基于Petri网模型的顺序离散事件机电系统在线Bayes故障诊断方法

Fault Diagnosis with Bayes of Sequential Discrete Event Mechatronic Systems Based on Petri Net

提出了顺序离散事件机电系统的概念,并基于Petri网理论,研究了赋时简单串联顺序事件Petri网对该类系统建模.将变迁过程的时间度量看成统计量,提出一种Bayes试验鉴定方法,用于对统计量方差差异进行显著性检验,并通过结合Bayes方法与先验知识对系统进行故障诊断.实验结果表明,该故障诊断算法能够充分将经验知识和实时监测数据相结合,可以较准确地检测某物料自动输送系统的故障.

This paper presented a novel method for fault diagnosis of a proposed sequential discrete event mechatronic（SDEM） system based on Petri net.A timed series connection of sequential discrete event Petri net was defined to model the SDEM system.Time measurement of transition was considered as a statistic.A Bayes based test certification method was put forward and applied in the significant test of variance difference.The prior knowledge was well combined with the real time monitoring information based on the proposed method.It was used in fault diagnosis of an automatic material transfer system and the results illustrate the validity and the feasibility of the method.