Rolling Bearing Fault Diagnosis Based on Multiscale Permutation Entropy and SOA-SVM

The service conditions of underground coal mine equipment are poor, and it is difficult to accurately extract the fault characteristics rolling bearings. In order better improve accuracy identification bearings, a fault-detection method based on multiscale permutation entropy SOA-SVM proposed. First, whale optimization algorithm used select modal analysis number K penalty factor α variational mode decomposition algorithm. Then, vibration signal bearings dissolved according optimized algorithm, multi-scale main intrinsic function calculated. Finally, feature values matrix entered into SVM by seagull obtain classification result. experimental results published bearing datasets Western Reserve University show that success rate proposed can reach 98.75%. detection be completed efficiently.