- Current Issue
- Online First
- Adopt
- Most Downloaded Archive
-
Mao Jialong, Liu Qingquan, Pan Xu, Wang Ke
2024,47(13):1-9, DOI:
Abstract:
Aiming at the demand of UAV for high-altitude weather detection, in this paper, an armoured platinum resistance temperature sensor with radiation shield is designed. Firstly, a computational fluid dynamics (CFD) approach was employed to work out the solar radiation error of armoured platinum resistance temperature sensors with or without radiation shield under multi-physical fields, and the comparative analysis was carried out. Then, Support Vector Machine (SVM) and Particle Swarm Optimization Support Vector Machine (PSO-SVM) algorithms were used for training data to compare the the forecast models. Finally, a low-pressure wind tunnel experimental setup was constructed for simulating the upper atmosphere environment, and the experimental data and the algorithm prediction results were compared. The experimental findings indicate that the mean measurement discrepancy of the proposed platinum resistance temperature sensor with radiation shield is 0.014 1 K, and the root mean square error is 0.015 0 K.
-
Wang Kuantian, Yao Jiangyun, Tang Yongzhong, Liang Shihua
2024,47(13):10-17, DOI:
Abstract:
This paper addresses the challenges of poor accuracy and reliability in fault diagnosis for hydraulic mechanical drive gear sets by proposing a research approach based on Support Vector Machines (SVM). The study begins by collecting vibration signals from the hydraulic mechanical drive gear group and constructing a fault signal separation model. Utilizing a low-rank algorithm, the research separates the vibration source signals of the hydraulic mechanical drive gearbox. Constraint conditions are designed for gear group fault signals to facilitate their classification. Based on these classification results, the SDAE model is employed to extract fault features from the hydraulic mechanical drive gear group. The extracted features are then input into the SVM for training, with the final output being the optimal diagnostic result. This approach achieves fault diagnosis of the hydraulic mechanical drive gear group based on SVM. Experimental results demonstrate that the classification error rate of this method does not exceed 3.5%, confirming its high feasibility.
-
Liu Jian, Chen Hewei, Zeng Guoqi
2024,47(13):18-26, DOI:
Abstract:
In unexpected emergency response scenarios, it is necessary to quickly obtain global situational images of the scene for subsequent assessment and decision-making. Swarm UAVs have the advantages of large number, low cost and fast imaging, and are widely used in military fields. This paper explores the application of swarm UAV cooperative reconnaissance to the field of emergency remote sensing, and constructs a swarm UAV remote sensing digital simulation and verification system, which researches and simulates and verifies the swarm UAV′s formation coordination, airway planning, and cooperative splicing of multi-channel video. Aiming at the problem of unstable overlap rate between multiple video frames, an adaptive dynamic sampling algorithm is proposed to maintain the idempotence of the overall efficiency of the splicing algorithm under different overlap rates. Subsequently, for the unstable characteristics of video streams in response scenes, a breakpoint re-splicing algorithm is proposed to ensure that the availability of the algorithm can be maintained at the expense of splicing accuracy in poor shooting environments. The results show that: swarm UAVs can construct a global situational image of the scene in quasi real-time, and this paper can provide technical support for the application of swarm UAVs in the field of remote sensing in emergency response.
-
Dai Langjie, Cai Kailong, Wang Ajiu, Huang Fei
2024,47(13):27-34, DOI:
Abstract:
Aiming at the airway fault problems occurring during the operation of aero-engine, an aero-engine airway fault diagnosis model based on Convolutional Neural Network (CNN) combined with Bald Eagle Search Algorithm (BES) Optimized Extreme Learning Machine (ELM) is proposed. The aero-engine airway data are learned by CNN and the fault features hidden in the data are extracted, the BES algorithm is introduced to optimize the weights and biases of the ELM, and the optimized ELM is used to classify the abstract features extracted by the CNN, so as to achieve the purpose of fault diagnosis. The experimental results show that the CNN-BES-ELM-based model achieves an average accuracy of 97.80%, which is 2.7%, 5.4%and 7.35% higher than that of CNN-ELM, CNN and ELM, respectively, and compared with commonly used deep learning models such as Deep Belief Network (DBN) and Stacked Auto Encoder (SAE), the accuracy is improved by 5.4% and 3.4%; and still retains more than 90% accuracy in noise environments such as random noise, Gaussian noise and pretzel noise, which overall shows good diagnostic performance, generalization ability and noise immunity, and provides a theoretical basis for its practical application in aero-engine airway fault diagnosis.
-
Ma Shuaiqi, Ren Sijia, He Haiyu, Zhang Lilei, Zhao Jiayao
2024,47(13):35-44, DOI:
Abstract:
A double-closed-loop linear self-resistant control strategy is designed to solve the problem of the three-phase staggered-parallel bi-directional DC-DC converter affected by uncertainty perturbations in the DC microgrid systems. Firstly, a bidirectional DC-DC mathematical model is established, and the transfer function of the converter is derived by small-signal analysis. Secondly, a double closed-loop system with second-order LADRC in the current loop and first-order LADRC in the voltage loop is designed to estimate and compensate for the external disturbances and the internal uncertainties of the system in real time by designing its corresponding linear extended state observers and linear state error feedback. Finally, the stability of the control system is proved according to the Lienard-Chipard stability criterion, and the three control strategies are simulated in MATLAB/Simulink for comparison and verification under different operating conditions. The simulation results show that, compared with the traditional proportional-integral controller, the control strategy proposed optimizes the maximum dynamic deviation ratio of the bus voltage by 0.5% and 0.97% and shortens the regulation time by 78.3% and 76.9% under the disturbances of 20% voltage increase and decrease on the energy storage side, and optimizes the maximum dynamic deviation ratio of bus voltage by 0.79% and 1.5% and shortens the regulation time by 72% under the disturbances of 20% load increase and decrease, which effectively improves the dynamic performance and anti-disturbance capability of the system under the premise of ensuring the equal flow of each phase.
