Rolling Bearing Fault Diagnosis Based on Time-Frequency Feature Extraction and IBA-SVM

Accurate fault diagnosis of rolling bearings is necessary to ensure the safe and reliable operation of mechanical equipment. Aiming at the problem of low accuracy of rolling bearing fault diagnosis, a rolling bearing fault diagnosis algorithm based on time-frequency feature extraction and improved bat algorithm-support vector machine (IBA-SVM) model is proposed in this paper. In this algorithm, the feature of the vibration signal in time domain and the frequency spectrum signal obtained by fast Fourier transform (FFT) is extracted, and then the multi-dimensional scaling is used. Multiple dimensional scaling (MDS) algorithm is adopted to reduce the data dimension of eigenvalues to reduce the model complexity, and finally improves the iteration speed and diagnosis accuracy. The improved bat algorithm (IBA) algorithm is used to optimize the parameters of the support vector machine (SVM) model, and the optimal IBA-SVM diagnosis model is obtained for determining the fault type of the rolling bearing. The experimental results show that the accuracy of the proposed rolling bearing fault diagnosis method can reach 99.6667%, which is significantly higher than the state-of-the-art models, and its robustness is stronger. Compared with the existing that use the time-domain or frequency-domain features alone, the proposed algorithm that combines time-domain and frequency-domain features shows significantly improved accuracy in fault diagnosis.