Experimental Study on Optimization of Multi-Features of Ultrasonic Signals of Resistance Spot Welding Defects
HUANG Hong 1 , WU Wei 1, 2 , LI Kunhang 1 , YANG Hongrui 1 , YIN Xiangjie 1 ,#br# JIANG Qiming 1 , DENG Zhanying 1
1. Chongqing University of Technology, Chongqing 400054, China ;
2. Chongqing Engineering Research Center for Special Welding Materials and Technology, Chongqing 400054, China
摘要针对铝合金点焊接头常见的气孔、未熔合、无缺陷等超声回波信号,首先采用经验模态分析进行降噪与重构,利用统计学方法分别提取时域、频域中多尺度特征值,分析不同缺陷的特征值变化规律。其次采用主成分分析法与线性判别分析法对特征值进行优化,获得缺陷回波信号的主元特征。最后以主元特征做 BP 神经网络的输入,对缺陷信号进行识别。试验结果表明,两种降维方法构造后的特征量与未经过降维的特征量相比具有更好的分类结果,其中 PCA 作用更优,有效提高了 BP 神经网络的缺陷识别准确率。
Abstract:For the common ultrasonic echo signals of porosity, unfused and defect-free aluminum alloy spot welded joints, noise reduction and reconstruction were first performed with empirical mode decomposition (EMD) analysis, and multi-scale eigenvalues in the time and frequency domains were extracted using statistical methods to analyze the eigenvalue variation patterns of different defects. The principal component analysis (PCA) and linear discriminant analysis (LDA) are used to optimize the feature values and obtain the principal element features of the defective echo signal, finally the principal element features are used as the input of the BP neural network to identify the defect signal. The experimental results show that the feature quantities constructed by the two dimensionality reduction methods have better classification results compared with those without dimensionality reduction, with PCA acting better and effectively improving the defect recognition accuracy of BP neural networks.