Neural-Network Vector Controller for Permanent-Magnet Synchronous Motor Drives: Simulated and Hardware-Validated Results

This paper focuses on current control in a permanent-magnet synchronous motor (PMSM). This paper has two main objectives: the first objective is to develop a neural-network (NN) vector controller to overcome the decoupling inaccuracy problem associated with the conventional proportional–integral-based vector-control methods. The NN is developed using the full dynamic equation of a PMSM, and trained to implement optimal control based on approximate dynamic programming. The second objective is to evaluate the robust and adaptive performance of the NN controller against that of the conventional standard vector controller under motor parameter variation and dynamic control conditions by: 1) simulating the behavior of a PMSM typically used in realistic electric vehicle applications and 2) building an experimental system for hardware validation as well as combined hardware and simulation evaluation. The results demonstrate that the NN controller outperforms conventional vector controllers in both simulation and hardware implementation.

[1]  A. S. Mehr,et al.  Parameter-dependent mixed [Hamiltonian (script capital H)]2/[Hamiltonian (script capital H)]∞ filtering for linear parameter-varying systems , 2012 .

[2]  Cheng-Kai Lin,et al.  Model-Free Predictive Current Control for Interior Permanent-Magnet Synchronous Motor Drives Based on Current Difference Detection Technique , 2014, IEEE Transactions on Industrial Electronics.

[3]  Kyo-Beum Lee,et al.  Torque-Ripple Minimization and Fast Dynamic Scheme for Torque Predictive Control of , 2015 .

[4]  D. M. Vilathgamuwa,et al.  Implementation of an artificial-neural-network-based real-time adaptive controller for an interior permanent-magnet motor drive , 2003 .

[5]  Eduard Muljadi,et al.  Characteristic Study of Vector-controlled Direct-driven Permanent Magnet Synchronous Generator in Wind Power Generation , 2009 .

[6]  Qinglai Wei,et al.  Adaptive Dynamic Programming-Based Optimal Control Scheme for Energy Storage Systems With Solar Renewable Energy , 2017, IEEE Transactions on Industrial Electronics.

[7]  Huaguang Zhang,et al.  General value iteration based reinforcement learning for solving optimal tracking control problem of continuous-time affine nonlinear systems , 2017, Neurocomputing.

[8]  Marek Stulrajter.  3-Phase PMSM Motor Control Kit with the MPC5604P , 2015 .

[9]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[10]  Soohee Han,et al.  Adaptive Torque Estimation for an IPMSM with Cross-Coupling and Parameter Variations , 2017 .

[11]  D. Wunsch,et al.  Vector Control of Permanent Magnet Synchronous Motor using Adaptive Recurrent Neural Networks , 2022 .

[12]  Iqbal Husain,et al.  Online Parameter Estimation and Adaptive Control of Permanent-Magnet Synchronous Machines , 2010, IEEE Transactions on Industrial Electronics.

[13]  Changliang Xia,et al.  Smooth Speed Control for Low-Speed High-Torque Permanent-Magnet Synchronous Motor Using Proportional–Integral–Resonant Controller , 2015, IEEE Transactions on Industrial Electronics.

[14]  Essam Allam,et al.  Hybrid Electric Vehicle Power Train using Battery Model Simulation in Simulink and Its Use for Power Management Studies , 2012 .

[15]  Qian Miao-wang.  Mixed H_2/H_∞ control of permanent magnet synchronous motor based on particle swarm optimization algorithm , 2012 .

[16]  Shuhui Li,et al.  An adaptive recurrent neural-network controller using a stabilization matrix and predictive inputs to solve a tracking problem under disturbances , 2014, Neural Networks.

[17]  Louis B. Rall,et al.  Automatic Differentiation: Techniques and Applications , 1981, Lecture Notes in Computer Science.

[18]  Ned Mohan.  Advanced electric drives , 2014 .

[19]  Gomaa F. Abdelnaby,et al.  Sensorless Field Oriented Control of Permanent Magnet Synchronous Motor , 2015 .

