Intelligent device failure diagnosis method based on support vector machine

Abstract

The invention provides an intelligent device failure diagnosis method based on a support vector machine. The method includes the steps that preprocessing operation is conducted on device data; a failure diagnosis case knowledge base is built; failure diagnosis is conducted on the support vector machine; the failure information is obtained, and troubleshooting guide is conducted. By means of the intelligent device failure diagnosis method based on the support vector machine, the failure feature of a device is highlighted to the maximum degree, the situations that the device data are incomplete and imprecise are reduced, the method provides the possibility for building a precise and reliable failure diagnosis model, the problem of aging of the diagnosis model along with the runtime of the device is solved, the misdiagnosis rate of the failure diagnosis model is reduced, and the correct rate and speed of the device failure diagnosis are increased to the maximum degree.

Description

technical field [0001] The present invention mainly relates to the technical field of equipment fault diagnosis, and more specifically relates to a method in the field of diagnostic research based on a support vector machine. Background technique [0002] In some important occasions such as power plants, ironworks, satellite launch sites, etc., in order to ensure the safe operation of key equipment, factories often invest a large number of maintenance personnel to ensure the safe operation of the equipment. However, due to their own diagnostic skills or attention problems, the staff inevitably ignore some signs of abnormal equipment. Once the abnormal equipment develops into a production failure, it will bring huge economic losses to the enterprise. Therefore, researchers in related fields have invested a lot of energy to establish an intelligent equipment diagnosis system for production enterprises to ensure the safe operation of important equipment in the factory. [0003...

AI Technical Summary

Problems solved by technology

The present invention can highlight the fault characteristics of the equipment to the greatest extent through the regression filtering method, reduce the incomplete and inaccurate situation of the equipment data, and provide the possibility for building an accurate and reliable fault diagnosis model; the present invention is based on the use of support vector machines , use a simple and convenient way to realize the function of model incremental learning, to solve the problem of diagnostic model aging with equipment running time, and reduce the misdiagnosis rate of fault diagnosis model; the present invention uses support vector machines on the basis of identifying new faults , to realize the continuous improvement of the fault knowledge base; the fault diagnosis model realized by the present invention can provide more detailed fault diagnosis information, not only the simple fault type, but also includes the reliability, fault location and origin of each fault that this fault belongs to The fault maintenance guidance and suggestions extracted from the expert knowledge base greatly improved the accuracy and speed of equipment fault diagnosis

Images