Physics-Informed Cross-Domain Fault Diagnosis for Rolling Bearings under Robustness and Interpretability: a Novel Feature Adaptation Framework

Cross-Domain Bearing Fault Diagnosis Using Quantile-Based Domain Adaptation and Random Subspace Ensemble

Physics-mechanism consistent fault diagnosis of rolling bearings: a multi-channel image fusion and quantitative interpretable framework

In complex industrial environments, data-driven fault diagnosis of rolling bearings is often constrained by time-varying operating conditions, severe noise interference, and the ‘black-box’ nature of deep learning models. To overcome these challenges, this study systematically integrates an improved Harris Hawks optimization (IHHO) algorithm, a convolutional neural network, and a bidirectional long short-term memory network to establish a physics-consistent fault diagnosis framework. First, a multi-channel image fusion architecture based on continuous wavelet transform is constructed to effectively encode the deep spatiotemporal correlations embedded in triaxial vibration signals. To enhance model adaptability, a Cauchy mutation–based IHHO strategy is introduced for autonomous hyperparameter optimization, effectively alleviating premature convergence to local optima. The core innovation of this work lies in the development of a quantitative interpretability framework centered on a novel metric termed the energy capture ratio (ECR). By jointly employing SHAP and gradient-weighted class activation mapping visualization techniques, the proposed model is demonstrated to exhibit strong physical consistency, enabling adaptive suppression of noise-dominated channels while accurately focusing on theoretically relevant fault resonance frequency bands. Extensive experiments on the HUST, case western reserve university, and southeast university benchmark datasets demonstrate that the proposed framework achieves average diagnostic accuracies of 99.0%, 100.0%, and 99.0%, respectively; even under severe noise interference at −5 dB, the accuracy remains as high as 89.6%. Quantitative evaluations show that the principal-axis relative ECR (RECR) consistently remains above 1.0 across all fault conditions, providing strong evidence for the mechanistic reliability of the model. These findings indicate that the proposed method provides an accurate and reliable solution for predictive maintenance of bearings in practical engineering applications.

Domain-Specific Structured Reliability-Aware Open-Set Domain Adaptation for Cross-Condition Rolling Bearing Fault Diagnosis

Cross-condition fault diagnosis is important for ensuring the reliable operation of mechanical systems. However, most existing methods assume that the source and target domains share identical fault label spaces and data distributions, limiting adaptation to unknown faults and cross-condition shifts in practical industrial scenarios. To address this issue, a structured, reliable, domain-specific open-set domain adaptation method is proposed. The proposed method first constructs a domain-specific batch normalization-based feature extraction network, in which independent normalization branches model statistical discrepancies under different operating conditions; it then designs a cross-domain structured representation consolidation module to enhance feature discriminability through source-domain anchor compactness, target-domain multi-view contrastive, and prototype entropy regularization constraints; an open-set boundary learning mechanism is further introduced to establish a discriminative boundary between known and unknown classes; finally, a reliability-aware pseudo-label propagation strategy refines target-domain pseudo-labels and imposes separate prediction-consistency constraints on known and unknown classes. Experimental results on the CWRU bearing dataset and the self-built rolling bearing dataset show that the proposed method achieves average H-scores of 93.32% and 97.65%, respectively, on open-set transfer tasks. Compared with several baseline methods, the proposed method achieves a better balance between known-class recognition and unknown-class detection, thereby improving cross-condition open-set fault diagnosis performance.

PFA-Net: a physics-informed feature enhancement and attention network for interpretable bearing fault diagnosis under strong noise.

A fault diagnosis network that integrates physical feature enhancement and attention mechanisms-PFA-Net is proposed, providing a structurally clear and high-performance solution for intelligent fault diagnosis.

Noise in Rolling Bearing Fault Diagnosis: From Characterization to Robust Solutions

Rolling bearing fault diagnosis is essential for the reliability and safety of rotating machinery, yet its effectiveness in industrial practice is fundamentally challenged by noise. This narrative review argues that noise in bearing fault diagnosis should not be treated as a single additive disturbance, but rather as a collection of distinct phenomena — environmental and background signal noise, sensor and acquisition noise, operating-condition-induced domain shift, label noise, and compound noise scenarios — each affecting different stages of the diagnostic pipeline and demanding differentiated strategies. This review develops a noise taxonomy for rolling bearing fault diagnosis and systematically examines how each noise type degrades signal processing, feature extraction, and diagnostic decision-making. It surveys denoising strategies, noise-robust feature engineering approaches, and noise-aware diagnostic models through this noise-type lens, identifying which strategies are appropriate for which noise conditions. A standardized evaluation and benchmarking protocol is proposed to address the inconsistency that currently prevents meaningful comparison of noise-robustness claims across studies. The central synthetic contribution is a noise–method matching matrix that maps each noise category to appropriate combinations of denoising, feature, model, and evaluation strategies, providing a structured framework for method selection and future research design. The review concludes that robust bearing fault diagnosis cannot be achieved through a single universal model. The more realistic path forward requires noise-type-aware strategies, standardized multi-noise evaluation, and methods co-designed for industrial deployment constraints.

A generalization bearing fault diagnosis method via joint hierarchical suppression of domain features

A novel joint hierarchical suppression framework is developed, which collaboratively operates on channel and spatial dimensions under domain label supervision to identify and remove domain-specific features in shallow network layers and is embedded into fully connected layers to drive the model to learn residual domain-invariant features, thus greatly boosting generalization performance.