Different neural architectures produce qualitatively distinct controls in PINN optimal control for RLC and Duffing systems, with Fourier versions yielding richer oscillations and smoother nets yielding more regular efficient trajectories.
Dzimah, Fernando Carlos L´ opez Hern´ andez, Sonia Rubio Herranz, and An- tonio L´ opez Montes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Neural Architectures as Functional Priors in Physics-Informed Control Problems
Different neural architectures produce qualitatively distinct controls in PINN optimal control for RLC and Duffing systems, with Fourier versions yielding richer oscillations and smoother nets yielding more regular efficient trajectories.