method.
- 1
-
Fault electrostatic recognition for bearings via SVM optimized by Bayesian optimization
Abstract:
Aiming at the problem of easy interference of electrostatic signal and low fault recognition rate when the new electrostatic monitoring technology is applied to rolling bearing fault diagnosis, a method of electrostatic signal recognition of rolling bearing fault based on the combination of Bayesian optimization SVM is proposed. First of all, through the electrostatic simulation test platform constructed, the electrostatic signals of different wear states of bearings under high speed are collected, and the feature sets of different working conditions are selected according to the time-domain feature parameters; and then the hyper-parameters of the minimum error of SVM are selected using Bayesian optimization to achieve the effect of completing the diagnostic model training, and the diagnostic accuracy of the models is evaluated with the results of the confusion matrix after training. The research results show that this method has certain recognition ability for bearings with different fault characteristics under electrostatic monitoring, and the Bayesian optimization algorithm can effectively improve the recognition efficiency, and its average recognition accuracy can reach 98.82%.
- 1
-
Multi-interface video codec system based on FPGA
Abstract:
In order to further improve the compatibility of machine vision systems and enrich the types of video formats processed by encoding and decoding systems, a multi interface video encoding and decoding system based on FPGA was designed. By using the asynchronous DDR read-write principle to build the codec selection module and complete the conversion operation of different video formats, the final system supports the decoding of PAL, HDMI and Cameralink videos as well as the encoding functions of HDMI, Cameralink and LVDS videos. Meanwhile, by comparing the transmission characteristics of different video interfaces, The seamless conversion between the above video interface standards is realized. The system can not only be used as an independent video codec system, but also can be connected to ARM processor through LVDS interface, thus expanding its application scenarios. Experimental results show that the system can accurately decode PAL video with a resolution of 720×576, Cameralink video with a resolution of 640×512 and HDMI video with a resolution of 1080p, and output it through HDMI, Cameralink and LVDS video interfaces respectively. In addition, The consumption of all kinds of resources in the system does not exceed 50%, which ensures the efficient operation of the system.
- 1
-
Marine life identification method based on improved RT-DETR
Abstract:
Addressing the issue of subpar performance in identifying shallow water marine life in underwater environments using existing methods, we propose an improved method based on the RT-DETR benchmark model. Initially, the Reparameterization Network RepViT is utilized as the backbone of the model, enhancing its feature extraction capabilities. Subsequently, a Reparameterized Parallel Dilated Convolution (RepPDC) is constructed and incorporated into the neck network, enabling the model to effectively capture long-range contextual information, thereby improving the model"s recognition accuracy. Lastly, a Bidirectional Feature Fusion Module (CAFM) is constructed based on the attention mechanism, enhancing the model"s ability to focus on key information in underwater environments. Experimental results demonstrate that the improved method significantly boosts the mAP50 to 87.5%, mAP75 to 70.9%, and mAP50:95 to 64.9%, with fewer parameters, making it a promising candidate for practical applications in the identification of shallow water marine life.
- 1
-
Machine vision-based dual-light-source tobacco flavor appearance quality inspection device
Abstract:
The application formula and process of tobacco fragrance are the core technology of the tobacco industry. In China, each tobacco industry has chosen the construction of fragrance categories as the next round of strategic choices. Its differentiation is a technical key point for the competition among various cigarette brands. This paper proposes a machine vision method combining dual light source illumination to solve the problem of poor quality judgment by manual judgement in the processing of tobacco fragrance configuration and preparation, and designs and manufactures an appearance quality qualification detection device for tobacco fragrance based on this. Using white light and red light as the main test light sources and green light as auxiliary detection light source, a dual light source coaxial forward illumination environment is set up; by fixing the optical plate for lighting and image acquisition module as a whole and combining the slide table with the stepping motor to rotate and stop at designated points, the machine vision method is used to eliminate reflections and automatically analyze color model parameters and detect the appearance quality qualification of the tobacco fragrance. The results show that the relative standard deviation of the parallel test of single tube sample image is less than 0.9968%, and the relative standard deviation of the parallel test of the same batch sample is less than 0.0217%. The experimental results show that the precision and repeatability of the instrument are good, and can provide support for further promoting the intelligent management of the tobacco fragrance configuration detection industry.
- 1
-
Image inpainting algorithm based on multi-feature fusion
Abstract:
Aiming at the problems of poor structural consistency and insufficient texture details in the inpainting results of existing image inpainting algorithms, an image inpainting algorithm based on multi-feature fusion was proposed under the framework of Generative Adversarial Network (GAN). Firstly, the dual encoder-decoder structure is used to extract the texture and structure feature information, and the fast Fourier convolution residual block is introduced to effectively capture the global context features. Then, the information exchange between structure and texture features was completed through the Attention Feature Fusion (AFF) module to improve the global consistency of the image. The Dense Connected Feature Aggregation (DCFA) module was used to extract rich semantic features at multiple scales to further improve the consistency and accuracy of the inpainted image, so as to present more detailed content. Experimental results show that, compared with the optimal comparison method, the proposed algorithm improves PSNR and SSIM by 1.18%and 0.70%respectively, and reduces FID by 3.99% on the Celeba-HQ dataset when the proportion of damaged regions is 40%-50%. On the Paris Street View dataset, PSNR and SSIM are increased by 1.17% and 0.50%, respectively, and FID is reduced by 2.29%. Experimentally, it is proved that the suggested algorithm can effectively repair large broken images, and the repaired images have a more sensible structure and richer texture details.
