Target-specific Adaptation and Consistent Degradation Alignment for Cross-Domain Remaining Useful Life Prediction

2025-12-02

IEEE Transactions on Automation Science and Engineering

AI Summary

To address performance degradation in cross-domain Remaining Useful Life (RUL) prediction—caused by source-target domain distribution shift, inconsistent degradation phase alignment, and loss of target-specific degradation information—this paper proposes a novel framework integrating domain-invariant learning with target-adaptive modeling. Our key contributions are: (1) a target-domain reconstruction module that explicitly preserves target-specific degradation characteristics; (2) a degradation-phase-aware clustering-based pairing mechanism enabling fine-grained alignment of source and target samples along dynamic degradation trajectories; and (3) an end-to-end trainable architecture combining adversarial domain adaptation, feature disentanglement, and autoencoder-based reconstruction. Extensive experiments on multiple public RUL datasets demonstrate that our method achieves statistically significant improvements over state-of-the-art approaches in both RMSE and MAE, exhibiting strong generalizability across domains. The implementation code is publicly available.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Adversarial Attacks & Robustness
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Accurate prediction of the Remaining Useful Life (RUL) in machinery can significantly diminish maintenance costs, enhance equipment up-time, and mitigate adverse outcomes. Data-driven RUL prediction techniques have demonstrated commendable performance. However, their efficacy often relies on the assumption that training and testing data are drawn from the same distribution or domain, which does not hold in real industrial settings. To mitigate this domain discrepancy issue, prior adversarial domain adaptation methods focused on deriving domain-invariant features. Nevertheless, they overlook target-specific information and inconsistency characteristics pertinent to the degradation stages, resulting in suboptimal performance. To tackle these issues, we propose a novel domain adaptation approach for cross-domain RUL prediction named TACDA. Specifically, we propose a target domain reconstruction strategy within the adversarial adaptation process, thereby retaining target-specific information while learning domain-invariant features. Furthermore, we develop a novel clustering and pairing strategy for consistent alignment between similar degradation stages. Through extensive experiments, our results demonstrate the remarkable performance of our proposed TACDA method, surpassing state-of-the-art approaches with regard to two different evaluation metrics. Our code is available at https://github.com/keyplay/TACDA.

Problem

• Addresses domain discrepancy in cross-domain RUL prediction
• Retains target-specific information during adversarial adaptation
• Aligns similar degradation stages for consistent performance

Innovation

• Target domain reconstruction strategy retains specific information
• Clustering and pairing aligns similar degradation stages consistently
• Adversarial adaptation learns domain-invariant features for cross-domain prediction