结合D-S证据推理的贝叶斯网络法在配电网可靠性评估中的应用  

Reliability Evaluation of Power Distribution System Based on D-S Evidence Inference and Bayesian Networks Method

作　　者：赵书强[1] 程德才[1] 刘璐[1] 

机构地区：[1]华北电力大学电气与电子工程学院,保定071003

出　　处：《电工技术学报》2009年第7期134-138,共5页Transactions of China Electrotechnical Society

基　　金：国家科技支撑计划资助项目(2008BAA14B05)

摘　　要：D-S证据理论的不确定推理方法,能够很好地处理具有模糊和不确定信息的合成问题。本文针对配电网可靠性评估中原始参数的不完整或者主观性参数对评估结果的影响,将D-S证据推理方法与传统的贝叶斯网络法相结合,进行配电系统的可靠性评估。通过构造信任函数、似然函数和多状态的节点模型,建立改进的贝叶斯网络模型。该方法很好地解决了由于信息的不完整和不确定对可靠性评估结果造成的影响,减少了传统可靠性评估方法对设备原始参数的依赖性,更加客观地反映了系统的可靠性。通过实例分析,验证了该方法的有效性。The uncertain inference of D-S evidence theory can deal with the ambiguity and uncertainty of information issues. This paper aims for the effect of incomplete of the original parameters or the effect of subjective parameters in the reliability evaluation of distribution system. A D-S evidence inference method contacted with Bayesian networks for reliability evaluation of distribution system is presented. It constructs improved Bayesian networks model by means of belief functions, plausibility functions and multimode node models. This method resolves the influence of informative inadequacy and uncertainty, and makes a more rational evaluation result. It is proved to be available and valid through an example.

关 键 词：D-S证据推理 贝叶斯网络 配电系统 可靠性 

分 类 号：TM732[电气工程—电力系统及自动化]