许桢英,罗来齐,王匀,俞慧芳,刘欢.基于PCA的管道缺陷导波信号特征优化方法[J].电子测量技术,2016,39(4):160-163
基于PCA的管道缺陷导波信号特征优化方法
Feature optimization method of pipe defect guided signals based on PCA
  
DOI:
中文关键词:  超声导波  管道检测  缺陷识别  主成分分析  特征优化  BP神经网络
英文关键词:ultrasonic guided wave  pipe defection  defect recognition  PCA  feature optimization  BP neural network
基金项目:
作者单位
许桢英 江苏大学机械工程学院镇江212013 
罗来齐 江苏大学机械工程学院镇江212013 
王匀 江苏大学机械工程学院镇江212013 
俞慧芳 江苏大学机械工程学院镇江212013 
刘欢 江苏大学机械工程学院镇江212013 
AuthorInstitution
Xu Zhenying School of Mechanical Engineering, Jiangsu University, Zhenjiang 212013,China 
Luo Laiqi School of Mechanical Engineering, Jiangsu University, Zhenjiang 212013,China 
Wang Yun School of Mechanical Engineering, Jiangsu University, Zhenjiang 212013,China 
Yu Huifang School of Mechanical Engineering, Jiangsu University, Zhenjiang 212013,China 
Liu Huan School of Mechanical Engineering, Jiangsu University, Zhenjiang 212013,China 
摘要点击次数: 382
全文下载次数: 419
中文摘要:
      针对超声导波管道缺陷检测中存在的识别率低、鲁棒性差等问题,应用了主成分分析对管道缺陷回波信号进行特征优化。首先,通过对超声导波缺陷回波信号进行处理,提取了信号在时域和时频域内的特征参数,构成联合特征向量。然后使用主成分分析法(principal component analysis,PCA)对联合特征向量进行降维处理,通过提取累计贡献率达到89%的主成分得到融合特征。最后用BP神经网络对融合特征进行训练和识别。这种方法可以有效的识别管道缺陷,与联合特征向量相比具有更高的识别率。
英文摘要:
      In order to solve low recognition rate and poor robustness in pipe defect recognition based on ultrasonic guided wave, principal component analysis (PCA) is used to optimize the feature of pipe defect echo signals. First, a few characteristic parameters in domain of time and time frequency were extracted by means of dealing with the ultrasonic guided echo signals of the pipe defect to construct a multi feature vector. The multi feature vector dimension is then reduced using principal component analysis. The fusion feature is generated by extracting the principal component whose cumulative contribution rate is about 89%. Finally, BP neural network is used to train and recognize fusion feature. This method can effectively recognize the pipe defect, and has higher recognition rates than that of the multi feature vector.
查看全文  查看/发表评论  下载PDF阅读器