TY - JOUR

T1 - Health prognosis of bearings based on transferable autoregressive recurrent adaptation with few-shot learning

AU - Zhuang, Jichao

AU - Jia, Minping

AU - Huang, Cheng Geng

AU - Beer, Michael

AU - Feng, Ke

N1 - Funding Information: The authors gratefully acknowledge the financial support of the National Natural Science Foundation of China (No. 52075095 ) and the China Scholarship Council. And the authors would like to appreciate the anonymous reviewers and the editor for their valuable comments.

PY - 2024/4/1

Y1 - 2024/4/1

N2 - Data-driven prognostic and health management technologies are instrumental in accurately monitoring the health of mechanical systems. However, the availability of few-shot source data under varying operating conditions limits their ability to predict health. Also, the global feature extraction process is susceptible to temporal semantic loss, resulting in reduced generalization of extracted degradation features. To address these challenges, a transferable autoregressive recurrent adaptation method is proposed for bearing health prognosis. In the enhancement of few-shot data, a novel sample generation module with attribute-assisted learning, combined with adversarial generation, is introduced to mine data that better matches the source sample distribution. Additionally, a deep autoregressive recurrent model is designed, incorporating a statistical mode to consider the degradation processes more comprehensively. To complement the semantic loss, a semantic attention module is developed, embedded into the basic model of meta learning. To validate the effectiveness of this approach, extensive bearing prognostics are conducted across six tasks. The results demonstrate the clear advantages of this proposed method in bearing prognosis, especially when dealing with limited bearing data.

AB - Data-driven prognostic and health management technologies are instrumental in accurately monitoring the health of mechanical systems. However, the availability of few-shot source data under varying operating conditions limits their ability to predict health. Also, the global feature extraction process is susceptible to temporal semantic loss, resulting in reduced generalization of extracted degradation features. To address these challenges, a transferable autoregressive recurrent adaptation method is proposed for bearing health prognosis. In the enhancement of few-shot data, a novel sample generation module with attribute-assisted learning, combined with adversarial generation, is introduced to mine data that better matches the source sample distribution. Additionally, a deep autoregressive recurrent model is designed, incorporating a statistical mode to consider the degradation processes more comprehensively. To complement the semantic loss, a semantic attention module is developed, embedded into the basic model of meta learning. To validate the effectiveness of this approach, extensive bearing prognostics are conducted across six tasks. The results demonstrate the clear advantages of this proposed method in bearing prognosis, especially when dealing with limited bearing data.

KW - Adversarial augmentation

KW - Autoregressive regression

KW - Meta learning

KW - Remaining useful life

KW - Semantic attention mechanism

UR - http://www.scopus.com/inward/record.url?scp=85183972482&partnerID=8YFLogxK

U2 - 10.1016/j.ymssp.2024.111186

DO - 10.1016/j.ymssp.2024.111186

M3 - Article

AN - SCOPUS:85183972482

VL - 211

JO - Mechanical Systems and Signal Processing

JF - Mechanical Systems and Signal Processing

SN - 0888-3270

M1 - 111186

ER -