基于粗糙集和量子遗传算法的BP神经网络电网故障诊断

Fault Diagnosis of Power Grid on BP Neural Network Based on Rough Set and Quantum Genetic Algorithm

为提高电网故障诊断的准确率、容错性以及缩短诊断时间,提出基于粗糙集和量子遗传算法融合的BP神经网络电网故障诊断方法.分析电网模型,得到原始决策表,利用粗糙集中的差别函数约简冗余的决策属性,得到约简后的故障诊断决策表;利用量子遗传算法优化BP神经网络参数;对数据进行训练学习,构建基于粗糙集和量子遗传算法融合的BP神经网络电网故障诊断模型.仿真验证表明:与传统的BP神经网络故障诊断方法相比,利用该方法,电网故障诊断的准确率和容错性都得到了有效提升.

In order to improve the accuracy,fault tolerance and shorten the diagnosis time of power grid fault diagnosis,the fault diagnosis method of BP neural network power grid based on rough set and quantum genetic algorithm is proposed.By analyzing the power grid model,the original decision table is obtained,and the redundant decision attributes are reduced by using the difference function in rough set to obtain the reduced fault diagnosis decision table.BP neural network parameters are optimized by quantum genetic algorithm.After training and learning the data,a BP neural network fault diagnosis model based on rough set and quantum genetic algorithm is constructed.Simulation results show that the accuracy and fault tolerance of power grid fault diagnosis are effectively improved by using this method,compared with the traditional BP neural network fault diagnosis method.