Sensorless IPMSM drive system using saliency back-EMF-Based intelligent torque observer with MTPA control

A saliency back-electromotive force (EMF)-based wavelet fuzzy neural network (WFNN) torque observer using a new maximum torque per ampere (MTPA) control is proposed in this study to improve the speed estimating performance of a sensorless interior permanent magnet synchronous motor (IPMSM) drive system. First, the characteristics and mathematical model of the saliency back-EMF-based proportional-integral-derivative (PID) torque observer with the mechanical model-based phase-lock-loop (PLL) for the estimation of the rotor flux angle and speed of the IPMSM are discussed. Then, a new saliency back-EMF-based MTPA control suitable for the implementation using digital signal processor (DSP) is introduced. Moreover, the saliency back-EMF-based rotor flux angle and speed estimation method using WFNN torque observer is proposed. Furthermore, detailed network structure and online learning algorithms of WFNN are described. Finally, the feasibility of the proposed control schemes is verified through experimental results.