Mechanical Fault Diagnosis Using a SVDD Intelligent Algorithm in Fabrics

Abstract

To shorten the time and improve the accuracy in mechanical fault diagnosis, the fault diagnosis mechanism is studied of the high voltage switch in power system, and a new system is proposed as a fast, safe, and accurate mechanical fault diagnosis scheme of high voltage switch. First, the basic structure and common faults of high voltage switches are analyzed, the feature data set has a poor classification effect, and the SVM (Support Vector Machine) algorithm model can process all the feature data for an effective classification and recognition process. Finally, the high voltage switches mechanical faults are extremely scattered, the improved SVDD (Support Vector Data Description) intelligent algorithm can acquire, screen, and classify the mechanical faults data. The results of the improved SVDD intelligent algorithm are less affected by the classification boundary and converge to the average sample value. The new fault diagnosis system is proposed for a high voltage switch based on the improved SVDD intelligent algorithm. Subsequently, the simulation experiment is conducted for a high voltage switch fault diagnosis system based on the SVDD intelligent algorithm. The experimental results show that compared with the traditional mechanical fault diagnosis system, the proposed system can identify new fault types effectively. Meanwhile, the proposed system can quickly and efficiently classify and identify the operation states and fault types of machinery. Consequently, the accuracy of the mechanical fault diagnosis system is improved, providing technical support for the power system operation. Hence, the proposed fault diagnosis system is very suitable for the production of the power system and can greatly promote mechanical fault diagnosis in China.