改进PSO优化RBF智能电能表端子温度检测方法

Terminal temperature detection method for smart meter based on RBF neural network optimized by improved PSO

针对智能电表前端接线端子温度难以直接检测的问题,提出一种改进粒子群优化径向基神经网络的智能电能表温度端子检测方法。首先基于RBF神经网络建立电能表端子温度与其影响因素映射关系式,通过K-Means++算法获取合适网络核函数的中心位置;然后利用递推最小二乘法求解网络核函数连接权值;最后通过改进粒子群优化RBF神经网络宽度系数和模型训练,推导优化温度映射表达式,据此实现智能电能表端子温度检测。仿真实验结果表明:提出的多种群互生改进粒子群优化径向基神经网络算法计算准确度高、搜索能力强、收敛速度快,温度检测相对误差小于0.17%,相比于现有检测方法具有更高的准确度。

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,and the optimized temperature mapping expression is derived.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.