Engineering Applications of Artificial Intelligence ( IF 7.5 ) Pub Date : 2020-04-28 , DOI: 10.1016/j.engappai.2020.103680 Tao Wang , Xiaoguang Wei , Jun Wang , Tao Huang , Hong Peng , Xiaoxiao Song , Luis Valencia Cabrera , Mario J. Pérez-Jiménez
This paper focuses on power system fault diagnosis based on Weighted Corrective Fuzzy Reasoning Spiking Neural P Systems with real numbers (rWCFRSNPSs) to propose a graphic fault diagnosis method, called FD-WCFRSNPS. In the FD-WCFRSNPS, an rWCFRSNPS is proposed to model the logical relationships between faults and potential warning messages triggered by the corresponding protective devices. In addition, a matrix-based reasoning algorithm for the rWCFRSNPS is devised to reason about the fault alarm messages using parallel representations. Besides, a layered modeling method based on rWCFRSNPSs is developed to adapt to topological changes in power systems and a Temporal Order Information Processing Method based on Cause–Effect Networks is designed to correct fault alarm messages before the fault reasoning. Finally, in a case study considering a local subsystem of a 220kV power system, the diagnosis results of five test cases prove that the proposed FD-WCFRSNPS is viable and effective.
中文翻译:
变拓扑电力系统故障诊断的加权校正模糊推理加标神经网络P系统
本文针对基于实数加权校正模糊推理尖峰神经P系统的电力系统故障诊断,提出了一种图形化的故障诊断方法,称为FD-WCFRSNPS。在FD-WCFRSNPS中,提出了一个rWCFRSNPS来对故障和由相应保护设备触发的潜在警告消息之间的逻辑关系进行建模。此外,针对rWCFRSNPS设计了基于矩阵的推理算法,以使用并行表示来推理故障警报消息。此外,开发了基于rWCFRSNPS的分层建模方法以适应电力系统的拓扑变化,并设计了基于因果网络的时间顺序信息处理方法以在故障推理之前纠正故障警报消息。最后,