Related papers: Generalized multiscale feature extraction for remaining useful life prediction of bearings with generative adversarial networks

Generalized multiscale feature extraction for remaining useful life prediction of bearings with generative adversarial networks

URL: http://arxiv.org/abs/2109.12513v1
Date: Sun, 26 Sep 2021 07:11:55 GMT
Title: Generalized multiscale feature extraction for remaining useful life prediction of bearings with generative adversarial networks
Authors: Sungho Suh, Paul Lukowicz, Yong Oh Lee
Abstract summary: Bearing is a key component in industrial machinery and its failure may lead to unwanted downtime and economic loss. It is necessary to predict the remaining useful life (RUL) of bearings. We propose a novel generalized multiscale feature extraction method with generative adversarial networks.
Score: 4.988898367111902
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Bearing is a key component in industrial machinery and its failure may lead to unwanted downtime and economic loss. Hence, it is necessary to predict the remaining useful life (RUL) of bearings. Conventional data-driven approaches of RUL prediction require expert domain knowledge for manual feature extraction and may suffer from data distribution discrepancy between training and test data. In this study, we propose a novel generalized multiscale feature extraction method with generative adversarial networks. The adversarial training learns the distribution of training data from different bearings and is introduced for health stage division and RUL prediction. To capture the sequence feature from a one-dimensional vibration signal, we adapt a U-Net architecture that reconstructs features to process them with multiscale layers in the generator of the adversarial network. To validate the proposed method, comprehensive experiments on two rotating machinery datasets have been conducted to predict the RUL. The experimental results show that the proposed feature extraction method can effectively predict the RUL and outperforms the conventional RUL prediction approaches based on deep neural networks. The implementation code is available at https://github.com/opensuh/GMFE.