Blade Fault Diagnosis Based on Hybrid Physics and Domain Adaptation: A Case Study of Variable-Speed Marine Current Turbines
As a machine learning approach, domain adaptation methods are widely applied in cross-scenario fault diagnosis. However, the target domain may need more annotated data, posing challenges to the performance of domain adaptation methods. This paper proposes a fault diagnosis method based on hybrid physics and domain adaptation (HPDA) with its application to marine current turbines (MCTs) scenarios. Specifically, this method first establishes a rotational feature alignment model based on physical variables. Then, it aligns the feature of the target domain data with physical parameters. Finally, an augmented domain adversarial model is trained using pre-alignment samples. Data from MCT prototypes are collected to validate the effectiveness of the proposed method. Experimental results demonstrate the proposed method's superior stability and data transferability compared with the state-of-the-art.
Funding
National Natural Science Foundation of China 62303305
National Natural Science Foundation of China 62303308
National Natural Science Foundation of China U2141234
Shanghai Pujiang Program 23PJ1404700
National Key R and D Program of China 2022ZD0119900
Shanghai Science and Technology program 22015810300
Hainan Province Science and Technology Special Fund ZDYF2021GXJS041
History
Email Address of Submitting Author
xietao0906@sjtu.edu.cnORCID of Submitting Author
0000-0001-7911-0517Submitting Author's Institution
Shanghai Jiaotong UniversitySubmitting Author's Country
- China