Research on hydraulic control system fault diagnosis method based on rough set theory

摘要

Hydraulic control system is a typical highly nonlinear system, the loops of the system are coupled each other, so that the failure modes, failure mechanism of the hydraulic control system is very complex and diverse. Fault diagnosis of hydraulic control system is a uncertainty, incomplete information systems, which makes wrong diagnosis. Directing to the hydraulic press's hydraulic control system, a fault diagnosis rules extraction method is proposed based on rough set theory, in which, the fault diagnosis decision table is deducted on attribute through the improved distinct matrix and distinct functions, and construct a decision network of variety reduced levels. Take the attribute reduction set as the initial node of this network; get the decision rule set according to the nodes. At the same time, in order to effectively filter the noise, the concept of rule's coverage is introduced on the basis of accuracy. It further evaluates the extracted rules and acquires the final effective diagnostic rules.