750kV变电站贝叶斯网故障诊断  

Fault Diagnosis for 750 kV Substation Based on Bayesian Network

作　　者：尚坡利[1] 董海鹰[1] 吴宁[2] 任伟[3] 

机构地区：[1]兰州交通大学自动化与电气工程学院,甘肃兰州730070 [2]兰州工业学院电气工程学院,甘肃兰州730050 [3]甘肃省电力公司检修公司,甘肃兰州730050

出　　处：《兰州交通大学学报》2015年第3期91-96,共6页Journal of Lanzhou Jiaotong University

基　　金：国家自然科学基金(61165006)

摘　　要：针对750kV变电站双网双重保护配置特点及保护装置和断路器存在的误动、拒动等不确定情况,提出了一种具有冗余保护的750kV变电站贝叶斯网故障诊断方法.在该方法中,建立了可疑故障元件贝叶斯网的主网和冗余网诊断模型,同时,将元件的双重保护配置信息在诊断模型中进行冗余知识表示,使诊断结果具有高容错性.采用信息熵理论确定可疑故障元件的初始概率,避免了大量样本数据获取难度大的情况及采用专家经验获取时存在的主观缺陷.通过贝叶斯网的概率推理获得可疑故障元件的后验概率,对两个模型的诊断结果进行综合判定后确定故障元件,实现对750kV变电站常见故障可靠定位,案例分析验证了该方法的正确性和有效性.As 750 kV substation has the characteristics like dual net dual protective configuration and uncertain information,a fault diagnosis method of substation with redundant protection configuration based on BN（Bayesian Network）is proposed.In this method,BN fault diagnosis model is established and decomposed into two sub-models,the main and the redundant model.The redundant knowledge of component diagnosis which takes information from two protective devices is represented,and the redundant information makes the diagnostic results have high fault tolerance.The initial probability is determined by using the information entropy theory to avoid a large number of sample data statistics for the difficulty of existence and using expert experience gain of subjectivity.The posterior probability can be obtained by using of BN probabilistic reasoning.The faulty components are determined by comprehensive determining of two diagnosis results.The result shows that the proposed method is correct and effective.

关 键 词：750KV变电站 双网双重保护 故障诊断 冗余知识表示 贝叶斯网 信息熵 

分 类 号：TM72[电气工程—电力系统及自动化]