- Conference Article
1
- 10.1109/ddcls55054.2022.9858515
Bearing Fault Diagnosis Based on Multiple Feature Transfer Learning Network
- Aug 03, 2022
- Huanzhang Qiao + 3 more +3
The intelligent fault diagnosis methods have gained great success, they usually depend on large amounts of labeled data. Unfortunately, it is a realistic problem to collected massive labeled data in actual industrial scene. In addition, even labeled data is easy to collect, the methods trained by these labeled data may not be able to classify unlabeled data obtained under different working states. Inspired by transfer learning, in the paper we propose a deep learning-based fault diagnosis method named multiple feature transfer learning network (MFTLN) to resolve the data distribution difference due to changed working conditions. MFTLN employee multiple extractors to get domain-invariant features and align source domain and target domain by maximum mean discrepancy (MMD) metric. We performed six bearing fault diagnosis transfer learning experiments to verify the superiority of the proposed method, the experimental results indicated that the recognition accuracy of the proposed method is obviously higher than those of the other 5 popular domain adaptive fault diagnosis methods when the target domain data is unlabeled.
Read more