基于循环神经网络的运行变压器绕组压紧状态检测  

Clamping State Detection of Transformer Windings Based on Recurrent Neural Networks

作　　者：钱国超 胡锦 代维菊 王浩州 赵汉武 洪凯星 QIAN Guochao;HU Jin;DAI Weiju;WANG Haozhou;ZHAO Hanwu;HONG Kaixing(Yunnan Electric Power Research Institute,Kunming 650217,China;Kunming Power Supply Bureau,Kunming 650217,China;College of Mechanical and Electrical Engineering,China Jiliang University,Hangzhou 310018,China)

机构地区：[1]云南电网有限责任公司电力科学研究院,云南昆明650217 [2]云南电网有限责任公司昆明供电局,云南昆明650217 [3]中国计量大学机电工程学院,浙江杭州310018

出　　处：《智慧电力》2024年第8期129-136,共8页Smart Power

基　　金：国家重点研发计划资助项目(2023YFF0612502);浙江省自然科学基金资助项目(LY22F030001)。

摘　　要：绕组是变压器的核心部件,以压紧力松动为代表的机械结构衰退会造成绕组抗短路能力下降。根据电磁力激励下的绝缘材料应力与应变之间的非线性关系,建立了结构刚度与负载电流之间的动态模型,并将运行绕组结构等效成一个参数振动系统。针对系统中的参数识别问题,提出了一种包含结构物理信息的循环神经网络(RNN),并用于动态刚度的提取。在实验中,通过短路负载实验,获取绕组在不同轴向压紧力下的电流与振动数据。实验结果表明,当绕组压紧力较小时,电磁力作用下的结构动态刚度较显著,且动态刚度特征能准确地反映绕组压紧力状态。The winding is the core component of power transformer,and the mechanical degradation represented by the clamping force looseness can lead to a decrease in the short-circuit withstand capability of the windings.A dynamic model between structural stiffness and load current is established based on the nonlinear relationship between stress and strain of insulating materials under electromagnetic force excitation,and the operating winding structure is equivalent to a parametric vibration system.A recurrent neural network containing structural physical information is proposed for parameter identification,which is further used to extract the dynamic stiffness.The current and vibration data of the windings under different axial clamping forces are obtained by short-circuit load experiments.The experimental results show that when the winding clamping force is small,the dynamic stiffness of the structure under electromagnetic force is significant,and the dynamic stiffness characteristics can accurately reflect the state of the winding clamping force.

关 键 词：变压器绕组 循环神经网络 动态刚度 压紧力检测 

分 类 号：TM411[电气工程—电器]