摘要
本文针对现役电站燃气轮机故障样本少,以往的故障诊断方法依赖于海量的带有故障标签的数据,难以在实际生产中取得预期的诊断效果的现象,提出了一种通过利用贝叶斯网络进行反事实推理来识别燃气轮机故障原因的方法。本文首先介绍了贝叶斯网络的基本原理,然后将故障模式和影响分析及故障树技术应用于贝叶斯网络的搭建,最后通过实际案例分析,验证了这一方法的有效性。本文的故障诊断方法可以根据燃气轮机在运行中出现的异常现象分析出可能的故障和相应的故障原因,帮助运行及检修人员及时发现和排除故障,并且弥补了基于数据驱动的故障诊断方法缺少专业知识支撑的缺陷,为燃气轮机的故障诊断提供了一种灵活、高效、可靠的新选择。
Aiming at the phenomenon that there are small amount of fault samples of existing power station gas turbine,and the previous fault diagnosis methods rely on a large amount of data with fault labels,which is difficult to obtain the expected diagnosis effect in actual operation,this paper presents a method to identify the cause of gas turbine failure by using Bayesian network counterfactual reasoning.This paper first introduces the basic principle of Bayesian network,then applies failure mode and effects analysis as well as fault tree analysis to the construction of Bayesian network,and finally verifies the effectiveness of this method through the actual case analysis.The fault diagnosis method proposed in this paper can analyze possible faults and corresponding fault causes according to abnormal phenomena in the operation of gas turbines,help operation and maintenance personnel to discover and eliminate faults in time,and make up for the lack of professional knowledge support of data-driven fault diagnosis methods,and provides a flexible,efficient and reliable new option for fault diagnosis of gas turbines.
作者
白晔
朱萍
BAI Ye;ZHU Ping(North China Electric Power University,Changping 102206,Beijng,China)
出处
《电力大数据》
2024年第1期45-53,共9页
Power Systems and Big Data
