风电机组故障诊断中不确定性信息处理的贝叶斯网络方法  

Method of Bayesian Network for Uncertainty Information Processing of Wind Turbines Fault Diagnosis

作　　者：周真[1] 周浩[1] 马德仲[1] 张茹[1] 蒋永清[1] 

机构地区：[1]哈尔滨理工大学测控技术与仪器黑龙江省高校重点实验室,黑龙江哈尔滨150080

出　　处：《哈尔滨理工大学学报》2014年第1期64-68,共5页Journal of Harbin University of Science and Technology

基　　金：国家高技术研究发展计划(863计划)重点项目(2008AA042207);黑龙江省科技攻关项目指导项目(GZ11A406)

摘　　要：针对风电机组故障信息耦合性、模糊性的不确定性特点,结合贝叶斯网络在处理不确定性问题上的优势,提出了风电机组故障诊断的贝叶斯网络方法.重点研究了该方法的两个关键问题,即风电机组故障诊断的贝叶斯网络建模和贝叶斯网络推理.构建了一种基于事故树分析方法的三层CME贝叶斯网络模型并解析了贝叶斯网络的故障推理过程,通过风电机组齿轮箱的故障诊断实例验证了上述模型的可行性和贝叶斯网络推理的有效性.研究成果对具有相关不确定性问题的机电设备故障诊断有借鉴意义.Abstract：Taking the advantage of Bayesian network in dealing with the issue of uncertainty, this paper puts forward a fault diagnosis method based on Bayesian network for wind turbines according to its strong uncertainty of fault feature information such as coupling and ambiguity. We focus on two key problems of this method, namely Bayesian network modeling and Bayesian network inference of fault diagnosis of Wind Turbines, building three lay- ers of CME Bayesian network model based on the fault tree analysis method and analytic the fault reasoning process of Bayesian network. Through an example of the wind turbines gearbox fault diagnosis, we verify the feasibility of the model and the effectiveness of Bayesian network inference. Research on electromechanical equipment fault diag- nosis with associated uncertainty problems has referential significance.

关 键 词：风电机组 故障诊断 贝叶斯网络 推理 

分 类 号：TP206.3[自动化与计算机技术—检测技术与自动化装置]