关键词: 纤维, 拉伸断裂, 声发射信号, 增强经验模态分解, 主成分分析, 最小二乘支持向量机

Abstract:

For problems of acoustic emission signal of fiber tensile fracture such as nonstationarity and high overlap between signal characteristics, a model was presented for the feature extractionof acoustic emission signal and fiber type diagnosis. This model can be used to identify the type of fibers that are stretched. Firstly, different kinds of tensile fracture acoustic emission signals were preprocessed and decomposed by wavelet transform and ensemble empirical mode decomposition (EEMD). Then, the frequency characteristics were extracted by the principal component analysis (PCA). Finally, least squares support vector machine (LSSVM) was used to classify the characteristic frequency of the fiber stretched. Results show that the principal component analysis method can further select the eigenvector sets of the two kinds of fiber tensile fracture acoustic emission signals, and make the signal characteristics from high dimensional to low dimensional. At the same time, the correlation between the features is reduced, and the accuracy of recognition of fiber tensile fracture of AE signal is improved. The EEMD-PCA-LSSVM model has a total recognition rate of 96% for the acoustic emission signals of PMIA ( poly-m-phenylene isophthalamide) and high performance vinylon fiber.

Key words: fiber, tensile failure, acoustic emission, ensemble empirical mode decompositon, principal component analysis, least squares support veotor maohine