-
Zhu Yanmin, Li Zhonghu, Wang Jinming, Yang Liqing, Zhang Xinyu
2024,47(13):45-52, DOI:
Abstract:
To study fault prediction methods for wind turbines based on SCADA data, the SCADA data of a 2 000 kW doubly-fed wind turbine over 14 months is used as the research subject. First, the data is preprocessed to ensure its usability. Considering the issues with the traditional Transformer model, such as complex structure and numerous parameter settings, a Transformer model is constructed by introducing a linear decoder structure. This model is then used for fault prediction research on wind turbines. The study shows that the constructed algorithm model has long-term stability, can eliminate false predictions, and can predict faults 6 days in advance, providing a safeguard to prevent sudden shutdowns due to fault deterioration.
-
Wang Siyun, Chen Mingming, Li Zhixin, Lu Shufeng, Bao Jin
2024,47(13):53-60, DOI:
Abstract:
On the basis of existing ways of realizing remote calibration and traceability of measuring instruments, a remote calibration method of electrical parameters based on modern communication technology is proposed. The calibration method combines the remote calibration method with non-physical standards as the transmission object and the standard source method of DC voltage source calibration, which places the standards in the laboratory rather than transmitting them to the field, solving the problems of long calibration period and difficult to measure additional errors of the traditional electrical parameter calibration method. Based on the principle of time-frequency calibration by the satellite co-vision method, the standard voltage source and the calibrated electrical parameters are converted into reliable digital quantities for the remote transmission of the electrical parameters, and the transmission and traceability chain of the electrical parameters is established; the reference voltage remote calibration module of the AD conversion module is designed, and a model of the remote self-calibration of the AD conversion module is established, and the remote calibration algorithm of the electrical parameters based on the satellite co-vision is investigated, and the remote self-calibration algorithm of the A/D conversion is also investigated. The remote self-calibration algorithm of analog-to-digital conversion is studied, and the conversion results of high-precision electric parameter acquisition module are corrected. After data analysis, its accuracy is 0.1 level.
-
Zhang Xiuqing, Hou Xuedong, An Guochen, Yi Hongbo, Wang Xiaojun
2024,47(13):61-67, DOI:
Abstract:
In the satellite navigation and positioning system, due to the low power of the navigation signal, it is easy to be interfered when it reaches the ground, resulting in positioning failure. Adaptive null steering technology can effectively improve the anti-jamming ability of satellite navigation receiver. However, due to the common space-time combined minimum power response, null steering jitter often occurs, so the anti-jamming performance of the receiver can not be effectively aligned. In this case, the paper proposes a method of smoothing and filtering the weights in the anti-interference algorithm, and verifies the feasibility of the algorithm by means of simulation, FPGA implementation and field measurement. This method can effectively suppress the jitter of the system weight and the zero trap position, so as to improve the stability and reliability of the anti-interference algorithm, and has certain reference value for related engineering fields.
-
Song Qiannan, Liu Guangzhu, Wu Lelin, Gai Mingjun
2024,47(13):68-73, DOI:
Abstract:
As research and development in the field of machine vision continue to advance, the requirements for image processing have become more complex and diverse. Edge information detection is particularly important when processing real-time images. This paper designs an FPGA image edge detection system based on the Sobel algorithm, capable of real-time video image acquisition, processing, and display. Adaptive threshold and non-maximum suppression algorithms are used, combined with an 8-direction Sobel edge detection algorithm to improve detection accuracy. The Sobel edge detection algorithm is validated and implemented in hardware before and after improvement. A pipeline design is adopted to generate a sliding window to accelerate image processing and enhance the real-time performance of image processing. Hardware synthesis experiments show that the FPGA image edge detection system based on the Sobel algorithm can efficiently achieve image edge detection of video streams, improving image processing speed by 57%, providing comprehensive edge detail detection, enhancing video image processing efficiency, and can be used for target recognition and tracking research.
-
Zhang Lieping, Chen Yao, Zheng Xinpeng, Lu Haizhao, Zhang Cui
2024,47(13):74-83, DOI:
Abstract:
This paper proposes an information complementation algorithm of K nearest neighbor-random forest with an improved distance formula, aiming at the problem of indoor fingerprint localization fingerprint database data in the real environment with missing data leading to large positioning errors.First, the gathered fingerprint data is preprocessed using Gaussian filtering to eliminate interfering data points and enhance data dependability.Second, the nearest-neighbor set is sampled using the KNN algorithm, which combines Manhattan distance and Euclidean distance.The RF algorithm is then used to optimize the training of the nearest-neighbor set, and the prediction results of each individual decision tree are averaged to determine the predicted values of the missing data.This process is based on the division of the fingerprint data into training and testing sets.Finally, the improved complementary algorithm is compared with KNN, improved KNN,RF and KNN-RF complementary algorithms.The experimental results demonstrate that the modified complementary method in this study has superior prediction accuracy and precision than other algorithms, with a prediction accuracy of 91.3%.In the meantime, the fingerprint library of this paper′s complimentary algorithm has an average positioning error of 1.82 m, which is 1.6%~7.2% less than that of other complementary algorithms, and the positioning performance is improved.
