基于深度确信策略梯度的电动汽车异步电机参数标定方法

doi:10.19595/j.cnki.1000-6753.tces.191095

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (93185 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Most existing calibration methods of electric vehicle induction motor parameters have the problems of low calibrated accuracy and large workload. Therefore, a method for calibrating electric vehicle induction motor parameters based on deep deterministic policy gradient is proposed, and the framework of algorithm for induction motor parameter calibration task is illustrated. The experimental results verify the effectiveness and feasibility of the proposed method. The proposed method has the following advantages: ① the parameters calibrated by the proposed method are not the real modeling parameters, but the ones that enable the motor to run at the optimal torque in any given speed and current, which is more suitable for electric vehicle application; ② the proposed method is an end-to-end method, that is, all work is automatically completed by computers without manual assistance, thereby greatly reducing the workload of the calibration engineers.

Key words： Electric vehicle induction motor parameter calibration deep deterministic policy gradient

Received: 27 August 2019

PACS:

TM351

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Qi Xing
	Zheng Changbao
	Zhang Qian

Cite this article:

Qi Xing,Zheng Changbao,Zhang Qian. An Electric Vehicle Induction Motor Parameters Calibration Method Based on Deep Deterministic Policy Gradient[J]. Transactions of China Electrotechnical Society, 2020, 35(20): 4266-4277.

URL:

https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.191095 OR https://dgjsxb.ces-transaction.com/EN/Y2020/V35/I20/4266