- 1
-
Multi-point path planning based on ant colony algorithm and bat algorithm
Abstract:
Aiming at the multi-point path planning problem of mobile robots, a path planning algorithm combining ant colony algorithm and bat algorithm is proposed in this paper. The ant colony algorithm is used to establish the shortest path network between nodes. The pointing angle and turning angle are introduced as heuristic information in the traditional ant colony algorithm to reduce the paths' turning times and turning angles. The reward and punishment mechanism is used to optimize the pheromone updating mode and improve the convergence speed of the algorithm. The objective function of multi-point path planning is based on the shortest path network. When solving the optimal node access order, the structure of the bat algorithm is improved, the hierarchical search method and a new local optimization mechanism are introduced, and the bat algorithm's solving accuracy, speed, and stability are improved. The simulation results demonstrate that the proposed algorithm effectively addresses the issue of multi-point path planning. In comparison to existing algorithms, it exhibits lower computational complexity, higher search efficiency, smoother overall paths, and shorter lengths.
- 1
-
Intelligent Online Upgrade Storage System Design Based On FPGA
Abstract:
To address the frequent disassembly required for program updates in storage systems within the industrial testing field, as well as the unique need for data storage without a host computer, a smart online upgrade storage system design based on FPGA is proposed. This system utilizes FPGA as the main controller and employs a combination of Gigabit Ethernet and FLASH. Update instructions and configuration files are transmitted via Gigabit Ethernet to the program memory, where they are partitioned, erased, and written to SPI Flash, enabling online upgrades of the FPGA program. Additionally, the optocoupler instruction parsing module enables the system to operate independently of a host computer, performing intelligent data storage autonomously. Furthermore, the system integrates a reliable feedback design using a custom DR_UDP protocol, optimizing the communication efficiency and stability of the Gigabit Ethernet port. Functional verification analysis confirms that the system operates stably, flexibly, and reliably, with a Gigabit Ethernet transmission rate reaching 700Mb/s , and no data loss detected. This system can be widely applied in various scenarios where disassembly is inconvenient.
- 1
-
Improved feature matching and dense mapping algorithm based on ORB-SLAM2
Abstract:
To address problem that the ORB-SLAM2 algorithm is prone to mismatching and cannot build a dense map during feature matching, the GMS algorithm is introduced to improve the mismatching problem in the ORB-SLAM2 algorithm and add a dense map thread. First, an image pyramid is established, and a grid division is performed on each layer of the image pyramid to extract feature points. A four-tree strategy is introduced for feature point selection in each grid, resulting in a uniform distribution of feature points. Second, the GMS algorithm is introduced in the feature matching stage to eliminate false matches. Finally, the dense point cloud map is built based on the pose estimation and key frames. Through the experimental verification on TUM data set, the results show that the matching number of the improved algorithm is 7.82% higher than that of the original ORB-SLAM2 algorithm, and the matching time is reduced by 8.53%. The improved algorithm is applied to the automatic navigation and obstacle avoidance of mobile robot, which can improve the reliability and operation efficiency of the system.
- 1
-
Textile material classification method based on DSCI-Yolov8
Abstract:
In view of the inefficiency of the artificial material classification method used by traditional textile production plants, it is difficult to meet the needs of large-scale textile production. Artificial intelligence and computer vision advanced technologies were applied to textile material classification, and a textile material classification method based on DSCI-Yolov8 was proposed. On the basis of the Yolov8 classification model, the ability of the model to extract the features of textiles at different scales is enhanced by adding the coordinate information attention module, and the distribution offset convolution is added to the c2f network module to achieve lower memory usage and higher computing speed. Experimental results show that compared with the Yolov8 network model, the accuracy of the proposed model is increased by 2.09 percentage points, and the detection speed is increased by 24.9%.While greatly reducing the calculation cost, it effectively improves the accuracy and speed of textile material classification. It can meet the testing needs of the textile industry for product category classification and quality.
- 1
-
Classification of make-up torque sequence data based on improved TCN
Abstract:
In the field of oil and gas development, the sealing performance test of oil casing after installation is particularly important.Torque sequence data is an important basis for judging the sealing performance of the oil casing, which can be used to judge whether the buckle is qualified. In order to identify and classify the sealing performance of the oil casing by using the information of the buckled torque sequence data, a new network model was built which named PSE-TCN network based on the TCN model integrated with position encoding and self-attention mechanisms. By comparing the accuracy of results under different strategies, the learning process of the model was demonstrated. The effectiveness of this method was validated by comparing it with other network models. Experimental results show that torque sequence recognition accuracy was significantly improved by the PSE-TCN network compared with other classical network models and several improved TCN models. The recognition accuracy of this model achieved 93.41% on the self-made UCR_whorl dataset.
