ABSTRACT
Emerging computational paradigms such as quantum‑inspired optimization (QIO) and physics‑informed machine learning (PIML) offer novel solutions to complex design challenges in electrical drives. These approaches merge physics knowledge with advanced computational search and inference techniques to achieve optimal performance under multi‑objective constraints. This paper investigates the theoretical foundations of QIO and PIML and their application to drive design problems, including torque ripple minimization, energy efficiency, and fault tolerance. Numerical results and design frameworks demonstrate how physics‑guided learning improves generalization while reducing reliance on large training datasets. Original studies and comparative data are used to illustrate efficacy.
KEYWORDS: Quantum‑inspired optimization, physics‑informed machine learning, drive design, electrical machines, hybrid modeling.
Full Issue
| View or download the full issue | PDF 136-141 |