| 基于GA-BP神经网络的变压器绕组热点温度预测 |
| |
| 引用本文： | 王兴桐,邹宇,喻彩云.基于GA-BP神经网络的变压器绕组热点温度预测[J].电工材料,2021(1):27-29,34. |
| |
| 作者姓名： | 王兴桐 邹宇 喻彩云 |
| |
| 作者单位： | 三峡大学 电气与新能源学院,湖北宜昌 443002;广西电网钦州供电局,广西钦州 535000;三峡大学 电气与新能源学院,湖北宜昌 443002 |
| |
| 摘 要： | 本文针对现有变压器绕组热点温度预测方法中存在的不足,采用遗传算法对BP神经网络的权值和阈值进行优化,克服了BP神经网络容易陷入局部最小值的缺陷,加快了算法的收敛速度,建立基于遗传算法优化BP神经网络的变压器绕组热点温度预测模型。利用500组变压器试验数据进行仿真,结果表明,基于GA-BP神经网络的变压器绕组热点温度预测值与实际值的变化趋势基本一致,平均相对误差和均方根误差分别为2.05%和0.21。
|
| 关 键 词： | 遗传算法 BP神经网络 变压器 热点温度 预测 |
Prediction of Transformer Winding Hot Spot Temperature Based on GA-BP Neural Network |
| |
| WANG Xingtong,ZOU Yu,YU Caiyun.Prediction of Transformer Winding Hot Spot Temperature Based on GA-BP Neural Network[J].Electrical Engineering Materials,2021(1):27-29,34. |
| |
| Authors: | WANG Xingtong ZOU Yu YU Caiyun |
| |
| Affiliation: | (College of Electrical Engineering&New Energy,China Three Gorges University,Yichang 443002,Hubei,China;Qinzhou Power supply Bureau of Guangxi Power Grid,Qinzhou 535000,Guangxi,China) |
| |
| Abstract: | In this paper,the weight and threshold value of BP neural network are optimized by genetic algorithm to overcome the defect that BP neural network is easy to fall into local minimum value,accelerate the convergence speed of the algorithm,and establish the prediction model of transformer winding hot spot temperature based on BP neural network optimized by genetic algorithm.Using 500 groups of transformer test data for simulation,the results show that the predicted value of transformer winding hot spot temperature based on GA-BP neural network is basically consistent with the change trend of the actual value,the average relative error and root mean square error are 2.05%and 0.21 respectively. |
| |
| Keywords: | BP neural network transformer hot spot temperature prediction |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