- 1
-
Laser center extraction algorithm of metal workpiece surface line based on Principal Component Analysis
Abstract:
In the surface measurement of metal workpieces based on line structured light, this paper proposes a laser stripe centerline extraction algorithm based on improved principal component analysis to address issues such as strong reflection and laser stripe breakage on the surface of metal workpieces. Firstly, for the irregular reflection of metal workpiece surface, the optical fringe region of image was extracted based on maximal variance between clusters (OTSU); Secondly, in response to the problems of high convolution operations, low efficiency, and poor real-time performance of the Steger algorithm, an improved Steger algorithm based on principal component analysis (PCA) was proposed. The covariance matrix of the gradient vector was constructed using PCA to estimate the normal direction of the stripe, and the second-order Taylor expansion was used in this direction to obtain accurate sub-pixel coordinates of the stripe center. The experimental results show that the algorithm proposed in this paper can effectively extract laser stripe areas under severe reflection conditions on the surface of metal workpieces. At the same time, the standard deviation of the extracted laser stripe centerline is reduced by about 0.25 pixels compared to the grayscale centroid method, and the speed is increased by nearly 13 times compared to the Steger algorithm. It can quickly and accurately extract the laser stripe centerline, meeting the real-time detection requirements of structured light 3D vision.
- 1
-
Lithium-ion battery state of health estimation based on IViT
Abstract:
It is essential to accurately predict the state of health (SOH) of lithium-ion batteries. Aiming at challenges such as differences in degradation mechanisms at different stages of a single battery cycle and incomplete data acquisition in practical utilization scenarios, a lithium-ion battery SOH estimation method based on Involution-Vision Transformer (IViT) is proposed. Features that can effectively characterize the degradation information of lithium-ion batteries are automatically extracted from the voltage-time profile, weights are adaptively assigned at different positions using the Involution module, and Vision Transformer is used to learn the high-level feature representations at different stages and capture the global dependencies. The experimental results show that the prediction error of IVIT is around 0.5%, and the error is only around 2% when the overall data is missing 50%, proving the effectiveness and stability of the proposed method.
- 1
-
Surface defect detection method for inner handle of car door based on Improved RT-DETR
Abstract:
To address the challenges of small defect targets, multi-scale issues, and high reflectivity on the surface of the inner car door handle, we first tackle the problem of defect features being obscured during image acquisition due to surface curvature and mirror reflection by using a bowl-shaped light source and reducing the angle of the image acquisition surface. Then, recognizing the limitations of traditional RT-DETR models, such as poor detection accuracy and slow speed, we propose an improved RT-DETR object detection method. This method builds upon the RT-DETR framework, utilizing parallel dilated convolutions and the CA attention mechanism combined with convolutional re-parameterization in the backbone network to increase the receptive field and establish long-distance semantic information while improving the network inference speed. Additionally, extra detection layers are added to improve the network"s feature extraction capability for small object detection. In the multi-scale feature fusion stage, we use an improved BIFPN structure to enhance the model"s information interaction capability. Finally, ablation experiments show that, compared to traditional RT-DETR-based detection methods, our proposed improved RT-DETR method increases the mean Average Precision (mAP) by 6.5%,
achieves a detection speed (FPS) 1.6 times that of the traditional model, and reduces the model"s parameter count to only 76.5% of the original network, validating the effectiveness of our proposed method.- 1
-
Self-explosion defect detection of insulator based on improved YOLOv8
Abstract:
To address the problems of low accuracy, easy false detection and missed detection in the existing insulator self-explosion defect detection methods under complex backgrounds and foggy environments, an improved YOLOv8 insulator self-explosion defect detection algorithm is proposed. First, the SPD-Conv module for low resolution image and small target detection is introduced into the backbone network to fully extract the feature information of insulator defect target. Secondly, BiFPN is integrated with the SimAM attention mechanism to build the BiFPN_SimAM module, replacing the concat connection of PANet to achieves multi-scale feature fusion and enhances the overall performance of the network. The experimental results show that the precision and mAP@0.5 of the improved algorithm for insulator self-explosion defect detection reach 95% and 93.1%, respectively, which are increased by 1.8% and 1.5% compared with the original YOLOv8 algorithm, and it also has a good detection effect on insulator self-explosion defect detection under complex background and foggy environment.
- 1
-
Hyperspectral image classification based on deep feature extraction residual network
Abstract:
Deep learning has become one of the important tools for hyperspectral image classification due to its modular design and powerful feature extraction capability. However, effectively extracting deeper features and simultaneously improving the analysis of spatial and spectral joint features remains an urgent challenge. In response to these issues, a deep feature extraction residual network is proposed in this paper, composed of two key components: a multi-level transfer fusion residual network and a spatial-spectral multi-resolution fusion attention residual network. The multi-level transfer fusion residual network effectively promotes interaction between feature information to obtain deeper-level features. Subsequently, the spatial-spectral multi-resolution fusion attention residual network en-sures comprehensive extraction of spatial-spectral joint features and multi-resolution features from hyperspectral data. To validate its effectiveness, the performance of the proposed method was evaluated on three hyperspectral datasets, Indian Pines, Pavia University, and Salinas Valley, achieving classification accuracies of 98.10%, 99.81%, and 99.94% respectively. Experimental results demonstrate that, compared to other methods, this network exhibits better generalization capability and classification performance.
