A novel intelligent fault diagnosis method of rotating machinery based on signal-to-image mapping and deep Gabor convolutional adaptive pooling network

作者：

Highlights：

• The VSI refines the features to expand the distinction between different faults.

• The GaCF guides the model to extract multi-scale and multi-directional features.

• ADPooling facilitates the learning of critical features and suppresses feature decay.

• The DGCAPN is beneficial to increase the diversity and recognition of features.

• The proposed method improves the accuracy and robustness of fault diagnosis.

摘要

•The VSI refines the features to expand the distinction between different faults.•The GaCF guides the model to extract multi-scale and multi-directional features.•ADPooling facilitates the learning of critical features and suppresses feature decay.•The DGCAPN is beneficial to increase the diversity and recognition of features.•The proposed method improves the accuracy and robustness of fault diagnosis.

论文关键词：Adaptive dynamic pooling,Deep convolution neural network,Fault diagnosis,Gabor filter,Signal-to-image mapping

论文评审过程：Received 19 October 2021, Revised 15 May 2022, Accepted 30 May 2022, Available online 3 June 2022, Version of Record 4 June 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117716