基于贝叶斯网络的柴油机润滑系统多故障诊断研究.PDFVIP

第xx卷 第x期 控 制 与 决 策 Vol.xx No.x xxxx年 x 月 Control and Decision xxx. xxxx DOI: 10.13195/j.kzyjc.2017.1399 基于贝叶斯网络的柴油机润滑系统多故障诊断研究 王金鑫, 王忠巍 , 马修真, 刘龙, 袁志国 (哈尔滨工程大学动力与能源工程学院，哈尔滨 150001) 摘 要: 为解决柴油机润滑系统多故障的解耦与诊断问题,提出一种基于贝叶斯网络模型的故障诊断方法.建立润 滑系统的贝叶斯网络诊断模型包括两部分:利用有向无环图描述多故障耦合关系、采用概率形式表示故障诊断 定量知识.首先,按照故障类型将润滑系统故障诊断任务分解为各类故障的诊断子任务.对各子任务,利用故障树模 型分析故障与征兆、及多故障间的耦合关系,并通过故障树向贝叶斯网络的转化,建立润滑系统的贝叶斯网络模 型结构.在定量参数方面,采用noisy-OR/AND模型分析故障与征兆间的因果关联强度,通过设定故障的先验发生概 率描述润滑系统的历史运行状况.最后,通过两起“进机油压过低”故障实例,验证了该方法的有效性. 关键词: 柴油机; 润滑系统; 多故障诊断; 贝叶斯网络; 故障树; Noisy-OR/AND 模型 中图分类号: TK428 文献标志码: A Research on Diagnosis of Multiple Faults of Diesel Engine Lubrication System Based on Bayesian Networks WANG Jin-xin, WANG Zhong-wei , MA Xiu-zhen, LIU Long, YUAN Zhi-guo (College of Power and Energy Engineering, Harbin Engineering University, Harbin 150001, China) Abstract: Motivated by decoupling and diagnosing of the multiple faults of diesel engine lubrication system, a novel fault diagnosis method based on Bayesian networks is proposed. The establishment of a diagnosis Bayesian networks model for lubrication system includes two processes: representing the coupling relationship between multiple faults through directed acyclic graph, and setting up the quantitative parameters in the form of probability. Before the implementation of the proposed method, diagnostic task of lubrication system is decomposed according to the types of failure. Fault tree model is utilized in every single diagnostic subtask to analyze the coupling between failures and symptom