-
2024,47(13):84-88, DOI:
Abstract:
In order to solve the problem of high computational cost of model predictive control when solving nonlinear optimization problems in large nonlinear systems such as wastewater treatment, this paper proposes a reduced-order neural network model predictive control algorithm applied to wastewater treatment benchmark. First, for large-scale nonlinear and strongly coupled systems in wastewater treatment, the intrinsic orthogonal decomposition method is used to construct a reduced-order process model to reduce the complexity of the nonlinear system. Then, the long short-term memory network is used to approximate the reduced-order system, thereby solving the problem that the reduced-order system is difficult to express explicitly. Finally, a model predictive controller is designed based on this reduced-order system to achieve efficient control of wastewater treatment. Experimental results show that while ensuring good control effect, the proposed reduced-order neural network model predictive control strategy significantly reduces the computational time compared with the model predictive control strategy of the first principle model of wastewater treatment.
-
Li Bing, Zhang Yimu, Wei Letao, Wang Yue, Zhai Yongjie
2024,47(13):89-99, DOI:
Abstract:
As an important component of wind turbines, blades are easily affected by the natural environment, leading to damage such as erosion, cracks, and detachment of rubber coats, thereby affecting the efficiency of wind power generation and the safe operation of the unit. A modified YOLOv8 fan blade defect detection algorithm is proposed to address the issue of low accuracy in detecting blade defects in complex environments. The single module SPPF in the backbone feature extraction network is integrated into the LSKA attention mechanism to enhance the network′s attention to important features and improve the performance of the model; Secondly, the Neck section adopts a weighted bidirectional feature pyramid Bi-FPN structure and use FasterBlock to improve the C2f module. The Bi-YOLOv8-faster lightweight network structure is proposed to enhance the multi-scale feature fusion ability of the model and improve the accuracy of small target detection; Finally, the Inner-IoU method, which assists in calculating the loss of bounding boxes, is used to optimize the loss function and improve the accuracy and generalization ability of the model′s defect detection. Through the experiment of defect detection on the image of fan blades, the results show that the proposed method improves the accuracy rate of defect detection by 7.3%, mAP50 by 3.3%, and reduces the number of parameters by 27%.
-
Qi Ruijie, Yuan Yuying, Sun Liyun, Qiao Shichao
2024,47(13):100-109, DOI:
Abstract:
Construction sites such as construction, mining, and exploration are very complex and diverse areas. When conducting helmet wearing detection in such scenarios, there are problems such as severe image occlusion and easy loss of small target information. This article proposes a helmet wearing detection algorithm based on improved YOLOv8n. Firstly, the C2f module of the YOLOv8n model is improved by incorporating an improved inverted residual block attention mechanism, enabling the model to efficiently capture global features and fully utilize the key information of safety helmet features; secondly, by combining the SPPF module and LSKA attention mechanism, the SPPF LSKA module is proposed to enhance the network′s attention to key information of safety helmets and avoid the influence of background information on the detection of safety helmet wearing status in practical complex scenarios; finally, the Inner-SIoU loss function is used to optimize the network model and improve the stability of the model in detecting the wearing status of safety helmets. The experimental results show that the algorithm proposed in this paper can effectively detect the wearing status of helmets in complex environments mAP@0.5 has reached 93.7%, compared to the original YOLOv8 algorithm′s P, R, mAP@0.5 and mAP@0.5:0.95 has increased by 2.4%, 4.0%, 3.4%, and 5.3% respectively, the number of parameters has decreased by 6.7%, and the computational workload has decreased by 4.8%, improving the detection of false and missed safety helmet wearing status, facilitating the deployment of practical detection applications.
-
Wang Zhenzhou, Yang Rong, Su Jingfang
2024,47(13):110-119, DOI:
Abstract:
In recent years, there has been an increasing demand for higher quality cigarette pack packaging. While modern production has significantly increased the speed of cigarette box production and made production equipment more intelligent, surface quality inspection of cigarette boxes still relies on manual methods. Addressing the issues of human error such as missed or incorrect detections in surface defect inspection, a cigarette box defect detection algorithm based on improved YOLOv8 is proposed. Firstly, a Gather-and-Distribute mechanism is introduced into the neck network of YOLOv8 to enhance the model′s fusion capability for information across different hierarchies. Secondly, a scale sequence feature fusion module is incorporated to strengthen the network′s ability to extract information from different scales. Finally, the head network of YOLOv8 is replaced with the Decoder of RT-DETR, eliminating the need for complex post-processing steps such as Non-Maximum Suppression, thereby simplifying the detection process and improving efficiency. Experimental results show that the improved algorithm model achieves a detection accuracy of 94.6% and a detection speed of 121.4 FPS on a self-made cigarette box defect dataset compared to YOLOv8. Moreover, compared with other object detection algorithms, the improved algorithm has certain advantages in terms of detection accuracy and speed, making it more suitable for application in cigarette factories for surface quality inspection of cigarette boxes.
