Partial Domain Adaptation in Remaining Useful Life Prediction With Incomplete Target Data

• Published in: IEEE/ASME transactions on mechatronics Vol. 29; no. 3; pp. 1903 - 1913
• Main Authors: Li, Xiang, Zhang, Wei, Li, Xu, Hao, Hongshen
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.06.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation; Adaptation models; Algorithms; Artificial intelligence; Artificial neural networks; Data models; Deep learning; Degradation; domain adaptation; Feature extraction; incomplete target data; Life prediction; Machine learning; Predictive models; Prognostics and health management; remaining useful life (RUL) prediction; Training; transfer learning; Useful life
• ISSN: 1083-4435; 1941-014X
• DOI: 10.1109/TMECH.2023.3325538

Intelligent machinery prognostics and health management (PHM) methods have been attracting growing attention in the past years, with the rapid development of the artificial intelligence algorithms. The remaining useful life (RUL) prediction problem is critical in prognostics for optimization of the maintenance strategy. Despite the promising advances, the current algorithms basically assume the training and testing entities are operating under identical condition, which is less practical in the real industries. In the cross-domain PHM studies, domain adaptation techniques have been successfully applied for building generalized data-driven models. However, the availability of target-domain data in full life cycle is basically required by the existing methods. In most scenarios, only the target data at early degradation period can be obtained, that poses great challenges in transfer learning. This article proposes a partial domain adaptation method for RUL prediction with incomplete target-domain data. Deep neural network-based adversarial learning strategy is adopted as the main framework, and the source-domain instance-weighted degradation fusion scheme is proposed for conditional domain adaptation at similar degradation levels. The source outliers can be well filtered out in learning generalized features across domains. Experiments of machine run-to-failure tests are implemented for validation, and the results indicate the proposed methodology is well suited for practical cross-domain RUL predictions.