基于Petri网的设备故障诊断研究

A Study on Fault Diagnosis of Equipment Based on Petri Nets

基于设备故障诊断知识的特点，采用层次树结构统一表示故障深浅知识。对普通Ｐｅｔｒｉ 网进行拓展定义，并用拓展Ｐｅｔｒｉ 网综合实现故障知识的表示和故障的诊断推理。诊断时首先基于拓展Ｐｅｔｒｉ 网模型的正向可达性分析进行正向不确定推理，限定可能的故障模块，然后基于Ｐｅｔｒｉ 网模型的反向推理功能在故障模块内具体诊断出故障原因。基于ＦＭＳ故障诊断知识的分析，文中给出了一个利用拓展Ｐｅｔｒｉ 网进行知识表示和推理的实例，证明了方法的可行性。

Based on the characteristics of diagnostic knowledge of equipment's faults, the hierarchy tree is adopted to represent both deep and shallow diagnostic knowledge. Then the common Petri Net is defined extendedly. Extended Petri Nets are used to realize the knowledge representation and fault diagnosis. In fault diagnosis the uncertain forward reasoning based on the forward reachability analysis of Petri Nets is firstly carried through to locate possible faulty modules, whereafter the detailed fault causes are determined in the faulty modules by using the backward reasoning based on Petri Nets' backward reachability analysis. In the end,based on some diagnostic knowledge of FMS, an example is presented to show how the extended Petri Nets works,testifying the feasibility of the method.