基于领域对抗网络的永磁同步电机初始位置估计  

Initial Position Estimation of Surface Permanent Magnet Synchronous Motor Base on Domain-Adversarial Neural Networks

作　　者：王恒泓 王激尧 徐炜 金振 胡友康 Wang Henghong;Wang Jiyao;Xu Wei;Jin Zhen;Hu Youkang(School of Electrical Engineering Southeast University,Nanjing 210096,China)

机构地区：[1]东南大学电气工程学院,南京210096

出　　处：《电工技术学报》2025年第2期425-438,共14页Transactions of China Electrotechnical Society

基　　金：国家自然科学基金资助项目(52275009,52207038)。

摘　　要：永磁同步电机(PMSM)的低速无位置传感器控制主要依赖于电机的凸极性,表贴式永磁同步电机(SPMSM)的电感凸极率低,位置信号的信噪比(SNR)较低,使传统高频注入法获得高精度初始位置面临挑战。深度机器学习能够挖掘比较微弱的信号特征,即使在SNR较低的情况下,也能够获取准确的位置信息,但是传统单流结构机器学习的估算性能比较依赖于训练集的数据概率分布,存在数据泛化能力差的问题。针对这一问题,该文提出一种数据分布自适应的领域对抗神经网络(DANN),在传统卷积神经网络(CNN)的基础上,增加领域判别器和梯度反转层(GRL)将单流结构变为双流结构,使两个网络能够通过抗迁移学习,以学习到领域的不变特征,实现数据分布的自适应,从而解决因数据概率分布不一致带来的位置估算性能下降的问题。实验结果证明,该方法能够有效实现对低凸极率电机的初始位置估算,对新数据能够实现比单流CNN结构更好的位置估算效果,有效解决单流结构CNN位置估算模型数据泛化能力差的问题。The low-speed sensorless control of the permanent magnet synchronous motor(PMSM)primarily depends on the motor's saliency characteristics.However,the surface-mounted permanent magnet synchronous motor(SPMSM)exhibits a low inductive saliency ratio,leading to a poor signal-to-noise ratio(SNR)in position signals.It challenges traditional high-frequency injection position estimation models in achieving high-precision estimation.Deep machine learning can extract features from subtle signals and accurately determine position even in low SNR environments.However,traditional supervised machine learning methods require abundant labeled training data.In practical applications,instantaneous load variations make it challenging to collect comprehensive samples and accurately label position tags,thus impacting the generalization ability of position estimation models trained on steady-state datasets.This paper proposes a data domain-adversarial neural network(DANN).This method enhances the traditional convolutional neural network(CNN)by introducing a domain classifier and a gradient reversal layer(GRL),transitioning from a single-stream to a dual-stream structure.The two networks learn invariant domain features,adapt data distribution,and mitigate the degraded position estimation by anti-transfer learning.Balanced three-phase high-frequency excitation voltages are applied to the three-phase windings of the motor in the stationary reference frame.The negative-sequence first-order component and the positive-sequence second-harmonic component of the high-frequency response current are combined to form a new current vector,facilitating the extraction of position and polarity information.These reconstructed current vectors are graphically depicted and employed as inputs for the CNN.Implicit position feature information is extracted from two-dimensional images,and a correspondence between the images and the rotor positions is established through training.Consequently,the CNN model accurately recognizes two-dimensional images for posi

关 键 词：图像识别 迁移学习 网络对抗 数据自适应 数据泛化 

分 类 号：TM614[电气工程—电力系统及自动化]