摘要
针对随机系统模型,提出一种随机离散事件系统的故障预测方法.先对随机离散事件系统的故障可预测性进行形式化,再通过引入概率转移矩阵构建一个故障预测器自动机,得到关于随机离散事件系统的故障可预测性的充分必要条件.由此,在故障预测器的基础上,通过计算其扩展马尔可夫矩阵,可判定随机离散事件系统是否具有故障可预测性,从而实现对故障事件在其发生之前的准确预测.
An approach for failure prediction for stochastic DESs modeled by stochastic finite state automata isproposed. Firstly, the notion of predictability of failure events of stochastic systems is formalized. Then a predictorautomaton is constructed by introducing the probability transition matrix, and a necessary and sufficient conditionof the predictability of stochastic systems is presented. Based on the fault predictor, a method for checking whetherthe considered stochastic DES has been equipped with the capability of failure prediction is developed bycomputing the extended Markov matrix, which results in the realization of accurate prediction of the failure eventsbefore occurring.
作者
叶彬彬
刘富春
Ye Bin-bin;Liu Fu-chun(School of Computers,Guangdong University of Technology,Guangzhou 510006,China)
出处
《广东工业大学学报》
CAS
2018年第6期83-89,共7页
Journal of Guangdong University of Technology
基金
国家自然科学基金资助项目(61273118
6167020389)
广东省教育厅省级重大项目(2014KZDXM033)
广东省公益研究与能力建设专项资金项目(2015A030402006)
关键词
随机离散事件系统
故障诊断
故障预测
马尔可夫矩阵
stochastic discrete event systems
failure diagnosis
failure prediction
Markov matrix
