LGAISYSYApr 16

SOLIS: Physics-Informed Learning of Interpretable Neural Surrogates for Nonlinear Systems

arXiv:2604.1487937.72 citationsh-index: 23
AI Analysis

For nonlinear system identification, SOLIS bridges the gap between interpretability and flexibility, enabling control-relevant model learning from sparse data.

SOLIS introduces a physics-informed neural surrogate that learns interpretable Quasi-LPV models from sparse data, recovering natural frequency, damping, and gain without assuming a known governing equation. It achieves accurate parameter-manifold recovery and coherent rollouts where standard inverse PINNs fail.

Nonlinear system identification must balance physical interpretability with model flexibility. Classical methods yield structured, control-relevant models but rely on rigid parametric forms that often miss complex nonlinearities, whereas Neural ODEs are expressive yet largely black-box. Physics-Informed Neural Networks (PINNs) sit between these extremes, but inverse PINNs typically assume a known governing equation with fixed coefficients, leading to identifiability failures when the true dynamics are unknown or state-dependent. We propose \textbf{SOLIS}, which models unknown dynamics via a \emph{state-conditioned second-order surrogate model} and recasts identification as learning a Quasi-Linear Parameter-Varying (Quasi-LPV) representation, recovering interpretable natural frequency, damping, and gain without presupposing a global equation. SOLIS decouples trajectory reconstruction from parameter estimation and stabilizes training with a cyclic curriculum and \textbf{Local Physics Hints} windowed ridge-regression anchors that mitigate optimization collapse. Experiments on benchmarks show accurate parameter-manifold recovery and coherent physical rollouts from sparse data, including regimes where standard inverse methods fail.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes