Rolling bearings fault diagnosis method based on NRBO-SVM

A fault diagnosis model is proposed for the analysis of rolling bearing vibration signals, aimed at overcoming challenges related to fault identification and low classification accuracy. The model leverages a Newton-Raphson-based optimizer (NRBO) to optimize the parameters of the Support Vector Machine (SVM). By integrating the NRBO algorithm into the optimization process of SVM parameters, an NRBO-SVM fault classification model is constructed, enhancing the adaptive capability and classification accuracy of SVM. This model processes fault features for both fault identification and classification purposes. Notably, experimental results demonstrate that the NRBO-SVM algorithm achieves a satisfactory classification performance, outperforming traditional SVM algorithms in terms of classification accuracy.