Global-focal Adaptation with Information Separation for Noise-robust Transfer Fault Diagnosis

2025-10-15

AI Summary

Industrial fault diagnosis faces dual challenges of noise corruption and domain shift, yet existing methods lack robustness due to assumptions of clean data or domain similarity. This paper proposes a robust cross-domain fault diagnosis framework. Its core innovations are: (1) an information-separation architecture that disentangles fault-relevant features, noise components, and domain-specific discrepancies; and (2) a global–focal adaptive adversarial mechanism that jointly optimizes conditional/marginal distribution alignment and orthogonal feature constraints. Specifically, a focal domain-adversarial classifier and an improved orthogonal loss enable multi-level feature disentanglement and distribution harmonization. Extensive experiments on three public benchmarks demonstrate significant improvements over state-of-the-art methods, validating the framework’s high accuracy and strong transfer robustness under noisy cross-domain conditions. The code and datasets are publicly available.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Computer Vision: Adversarial Attacks & Robustness
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Responsible Web: Algorithmic accountability and transparency on the web
• Systems and Infrastructure for Web, Mobile and WoT: Web applications in cross-disciplinary domains and verticals such as mixed reality, smart cities, and digital health

Abstract

Existing transfer fault diagnosis methods typically assume either clean data or sufficient domain similarity, which limits their effectiveness in industrial environments where severe noise interference and domain shifts coexist. To address this challenge, we propose an information separation global-focal adversarial network (ISGFAN), a robust framework for cross-domain fault diagnosis under noise conditions. ISGFAN is built on an information separation architecture that integrates adversarial learning with an improved orthogonal loss to decouple domain-invariant fault representation, thereby isolating noise interference and domain-specific characteristics. To further strengthen transfer robustness, ISGFAN employs a global-focal domain-adversarial scheme that constrains both the conditional and marginal distributions of the model. Specifically, the focal domain-adversarial component mitigates category-specific transfer obstacles caused by noise in unsupervised scenarios, while the global domain classifier ensures alignment of the overall distribution. Experiments conducted on three public benchmark datasets demonstrate that the proposed method outperforms other prominent existing approaches, confirming the superiority of the ISGFAN framework. Data and code are available at https://github.com/JYREN-Source/ISGFAN

Problem

• Addresses fault diagnosis under noise and domain shifts
• Decouples domain-invariant features from noise interference
• Enhances transfer robustness via global-focal adversarial learning

Innovation

• Information separation architecture decouples domain-invariant fault representation
• Global-focal adversarial scheme constrains conditional and marginal distributions
• Focal component mitigates category-specific transfer obstacles from noise