Parallel Decision Models Based on Support Vector Machines and Their Application to Distributed Fault Diagnosis

摘要

In industrial process, there are many complex distributed systems. To ensure such system operates under working order, distributed parameter values are often inspected from subsystems or different points in order to judge working conditions of the system and make global decisions. In this paper, two parallel decision models based on support vector machine (PDMSVMs) are proposed and applied to the distributed fault diagnosis on diesel engine. Simulation results show PDMSVMs perform well in fault diagnosis. PDMSVMs are very convenient to information fusion of distributed decision system. PDMSVMs make decision based on synthetic information of subsystems and can richly exploit information of subsystems according to significance of subsystems to whole system. Therefore decisions made by PDMSVMs are reliable and accurate.