-
2024,47(13):120-127, DOI:
Abstract:
A hybrid optimization algorithm based on Levy-flight improved tuna swarm optimization and variable step size perturbation observation method is proposed to solve the problem that the traditional maximum power point tracking algorithm is prone to local optimality due to the multi-peak power of photovoltaic arrays under local shade conditions. The real-time position update law of Levy-flight improved tuna swarm optimization algorithm is introduced to reduce the possibility of falling into local optimal. A new step change law which changes with the slope of power characteristic is designed to improve the conventional perturbation observation method and increase the maximum power tracking speed. Combining Levy-flight improved tuna swarm optimization and variable step size perturbation observation method, a hybrid optimization algorithm is constructed to further improve tracking accuracy and speed, and suppress the influence of disturbance signals. Simulation results show that the optimization time and tracking error of the proposed algorithm are 0.036 s and 0%, 0.04 s and 1.06%, and 0.05 s and 1.06%, respectively, under the three lighting conditions of uniform full illumination, static local shading and dynamic local shading, which are superior to other comparison algorithms. And more accurate and fast to achieve the maximum power tracking of photovoltaic systems.
-
2024,47(13):128-135, DOI:
Abstract:
The three-dimensional path planning problem of unmanned aerial vehicle (UAV) is a very complex global optimization problem. However, UAV path planning based on heuristic optimization algorithms has the problems of slow speed and insufficient accuracy. To solve this problem, a UAV path planning method that improves the dung beetle optimization algorithm is proposed. First, an improved dung beetle optimization algorithm (BCLDBO) is proposed by introducing Bernoulli chaos map, variable spiral search strategy, new inertia weight and Levy flight strategy. Through experimental comparison with other algorithms on six benchmark test functions, it is proved that the BCLDBO algorithm has higher optimization accuracy and faster convergence speed. Secondly, the path planning objective function is established through the track length cost, height cost, smoothing cost and threat cost, and three-dimensional mission spaces with different complexities are constructed. Finally, the BCLDBO algorithm is applied to the UAV three dimensional path planning problem, which proves that this algorithm has lower path cost and better path planning effect than other algorithms.
-
Li Zicheng, Jia Wei, Zhao Xuefen, Gao Hongjuan
2024,47(13):136-147, DOI:
Abstract:
Existing staining normalization methods are unable to accurately extract the complex structural features of colorectal pathological images, resulting in the loss of partial structural information and the inability to generate high-quality staining-normalized colorectal pathological images. To address this issue, a staining normalization method for colorectal pathological images based on a conditional diffusion model is proposed. The proposed method includes conditional diffusion model and image feature reconstruction. In conditional diffusion model，firstly, the Markov chain forward process is employed to add noise to the original colorectal pathological images. Then, the noisy images and conditional images are input into an enhanced denoising network for denoising. During this process, an enhanced activation module is utilized to learn the deep features of the colorectal pathological images and capture more contextual information. A skip-connection spatial attention module is introduced between the encoder and decoder to accurately extract the positional spatial information of the colorectal pathological images. Finally, a pyramid feature extraction module is designed to extract the features of the multi-scale conditional images and generated images, and a reconstruction loss function is constructed to optimize the performance of the entire network. Experimental results demonstrate that compared with existing methods, the proposed staining normalization method can generate higher-quality staining-normalized colorectal pathological images on public datasets GlaS and CRAG.
-
Li Jintao, Zhou Xinglin, Yin Yufei, Ao Siming
2024,47(13):148-156, DOI:
Abstract:
This paper proposes an improved TAS-YOLO network model method based on YOLOv5s to address the issues of low accuracy, high missed and false detection rates, and difficulty in collecting uniformly distributed defect types datasets for detecting small road surface defects. Firstly, in the prediction result stage, a context decoupling head for a specific task is used to enhance the accuracy of the localization detection box by separating classification and localization tasks; secondly, by using the FPN structure to input feature maps of 5 scales into the decoupling head for prediction, the multi-scale feature information of small targets is enhanced; finally, use the silde loss function to optimize YOLOv5 and improve the detection accuracy of difficult to classify samples. The experimental results showed that TAS-YOLO algorithm improved the average detection accuracy of various defects, with mAP50 reaching 91.4% and FPS reaching 126, which improved the detection accuracy and efficiency compared with mainstream detection algorithms such as YOLOv7l, YOLOv8s, YOLOv9c-gelan and Efficientdet.
-
Liu Gang, Yan Shuguang, Liu Yu, Hou Enxiang, Huang Yingzheng
2024,47(13):157-166, DOI:
Abstract:
To address the issue of missed and false detections for distant small objects and occluded objects in current road target detection algorithms in autonomous driving scenarios, a road target detection algorithm based on an improved YOLOv8n is proposed. In terms of feature extraction, the Receptive-Field Attention Convolution is lightweightly improved, and the C2f module is reconstructed to solve the problem of non-shared parameters in convolution calculations, enabling the network to effectively capture critical information. Then, a lightweight point sampling operator is introduced to reduce the loss of feature details during the upsampling process, better preserving image detail information. In terms of feature fusion, a multi-scale feature fusion network is designed to enhance small target feature information and enrich the bidirectional fusion of features at different scales. Simultaneously, a normalization attention mechanism is used to suppress irrelevant background information interference, improving the model′s anti-interference capability. Experimental results show that the proposed improved algorithm achieves detection accuracies of 92.6% and 78.7% on the KITTI dataset and the Udacity dataset, respectively, representing improvements of 2.1% and 1.6% compared to the original algorithm. The model still meets lightweight requirements and enhances adaptability to complex road scenes to a certain extent.
