Muti-Parameter Decoupling Online Identification of Permanent Magnet Synchronous Motor Based on Neural Network
Gu Xin1,Hu Sheng2,Shi Tingna2,Geng Qiang1
1. Tianjin Key Laboratory of Advanced Technology of Electrical Engineering and Energy Tianjin Polytechnic University Tianjin 300387 China; 2. Tianjin University Tianjin 300072 China
Abstract：A parameters identification method for surface permanent magnet synchronous motors (SPMSMs) is put forward to eliminate the parameters coupling during the multi-parameter online identification in this paper. The parameters coupling are often caused by the rank-deficient of SPMSMs’ mathematical model. The proposed method based on neural network can identify the stator resistance, inductance and rotor flux by negative sequence d-axis current short-term injecting and minimum mean square algorithm. The impacts on identification accuracy due to the inverter voltage dropping and dead time can also be weakened by improving the network structure. The validity of the proposed method is proved by the experiment results.
[1] Vukosavic S N, Stojic Milic R. On-line turning of the rotor time constant for vector-controlled induction motor in position control application[J]. IEEE Transac- tions on Industrial Electronics, 1993, 40(1): 130-138. [2] Hatounian F K, Moreau S, Janot A. Parameter estima- tion of the actuator used in haptic interfaces: comparison of two identification methods[C]. IEEE ISIE, France, 2006: 211-216. [3] 杨宗军, 王莉娜. 表贴式永磁同步电机的多参数在线辨识[J]. 电工技术学报, 2014, 29(3): 111-118. Yang Zongjun, Wang Lina. Online multi-parameter identification for surface-mounted permanent magnet synchronous motors[J]. Transactions of China Elec- trotechnical Society, 2014, 29(3): 111-118. [4] 刘朝华, 李小花, 周少武, 等. 面向永磁同步电机参数辨识的免疫完全学习型粒子群算法[J]. 电工技术学报, 2014, 29(5): 118-126. Liu Zhaohua, Li Xiaohua, Zhou Shaowu, et al. Comprehensive learning particle swarm optimization algorithm based on immune mechanism for permanent magnet synchronous motor parameter identification[J]. Transactions of China Electrotechnical Society, 2014, 29(5): 118-126. [5] Samuel J. Underwood, Iqbal Husain. Online parameter estimation and adaptive control of permanent-magnet synchronous machines[J]. IEEE Transactions on Indus- trial Electronics. 2010, 57(7): 2435-2443. [6] 杨立永, 张云龙, 陈智刚, 等. 基于参数辨识的PMSM 电流环在线自适应控制方法[J]. 电工技术学报, 2012, 27(3): 86-91. Yang Liyong, Zhang Yunlong, Chen Zhigang, et al. On-line adaptive control of PMSM current-loop based on parameter identification[J]. Transactions of China Electrotechnical Society, 2012, 27(3): 86-91. [7] Boileau T, Leboeuf N. On-line identification of PMSMs parameters: parameters identifiability and estimators comparative study[J]. IEEE Transaction on Industry Application, 2011, 47(4): 1944-1957. [8] Tomonobu Senjyu, Yoshiaki Kuwae. Accurate para- meter measurement for high speed permanent magnet synchronous motors[C]. Power Electronics Specialists Conference, Vancouver, BC, Canada, 2001: 772-777. [9] 安群涛, 孙力, 赵克. 一种永磁同步电动机参数的自适应在线辨识方法[J]. 电工技术学报, 2008, 23(6): 31-36. An Quntao, Sun Li, Zhao Ke. An adaptive on-line identification method for the parameters of permanent maget synchronous motor[J]. Transactions of China Electrotechnical Society, 2008, 23(6): 31-36. [10] 刘侃, 张兢. 基于自适应线性元件神经网络的表面式永磁同步电机参数在线辨识[J]. 中国电机工程学报, 2010, 30(30): 68-73. Liu Kan, Zhang Jing. Adaline neural network based online parameter estimation for surface-mounted permanent magnet synchronous machines[J]. 2010, 30(30): 68-73. [11] Liu Kan, Zhang Qiao, Chen Jintao. Online multipara- meter estimation of nonsalient-pole PM synchronous machines with temperature vatiation thracking[J]. IEEE Transaction on Industrial Electronics, 2011, 58(5): 1776-1788. [12] Widrow B, Lehr M A. 30 years of adaptive neural networks: percentron, MAdaline, and backpropagat- tion[J]. Proceedings of the IEEE, 1990, 78(9): 1415- 1442. [13] Mellor P H, Chaaban F B. Estimation of parameters and performance of rare-earth permanent-magnet motors avoiding measurement of load angle[J]. IEE Procee- dings-B, 1991, 138(6): 322-333.
2015, Vol. 30 
