Joint training of a predictor network and a generative adversarial network for time series forecasting: A case study of bearing prognostics

作者：

Highlights：

• Perform data augmentation for deep learning model in bearing prognostics.

• Adopt ISO standard, using RMS in velocity domain as bearing health indicator.

• Develop a GAN-LSTM method that integrates the LSTM prediction model into GAN.

• The proposed method is evaluated by a numerical problem and a practical example.

摘要

•Perform data augmentation for deep learning model in bearing prognostics.•Adopt ISO standard, using RMS in velocity domain as bearing health indicator.•Develop a GAN-LSTM method that integrates the LSTM prediction model into GAN.•The proposed method is evaluated by a numerical problem and a practical example.

论文关键词：Long short-term memory,Generative adversarial network,Time series prediction,Bearing prognostics

论文评审过程：Received 19 December 2021, Revised 25 March 2022, Accepted 25 April 2022, Available online 7 May 2022, Version of Record 17 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117415