基于模糊神经Petri网的故障诊断模型

Research on Fault Diagnosis Model Based on Fuzzy Neural Petri Nets

Petri网是对具有产生式规则的故障诊断系统的有力建模工具,但其缺乏较强的学习能力.本文以Petri网的基本定义为基础,结合模糊逻辑和Petri网模型,定义了模糊Petri网模型,在此基础上引入人工神经网络技术,给出了人工神经网络的模糊Petri网表示方法,并针对工程机械故障诊断异步、离散等特点,提出并建立了故障诊断的模糊神经Petri网模型及其改进模型.基于模糊神经Petri网的故障诊断系统结合了Petri网和人工神经网络的优点,经过自学习后同时具有很强的推理能力和自适应能力.

Petri net is a powerful modeling tool for fault diagnosis system based on production rules. But Petri net lack of stronger learning ability, In this paper, based on the basic definition of Petri nets, combined with the fuzzy logic, a fuzzy Petri nets model is given. On this foundation, imported the artificial neural networks, introduced the fuzzy Petri nets model of neural networks, Considered the asynchronous and discrete measures in fault diagnosis of engineering machines, presented and established Fuzzy Neural Petri Nets model of fault diagnosis as well as amendment model. Fault diagnosis system based on fuzzy neural Petri net has the advantages both of Petri net and artificial neural networks. It has powerful reasoning ability and adap- tation ability.