-
2024,47(13):167-175, DOI:
Abstract:
Low illumination environments can lead to situations such as inconspicuous image target features and severe noise interference, which affect the detection performance of the object detector.To address the above problems, a multi-scale image feature enhancement module FEM is constructed, and in conjunction with YOLOv8s object detection network, an end-to-end low-light image object detection method FE-YOLO is constructed.Firstly, FEM is employed to extract feature information from the input image at three different scales and efficiently fuse them to obtain an enhanced image with rich feature representation.Then, in the neck network of YOLOv8s, a target feature enhancement module TFE is incorporated. TFE works by suppressing background noise information in higher-level features, thereby accentuating the representation capacity of target features.The experimental results show that the mean average precision mean (mAP) on the low-light image object detection dataset ExDark reaches 75.63%, which is 3.03% higher than the original YOLOv8s algorithm, and this paper′s algorithm achieves a better detection result in the low-light object detection task.
-
Li Hui, Li Guangya, Wu Jie, Yu Jinning
2024,47(13):176-182, DOI:
Abstract:
Aiming at the defects of existing algorithms such as structural confusion and texture blurring when repairing murals with complex patterns, a dual-generation adversarial network model incorporating structural and textural feature guidance is proposed. Firstly, U-Net is introduced into the dual-generation network, and the texture and structure information extracted by using the direction and channel dual-attention mechanism guides the structure and texture decoders to complete the feature reconstruction of the structure and texture, respectively, and combines with the null residual block and the jump connection to achieve the extraction of multi-scale feature fusion. Secondly, the feature maps output from the two branches are deeply fused by the dual gated feature fusion module to complete the feature information interaction. Finally, the defect repair is completed through the joint dual-discriminator confrontation, enhancing the detail richness and global consistency of the mural restoration effect.The experiments use self-made dataset of non-national treasure real murals somewhere in Wutai Mountain for training and testing, and verified by comparison experiments and ablation experiments, this paper achieves an average improvement of 4.24 dB in the peak signal-to-noise ratio metric, and improves an average of 3.6% in structural similarity index. The experiments show that the method can effectively repair the damaged murals, so that they present better structural and textural information, and the visual effect is clearer and more natural.
-
Zhao Yongsheng, Yan Zhiyuan, Mao Ruixia, Wu Zhang, Zhu Hongna
2024,47(13):183-190, DOI:
Abstract:
Due to complex image backgrounds, multiscale coexistence and wide distribution of targets in underwater optical image target detection, an underwater target detection algorithm named MEAS-YOLO is proposed here. Firstly, this algorithm augments training samples to achieve data enhancement by utilizing the Mosaic and Mixup algorithms. Secondly, the efficient multi-scale attention module is integrated with the YOLOv5 backbone section to enhance the model′s feature extraction capabilities. Simultaneously, the adaptively spatial feature fusion structure is introduced to enable the model to fully integrate features of different scales. Finally, the SIoU is used in the network model to improve detection accuracy. Experimental results demonstrate that our model has a mAP of 86.4% on the URPC 2020 dataset, improving the mAP by 2.1% than that of original model. This model exhibits high detection accuracy and lower model params, which provides a new support for precise underwater target detection.
-
Zhao Yang, Wang Junkai, Lin Zhiyi, Zhou Zhongxiang, Xu Sen
2024,47(13):191-198, DOI:
Abstract:
To address the challenges posed by the diverse types of defects, significant size variations, and high complexity of existing models with insufficient detection accuracy in steel surface defect detection, this paper proposes a detection algorithm named YOLOv8-ODAW based on an improved YOLOv8n. Firstly, Omni-dimensional Dynamic Convolution (ODConv) was introduced to enhance the capability of capturing multi-dimensional features and reduce information loss. Secondly, an Asymptotic Feature Pyramid Network (AFPN) was embedded to improve the feature fusion process, enabling direct interaction between non-adjacent level features and effectively alleviating semantic disconnection. Finally, the Wise-IoUv3 loss function with a dynamic non-monotonic focusing mechanism was adopted to optimize bounding box regression, accelerating network convergence while improving detection accuracy. A series of experiments were conducted on the NEU-DET dataset, and the results demonstrated that the modified YOLOv8-ODAW network model outperformed the original network model with a 7.3% increase in mAP at 50% and a 21.95% decrease in computational complexity (GFLOPs). This showcases superior localization and recognition capabilities for steel surface defects while meeting the speed requirements for industrial applications.
Volume 47, 2024 Issue 13
Research&Design
Theory and Algorithms
Information Technology & Image Processing
-
Research on underwater image super-resolution reconstruction based on improved SRResNet
Abstract:
Due to the absorption and scattering of light by water characteristics, underwater images usually present problems such as blurred details and low resolution. In order to improve the clarity of underwater images, an underwater image super-resolution reconstruction method that improves SRResNet is proposed. This method introduces the hybrid attention mechanism into the deep residual network to enhance the clarity of underwater images. Secondly, the structural similarity loss function is introduced to better protect image content, improve image quality, and make the training results more consistent with human visual perception. Experimental results show that the underwater image super-resolution reconstruction method based on improved SRResNet can effectively deal with problems such as blurred underwater images and low resolution. Compared to various other underwater image reconstruction methods on different datasets, this method improved the PSNR by 0.69 dB to 2.43 dB and the SSIM by 2.66% to 7.17%, demonstrating superior performance across all metrics.