[20]  Saptarshi Das,et al.  On the Mixed H2/H-infinity Loop Shaping Trade-offs in Fractional Order Control of the AVR System , 2013, ArXiv.

[21]  Huaguang Zhang,et al.  Adaptive Dynamic Programming: An Introduction , 2009, IEEE Computational Intelligence Magazine.

[22]  Anton A. Stoorvogel,et al.  The H ∞ control problem: a state space approach , 2000 .

[23]  P. Werbos.  Backwards Differentiation in AD and Neural Nets: Past Links and New Opportunities , 2006 .

[24]  Danil V. Prokhorov,et al.  Adaptive behavior with fixed weights in RNN: an overview , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[25]  Yixin Yin,et al.  Hamiltonian-Driven Adaptive Dynamic Programming for Continuous Nonlinear Dynamical Systems , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[26]  Derong Liu,et al.  A Novel Dual Iterative $Q$-Learning Method for Optimal Battery Management in Smart Residential Environments , 2015, IEEE Transactions on Industrial Electronics.

[27]  Xin Zhang,et al.  Data-Driven Robust Approximate Optimal Tracking Control for Unknown General Nonlinear Systems Using Adaptive Dynamic Programming Method , 2011, IEEE Transactions on Neural Networks.

[28]  Turker Turker,et al.  A Robust Predictive Current Controller for PMSM Drives , 2016, IEEE Transactions on Industrial Electronics.

[29]  Ling Xu,et al.  Conventional and novel control designs for direct driven PMSG wind turbines , 2010 .

[30]  Dimitri P. Bertsekas,et al.  Dynamic Programming and Optimal Control, Two Volume Set , 1995 .

[31]  Changliang Xia,et al.  A Neural-Network-Identifier and Fuzzy-Controller-Based Algorithm for Dynamic Decoupling Control of Permanent-Magnet Spherical Motor , 2010, IEEE Transactions on Industrial Electronics.

[32]  Tomasz Pajchrowski,et al.  Application of Artificial Neural Network to Robust Speed Control of Servodrive , 2007, IEEE Transactions on Industrial Electronics.

[33]  H. Shayeghi,et al.  A robust mixed H2/H∞ based LFC of a deregulated power system including SMES , 2008 .

[34]  Derong Liu,et al.  Multibattery Optimal Coordination Control for Home Energy Management Systems via Distributed Iterative Adaptive Dynamic Programming , 2015, IEEE Transactions on Industrial Electronics.

[35]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[36]  Shuhui Li,et al.  Training Recurrent Neural Networks With the Levenberg–Marquardt Algorithm for Optimal Control of a Grid-Connected Converter , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[37]  Roberto A. Santiago,et al.  Adaptive critic designs: A case study for neurocontrol , 1995, Neural Networks.

[38]  Frank L. Lewis,et al.  Reinforcement Learning and Approximate Dynamic Programming for Feedback Control , 2012 .

[39]  M. A. Rahman,et al.  On-line adaptive artificial neural network based vector control of permanent magnet synchronous motors , 1998 .

[40]  W. Haddad,et al.  LQG control with an H∞ performance bound: a riccati equation approach , 1988, 1988 American Control Conference.

[41]  Kyo-Beum Lee,et al.  Torque-Ripple Minimization and Fast Dynamic Scheme for Torque Predictive Control of Permanent-Magnet Synchronous Motors , 2015, IEEE Transactions on Power Electronics.

[42]  Haibin Yu,et al.  Mixed H2 / H∞ optimal control for three-phase Grid Connected Converter , 2015, 2015 IEEE International Conference on Information and Automation.

[43]  Yuan Ren,et al.  Direct Torque Control of Permanent-Magnet Synchronous Machine Drives With a Simple Duty Ratio Regulator , 2014, IEEE Transactions on Industrial Electronics.

[44]  Annemarie Thomas,et al.  dSPACE DS1103 Control Workstation Tutorial and DC Motor Speed Control Tutorial , 2009 .