PSO-BP神经网络在开关柜设备温度预测中的应用

Application of PSO-BP neural network in temperature prediction for switchgear equipment

温度是衡量电力开关柜设备健康状态的重要指标,对开关柜内设备进行准确的温度预测可有效的提前把握其运行状态.传统BP神经网络可以实现温度预测,但由于该网络在训练过程中容易陷入局部极小值,影响了温度预测的准确性.提出了一种PSO优化BP神经网络对设备温度进行预测的方法.首先,将电力运行数据集进行预处理,在网络训练前,利用PSO对神经网络的权值和阈值进行优化,得到PSO-BP预测模型;最后将预测模型运用到开关柜设备温度预测中.实验结果表明:相较于传统的神经网络温度预测方法,文中提出的方法能够对开关柜内设备温度进行有效的预测,为电网管理实现从传统预防性维护到主动预测性的转变提供了一种有效途径.

Temperature is an important indicator to measure the health status of power switchgear equipment.Accurate temperature prediction of equipment in the switchgear can effectively grasp its operating status in advance.The traditional BP neural network can realize temperature prediction,but it is easy to fall into local minimum values during the training process,which affects the accuracy of temperature prediction.This paper proposes a PSO-optimized BP neural network to predict the temperature of equipment.Firstly,the power operation data set is preprocessed.Before the network training,the weight and threshold of the neural network are optimized by PSO to obtain the PSO-BP prediction model.Finally,the established prediction model is applied to the temperature prediction for the switchgear equipment.The experimental results show that,compared with the traditional neural network temperature prediction method,the method proposed in this paper can effectively predict the temperature for equipment in the switchgear.This method provides an effective way for grid management from traditional preventive maintenance to active predictive.