- 1
-
Extraction of body movement features and action recognition based on Multi-Domain feature fusion in electroencephalogram signals
Abstract:
In the classification and recognition of limb motion imagery features in Electroencephalogram, the problem of low action recognition accuracy exists when fusing different domain feature extractions. Based on the complex and different domain relationships of limb motion imagery brain electrical characteristics in multi-channel acquisition, this paper constructs an EEG-Symmetric Positive Definite Netmotion feature classification model for limb action recognition, which effectively extracts and fuses different domain features to realize the extraction of limb motion features based on brain electrical signals. The main research contents include: 1) A time domain feature extraction module is designed, which incorporates the channel-wise features weighted into the time domain features, and uses multi-scale separable convolution to fully extract the time domain features, improving the recognition accuracy of limb actions; 2) The extracted time domain features are mapped to a high-dimensional manifold that can more effectively describe their distribution, and a manifold mapping module is designed to solve the problem of ineffective fusion of time domain features and spatial domain features; 3) To make up for the lack of frequency domain information in the time domain, a frequency domain feature extraction module is designed to enrich the motion features such as gestures. By integrating the above multiple modules, the EEG-SPDNet classification model is constructed, and the effective recognition of limb motion actions is realized based on motor imagery brain electrical information. Experimental results show that on the BCI Competition IV 2a motion imagery dataset for recognizing four types of limb motion, the accuracy of action recognition based on the constructed classification model reaches 0.85, and the Kappa coefficient reaches 0.80, with high precision.
- 1
-
Double-perspective visual angle measurement method based on complex-valued neural networks
Abstract:
To enhance the stability of angle measurement methods based on single-vision techniques, which are susceptible to random disturbances from environmental or systemic sources, we propose a dual- perspective visual angle measurement method based on complex-valued neural networks. Feature extraction is conducted manually, followed by an assessment of the features’ relevance and monotonicity with respect to angles to facilitate feature selection. To address the significant numerical discrepancy between the 0°and 360° labels, which impacts training outcomes, angles are represented using Euler"s formula. This representation facilitates the construction of a complex-valued neural network with both complex inputs and outputs for angle computation. Experimental results demonstrate a significant improvement in measurement accuracy; the proposed method reduces the mean error by 0.322° and the root mean square error by 0.64° compared to methods based on deep neural networks using a single viewpoint, maintaining high performance across various environmental test sets. By leveraging the robustness against environmental disturbances provided by dual viewpoints and the strong fitting capabilities of complex-valued neural networks for angle labels, this model enhances the accuracy and stability of radial visual angle measurements while adhering to the constraints and stability of mathematical models.
- 1
-
Research on the improved semantic segmentation model of photovoltaic panels based on DeepLabV3+
Abstract:
The segmentation and extraction of PV panel region information from infrared images of PV panels can greatly improve the accuracy of PV panel fault detection. However, the traditional semantic segmentation algorithm is not effective in processing the boundary information of PV panels, and there are cases that the boundary of PV panels is wave-like, sticking to each other, and the background is mis-segmented. To solve this situation, this paper proposes a semantic segmentation algorithm model for PV panels based on improved DeepLabV3+, which changes the backbone network to MobileNetV2, introduces the Canny edge detection algorithm to output new shallow feature semantic information, and designs the SE-ASPP module to re-calibrate the feature channels to enhance the network expression capability, and increase the number of channels of shallow feature semantic information to strengthen the attention to shallow feature semantic information. Experimental results show that the precision, mIoU, recall and F1 score of the improved DeepLabV3+ algorithm model reach 99.50%, 99.21%, 99.61% and 99.55%, respectively, which are 2.24%, 1.58%, 1.57% and 1.72% higher than the original DeepLabV3+ model, respectively. Improved DeepLabV3+ model performs well in real segmentation tasks and has higher detection accuracy and reliability.
- 1
-
Analysis on the influence of C-field current source on the performance of rubidium fountain atomic clock
Abstract:
The C-field current stability of rubidium atomic fountain clock can affect the second-order Zeeman frequency shift of the clock. Traditional methods to optimize the physical system of the C-field are complicated and difficult to meet the miniaturization requirements .Starting from the circuit system of rubidium atomic fountain clock, this paper puts forward the method of optimizing C-field circuit by using chip current source.Firstly, the influence of the chip current source output fluctuation on the second order Zeeman frequency shift of the rubidium atomic fountain clock is analyzed and the relationship between the second order Zeeman frequency shift of the rubidium atomic fountain clock and the output current of the C-field chip current source is obtained；Secondly, the measurement experiment of VC12MA current source is carried out.The experiment shows that when the C field is generated by VC12MA current source, the Allan variance of the output current value is 2.24×10-9, and the relative disturbance to the second-order Zeeman frequency shift of the rubidium atomic fountain clock is 1.78×10-17. The frequency stability of the second-order Zeeman shift of the rubidium atomic fountain clock is improved from the original 10-16 order to the optimized 10-17 order. The method presented in this paper has great application value in the performance improvement and miniaturization of the rubidium atomic fountain clock.
