Rolling bearing prognostic analysis for domain adaptation under different operating conditions. (September 2022)

• Record Type: Journal Article
• Authors: Singh Rathore, Maan; Harsha, S.P.
• Is Part Of: Engineering failure analysis. Volume 139(2022)
• Publication Date: 2022-09
• Subjects: Remaining useful life -- Domain adaptation -- Bi-directional LSTM -- Prognostic features -- Transfer learning -- Maximum mean discrepancy; System failures (Engineering) -- Periodicals; Fracture mechanics -- Periodicals; Reliability (Engineering) -- Periodicals; Pannes -- Périodiques; Rupture, Mécanique de la -- Périodiques; Fiabilité -- Périodiques; Fracture mechanics; Reliability (Engineering); System failures (Engineering); Periodicals; Electronic journals; 620.112
• DOI: 10.1016/j.engfailanal.2022.106414
• Languages: English
• ISSNs: 1350-6307

Abstract

Highlights: Develop a framework TBiLSTM that is used to estimate bearing RUL under different operating conditions. The extracted prognostic features are highly correlated with bearing degradation over time are obtained utilizing the BiLSTM network. The distribution discrepancy between different domains is reduced using multi-kernel MMD to realize effective transfer learning. This method provides domain-invariant features which greatly improves the RUL predictions across different domains. The feasibility and superiority of the proposed method are represented on both experimental datasets and IEEE PHM-bearing datasets. The results obtained indicate that the features extracted using TBiLSTM are highly prognostic sensitive and effective domain-invariant features are obtained using MK-MMD. Therefore, suitable for RUL prognostic tasks under different conditions of bearing operation. Abstract: In real-world applications, machinery operates under non-stationary conditions such as operating environment, failure modes, and noise where domain shift problems generally arise. Hence, deep learning methods are trained on one working condition cannot generalize effectively on different conditions. Also, the suitability of prognostic features significantly affects the prediction results. To address these issues, this paper proposes a transfer learning-based bi-directional Long Short-Term Memory (TBiLSTM) network for extracting prognostic sensitive features, and domain adaptation is realized using multi-kernel maximum mean discrepancy (MK-MMD). Therefore, the proposed TBiLSTM network can be utilized for RUL prediction of bearings under multiple working conditions. The superiority and effectiveness of the TBiLSTM method are validated by both experimentation and comparison with state-of-art methods. In addition to this, prediction results demonstrate its effectiveness on IEEE PHM challenge datasets. Hence, the results demonstrate that the prognostic features are more reliable and domain-invariant for RUL prediction.