基于改进D-S证据理论的电网故障多源信息智能融合诊断方法

Intelligent Fusion Diagnosis Method for Multi-source Information of Power Grid Fault Based on Improved D-S Evidence Theory

为了满足电网调度精益化管理的需求,提高继电保护智能化水平,提出一种电网故障多源信息智能融合诊断方法。该方法通过主动激励召唤和任务动态调整来实现继电保护主站的性能提升与信息同步,利用一对一支持向量机多分类算法进行故障信息分类,基于改进Dempster-Shafer(D-S)证据理论进行多源信息融合诊断和同源故障信息确认,根据多源信息融合规则和流程完成同源故障快速决策。实验结果表明,所提出的诊断方法在故障快速反应、精准诊断定位、可靠决策支持和免人工干预等方面具有良好的应用效果。

In order to meet the demand of fine-grained management of power grid dispatching and improve intelligence level of relay protection,this paper proposes an intelligent fusion diagnosis method for multi-source information of power grid fault.The method can realize performance improvement and information synchronization of the relay protection master stations through active incentive calling and task dynamic adjustment,it uses one-to-one SVMs for fault information classification,makes multi-source information fusion diagnosis and homology information identification based on the improved D-S evidence theory,and completes fast decision of homologous fault according to the principle and flow of multi-source information fusion.The experimental results show that the proposed diagnosis method has good application effect in terms of fast fault response,accurate diagnosis and positioning,reliable decision support,and free of manual intervention.