五相鼠笼异步电机定子匝间短路诊断方法  

Diagnosis method of stator inter-turn short circuit for five-phase squirrel-cage induction motor

作　　者：党月懋 张睿成 吴立建 许明阁 詹皓岚 张品佳 DANG Yuemao;ZHANG Ruicheng;WU Lijian;XU Mingge;ZHAN Haolan;ZHANG Pinjia(Department of Electrical Engineering,Tsinghua University,Beijing 100084,China;College of Electrical Engineering,Zhejiang University,Hangzhou 310027,China;State Key Lab of Reliability and Intelligence of Electrical Equipment,Hebei University of Technology,Tianjin 300401,China)

机构地区：[1]清华大学电机系,北京100084 [2]浙江大学电气工程学院,浙江杭州310027 [3]河北工业大学省部共建电工装备可靠性与智能化国家重点实验室,天津300401

出　　处：《电机与控制学报》2025年第1期1-14,共14页Electric Machines and Control

基　　金：国家杰出青年科学基金(52225702);国家重点研发计划项目(2022YFE0102500)。

摘　　要：多相鼠笼异步电机功率密度大、可靠性高,广泛应用于大功率传动领域。由于恶劣运行工况导致的定子匝间短路故障,可使电机性能恶化,甚至造成停机等严重后果,因此本文对其准确诊断进行研究。基于定子匝间短路故障的Park矢量轨迹特征,采用粒子群优化的卷积神经网络(PSO-CNN)的数据驱动方法,进行定子匝间短路的故障诊断与定位,具有准确率高、获取故障信息全面等优势。首先建立了五相鼠笼异步电机等效模型,进行坐标变换得到Park矢量轨迹,使用对称分量法阐明其轨迹方程与五序分量的关系;进而对定子匝间短路故障不同模式及不同故障严重程度下的Park矢量轨迹进行椭圆参数拟合,得到故障特征参数与故障模式的数据集;最后,采用数据驱动方法进行五相鼠笼异步电机定子匝间短路故障诊断,实现对故障模式与短路匝数比的准确识别,并通过样机实验验证了该方法的有效性。Multiphases squirrel-cage induction motors have high power density and reliability,which are widely used in the field of high-power transmission.Due to the harsh operating conditions,the stator inter-turn short circuit fault leads to the deterioration of motor performance and even serious consequences such as shutdown.Accurate diagnosis was studied.A fault diagnosis and localization method was proposed using particle swarm optimized convolutional neural network(PSO-CNN),based on the Park vector trajectory characteristics,which has the advantages of high accuracy rate and accessibility of comprehensive fault information.Firstly,the equivalent model of a five-phase squirrel-cage induction motor was established,coordinate transformation was performed to obtain Park vector trajectory,and the symmetric component method was used to elucidate the relationship between its trajectory equations and the five-sequence components;Furthermore,the Park vector trajectories under different modes and severities of stator inter-turn short circuit are fitted with elliptical parameters to obtain a dataset of fault characteristic parameters and fault modes;Finally,a data-driven method was used to diagnose the stator inter-turn short circuit of a five-phase squirrel-cage induction motor,achieving accurate identification of the fault mode and the ratio of short circuit turns.Prototype experiment was conducted to verify effectiveness of this method.

关 键 词：数据驱动 故障诊断 定子匝间短路 对称分量法 PARK矢量 五相鼠笼异步电机 

分 类 号：TM307[电气工程—电机]