A novel adaptive neuro-fuzzy and adaptive proportional resonant control scheme for PMSM based electric vehicle applications

The permanent magnet synchronous motor (PMSM) offers a very competitive technology for field oriented control (FOC) technique in electric vehicles (EVs) due to its increased efficiency and high power density. However, achieving precise speed and current control under varying driving conditions remains a challenging part. To overcome the speed and current control issues in PMSM this paper proposed a two-stage control technique: one is an adaptive neuro- fuzzy inference system (ANFIS) based speed controller in the outer loop, while adaptive proportional resonant (PR) controller in the current loop. The ANFIS controllers effectively suppress the speed ripples during transient state, while the adaptive PR controller improves the sinusoidal current tracing performance and reduce the steady state error of the controller. The key contribution of the proposed controller is its ability to dampen torsional mode oscillation caused by steady state and dynamic condition in both speed and current loop. The effectiveness of the proposed controller is evaluated using MATLAB/Simulator and it is compared with hardware in the loop (HIL) real time simulator using RT5700. The proposed controller results show good transient efficiency, gives the best speed control in start-up, acceleration, deceleration and load changing situations also reduce the torque ripple and current harmonics in EV application compared to conventional controllers.