首页|基于工况参数和改进LSTM的空冷器热风温度预测

基于工况参数和改进LSTM的空冷器热风温度预测

扫码查看
原文链接
  • 万方数据
  • 维普
针对传统抽水蓄能电站技术供水系统存在的智能化水平偏低，供水对象的温度与许多参数变量之间相互耦合的问题，建立了基于工况参数和改进长短期记忆(LSTM)神经网络的发电机空气冷却器热风温度预测模型。首先对原始数据进行清洗，其次采用随机森林(RF)特征降维，对参与目标预测的诸多高维测点变量进行重要度排序，验证所提的工况参数与预测对象温度的相关性，最后再将其输入PSO-LSTM神经网络进行模型的求解。将所提的基于工况参数和改进LSTM方法与最小二乘法、BP神经网络以及原始的LSTM方法进行对比。结果表明，所提模型能有效预测发电机空气冷却器热风温度，相较其他的模型，预测误差能够下降50%左右，同时拥有更优的预测稳定性。
Air cooler hot air temperature prediction based on working condition parameters and improved LSTM
In view of the low level of intelligence in the water supply systems of traditional pumped storage power station technology and the coupling problem between the temperature of the water supply objects and many parameter variables,a generator air cooler hot air temperature prediction model based on operating condition parameters and improved long short-term memory(LSTM)neural network was established.Firstly,the original data was cleaned to eliminate redundant data.Secondly,the Random Forest(RF)feature dimension reduction method was used to select several high-dimensional measure-ment point variables involved in the target prediction to verify the correlation between the proposed working parameters and the predicting temperature objects.Finally,these working parameters were keyed into the PSO-LSTM neural network for prediction.The proposed improved LSTM methods based on working condition parameters were compared with the least squares method,BP neural network,and the original LSTM method.The results show that the proposed model can effectively predict the hot air temperature of the generator air cooler.Compared with other models,the prediction error can be re-duced by 50%,and it has better prediction stability.

generator air coolerhydropower station technology water supply systemrandom forest feature dimension reductionLSTM neural networksparticle swarm optimization

刘平、袁静、赵锋、张磊、郑晓楠

展开 >

华东桐柏抽水蓄能发电有限责任公司,浙江 杭州 310000

中国电建集团华东勘测设计研究院有限公司,浙江 杭州 310000

河海大学能源与电气学院,江苏 南京 211100

发电机空气冷却器 水电站技术供水系统 随机森林降维 LSTM神经网络 粒子群算法

国家电网新源集团(控股)有限公司科技项目

SGXYTB00YWJS2100090

2024

10.3969/j.issn.1674-8530.23.0075

排灌机械工程学报
中国农业机械学会排灌机械分会,江苏大学流体机械工程技术研究中心

排灌机械工程学报

CSTPCD北大核心
影响因子：1.055
ISSN：1674-8530
年,卷(期)：2024.42(6)
  • 1
  • 5