基于改进径向基函数神经网络的10kV电缆接头温度计算

Calculation of 10kV Cable Joint Temperature Based on Improved Radial Basis Function Neural Network

对电缆接头进行热点温度计算具有重要意义,为此提出改进径向基函数神经网络,建立电缆接头温度的计算模型,以电流、预制橡胶的表面温度和环境温度作为输入,以实时电缆接头温度作为输出。计算机实验仿真结果表明,基于RBF径向基函数神经网络的计算温度与试验结果吻合较好,表明径向基神经网络具有较高精度,该研究对评估电缆接头的绝缘状态具有重要意义。

It is of great significance to calculate the hot spot temperature of cable joints.For this reason,the radial basis function neural network is improved,and the calculation model of the cable joint temperature is established.The current,the surface temperature of the prefabricated rubber and the ambient temperature are used as input,and the real-time cable joint temperature is used as the output.The computer experiment simulation results show that the calculated temperature based on the RBF radial basis function neural network is in good agreement with the experimental results,indicating that the radial basis function neural network has high accuracy.This research is of great significance for evaluating the insulation state of cable joints.