基于粗糙集和支持向量机的机械故障诊断系统

提出了一种基于粗糙集和支持向量机(SVM)的机械故障诊断系统：首先将故障诊断决策系统中的连续属性值离散化；再基于粗糙集理论计算决策系统的约简，根据实际需要确定最优决策系统；最后在最优决策系统基础上设计SVM多分类器进行故障诊断。4135柴油机的实际故障诊断结果验证了所提出的粗糙集理论与SVM相结合的故障诊断系统的可行性。

Diagnosis System of Machinery Fault Based on Rough Sets and Support Vector Machines

Considering the ability of rough sets theory on reduction of decision system and that of support vector machines for classification,a diagnosis system of machinery fault based on rough sets and support vector machines is proposed.Firstly,the continuous attributes data in diagnostic decision system are discretized.Then,reducts are found based on rough sets theory,and the key conditions for diagnosis are determined.Lastly,according to the chosen reduct,the multi-class support vector machines are designed for fault diagnosis.The diagnosis of a diesel demonstrates that the system can reduce the cost of diagnosis greatly.And it verifies the feasibility of the engineering application.