- 1
-
Individual identification method for communication radiation sources by integrating time-frequency characteristics
Abstract:
In response to the problem of low accuracy in individual identification of communication radiation sources under channel noise interference, a communication radiation source individual identification method that integrates time-frequency characteristics is proposed by utilizing the difference in channel noise interference suppression effect of signal mapping to different time-frequency domains. Firstly, extract I/Q, power spectrum, and wavelet spectrum information from the radiation source signal, and fuse the time-frequency information of the signal through one-dimensional convolution in both horizontal and vertical directions; Then, the channel attention module and spatial attention module are used to fuse time-frequency features; Finally, M-ResNeXt network is used to achieve individual identification of radiation sources under channel noise interference. The experimental results show that under the interference of three channel noises, Gaussian white noise with a signal-to-noise ratio (SNR) of 15dB, Rayleigh, and Rician, the recognition accuracy of the proposed time-frequency feature fusion method reaches 97.6%, 97.7%, and 98.5% respectively. Even when facing unknown noise interference at an SNR of 15dB, it can still achieve a recognition accuracy of over 97.7%. Therefore, the time-frequency feature fusion method can significantly improve the accuracy and robustness of individual communication radiation source identification.
- 1
-
Deep Learning Networks for Motor Imagery EEG Signal Classification
Abstract:
Motor imagery (MI) EEG signals are more difficult to recognize due to the inclusion of long, continuous eigenvalues as well as their own strong individual variability and low signal-to-noise ratio. In this study, we propose a model that combines a con-volutional neural network (CNN) with a Transformer, aiming to effectively decode and classify motor imagery EEG signals. The method takes the original multichannel motor imagery EEG signals as input, and learns the local features of the entire one-dimensional temporal and spatial convolutional layers by firstly performing a convolutional operation on the temporal domain of the signals in the first temporal convolutional layer, and then subsequently performing a convolutional operation on the null domain of the signals in the second spatial convolutional layer. Next, the temporal features are smoothed by averaging the pooling layers along the temporal dimension and passing all the feature channels at each time point to the attention mechanism to extract the global correlations in the local temporal features. Finally, a simple classifier module based on a fully connected layer is used to classify the EEG signals for prediction. Through experimental validation on the publicly available BCI competition dataset IV-2a and dataset IV-2b, the results show that the model can effectively classify MI EEG signals with average classification accuracies of up to 80.95% and 84.79%, which is an improvement of 6.45% and 4.31% in comparison to the EEGNet network, respectively, and effectively improves motor imagery evoked potential signals of the brain-computer interface performance.
- 1
-
Adaptive sliding mode control of permanent magnet synchronous motor with unknown disturbance information
Abstract:
In the absence of disturbance information, the chattering effect in terminal sliding mode control of a permanent magnet synchronous motor (PMSM) becomes more pronounced. To reduce the impact of unknown uncertainties and disturbances on control performance, this paper presents an improved adaptive fast terminal sliding mode control method based on a disturbance observer. First, a mathematical model of the PMSM is developed, accounting for parameter uncertainties and load disturbances, and a nonsingular fast terminal sliding surface is designed to enhance the system’s response speed. A disturbance observer is then utilized to estimate system uncertainties and unknown disturbances, with an adaptive gain introduced in the sliding mode controller to compensate for estimation errors, achieving adaptive robust control without requiring a known upper bound for disturbances. This improved adaptive control strategy dynamically compensates for disturbances, strengthening the system’s adaptability to unknown disturbances. Simulation and experimental results demonstrate that, in the absence of disturbance information, the proposed method effectively suppresses chattering caused by sliding mode control, improves the robustness of the PMSM system, and significantly enhances control accuracy and dynamic performance.
- 1
-
Vehicle trajectory extraction method at intersection based on multi-target tracking optimization
Abstract:
To address the problems of accuracy and efficiency limitations in traditional methods of studying vehicle trajectories and accelerate the promotion of digital road traffic management, this paper proposes a vehicle trajectory extraction method at intersections based on multi-target tracking optimization. First, based on the YOLOv8s algorithm framework, a multi-branch convolution strategy was introduced and an image processing method combining standard convolution and depthwise separable convolution was designed to improve the robustness of the model to different scenes and maintain a stable frame rate. Then, the loss function of the DeepSORT algorithm is improved by accurately quantifying the angle difference and distance loss to increase the convergence speed of the model and the accuracy of handling irregular objects. Finally, the accurate extraction of vehicle trajectories is ensured by deriving the conversion relationship between the pixel coordinate system and the real-world coordinate system. The experimental results show that the improved model has improved mAP, recall rate and MOTA by 2.9%, 5.6% and 0.7% respectively compared with the original model, and the number of encoding transformations (IDS) has decreased by 64%. The frame rate can be kept stable during detection. And by deriving the conversion relationship between the pixel coordinate system and the real-world coordinate system, the vehicle"s trajectory information in the surveillance video can be accurately extracted. This provides methodological support for in-depth research on vehicle characteristics and road traffic risks, and has high practical application value.
- 1
-
Multi-purpose cruise path planning based on the two-way A-star and the gray wolf algorithms
Abstract:
A path planning method based on an improved synchronous bidirectional A-star algorithm and grey wolf optimization algorithm is proposed for the multi-objective cruising path planning problem of unmanned boats. Firstly, the traditional A-star algorithm has been improved by introducing a synchronous bidirectional search strategy and dynamic weight adjustment, reducing path redundancy points and algorithm computation time. Then, the cruise path planning problem is transformed into a classic traveling salesman problem and solved using an improved grey wolf optimization algorithm to obtain the optimal cruise path. The experimental results show that the method proposed in this paper is superior to traditional methods in terms of total distance, number of turns, and computation time in path planning. It can effectively improve the cruising efficiency and safety of unmanned boats and provide a reliable solution for multi-target point cruising tasks of unmanned boats.
