Rolling bearing fault diagnosis based on RQA with STD and WOA-SVM

A rolling bearing fault diagnosis method based on Recursive Quantitative Analysis (RQA) combined with time domain feature extraction and Whale Optimization Algorithm Support Vector Machine (WOA-SVM) is proposed. Firstly, the recurrence graph of the vibration signal is drawn, and the nonlinear feature parameters in the recurrence graph combined with Standard Deviation (STD) are extracted by recursive quantitative analysis method to generate feature vectors; after that, in order to construct the optimal support vector machine model, the Whale Optimization Algorithm is used to optimize the c and g parameters. Finally, both Recursive Quantitative Analysis and standard deviation are combined with the WOA-SVM model to perform fault diagnosis of rolling bearings. The rolling bearing datasets from Case Western Reserve University and Jiangnan University were used for example analysis, and the fault identification accuracy reached 100% and 95.00%, respectively. Compared to other methods, the method proposed in this paper has higher diagnostic accuracy and wide practical applicability, and the risk of accidents can be reduced through accurate fault diagnosis, which is also important for safety and environmental policies. This research originated in the field of mechanical fault diagnosis to solve the problem of fault diagnosis of rolling bearings in industrial production, it builds on previous research and explores new methods and techniques to fill some gaps in the field of mechanical fault diagnosis.