| 张羽飞,孟凡勇,王永千,吴 越,李 红.基于改进型 LSTM 的电力设备温度预测方法研究[J].电子测量与仪器学报,2021,35(12):167-173 |
| 基于改进型 LSTM 的电力设备温度预测方法研究 |
| Research on temperature prediction method of powerequipment based on improved LSTM |
| |
| DOI： |
| 中文关键词: 卷积神经网络 长短期记忆神经网络 温度预测 电力设备 |
| 英文关键词:CNN LSTM temperature prediction power equipment |
| 基金项目: |
|
|
|
|
| 摘要点击次数: 809 |
| 全文下载次数: 799 |
| 中文摘要: |
| 实现电力设备温度的准确预测对于保障电力系统安全和提高维修效率具有重要意义。 传统预测方法无法满足高精度
的预测要求,提出一种基于改进型长短期记忆(long short-term memory,LSTM)神经网络的电力设备温度预测方法,利用去池化
的卷积神经网络(convolutional neural networks, CNN)对时间序列进行局部特征提取,然后利用 LSTM 设计的循环递归层对时间
序列进行长期特征提取,实现电气设备温度预测。 在首都国际机场的供电设备运行状态监测数据集的实验结果表明,温度预测
值在 20 ~ 60 min 内预测精度优于 1 ℃ ,且均方根误差(RMSE) 0. 12 均小于其他温度预测模型,可以有效实现电气设备温度
预测。 |
| 英文摘要: |
| It is of great significance to realize the accurate prediction of the temperature of power equipment to ensure the safety of the
power system and to improve maintenance efficiency. Traditional forecasting methods cannot meet the requirements of high-precision
forecasting. A temperature prediction method for power equipment based on an improved long short-term memory ( LSTM) neural
network is proposed, which uses de-pooling convolutional neural networks (CNN) to extract local features of time series, and then use
the recursive layer designed by LSTM to extract the long-term features of the time series to realize the temperature prediction of electrical
equipment. Experimental results on the Power monitoring temperature data set of Capital International Airport show that the prediction
accuracy of the temperature prediction value is better than 1 ℃ within 20 to 60 minutes, and the root mean square error (RMSE) 0. 12
is smaller than other temperature prediction models. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
