Year: 2026
Type: preprint
Abstract: This paper presents a physics-constrained neural network framework for magnetic modeling of saturable synchronous machines, including spatial harmonics. By embedding gradient networks into the machine equations to model conservative electromagnetic behavior, the framework satisfies reciprocity and energy conservation by construction, while universally approximating any physically feasible magnetic characteristic. Unlike lookup tables and black-box neural networks, it guarantees monotonicity, invertibility, and smooth outputs, and remains highly data efficient. The method is validated using measured and finite-element method (FEM) data from a 5.6-kW permanent-magnet (PM) synchronous reluctance machine, and is demonstrated in real-time closed-loop control on an embedded platform. The results confirm accurate, physically consistent, and computationally efficient performance.
Source: arXiv (Cornell University)
Institution: Aalto University
Subfield: Electrical and Electronic Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
Funder: Aalto-Yliopisto
OpenAlex ID: W7129240212
Cites:
Cited by:
Related to: