Rolling Bearing Failure Mode Identification Based on ECA-ConvNeXt
In order to address the issues of non-stationarity in the acoustic emission signal of rolling bearing faults,the high complexity of feature extraction,and the inadequate feature extraction of intelligent diagnostic models,a fault mode recognition method based on Variational Mode Decomposition(VMD)parameter adaptive optimization combined with Efficient Channel Attention Pure Convolutional Neural Network(ECA-ConvNeXt)was proposed.Experiments show that the proposed method can achieve effective feature information extraction and high accuracy in fault mode recognition,with an average fault identification accuracy of 97.6％.
Rolling bearingAcoustic emissionVariational mode decompositionConvolutional Neural Network
万方数据
维普
