Improving performance of electric vehicle drive system based a five-phase PMSM under fault using ANN and MPC.

The goal of this research is to create and test a fault‑tolerant control method for a five‑phase permanent‑magnet synchronous motor (PMSM) drive used in electric vehicles. Multi‑phase traction systems naturally resist faults, which is essential for keeping the vehicle moving when one or more phases open‑circuit or short‑circuit. To improve performance after a fault, the project proposes a hybrid controller that mixes an artificial neural network (ANN) with model predictive control (MPC). The MPC part selects the best voltage vectors and tries to keep torque ripples low when the fault is asymmetrical. The ANN supplies real‑time estimates of motor parameters, generates adaptive reference signals, or speeds up the optimization of

MPC’s cost function. The work includes: – building a model of the five‑phase PMSM, – designing a fault‑detection scheme, and – setting up the predictive‑control loop in a simulation environment. The controller’s success is measured by how much it reduces torque ripple, how quickly speed responds, and how much current harmonic distortion remains during single‑phase and multi‑phase open‑circuit faults. This methodology gives clear guidance for studying advanced fault‑tolerant topologies in modern electric‑vehicle drivetrains.

Message: Hi FE, I need help with “Improving performance of electric vehicle drive system based a five-phase PMSM under fault using ANN and MPC.” in “Electrical Engineering”