- 1
-
Xue Xianbin, Tan Beihai, Yu Rong, Zhong Wuchang
2024,47(6):1-7, DOI:
Abstract:
Urban intersections are accident-prone sections. For intelligent networked vehicles, it is very important to carry out risk detection and collision warning during driving to ensure the safety of driving. This paper proposes a traffic risk field model considering traffic signal constraints for urban intersections with traffic lights, and designs a three-level collision warning method based on this model. Firstly, a functional scenario is constructed according to the potential conflict risk points of urban intersections, and the vehicle risk field model is carried out considering the constraint effect of traffic signal. In order to solve the problem of collision warning, a three-level conflict area is proposed to be divided by the index, and the collision risk of the main vehicle is measured according to the position of the potential energy field around the main vehicle by calculating the corresponding field strength around the main vehicle. The experimental results show that the designed model can accurately warn the interfering vehicles entering the potential energy field of the main vehicle, the warning success rate can reach 100%, and the false alarm rate is only 3.4%, which proves the reliability and effectiveness of the proposed method.
-
Wei Jinwen, Tan Longming, Guo Zhijun, Tan Jingyuan, Hou Yanchen
2024,47(6):8-13, DOI:
Abstract:
To address the issue of low accuracy in indoor static target positioning with existing single-antenna ultra-high frequency RFID technology, this paper proposes a new RFID localization method based on an antenna boresight signal propagation model. The method first determines the height position of the target through vertical antenna scanning; secondly, it adjusts the antenna height to match that of the target and then performs stepwise rotational scanning to identify the target′s azimuth angle; furthermore, it utilizes a Sparrow Search Algorithm optimized back propagation neural network to establish a path loss model for ranging purposes; finally, it integrates the height, azimuth angle, and distance data to complete the target positioning. Experimental results show that in indoor environment testing, the proposed method has an average positioning error of 7.2 cm, which meets the positioning requirements for items in general indoor scenarios.
-
Zhang Huimin, Li Feng, Huang Weijia, Peng Shanshan
2024,47(6):86-93, DOI:
Abstract:
A lightweight improved model CAM-YOLOX is designed based on YOLOX to address the issues of false alarms of land targets and missed detections of shore targets encountered in ship target detection in large scene Synthetic Aperture Radar(SAR)images in near-shore scenes. Firstly, embed Coordinate Attention Mechanism in the backbone to enhance ship feature extraction and maintain high detection performance; Secondly, add a shallow branch to the Feature Pyramid Network structure to enhance the ability to extract small target features; Finally, in the feature fusion network, Shuffle unit was used to replace CBS and stacked Bottleneck structures in CSPLayer, achieving model compression. Experiments are carried out on the LS-SSDD-v1.0 remote sensing dataset. The experimental results show that compared with the original algorithm, the improved algorithm in this paper has the precision increased by 5.51%, the recall increased by 3.68%, and the number of model parameters decreased by 16.33% in the near-shore scene ship detection. The proposed algorithm can effectively suppress false alarms on land and reduce the missed detection rate of ships on shore without increasing the number of model parameters.
-
Zhang Fubao, Wu Ting, Zhao Chunfeng, Wei Xianliang, Liu Susu
2024,47(6):100-108, DOI:
Abstract:
In real-time detection of saw chain defects based on machine vision, factors like oil contamination and dust impact image brightness and quality, leading to a decrease in the feature extraction capability of the object detection network. In this paper, an automated saw chain defect detection method that combines low-light enhancement and the YOLOv3 algorithm is proposed to ensure the accuracy of saw chain defect detection in complex environments. In the system, the RRDNet network is used to adaptively enhance the brightness of the saw chain image and restore the detailed features in the dark areas of the image. The improved YOLOv3 algorithm is used for defect detection. FPN structure is added with a feature output layer, the a priori bounding box parameters are re-clustered using the K-means clustering algorithm, and the GIoU loss function is introduced to improve the object defect detection accuracy. Experimental results demonstrate that this approach significantly improve image illumination and recover image details. The mAP value of the improved YOLOv3 algorithm is 92.88%, which is a 14% improvement over the original YOLOv3. The overall leakage rate of the system eventually reduces to 3.2%, and the over-detection rate also reduces to 9.1%. The method proposed in this paper enables online detection of saw chain defects in low-light scenarios and exhibits high detection accuracy for various defects.
-
Wang Huiquan, Wei Zhipeng, Ma Xin, Xing Haiying
2024,47(6):14-19, DOI:
Abstract:
To solve the problem of low control accuracy of the tidal volume emergency ventilation for lower air pressure at high altitudes, we propose a dual-loop PID tidal volume control system, which utilizes a pressure-compensated PID controller to adjust fan speed, supplemented by an integral-separate PID controller in order to achieve precise control of airflow velocity.Compared with single-loop PID control, the rapid response and no overshooting are observed in the performance tests of the dual-loop control system at an altitude of 4 370 m and atmospheric pressure of 59 kPa, in addition, the output error of the average airflow velocity decrease to 3.19% (the maximum error is 4.1%), which is superior to that of current clinical equipment. Our work offers an effective solution for high-altitude emergency ventilator tidal volume control, and contributes important insights to the development of ventilation control technology in special environments.
