A Dynamic-Bayesian-Network-Based Fault Diagnosis Methodology Considering Transient and Intermittent Faults

Abstract

Transient fault (TF) and intermittent fault (IF) of complex electronic systems are difficult to diagnose. As the performance of electronic products degrades over time, the results of fault diagnosis could be different at different times for the given identical fault symptoms. A dynamic Bayesian network (DBN)based fault diagnosis methodology in the presence of TF and IF for electronic systems is proposed. DBNs are used to model the dynamic degradation process of electronic products, and Markov chains are used to model the transition relationships of four states, i.e., no fault, TF, IF, and permanent fault. Our fault diagnosis methodology can identify the faulty components and distinguish the fault types. Four fault diagnosis cases of the Genius modular redundancy control system are investigated to demonstrate the application of this methodology. Note to Practitioners-This paper is motivated by the problem of fault diagnosis of complex electronic systems in the presence of transient fault (TF) and intermittent fault (IF). Existing approaches do not involve the dynamic behavior of electronicsystems, i.e., degradation and aging. The results of fault diagnosis could be different at different times for the given identical fault symptoms because of the degradation and aging. This paper suggests a new fault diagnosis approach using dynamic Bayesian networks (DBNs). It aims at identifying the component faults and distinguishing the fault types, i.e., TF, IF, and permanent faults. We construct the DBN structure and parameter models and define two judgment rules to determine the fault diagnosis results. The future scope of work can be directed toward the development of a practice fault diagnosis system for an electronic system to validate the proposed methodology. Index Terms-Dynamic Bayesian network (DBN), fault diagnosis, intermittent fault (IF), transient fault (TF).

Bayesian network approach to fault diagnosis of a hydroelectric generation system

“…The implementation of BN relying on the Bayes' theorem is defined as the exhaustive event set B 1 ,B 2 ,...,B n and the event A exist in a sample space Ω, and they, respectively, meet the conditions of P(B i ) > 0 (i = 1,2,3,...,n) and P(A) > 0. Hence, we get 36,37 :…”

Research on the fault prediction method of an on-board subsystem in high-speed train control systems

“…故障预测是一个执因求果的过程, 在系统正常运行的情况下, 通过与故障相 关关键信号测试点的变化趋势建立起来的预测模型, 利用先进的预测算法推理系统在当前运行状况下 发生故障的概率. 贝叶斯网络算法是一个典型的推理算法, 相较于神经网络算法, 其优势在于其推理能 力, 且对先验概率的要求较低, 对数据量要求较小 [15] ; 相较于隐马尔科夫方法, 其优势在于贝叶斯网 络可以动态调整网络结构与参数, 预测能力更高 [16] , 因此贝叶斯网络被越来越广泛地应用 [17,18] . 2.2 小节介绍了目前实际现场的故障数据类型, 为文本类文件, 多描述功能性故障, 没有针对系统电气特 性参数的记录与分析, 因此很难提供大量的数据支撑神经网络算法.…”

Small‐batch‐size convolutional neural network based fault diagnosis system for nuclear energy production safety with big‐data environment

“…The data‐driven method is wildly researched and applied to fault diagnosis of nuclear energy production in recent years. Compared with the early precise mathematical model‐based method and qualitative reasoning method such as the Bayesian Network and Markov Chain, on the one hand, this method does not require to establish an accurate theoretical model, and on the other hand, it is not constrained by prior probability. Furthermore, this method relies on the relationships between relevant measurements within the system, which can be formulated in an implicit expression by training an empirical model.…”