Online MTPA Control of IPM Motor Using NN-Based Perturb and Observe Algorithm

In commercial electrical equipment, interior permanent magnet (IPM) synchronous motors undergo variations in temperature and parameters under different operating conditions. Conventional maximum torque per ampere (MTPA) control using fixed parameters lacks accurate motor parameter information, which can negatively impact the operating efficiency of electrical equipment. To address the above problem, this paper proposes a simple online MTPA control method without motor parameters. To approximate the interface structure of the conventional MTPA controller, a back propagation neural network (BP-NN) adjuster with a space vector decomposer is designed as the MTPA controller. Moreover, by leveraging the similarity between the loss function of the BP-NN and the stator current representing the efficiency of the IPM motor, the teacher signal is cleverly chosen to update the parameters of the BP-NN online. In the discrete domain, the motion mechanism of the proposed method is analyzed and characterized by the perturb & observe technique. Compared to the conventional MTPA control using fixed parameters, the feasibility and high efficiency of the proposed method for copper-loss-minimization control were validated in the simulation. The feasibility of the proposed method was further validated in simulated scenarios involving sudden changes in torque and speed. Furthermore, the transient characteristics of the output stator current were analyzed. Overall, the proposed method can achieve true online MTPA control without motor parameters.