Progressive Knowledge-Guided Large Language Model Framework for Bearing Fault Diagnosis
2026-06-15 • Computation and Language
Computation and Language
AI summaryⓘ
The authors developed a new method to detect bearing faults using vibrations by combining physics knowledge with advanced signal analysis. Their approach creates detailed features based on bearing mechanics, allowing quick and accurate fault detection without manual tuning. The method also intelligently focuses on important parts of the vibration signals and combines information across different scales automatically. Tested on public datasets, it showed high accuracy and much faster processing than traditional methods. The authors also confirmed that their features match real physical fault behavior, making their system trustworthy for industrial use.
bearing fault diagnosisvibration signal processingfeature extractionmulti-scale analysisphysics-guided modelingsignal segmentationcharacteristic defect frequenciesfault screeningmeasurement traceabilitydiagnostic accuracy
Authors
Jinghan Wang, Gaoliang Peng, Yanjun Chen, Wei Zhang, Wentao Wu, Tianchen Liu
Abstract
Vibration-based bearing fault diagnosis requires resolving three interrelated measurement challenges, including the trade-off between global statistical feature efficiency and local transient signal fidelity, insufficient traceability of measurement features to underlying fault physics, and ineffective multi-source measurement information fusion across diagnostic scales. This paper presents a progressive physics-guided multi-scale vibration signal processing framework that addresses all three challenges within a unified diagnostic pipeline. An 81-dimensional measurement descriptor, derived from bearing kinematic theory and characteristic defect frequencies, establishes a physically traceable feature space enabling real-time fault screening at approximately 20 ms per sample. A fault-adaptive signal segmentation mechanism then directs analytical attention toward fault-relevant waveform regions guided by physics-based priors, without manual feature engineering. Structured fault mechanism knowledge is further encoded implicitly in model parameters during training, enabling autonomous multi-scale measurement fusion without external knowledge dependencies at inference. Validated on four public benchmark datasets under diverse operating conditions, the framework achieves 98.49% diagnostic accuracy with a 12.6-fold reduction in computational cost relative to signal-level baselines. Interpretability analysis confirms that diagnostic feature activations align with established bearing fault mechanics, supporting measurement traceability in safety-critical industrial systems.