A novel method for rolling bearing fault diagnosis based on multi-domain feature extraction and particle swarm algorithm optimised support vector machine (PSO-SVM)

As a vital component of rotating machinery, the accurate fault diagnosis of rolling bearings is crucial to maintaining project continuity, minimizing economic losses, and ensuring safety. This document introduces an innovative method for diagnosing faults in rolling bearings, utilizing a blend of multi-domain feature extraction and PSO Support Vector Machine (PSO-SVM).This method integrates the time domain, frequency domain, and wavelet packet energy features of vibration signals to construct a comprehensive feature library that enhances sensitivity and classification accuracy. The PSO-SVM model classifies these fault features, with the particle swarm algorithm optimizing the parameters automatically and the support vector machine providing robust interpretability. To validate the effectiveness of the proposed method, tests were conducted using both open-source and laboratory data. Gaussian noise was introduced to the vibration signals to replicate complex operational conditions. The diagnostic accuracy of this model was then benchmarked against traditional SVM and Genetic Algorithm-Back Propagation (GA-BP) models. Evidence shows the technique's high accuracy, sturdiness, sturdiness, and resilience, making it suitable for diagnosing faults in rolling bearings.