- 1
-
Lightweight leather defect detection method based on improved YOLOv8
Abstract:
In order to solve the problems such as the large amount of YOLOv8 parameters affecting the detection speed, this paper proposes a lightweight leather defect detection algorithm based on the YOLOv8 framework by using automotive seat leather as a sample for defect detection on the surface of automotive seats. Firstly, the original backbone network of YOLOv8 is replaced with the lightweight network StarNet, which achieves the mapping of high-dimensional and nonlinear feature spaces through star arithmetic, thus demonstrating impressive performance and low latency with a compact network structure and low energy consumption. Second, the original detection head is replaced with a lightweight shared convolutional detection head (LSCD), which allows for a significant reduction in the number of parameters through the use of shared convolution, making the model lighter so that it can be easily deployed on resource-constrained devices. Finally, the C2f module of the neck network is replaced by the C2f_Star module, which fuses feature maps of different scales while the network is more lightweight to improve the accuracy and robustness of target detection. Experimental validation of the model on the home-made HSV-Leather dataset shows that the improved YOLOv8-Leather detection model outperforms the YOLOv8n model. Compared to the YOLOv8n model, the improved model reduces the number of parameters by 57%, improves the detection speed by 20%, reduces the model weights by 52%, and reduces the computation by 53%. The experiment verifies the feasibility of the improved model in solving the problem of leather surface defect detection.
- 1
-
Research on improved YOLOv8 urban driving road obstacle detection algorithm
Abstract:
Aiming at the current problems of insufficient obstacle detection accuracy, slow detection speed, large number of model parameters and poor detection of small target obstacles in the complex environment of urban roads, an improved YOLOv8n lightweight urban driving road obstacle detection algorithm is proposed. Firstly, the MRObstacle urban road obstacle target detection dataset is produced to extend the types and numbers of obstacle detection; secondly, a new SPS_C2f backbone network is designed to improve the backbone network, to reduce the number of network parameters and to improve the detection speed, and the M_ECA attention module is added to the Neck portion of the network, to improve the network detection speed and the feature expression ability; thirdly, the BiFPN is integrated with a feature pyramid and a small target detection algorithm is added to the network. feature pyramid and adding a small target detection head to better capture the features of small-sized obstacles; finally, using the loss function MPDIoU that optimises the values of the bounding box width and height to improve the performance of the network bounding box regression. Compared with the original YOLOv8n algorithm, the mAP0.5 metric of this algorithm is improved by 2.04% to 97.12%, the FPS value is improved by 12.08 frames per second (fps) to 107.45 fps, and the volume of the network parameter is reduced by 10% to 2.73 MB.This algorithm improves the detection accuracy and speed while decreasing the number of parameters, and it can be better applied to the urban road obstacle detection task.
- 1
-
Combining view-aware CNN and Transformer for Alzheimer's disease diagnosis research
Abstract:
To address the low diagnostic accuracy of Alzheimer's Disease (AD) caused by the subtle complexity and spatial heterogeneity of brain lesions in Structural Magnetic Resonance Imaging (sMRI) of AD patients, a hybrid architecture that combines the strengths of Convolutional Neural Networks (CNN) and Transformers is proposed for the AD diagnosis. First, a multi-view feature encoder is designed, in which a view local feature extractor with integrated hybrid attention mechanisms is employed to extract complementary information from the coronal, sagittal, and axial views of sMRI. The semantic representation of lesion regions is further enhanced through a multi-view information interaction learning strategy. Second, a cascaded multi-scale fusion subnetwork is designed to progressively fuse multi-scale feature map information, enhancing discriminative ability. Finally, a Transformer encoder is used to model the global feature representation of full-brain sMRI. Results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset show that the proposed method achieves classification accuracies of 94.05% for AD and 81.59% for Mild Cognitive Impairment (MCI) conversion prediction, outperforming several existing methods.
- 1
-
Improved photovoltaic cell defect detection for YOLOv8
Abstract:
Aiming at the problems of false detection and missing detection in the complex background of photovoltaic cell defect detection, an improved YOLOv8 based photovoltaic cell defect detection algorithm was proposed. Firstly, the bidirectional feature pyramid network is used as the feature fusion mechanism to achieve multi-scale feature fusion through top-down and top-down paths. Secondly, the context aggregation module is introduced into the neck network, and the context information of different receptive fields is obtained by using the cavity convolution of different cavity convolution rates, which helps the model to identify small targets more accurately, and thus improves the target detection performance of the model. Finally, the boundary frame loss function is optimized and its weight factor is adjusted continuously to improve the convergence speed and efficiency of the model. The experimental results show that compared with the detection network of YOLOv8 algorithm, the recall rate and average accuracy are respectively increased by 10.4% and 1.8%, and the detection frame rate reaches 270 frames /s, ensuring the lightweight requirements of real-time detection and subsequent deployment. The improved algorithm can carry out robust detection of photovoltaic cell defects under complex background.