[1] 崔纳新, 张承慧, 李珂, 等. 基于参数在线估计的交流异步电动机效率最优控制[J]. 电工技术学报, 2007, 22(9): 80-85.
Cui Naxin, Zhang Chenghui, Li Ke, et al.Efficiency optimization control of induction motor drives based on online parameter estimation[J]. Transactions of China Electrotechnical Society, 2007, 22(9): 80-85.
[2] 曹朋朋, 张兴, 杨淑英, 等. 基于李雅普诺夫稳定理论的异步电机在线转子时间常数辨识方法[J]. 中国电机工程学报, 2016, 36(14): 3947-3955.
Cao Pengpeng, Zhang Xing, Yang Shuying, et al.Online rotor time constant identification of induction motors based on Lyapunov stability theory[J]. Proceedings of the CSEE, 2016, 36(14): 3947-3955.
[3] 李松, 岳志芹, 韩松, 等. 一种永磁同步电机的自动标定方法系统和控制器: 中国: CN106301100A[P].2017-01-04.
[4] 曹朋朋, 张兴, 杨淑英, 等. 异步电机基于MRAC的转子时间常数在线辨识算法的统一描述[J]. 电工技术学报, 2017, 32(19): 62-70.
Cao Pengpeng, Zhang Xing, Yang Shuying, et al.Unified description of MRAC-based online rotor time constant identification algorithm for induction motors[J]. Transactions of China Electrotechnical Society, 2017, 32(19): 62-70.
[5] 张勇军, 孙寅飞, 王京. 基于单维离散滑模的模型参考自适应转速辨识方法[J]. 电工技术学报, 2012, 27(4): 54-58.
Zhang Yongjun, Sun Yinfei, Wang Jing.A speed estimation algorithm based on single-manifold discrete time sliding mode model reference adaptive system[J]. Transactions of China Electrotechnical Society, 2012, 27(4): 54-58.
[6] 刘金海, 陈为. 表贴式永磁同步电机准稳态多参数在线辨识[J]. 电工技术学报, 2016, 31(17): 154-160.
Liu Jinhai, Chen Wei.Online multi-parameter identi- fication for surface-mounted permanent magnet synchronous motors under quasi-steady-state[J]. Transactions of China Electrotechnical Society, 2016, 31(17): 154-160.
[7] Novotny D W, Lipo T A.Vector control and dynamics of AC drives[M]. Cambridge: Clarendon Press, 1996.
[8] Odhano S A, Bojoi R, Boglietti A, et al.Maximum efficiency per torque direct flux vector control of induction motor drives[J]. IEEE Transactions on Industry Applications, 2015, 51(6): 4415-4424.
[9] 张兴, 张雨薇, 曹朋朋. 基于定子电流和转子磁链点乘的异步电机转子时间常数在线辨识算法稳定性分析[J]. 中国电机工程学报, 2018, 38(16): 4863-4872.
Zhang Xing, Zhang Yuwei, Cao Pengpeng.Stability analysis of a dot product of stator currents and rotor flux based online rotor time constant updating algorithm in induction motor drives[J]. Proceedings of the CSEE, 2018, 38(16): 4863-4872.
[10] 张兴, 张雨薇, 曹朋朋, 等. 基于改进转矩模型的异步电机转子时间常数在线辨识算法[J]. 中国电机工程学报, 2019, 39(11): 3363-3372.
Zhang Xing, Zhang Yuwei, Cao Pengpeng, et al.Improved torque model for online rotor time constant estimation in induction motor drives[J]. Proceedings of the CSEE, 2019, 39(11): 3363-3372.
[11] 王捷, 艾红. 基于自适应模糊神经网络的异步电动机SVM-DTC控制[J]. 电气技术, 2017, 18(9): 40-45.
Wang Jie, Ai Hong.SVM-DTC control of induction motor based on adaptive fuzzy neural network[J]. Electrical Engineering, 2017, 18(9): 40-45.
[12] 鞠鲁峰, 王群京, 李国丽, 等. 永磁球形电机的支持向量机模型的参数寻优[J]. 电工技术学报, 2014, 29(1): 85-90.
Ju Lufeng, Wang Qunjing, Li Guoli, et al.Parameter optimization for support vector machine model of permanent magnet spherical motors[J]. Transactions of China Electrotechnical Society, 2014, 29(1): 85-90.
[13] Liu Zhaohua, Wei Hualing, Zhong Qingchang, et al.Parameter estimation for VSI-fed PMSM based on a dynamic PSO with learning strategies[J]. IEEE Transactions on Power Electronics, 2017, 32(4): 3154-3165.
[14] Chen Yize, Shi Yuanyuan, Zhang Baosheng.Optimal control via neural networks: a convex approach[C]// International Conference on Learning Representa- tions, New Orleans, Louisiana, United States, 2019: 256-264.
[15] 漆星, 张倩. Actor-Critic框架下的数据驱动异步电机离线参数辨识方法[J]. 电工技术学报, 2019, 34(9): 1875-1885.
Qi Xing, Zhang Qian.Data-driven induction motor parameters offline identification method based on Actor-Critic framework[J]. Transactions of China Electrotechnical Society, 2019, 34(9): 1875-1885.
[16] Sutton R S, Barto A G.Reinforcement learning: an introduction[M]. Cambridge: MIT Press, 1998.
[17] Sutton R S, Mcallester D A, Singh S P, et al.Policy gradient methods for reinforcement learning with function approximation[C]//Neural Information Pro- cessing Systems, Denver, Colorado, 1999: 1057-1063.
[18] Peters J, Schaal S.Natural actor-critic[J]. Neuro- computing, 2008, 71(7): 1180-1190.
[19] Lillicrap T P, Hunt J J, Pritzel A, et al.Continuous control with deep reinforcement learning[C]//Inter- national Conference on Learning Representations, San Juan, Puerto Rico, 2016: 219-225.
[20] Mnih V, Kavukcuoglu K, Silver D, et al.Human- level control through deep reinforcement learning[J]. Nature, 2015, 518(7540): 529-543.
[21] Qi Xing.Rotor resistance and excitation inductance estimation of an induction motor using deep-Q- learning algorithm[J]. Engineering Applications of Artificial Intelligence, 2018, 72(6): 67-79.
[22] Levi E.Impact of iron loss on behavior of vector controlled induction machines[J]. IEEE Transactions on Industry Applications, 1995, 31(6): 1287-1296.
[23] 李洁, 杜茜, 宋海军, 等. 考虑铁损的异步电机参数辨识实验研究[J]. 电工技术学报, 2014, 29(3): 89-95.
Li Jie, Du Xi, Song Haijun, et al.Experimental evaluation of induction machine parameter identi- fication considering iron loss[J]. Transactions of China Electrotechnical Society, 2014, 29(3): 89-95.