Adversarial Retain-Free Unlearning for Bearing Prognostics and Health Management
Authors:
- 26 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 22 (6) , 5231-5241
Abstract
Prognostics and health management (PHM) systems increasingly rely on machine learning for reliable bearing fault diagnosis. However, data deletion in PHM remains an open problem. Since retraining a model from scratch is often infeasible, this raises a new challenge. Moreover, in most cases, only the pretrained model and the user-requested data are available. Existing approaches under this constraint often fail to achieve proper unlearning and substantially degrade model performance, thereby disrupting the original embedding space and collapsing the structural integrity of the pretrained model. To address this, we propose adversarial retain-free unlearning (ARU). Our framework integrates adversarial samples generated from the pretrained model with a semantic-driven loss to preserve representational stability. Experiments on public and private bearing datasets demonstrate that ARU achieves unlearning efficacy and structural consistency comparable to Retrain while maintaining diagnostic accuracy. We believe that our proposed framework provides a practical and reliable solution for retain-free unlearning in real-world industrial PHM systems.Keywords
Funding Information
- National Research Foundation of Korea (RS-2025-20252986)
- Institute of Information and Coummunications Technology Planning and Evaluation, Information Technology Research Center (IITP-2026-RS-2024-00438056)
This publication has 37 references indexed in Scilit:
- Black-box adversarial examples via frequency distortion against fault diagnosis systemsApplied Soft Computing, 2025
- Evaluating practical adversarial robustness of fault diagnosis systems via spectrogram-aware ensemble methodEngineering Applications of Artificial Intelligence, 2024
- Anomaly-Based Intrusion Detection System using One-Dimensional Convolutional Neural NetworkProcedia Computer Science, 2023
- Generating Transferable Adversarial Examples for Speech ClassificationPattern Recognition, 2022
- Artificial intelligence in prognostics and health management of engineering systemsEngineering Applications of Artificial Intelligence, 2022
- Prognostics and Health Management (PHM): Where are we and where do we (need to) go in theory and practiceReliability Engineering & System Safety, 2022
- Intelligent fault diagnosis for rolling bearings based on graph shift regularization with directed graphsAdvanced Engineering Informatics, 2021
- Prognostics and health management design for rotary machinery systems—Reviews, methodology and applicationsMechanical Systems and Signal Processing, 2014
- The EU Proposal for a General Data Protection Regulation and the roots of the ‘right to be forgotten’Computer Law & Security Review, 2013
- Spearman Rank Correlation2005