A two-stage estimation method based on Conceptors-aided unsupervised clustering and convolutional neural network classification for the estimation of the degradation level of industrial equipment

作者：

Highlights：

• A novel Conceptors-aided clustering approach for variable-length time series.

• A novel Conceptors-based CNN for degradation level estimation.

• Our Conceptor-aided method avoids the use of sliding time windows.

• Validate our method on a synthetic case and two bearing cases of degradation level estimation.

• Our two-stage degradation level estimation method is superior to other alternative methods.

摘要

•A novel Conceptors-aided clustering approach for variable-length time series.•A novel Conceptors-based CNN for degradation level estimation.•Our Conceptor-aided method avoids the use of sliding time windows.•Validate our method on a synthetic case and two bearing cases of degradation level estimation.•Our two-stage degradation level estimation method is superior to other alternative methods.

论文关键词：Degradation level estimation,Conceptors,Reservoir computing,Time series clustering,Convolutional Neural Network (CNN),Bearings

论文评审过程：Received 8 August 2021, Revised 25 June 2022, Accepted 1 October 2022, Available online 8 October 2022, Version of Record 18 October 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118962