1.Power Supply Service Management Center of State Grid Jiangxi Electric Power Co,Ltd,Jianxi Nanchang;2.Hunan University
Aiming at the problem that it is difficult to directly detect the temperature of the front-end terminal of the smart meter, this paper proposes an improved particle swarm optimization radial basis function neural network for the detection of the temperature terminal of the smart meter. First, the mapping relationship between the terminal temperature of the electric energy meter and its influencing factors based on the RBF neural network is established, The central position of the appropriate network core function is selected through the K-Means++ algorithm, and the recursive least square method is used to obtain the network core function connection weight. The improved particle swarm algorithm is used to optimize the width coefficient of RBF neural network and model training, the optimized temperature mapping expression is derived, and then the terminal temperature detection of the smart electric energy meter is realized. The simulation results show that the improved particle swarm hybrid optimization radial basis function neural network algorithm proposed in this paper has high calculation accuracy, strong search ability, fast convergence speed, and the relative error of temperature detection is less than 0.17%. Compared with the existing detection methods, the proposed method has higher accuracy.