Optimized Spectral Fault Receptive Fields for Diagnosis-Informed Prognosis

2025-06-14

AI Summary

To address the challenges of weak early fault features and insufficient robustness in remaining useful life (RUL) prediction under variable operating conditions, this paper proposes frequency-domain bio-inspired Spectral Fault Receptive Fields (SFRFs), which— for the first time—introduce the retinal ganglion cell center-surround inhibition mechanism into vibration signal processing to enhance weak fault feature extraction. A multi-objective NSGA-II optimization framework is developed, jointly optimizing diagnostic accuracy, health indicator monotonicity, and degradation trajectory smoothness. Furthermore, an interpretable RUL prediction model is realized via a Bagging-based regression ensemble. Evaluated on the XJTU-SY dataset, the proposed method significantly improves early fault detection rate and RUL prediction accuracy, while generating high-monotonicity, low-noise health indicators. Experimental results validate its robustness under variable operating conditions and practical engineering applicability.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Feature Construction/Reformulation

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

This paper introduces Spectral Fault Receptive Fields (SFRFs), a biologically inspired technique for degradation state assessment in bearing fault diagnosis and remaining useful life (RUL) estimation. Drawing on the center-surround organization of retinal ganglion cell receptive fields, we propose a frequency-domain feature extraction algorithm that enhances the detection of fault signatures in vibration signals. SFRFs are designed as antagonistic spectral filters centered on characteristic fault frequencies, with inhibitory surrounds that enable robust characterization of incipient faults under variable operating conditions. A multi-objective evolutionary optimization strategy based on NSGA-II algorithm is employed to tune the receptive field parameters by simultaneously minimizing RUL prediction error, maximizing feature monotonicity, and promoting smooth degradation trajectories. The method is demonstrated on the XJTU-SY bearing run-to-failure dataset, confirming its suitability for constructing condition indicators in health monitoring applications. Key contributions include: (i) the introduction of SFRFs, inspired by the biology of vision in the primate retina; (ii) an evolutionary optimization framework guided by condition monitoring and prognosis criteria; and (iii) experimental evidence supporting the detection of early-stage faults and their precursors. Furthermore, we confirm that our diagnosis-informed spectral representation achieves accurate RUL prediction using a bagging regressor. The results highlight the interpretability and principled design of SFRFs, bridging signal processing, biological sensing principles, and data-driven prognostics in rotating machinery.

Problem

• Develops spectral filters for bearing fault detection in vibration signals
• Optimizes fault detection under variable operating conditions using NSGA-II
• Improves remaining useful life prediction with biologically inspired methods

Innovation

• Biologically inspired spectral fault receptive fields
• Multi-objective evolutionary optimization strategy
• Frequency-domain feature extraction for fault detection