Rethinking the Role of Operating Conditions for Learning-based Multi-condition Fault Diagnosis

2025-06-21

AI Summary

Fault feature distribution shifts across operating conditions (e.g., rotational speed, load) degrade the generalization of diagnostic models, while existing domain generalization (DG) methods tend to overfit condition-specific information. Method: We identify the significant modulation effect of operational conditions on fault features and propose a two-stage diagnosis framework: (1) a DG encoder learns condition-invariant fault representations; (2) lightweight retraining adapts the model to the target condition, balancing generalizability and discriminability. Contribution/Results: By decoupling invariant representation learning from condition-specific adaptation, our approach avoids end-to-end DG-induced overfitting to condition-specific patterns. Evaluated on a real-world gearbox dataset, it achieves robust cross-speed and cross-load fault diagnosis, with substantial accuracy improvements. The framework offers an interpretable, deployable paradigm for multi-condition industrial fault diagnosis.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Multi-condition fault diagnosis is prevalent in industrial systems and presents substantial challenges for conventional diagnostic approaches. The discrepancy in data distributions across different operating conditions degrades model performance when a model trained under one condition is applied to others. With the recent advancements in deep learning, transfer learning has been introduced to the fault diagnosis field as a paradigm for addressing multi-condition fault diagnosis. Among these methods, domain generalization approaches can handle complex scenarios by extracting condition-invariant fault features. Although many studies have considered fault diagnosis in specific multi-condition scenarios, the extent to which operating conditions affect fault information has been scarcely studied, which is crucial. However, the extent to which operating conditions affect fault information has been scarcely studied, which is crucial. When operating conditions have a significant impact on fault features, directly applying domain generalization methods may lead the model to learn condition-specific information, thereby reducing its overall generalization ability. This paper investigates the performance of existing end-to-end domain generalization methods under varying conditions, specifically in variable-speed and variable-load scenarios, using multiple experiments on a real-world gearbox. Additionally, a two-stage diagnostic framework is proposed, aiming to improve fault diagnosis performance under scenarios with significant operating condition impacts. By incorporating a domain-generalized encoder with a retraining strategy, the framework is able to extract condition-invariant fault features while simultaneously alleviating potential overfitting to the source domain. Several experiments on a real-world gearbox dataset are conducted to validate the effectiveness of the proposed approach.

Problem

• Addressing multi-condition fault diagnosis challenges in industrial systems
• Studying operating conditions' impact on fault information for diagnostics
• Improving generalization in fault diagnosis under varying operating conditions

Innovation

• Uses domain generalization for fault diagnosis
• Proposes two-stage framework with retraining
• Extracts condition-invariant fault features