A Fault Diagnosis Method Based on Improved Pattern Spectrum and FOA-SVM

Abstract

A fault diagnosis method using improved pattern spectrum (IP S) and F OA−SV M is proposed. Improved pattern spectrum is introduced for feature extraction by employing morphological erosion operator, and this feature is able to present fault information for roller bearing on different scales. Simulation analysis is processed and shows that, the value of IP S has a steady distinction among different fault types and the calculating amount is less than traditional method. After feature extraction, SV M with F OA, which can help with seeking optimal parameters, is employed for pattern recognition. Experiments were conducted, and the proposed method is verified by roller bearing vibration data including different fault types. The classification accuracy of the proposed approach on training is 87.5% ( 21 24 ) and reaches 91.7% ( 44 48 ) in a testing data set. The analysis shows that the method has a good diagnosis effect and an acceptable recognition result.

Market Risk Early Warning Based on Deep Learning and Fruit Fly Optimization

“…e results are shown in Table 6. Under the division condition of different sample proportion, models corresponding to different kernel functions and optimal parameter values perform well in G value, F value, and AUC value, and the differences are small, which indicates that the proposed model has good prediction performance and strong generalization ability [29].…”