- 1
-
Lightweight detection of flame and smoke on improved YOLOv8n
Abstract:
To address the issues of low accuracy and slow speed in flame and smoke detection in natural environments, this paper proposes an im-proved lightweight YOLOv8n-based detection algorithm for flames and smoke. The algorithm replaces the backbone network of YOLOv8n with the lightweight PP-LCNet network, introduces the CARAFE upsampling operator to enhance detail capture and reduce information loss, and adds the EMA attention mechanism module to improve the model’s ability to recognize and extract detection targets. Experimental results show that the improved YOLOv8n reduces the number of parameters by 0.89MB and the computational cost by 1.8G compared to the base-line YOLOv8n. Furthermore, compared with Faster R-CNN, SSD, YOLOv4, YOLOv5s, YOLOv7, YOLOv8n, and models from the liter-ature, it achieves precision, recall, mAP50, and F1 scores of 96.5%, 94.7%, 95.3%, and 95.6%, respectively, demonstrating the best perfor-mance. The improved algorithm not only enhances detection accuracy but also achieves lightweight characteristics, making it highly valuable for practical applications.
- 1
-
sleep staging based on attention gated multi-layer perceptron mechanisms
Abstract:
Sleep staging has attracted much attention as an important method for studying sleep disorders in recent years. The majority of the current automatic sleep staging methods focus on studying time-domain information and ignore the interrelation between features, resulting in low sleep classification accuracy. To solve these problems, a multi-scale features and attention gated multi-layer perceptron mechanisms named MA-SleepNet is proposed for automatic sleep stage classification, using single-channel electroencephalogram (EEG) signals. The network consists of a multi-scale feature extraction (MFE), squeeze and excitation network (SE), and an attention gated multi-layer perceptron mechanism(aMLP). The MFE module uses convolutional kernels of different sizes to fully extract different scale features from EEG signals. The SE module further optimizes the weight of features and improves the feature expression ability of the network. The aMLP module combines multi-layer perceptron with gating mechanism, adds tiny self-attention mechanism to realize data communication between different dimensions and integrates powerful feature representation.The MA-SleepNet model is evaluated on two public datasets, Sleep-EDF-20 and Sleep-EDF-78. It achieves the accuracy of 86.1% and 83.2% on the Fpz-Cz channel, respectively. Compared with the existing sleep staging methods, our method improves the classification performance.
- 1
-
Improve the Small Target Detection Algorithm of YOLOv8 UAV Aerial Image
Abstract:
Aiming at the problems of low feature extraction capability and scale diversity in UAV aerial images, an improved YOLOv8 object detection algorithm for UAV aerial images is proposed. Firstly, P2 layer is added to enhance the small target detection capability of the model. Secondly, the bidirectional feature alignment fusion method is designed to improve the neck. Combining the idea of feature alignment module and bidirectional feature pyramid, the multi-scale fusion capability of the model is improved to achieve a more complete feature fusion. Then, bi-level routing-spatial attention module is designed and added to the backbone. By connecting the bi-level routing attention module and spatial attention module, the feature capturing ability of the target is strengthened. Finally, the loss function Focaler-XIoU is designed to solve the influence of sample difficulty distribution on border regression, and enhance the stability and detection effect of the model. The experimental results show that the improved network model has improved the VisDrone dataset mAP50 by 9.2%, which has better detection effect than the current mainstream target detection algorithm, and can well complete the UAV aerial image detection task.
- 1
-
Research on the prediction of the remaining life of internal corrosion in oilfield water injection pipelines
Abstract:
In order to estimate the remaining safe service life of the pipeline, the extreme gradient boosting algorithm model besed on grey correlating analysis was proposed. Grey Relational Analysis (GRA) was used to calculate and rank the correlation values between each influencing factor and the remaining life, and the data of the influencing factors with high correlation were preferably input into the eXtreme Gradient Boosting (XGBoost) algorithm for the prediction of the remaining life of corroded pipelines. Taking an oilfield water injection pipeline as an example, the results showed that the Root Mean Square Error (RMSE) was 0.012, the Mean Absolute Error (MAE) was 0.068, and the goodness of fit (R2) was 0.999, compared with the other three prediction models, the results showed that the prediction accuracy and generalization performance of the model constructed in this paper were better.
- 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.
-
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.
-
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.
-
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.
-
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.
-
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.
-
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.
-
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.
-
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.
-
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%.
-
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.
-
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.
-
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.
-
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%.
-
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.
-
Li Hui, Hu Dengfeng, Zhang Kai, Zou Borong, Liu Wei
2024,47(6):164-172, DOI:
Abstract:
In signal generation algorithms, a large number of labeled signal samples are needed for network training, but it is usually difficult to obtain signals carrying message information markers in bulk. To address this problem, this paper proposes a method based on CycleGAN and transfer learning, which realizes the generation of Enhanced LORAN signals without the need for a large number of signals and the corresponding messages as markers and uses migration learning to generate them quickly with a small number of measured signals. The structure of the CycleGAN includes two generators and two discriminators, using the Enhanced LORAN signals and message data sets that do not need to be one-to-one correspondence, so that the generator learns the interconversion relationship between the two data sets, and realises that the input message data can generate the Enhanced LORAN signals corresponding to it, for the characteristics of the Enhanced LORAN signal, the network model is improved using a one-dimensional convolution, residual network, and self-attention mechanism. Experimentally confirmed, it is confirmed that the mean square error of the signal generated by this paper with the measured data is 0.015 3, the average Pearson correlation coefficient is 0.984 3, and the accuracy of the contained message information is 99.02%. To verify the universality of the algorithm, this paper validates the algorithm on PSK, ASK, and FSK datasets, and the experimental results show that the generated signals satisfy the expectations and provide a new idea for signal modulation and demodulation with unknown parameters.
