Journal
KNOWLEDGE-BASED SYSTEMS
Volume 238, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.knosys.2021.107932
Keywords
Time-series fault diagnosis; Long short-term memory; Deep metric learning; Quadruplet data pair; Imbalanced classification
Categories
Funding
- National Natural Science Foundation of China [61872063]
- Shenzhen Science and Technology Program, China [JCYJ20210324140407021]
- intelligent Terminal Key Laboratory of Sichuan Province, China [SCITLAB-0006]
Ask authors/readers for more resources
This paper proposes a deep learning framework for fault diagnosis that addresses the issue of imbalanced samples. It introduces a novel data pair and loss function to improve classification performance and encourage mining of imbalanced data.
Deep learning based methods are attractive and meaningful in the field of fault diagnosis recently. However, the sample size of different faults may be imbalanced in practical application scenarios, which results in performance degeneration. The optimization of data representation could be an effective way to alleviate such phenomenon. In this paper, a deep learning framework considering time series and distance metric called LSTM-Quadruplet Deep Metric Learning(LSTM-QDM) model is proposed. It maps original space to a feature space where the distribution of imbalance faults is more distinguishable. A novel quadruplet data pair is designed which adds a minor sample from imbalanced classes into traditional data pair. Based on such data pair, a quadruplet loss function is proposed to increase the distance between the imbalanced classes and other classes, and its combination with softmax loss would improve the representation ability and classification performance simultaneously. The proposed data pair and loss function encourage the full mining of imbalanced data in the training process. The experiments are carried out on two open-source datasets including TE and CWRU, and the fault diagnosis performance is validated under different imbalanced conditions. The experimental results indicate that our proposed model is effective and robust in the imbalanced fault diagnosis task. (c) 2021 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available