An interpretable data augmentation scheme for machine fault diagnosis based on a sparsity-constrained generative adversarial network

作者：

Highlights：

• A novel SC-GAN data augmentation scheme for stable raw vibration signal generation.

• An interpretation method to open the black box of the proposed neural network model.

• The model can learn frequency domain patterns from time domain vibration signals.

• Data augmentation improves the performance of the machine fault diagnosis model.

摘要

•A novel SC-GAN data augmentation scheme for stable raw vibration signal generation.•An interpretation method to open the black box of the proposed neural network model.•The model can learn frequency domain patterns from time domain vibration signals.•Data augmentation improves the performance of the machine fault diagnosis model.

论文关键词：Generative adversarial networks,Data augmentation,Mechanism interpretation,Machine fault diagnosis,Raw vibration signal

论文评审过程：Received 18 January 2021, Revised 12 April 2021, Accepted 16 May 2021, Available online 23 May 2021, Version of Record 29 May 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115234