Mitigating Negative Transfer Learning in Source Free-Unsupervised Domain Adaptation for Rotating Machinery Fault Diagnosis
- 9 October 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-16
Abstract
Driven by the data-centric industrial revolution, Prognostics and Health Management (PHM) technology based on sophisticated Deep Learning (DL) methods has become crucial for industrial fault diagnosis. Based on well-labeled data, the DL methods further improve PHM development. However, the efficiency of the involved DL methods is impacted significantly due to the limited data collection. To address this problem, Source Free-Unsupervised Domain Adaptation (SF-UDA) has been proposed to improve DL efficiency without fully labeled source data. However, the traditional SF-UDA methods are constrained by predefined label numbers and insufficient distribution alignment. To solve this problem, we propose the use of Initial Pseudo Labels (IPLs) generated through Adaptive Bandwidth-based Mean Shift Clustering (ABMSC), which are then refined using cosine similarity with unlabeled target data, bolstering SF-UDA’s efficiency. Furthermore, we introduce Weight-Aware Regularization (W-AR) to effectively mitigate negative transfer. Experimental results show significant accuracy improvements, with gains of 1.5%-6.7% and 1.3%-5% in the same operating environment, and 0.4%-24.8% and 3.1%-8.6% in different operating environments.Keywords
Funding Information
- Ministry of Science and Technology, Taiwan, (NSTC 111-2628-E-110-011-MY3, NSTC 113-2640-E-A49-005)
This publication has 25 references indexed in Scilit:
- Mitigate the Negative TL using Adaptive Thresholding for Fault Diagnosis2023
- A Systematic Literature Review on Transfer Learning for Predictive Maintenance in Industry 4.0IEEE Access, 2023
- Artificial intelligence for industry 4.0: Systematic review of applications, challenges, and opportunitiesExpert Systems with Applications, 2022
- Source-Free Adaptation Diagnosis for Rotating MachineryIEEE Transactions on Industrial Informatics, 2022
- Exploring Domain-Invariant Parameters for Source Free Domain Adaptation2022
- Intelligent Condition-Based Monitoring Techniques for Bearing Fault DiagnosisIEEE Sensors Journal, 2020
- Momentum Contrast for Unsupervised Visual Representation Learning2020
- Fine-tuning Pre-trained Convolutional Neural Networks for Gastric Precancerous Disease Classification on Magnification Narrow-band Imaging ImagesNeurocomputing, 2020
- A Deep Adversarial Transfer Learning Network for Machinery Emerging Fault DetectionIEEE Sensors Journal, 2020
- A New Deep Transfer Learning Method for Bearing Fault Diagnosis Under Different Working ConditionsIEEE Sensors Journal, 2019