基于CEEMDAN-GRU的主泵电机绕组温度预测  

Winding temperature prediction of primary pump motors based on CEEMDAN-GRU

作　　者：朱一虎 夏虹[1,2] 杨波[1,2] 朱少民 张汲宇 王志超[1,2] ZHU Yihu;XIA Hong;YANG Bo;ZHU Shaomin;ZHANG Jiyu;WANG Zhichao(Key Laboratory of Nuclear Safety and Advanced Nuclear Energy Technology,Ministry of Industry and Information Technology,Harbin Engineering University,Harbin 150001,China;Fundamental Science on Nuclear Safety and Simulation Technology Laboratory,Harbin Engineering University,Harbin 150001,China)

机构地区：[1]哈尔滨工程大学核安全与先进核能技术工业和信息化部重点实验室,黑龙江哈尔滨150001 [2]哈尔滨工程大学核安全与仿真技术重点学科实验室,黑龙江哈尔滨150001

出　　处：《应用科技》2023年第4期14-20,共7页Applied Science and Technology

基　　金：国家自然科学基金项目(U21B2083)。

摘　　要：针对核电站主泵电机绕组温度的预测问题,提出了基于自适应噪声完备集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN)和门控循环单元(gated recurrent unit,GRU)的预测模型。首先使用CEEMDAN对采集到的绕组温度序列进行分解,经过分量重构得到其高、低频分量和趋势项,在此基础上分别构建各分量的GRU预测模型,将各分量的预测结果叠加集成得到绕组温度的整体预测值。仿真结果表明,与传统的循环神经网络(recurrent neural network,RNN)、长短期记忆(long short-term memory,LSTM)模型和GRU模型相比,本文提出的预测模型在多元评价指标方面均优于其他模型,具有更高的预测精度,验证了该模型的可行性。A prediction model based on complete ensemble empirical mode decomposition with adaptive noise(CEEMDAN)and gated recurrent unit(GRU)is proposed to predict the winding temperature of primary pump motors in the nuclear power plant.Firstly,CEEMDAN is used to decompose the collected winding temperature series,and its high and low frequency components and trend items are obtained through component reconstruction.On this basis,the GRU prediction model of each component is respectively constructed,and the prediction results of each component are superimposed and integrated to obtain the overall predicted value of the winding temperature.The simulation results show that compared with the traditional recurrent neural network(RNN),long short-term memory(LSTM)model and GRU model,the prediction model proposed in this paper is superior to other models in terms of multiple evaluation indicators,and it has higher prediction accuracy.Thereby,the feasibility of the model is verified.

关 键 词：主泵 电机 绕组温度 时间序列 状态预测 自适应噪声完备集合经验模态分解 深度学习 门控循环单元 

分 类 号：TL363[核科学技术—核技术及应用]