Weibo Yang1, *, Jing Li2, Wei Peng2, Aidong Deng3
CMC-Computers, Materials & Continua, Vol.63, No.1, pp. 283-299, 2020, DOI:10.32604/cmc.2020.07511
Abstract Based on the theory of modal acoustic emission (AE), when the convolutional neural network (CNN) is used to identify rotor rub-impact faults, the training data has a small sample size, and the AE sound segment belongs to a single channel signal with less pixel-level information and strong local correlation. Due to the convolutional pooling operations of CNN, coarse-grained and edge information are lost, and the top-level information dimension in CNN network is low, which can easily lead to overfitting. To solve the above problems, we first propose the use of sound spectrograms and their differential features to construct multi-channel image… More >
Login
Register
