Application of integral reinforcement learning for optimal control of a high speed flux-switching permanent magnet machine
Yang Yu, Xiaohe Ma, Rong Su, Tseng King Jet, V. Viswanathan, Chandana Jayampathi Gajanayake, Sri Ramakrishna, Amitava Gupta · 2016
A novel control method using H∞tracking and integral reinforcement learning is applied to a flux-switching permanent magnet (FSPM) machine in a hostile environment. The proposed controller can maintain high performance in the presence of motor parameter uncertainties and load disturbances. The conventional design procedure for an H∞controller is to solve the Hamilton-Jacobi-Isaacs (HJI) equation which requires full information of the system model. The novel control method, the integral reinforcement learning (IRL) makes use of neural networks to parametrically represent the control policy and the performance of system, and learns the solution of HJI equations online. Therefore, the FSPM machine can work optimally under parameter uncertainties due to different operating conditions. The simulation in Matlab/Simulink vividly illustrates the control performance for a 45kW, rotor speed 9000 rpm, 12/5 poles flux-switching permanent magnet machine.