Real-Time Digital Twin-Driven Multi-Objective Optimization of Dual-Winding Permanent Magnet Synchronous Motors (DWPMSG)

The dual-winding permanent magnet synchronous motor (DWPMSM) offers superior power density and fault tolerance but remains challenged by electromagnetic vibration, torque ripple, and limited adaptability in dynamic environments. This paper introduces a real-time digital twin-driven framework for adaptive multi-objective optimization of DWPMSMs. The proposed approach integrates a hybrid physics-based and data-driven model with an online evolutionary optimizer to continuously adjust control and design parameters in response to real-time operational data. Simulations in ANSYS Maxwell and MATLAB/Simulink validate the method’s ability to enhance average torque, suppress vibration by over 50%, and improve thermal behavior under nominal, dynamic, and faulted conditions. Additionally, the framework achieves measurable reductions in carbon dioxide emissions, supporting sustainability in electric motor-driven systems.