Giulio Montecchio | Searcharxiv

arXiv2026

Horizon Selection in Physics-Enhanced Neural ODEs: Theoretical Insights and Flux Linkage Application

The integration horizon during the training plays a critical role in Physics-Enhanced Neural Ordinary Differential Equations. We draw conclusions about horizon extension in the training of Neural Ordinary Differential Equations based on classical nonlinear system identification of input-output models. In light of this insight, we propose a framework that exploits longer horizons to reduce bias in physical parameter estimates, extracts residual information from data, and acts as a regularizer improving generalization. In the learning of a model for permanent magnet synchronous machine, the method is used to jointly estimate the flux map and the resistance.

eess.SY↗

arXiv2026

Joint identification of permanent magnet synchronous machine and inverter

In electric drive modeling, identifying the magnetic flux maps is essential for predicting accurately the torque, parameterizing a controller for tracking the torque or creating a simulation model. However, the voltage output by the controller (commanded voltage) is usually disturbed by non-linearity of the inverter, which needs to be taken into account. This paper presents a novel approach to enhance the offline flux identification from commanded voltage inputs, circumventing the need for prior identification of inverter parameters. In the dq reference frame, the flux maps are represented as static relationships between dq fluxes and dq currents. We utilize a tensor product spline model to accurately capture saturation and cross-saturation effects. The effects of the voltage disturbance on the estimated flux maps are not negligible. It is demonstrated that a joint identification of the flux maps and a simple model of the inverter can highly improve the flux model. The method is validated on FEM simulation and test-bench data.

eess.SY↗