学术论文

      基于PSO-LIBSVM的广域后备保护新算法

      A new algorithm of wide-area backup protection based on PSO-LIBSVM

      摘要:
        广域后备保护利用电网线路IED和母线IED采集各组件相关信息,构造基于PSO-LIBSVM的线路和母线故障识别网络。以IED采集的信息作为输入向量,建立故障识别网络的训练样本矩阵;PSO算法寻找最优LIBSVM运行参数并训练故障识别网络,利用随机故障下的测试样本矩阵对线路和母线识别网络进行测试,以识别电网故障组件IED,进而确定故障组件。通过大量实验仿真了多种信息不准确情况下的故障识别,实验证明基于PSO-LIBSVM的广域后备保护新算法,识别准确率高,具有很好的容错性。
      Abstract:
      The related information of different power system element may be collected by line IED and bus IED for wide-area backup protection, then the fault recognition network of line and bus based on PSO-LIBSVM is established and the information collected by IED is taken as input vector for establishing the training sample matrix of the fault recognition network. PSO algorithm is used to search optimal parameter combination to train the fault identification network. The line and bus identification network is tested by the testing sample matrix of random failure, and the fault component IED is identified and the fault components are determined. A large number of experiments are made to simulate the fault identification under a variety of inaccurate information. Experiment results show that wide area backup protection based on PSO-LIBSVM has good accuracy and good fault-tolerance.
      作者: 吴浩 [1] 李群湛 [2] 刘炜 [2]
      Author: WU Hao [1] LI Qun-zhan [2] LIU Wei [2]
      作者单位: 西南交通大学电气工程学院,四川 成都 610031; 四川理工学院自动化与电子信息学院,四川 自贡 643000 西南交通大学电气工程学院,四川 成都,610031
      刊 名: 电力系统保护与控制 ISTICEIPKU
      年,卷(期): 2013, (15)
      分类号: TM77
      机标分类号: TM7 TP3
      在线出版日期: 2013年8月23日
      基金项目: 人工智能四川省重点实验室项目(2010RY005,2011RZY02,2011RYY08);四川省教育厅项目(11ZB100);四川理工学院培育项目