-
Fang Xin, Shen Lan, Li Fei, Lyu Fangxing
2024,47(6):20-27, DOI:
Abstract:
The high-frequency measurement data of underground vibration signals can record more specific details about the dynamic response of drilling tools, which is helpful for analyzing and diagnosing abnormal vibrations underground. However, the high-frequency measurement generates a large amount of measurement data, resulting in significant storage pressure for underground vibration measurement equipment. The proposed method uses compressed sensing technology to selectively collect and store sparse underground vibration data and then recover high-frequency measurement results through a signal reconstruction algorithm. In the process of realizing this method, an innovative method of constructing a layered Fourier dictionary against spectrum leakage is proposed, and an improved OMP signal reconstruction algorithm based on layered tracking is researched and realized, which greatly reduces the time required for signal recovery. Simulation and experimental test results demonstrate the method′s effectiveness, achieving a system compression ratio of 18.9 and a reconstruction error of 52.1 dB. The proposed method may greatly reduce the data storage pressure of the measuring equipment in the underground, and provides a new way to obtain high-frequency measurement data of underground vibration.
-
Zhan Huiqiang, Zhang Qi, Mei Jianing, Sun Xiaoyu, Lin Mu, Yao Shunyu
2024,47(6):123-130, DOI:
Abstract:
Aiming at the force test in low-speed pressurized wind tunnel, the original data source of aerodynamic characteristic curve is analyzed. With the balance signal, flow field state and model attitude as the main objects, combined with the test control process, the abnormal detection methods and strategies of the test data are studied from the dimensions of single point data vector, single test data matrix and multi-test data set in the same period, and an expert system for abnormal data detection is designed and developed based on this core knowledge base. The system inference engine automatically detects online during the test, and realizes the pre-detection and pre-diagnosis of the original data through data identification, rule reasoning, logical reasoning and knowledge iteration. The experimental application results show that the expert system is highly sensitive to the detection of abnormal types such as abnormal bridge pressure, linear segment jump point and zero point detection, which guides the direction of abnormal data analysis and improves the efficiency of problem data investigation.
-
Ma Zhewei, Zhou Fuqiang, Wang Shaohong
2024,47(6):94-99, DOI:
Abstract:
A feature point extraction algorithm based on adaptive threshold and an improved quadtree homogenization strategy are proposed to address the issue of low positioning accuracy or low matching logarithms of the SLAM system caused by the ORB-SLAM2 algorithm extracting fewer feature points in dark environments or environments with fewer textures, resulting in system crashes. Firstly, based on the brightness of the image, FAST (Features from Accelerated Seed Test) feature points are extracted using adaptive thresholds. Then, an improved quadtree homogenization strategy is used to eliminate and compensate the feature points of the image, completing feature point selection. The experimental results show that the improved feature point extraction algorithm increases the number of matching pairs by 17.6% and SLAM trajectory accuracy by 49.8% compared to the original algorithm in dark and textured environments, effectively improving the robustness and accuracy of the SLAM system.
-
Shi Shujie, Zhao Fengqiang, Wang Bo, Yang Chenhao, Zhou Shuai
2024,47(6):116-122, DOI:
Abstract:
Rolling bearings play an important role in rotating machinery. If a fault occurs, it can cause equipment shutdown, and in severe cases, endanger the safety of on-site personnel. Therefore, it is necessary to diagnose the fault. In response to the difficulty in extracting fault features of rolling bearings and the low accuracy of traditional classification methods, this paper proposes a fault diagnosis method based on Set Empirical Mode Decomposition (EEMD) energy entropy and Golden Jackal Optimization Algorithm (GJO) optimized Kernel Extreme Learning Machine (KELM), achieving the goal of extracting fault features of rolling bearings and correctly classifying them. Through experimental data validation, this method can extract the fault information features hidden in the original signal of rolling bearings, with a diagnostic accuracy of up to 98.47%.
-
Li Ya, Wang Weigang, Zhang Yuan, Liu Ruipeng
2024,47(6):64-70, DOI:
Abstract:
A task offloading strategy based on Vehicle Edge Computing (VEC) is designed to meet the requirements of complex vehicular tasks in terms of latency, energy consumption, and computational performance, while reducing network resource competition and consumption. The goal is to minimize the long-term cost balancing between task processing latency and energy consumption. The task offloading problem in vehicular networks is modeled as a Markov Decision Process (MDP). An improved algorithm, named LN-TD3, is proposed building upon the traditional Twin Delayed Deep Deterministic Policy Gradient (TD3). This improvement incorporates Long Short-Term Memory (LSTM) networks to approximate the policy and value functions. The system state is normalized to accelerate network convergence and enhance training stability. Simulation results demonstrate that LN-TD3 outperforms both fully local computation and fully offloaded computation by more than two times. In terms of convergence speed, LN-TD3 exhibits approximately a 20% improvement compared to DDPG and TD3.
