摘要
由雷电引起的输电线路雷电故障严重威胁电网的可靠性供电,提高输电线路雷电预测能力具有重要现实意义,为此提出了基于改进PSO-BP算法的雷电流概率预测研究。将输电线路进行了栅格划分,以利于雷电的分区预测;提出了采用PSO算法优化BP神经网络的方法,利用PSO的全局寻优能力确定BP神经网络的初始权值阈值,提升BP网络的收敛速度和预测精度;采用PSO-BP算法各个栅格内各种强度的雷电流发生概率。通过实验仿真,对比结果验证了PSO-BP算法相比于传统的BP算法在收敛速度和预测精度上都有了很大提高;采用PSO-BP算法预测的各个栅格雷电流情况与实际值相吻合,误差较小。
Lightning failure of transmission lines caused by lightning seriously threatens the reliability of power supply of power grid, and it is of great practical significance to improve the lightning prediction ability of transmission lines. In this paper, the probability prediction of lightning flow based on improved PSO-BP algorithm is proposed. Grid division of transmission lines is carried out to facilitate the zoning prediction of lightning. The PSO algorithm is used to optimize BP neural network, and the global optimization ability of PSO is used to determine the initial weight threshold of BP neural network, so as to improve the convergence speed and prediction accuracy of BP neural network. The probability of light- ning flow occurring at various intensities in each grid is calculated by PSO-BP algorithm. Compared with the traditional BP algorithm, the PSO-BP algorithm has improved greatly in convergence speed and prediction precision. The predicted lightning current of each grid by PSO-BP algorithm is consistent with the actual value, and the error is small.
作者
崔月生
Cui Yuesheng(Beijing Lightning Devices Security Test Center,Beijing 100089,China)
出处
《国外电子测量技术》
2018年第10期118-123,共6页
Foreign Electronic Measurement Technology
关键词
雷电流
PSO
BP
预测
lightning current
PSO
BP
predict
