结合粒子群算法和穷举法的配电网故障诊断方法

Distribution Network Fault Diagnosis Method Combining Particle Swarm Optimization and Exhaustive Method

在配电网的故障诊断中,基于智能算法的区段定位方法普遍存在未成熟收敛现象。针对此问题,利用穷举法的绝对收敛性对智能算法的早熟结果进行辨识,使得智能算法的未成熟收敛现象大幅减少。首先分析配电网的拓扑结构,构建出区段定位的分层模型;接着,在维度较大的第一层模型中,利用二进制粒子群算法进行定位;在维度较小的第二层模型中,利用穷举法进行定位,完成对早熟结果的辨识。通过算例分析,验证了所提方法在定位准确率和速度上的优势。

In the fault diagnosis of distribution network,the immature convergence is common in section location method based on intelligent algorithm.To solve this problem,the paper uses the absolute convergence of exhaustive method to identify the premature phenomenon of the intelligent algorithm,so that the immature convergence of the intelligent algorithm is greatly reduced.Firstly,the topological structure of the distribution network is analyzed,and a hierarchical model of segment location is constructed.Secondly,binary particle swarm optimization(BPSO)is used to locate in the first layer model with larger dimensions.In the second layer model with smaller dimensions,the exhaustive method is used to identify the premature result.Finally,an example is given to illustrate the superiority of the proposed method in location accuracy and speed.