-
Feng Zhibo, Zhu Yanming, Liu Wenzhong, Zhang Junjie, Li Yingchun
2024,47(6):34-40, DOI:
Abstract:
The data bits and spread spectrum codes of the spaceborne spread-spectrum transponder are asynchronous. Due to the influence of transmission system noise and Doppler frequency shift, it can cause attenuation of peak values related to receiving and transmitting spread spectrum codes, leading to a decrease in capture performance. Traditional capture techniques often have problems such as high algorithm complexity, slow capture speed, and difficulty adapting to the requirements of large frequency offsets of hundreds of kilohertz. This article proposes a spread spectrum sequence search method that truncates the spread spectrum sequence into two segments for correlation operations, and combines the signal squared sum FFT loop for a large frequency offset locking, effectively suppressing the attenuation of correlation peaks and improving pseudocode capture performance. MATLAB simulation and FPGA board level testing show that the proposed spread spectrum signal capture scheme can resist Doppler frequency shifts of up to ±300 kHz, with an average capture time of about 95 ms. In addition, the FPGA implementation of this algorithm saves about 47% of LUT, 43% of Register, and more than half of DSP and BRAM resources compared to traditional structures, making it of great application value in resource limited real-time communication systems.
-
Ma Dongyin, Wang Xinping, Li Weidong
2024,47(6):58-63, DOI:
Abstract:
Aiming at the Automatic Train Operation of high-speed train,an algorithm based on BAS-PSO optimized auto disturbance rejection control (ADRC) is used to design speed tracking controller.The ADRC is designed based on the train dynamics model,ITAE is used as the objective function,and the parameters are tuned by BAS-PSO.CRH380A train parameters are selected, The tracking effect of BAS-PSO, PSO and improved shark optimized ADRC algorithm on the target speed curve of the train is compared by MATLAB simulation,The tracking error of the train target speed curve based on the BAS-PSO optimized ADRC algorithm is kept in the range of ±0.4 km/h,which is closer to the target speed curve than the other two algorithms.The results show that the ADRC based on BAS-PSO optimization has the advantages of small tracking error and strong anti-interference ability.
-
Zhang Bian, Tian Ruyun, Han Weiru, Peng Yuxin
2024,47(6):109-115, DOI:
Abstract:
In order to solve the problems that the traditional SPD life alarm characterization method can not clearly correspond to the real life state of SPD, and the remaining life model characterized by a single degradation related parameter has poor predictability, a multi-parameter SPD life remote monitoring system based on STM32 is designed. With STM32 as the main controller, the important parameters such as surge current, leakage current, surface temperature and tripping status of SPD are collected in real time, and the status information is uploaded to the One net cloud platform through the BC20 wireless communication module. The One net cloud platform displays and stores the multi-parameter data of SPD in real time, and provides data management and analysis. The SVM classification model is used to judge whether SPD is damaged and the BO-LSTM prediction model is used to predict the remaining life of SPD. Based on the positioning function of BC20, the real-time geographic location of SPD can be viewed on the host computer. The results show that the root mean square error and average absolute error of the BO-LSTM prediction model are 0.001 3 and 0.001 8, and the system can monitor the SPD status in real time, effectively predict the remaining life value of SPD, and give early warning in time.
-
Yang Yi, Aimen Malik, Yuan Ruifu, Wang Keping
2024,47(6):41-49, DOI:
Abstract:
Hydraulic support pillar pressure prediction has been a pivotal basis for decision-making in the mining process. It has been one of the fundamental pieces of information for ensuring the stability of the surrounding rock. However, although the pressure of hydraulic support pillars followed certain patterns, it couldn’t be predicted using simple mathematical models. Additionally, during the mining process, issues such as the support detaching the roof, roof fragmentation, and sensor detection errors introduced a significant amount of random noise, turning the pressure data into a non-stationary time series. This significantly complicated the pressure prediction. Based on the Transformer model, this paper proposed a differencing non-stationary Transformer model, which introduced differencing normalization and de-normalization operations in the Transformer′s Encoder and Decoder, respectively, to enhance the stationarity of the series. At the same time, a de-stationary attention mechanism was deployed within the Transformer to calculate the correlations between sequence elements, which thereby enhanced the model′s predictive capabilities. Comparative experiments on a real coal mine support pillar dataset showed that the differencing non-stationary Transformer model proposed in this paper achieved a prediction performance of 0.674, which was significantly better than LSTM, Transformer, and non stationary Transformer models.
-
Zhou Guoliang, Zhang Daohui, Guo Xiaoping
2024,47(6):190-196, DOI:
Abstract:
The gesture recognition method based on surface electromyography and pattern recognition has a broad application prospect in the field of rehabilitation hand. In this paper, a hand gesture recognition method based on surface electromyography (sEMG) is proposed to predict 52 hand movements. In order to solve the problem that surface EMG signals are easily disturbed and improve the classification effect of surface EMG signals, TiCNN-DRSN network is proposed, whose main function is to better identify the noise and reduce the time for filtering the noise. Ti is a TiCNN network, in which convolutional kernel Dropout and minimal batch training are used to introduce training interference to the convolutional neural network and increase the generalization of the model; DRSN is a deep residual shrinkage network, which can effectively eliminate redundant signals in sEMG signals and reduce signal noise interference. TiCNN-DRSN has achieved high anti-noise and adaptive performance without any noise reduction pretreatment. The recognition rate of this model on Ninapro database reaches 97.43% 0.8%.
