遗传算法优化BP-NN在电网故障诊断中的研究

Research on Fault Diagnosis of Power System Based on Improved Genetic Optimize BP-NN

修改传统的遗传算法的交叉,采用改进的遗传算法优化BP神经网络训练的初始权重和阈值,以避免BP神经网络的局部极小问题。通过分析本文的案例和matlab的仿真可以看出,该方法可有效地诊断网络故障定位,并提高容错性和电网故障诊断效果。

In this paper, we can modify the crossover of traditional Genetic Algorithm, using improved genetic algorithm optimize BP neural network training initial weights and thresholds, to avoid the problem of BP neural network fall into local minima. The results of analysis by an example, the method can effciently diagnose network fault location, and improve fault-tolerance and grid fault diagnosis effect.