基于POD-DNN降阶模型的油浸式变压器绕组稳态温升快速计算方法  

Fast Calculation of Steady Temperature Rise of Oil-immersed Transformer Windings Based on POD-DNN Reduced Order Model

作　　者：赵庆贤 刘云鹏[1] 刘刚[1] 傅榕韵 邹莹 武卫革[2] ZHAO Qingxian;LIU Yunpeng;LIU Gang;FU Rongyun;ZOU Ying;WU Weige(Hebei Provincial Key Laboratory of Power Transmission Equipment Security Defense(North China Electric Power University),Baoding 071003,Hebei Province,China;Hebei Provincial Key Laboratory of Electromagnetic Structural Performance of Power Transmission and Transformation Equipment(Baoding Tianwei Baobian Electric Co.,Ltd.),Baoding 071056,Hebei Province,China)

机构地区：[1]河北省输变电设备安全防御重点实验室(华北电力大学),河北省保定市071003 [2]河北省输变电装备电磁与结构性能重点实验室(保定天威保变电气股份有限公司),河北省保定市071056

出　　处：《中国电机工程学报》2025年第6期2423-2436,I0033,共15页PROCEEDINGS OF THE CHINESE SOCIETY FOR ELECTRICAL ENGINEERING

基　　金：国家自然科学基金联合基金项目(重点支持项目)(U23B20135);河北省“三三三人才工程”项目(C20231116)。

摘　　要：为解决油浸式变压器绕组稳态温升计算耗时久的问题,该文提出一种基于POD-DNN降阶模型的快速计算方法。首先,通过绕组稳态温升全阶模型构建快照矩阵,并基于本征正交分解(proper orthogonal decomposition,POD)获得物理系统的模态及模态系数。然后,建立工况参数与模态系数间的深度神经网络(deep neural networks,DNN)代理模型,解决POD方法中非线性项求解效率低和控制方程依赖强的局限,同时设计网络正则化策略,避免小样本下模型过拟合。最后,将DNN代理模型预测的模态系数与对应的POD模态线性加权,重构绕组温度场。经验证,POD-DNN求解的绕组温升结果与Fluent仿真和试验测量高度一致,计算效率相较于全阶模型和Fluent仿真分别提升了247478倍和23056倍,该算法能够为变压器的在线监测、运行维护和绝缘设计提供技术支撑。In order to address the problem of long time-consuming calculation of the steady temperature rise of oil-immersed transformer winding,this paper proposes a fast calculation method based on POD-DNN reduced-order model(ROM).First,the snapshot matrix is constructed through the full-order model(FOM)of the steady temperature rise of transformer winding,and the modes and modal coefficients of the physical system are obtained based on proper orthogonal decomposition(POD).Next,a deep neural network(DNN)agent model between the working conditions and modal coefficients is established to solve the limitations of low solving efficiency of nonlinear terms and strong dependence of control equations in POD,and design network regularization strategies to avoid overfitting of the model under small samples.Finally,the modal coefficients predicted by DNN agent model are combined with the corresponding POD modes to reconstruct the temperature field of winding.It is verified that the winding temperature rise results solved by POD-DNN are very close to the Fluent simulation and experimental measurements,and the computational efficiency is improved by 247478 and 23056 times compared with the FOM and Fluent simulation,respectively.This algorithm can provide technical support for online monitoring,operation maintenance,and insulation design of transformers.

关 键 词：本征正交分解 深度神经网络 绕组稳态温升 快速计算 降阶模型 

分 类 号：TM411[电气工程—电器]