-
Zhou Jianxin, Zhang Lihong, Sun Tenghao
2024,47(6):79-85, DOI:
Abstract:
Aiming at the problems that the standard honey badger algorithm (HBA) is easy to fall into local optimum, low search accuracy and slow convergence speed, a honey badger algorithm based on elite differential mutation (EDVHBA) is proposed. The elite solution searched by the two optimization strategies in the standard HBA is combined with differential mutation to generate a new elite solution. The use of three elite solutions to guide the next iteration of the population can increase the diversity of the algorithm solution and prevent the algorithm from falling into premature convergence. At the same time, the nonlinear density factor is improved and a new position update strategy is introduced to improve the convergence speed and optimization accuracy of the algorithm. In order to verify the performance of the algorithm, simulation experiments are carried out on eight classical test functions. The results show that compared with other swarm intelligence algorithms and improved HBA, EDVHBA can find the optimal value 0 in the unimodal function, and converge to the ideal optimal value in the multimodal function after about 50 iterations, which verifies that EDVHBA has better optimization performance.
-
Cheng Dongxu, Wang Ruizhen, Zhou Junyang, Zhang Kai, Zhang Pengfei
2024,47(6):137-142, DOI:
Abstract:
For the tobacco industry, there is currently no detection device and method for detecting the heating temperature and temperature uniformity of heated cigarette smoking sets. In order to solve the temperature measurement needs of micro rod-shaped heating sheets in a narrow space, this article developed a cigarette heating rod thermometer, and designed a new structure suitable for temperature measurement of cigarette heating rods. In order to verify the accuracy and reliability of the measurement results of the cigarette heating rod thermometer, uncertainty analysis of the thermometer was performed. The analysis results are based on the "GB/T 13283-2008 Accuracy Level of Detection Instruments and Display Instruments for Industrial Process Measurement and Control" standard. The measurement range is 100 ℃~400 ℃, meeting the requirements of level 0.1. The final experiment verified that the heating temperature field of different cigarettes can be effectively measured.
-
Peng Duo, Luo Bei, Chen Jiangxu
2024,47(6):50-57, DOI:
Abstract:
Aiming at the non-range-ranging location problem of multi-storey WSN structures, a three-dimensional indoor multi-storey structure location algorithm IAODV-HOP algorithm based on improved Tianying is proposed in the field of large-scale indoor multi-storey structure location for some large commercial supermarkets, hospitals, teaching buildings and so on. Firstly, the nodes are divided into three types of communication radius to refine the number of hops, and the average hop distance of the nodes is modified by using the minimum mean square error and the weight factor. Secondly, the IAO algorithm is used to optimize the coordinates of unknown nodes, and the population is initialized by the best point set strategy, which solves the problem that the quality and diversity of the population are difficult to guarantee due to the random distribution of the initial population in the Tianying algorithm. In addition, the golden sine search strategy is added to the local search to improve the position update mode of the population, and enhance the local search ability of the algorithm. Through simulation experiments, compared with traditional 3D-DV-Hop, PSO-3DDV-Hop, N3-3DDV-Hop and N3-ACO-3DDV-Hop, the normalized average positioning error of the proposed algorithm IAODV-HOP is reduced by 70.33%, 62.67%, 64% and 53.67%, respectively. It has better performance, better stability and higher positioning accuracy.
-
Xu Ziqiang, Li Cheng, Mu Lianbo, Wang Suilin, Liu Jianjun
2024,47(6):143-150, DOI:
Abstract:
To improve the positioning accuracy of the leakage application of the direct buried hot water heating pipe network by acoustic method, based on the analysis of the applicability of various wavelet threshold functions, an improved threshold function noise reduction method is proposed. This method can theoretically overcome the constant deviation of the soft threshold function and the shortcomings of the hard threshold function signal oscillation. Through setting adjustment parameters, improving the noise reduction ability, and retaining the signal of the region less than the threshold point to avoid effective signal loss. The experiment was carried out in a large direct buried hot water circulation pipe network. The research showed that the leakage positioning error was within ±1 m and the positioning accuracy reached 0.11%~3.49%. Finally, the acoustic leakage detection method was adopted in a practical engineering case of a Beijing heating system. The leakage location error is 0.37%~0.66%, and the positioning accuracy has efficiently is improved.
-
2024,47(6):28-33, DOI:
Abstract:
With the increasing demand for satellite network, vehicle-connected network, industrial network and other service simulation, this paper proposes a multi-session delay damage simulation method based on delay range strategy to build flexible software network damage simulation, aiming at the problems of small number of analog links, low flexibility and high resource occupation of traditional dedicated channel damage instruments. In this method, the delay damage of each session flow is identified and controlled independently, and the multi-queue merging architecture based on time delay strategy is adopted to reduce the resource consumption. The experimental results show that compared with the traditional dedicated device and simulation software NetEm, the proposed method supports the independent delay configuration of million-level links, increases the number of session streams from ten to one million, and reduces the memory consumption by at least 85% under each bandwidth, which meets the requirements of large scale and accuracy, and greatly reduces the system cost.
