Time-Series Transfer Learning: An Early Stage Imbalance Fault Detection Method Based on Feature Enhancement and Improved Support Vector Data Description

• Published in: IEEE transactions on industrial electronics (1982) Vol. 70; no. 8; pp. 8488 - 8498
• Main Authors: Ni, Xueqing, Yang, Dongsheng, Zhang, Huaguang, Qu, Fuming, Qin, Jia
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.08.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Data imbalance; Data models; early stage fault detection; Employee welfare; Fault detection; feature enhancement; Feature extraction; Generative adversarial networks; Generators; Learning; mismatched working condition; power pole tower; Task analysis; Time series
• ISSN: 0278-0046; 1557-9948
• DOI: 10.1109/TIE.2022.3229351

Early stage fault detection plays a pivotal role in Industrial equipment accidents avoidance and scientific maintenance. While limited by the complex operation background, its application encounters with the conundrum of fault feature indistinctness. To address the challenge, a time-series transfer learning (TSTL) method is proposed, which contains two phases: first, early stage series are transferred to their corresponding serious stage for fault feature enhancement. Moreover, due to the improvement of model structure and loss function, the limitation of mismatched working condition is well-weaken. Second, a transferred fault mode recognition model is trained by using transferred normal series that provides a novel solution for data imbalance. Finally, the TSTL method is verified by actual vibration datasets of power pole tower bolts. Its superiority in feature transfer and fault detection is confirmed by several groups of comparative experiments and results demonstrate TSTL outperforms mainstream methods.