Dual-Network PINNs for Optimal Control: A Reproducible Benchmark on the Mass-Spring-Damper System

Abstract:This work presents a transparent and reproducible benchmark study of a direct dual-network Physics-Informed Neural Network (PINN) formulation for the optimal control of a mass-spring-damper system. The classical linear-quadratic optimal control problem is solved by two independent classical methods -- Pontryagin's Minimum Principle with single shooting, and direct transcription through trapezoidal collocation -- and recast as a constrained optimization problem solved by two feedforward neural networks: a state network whose boundary conditions are enforced exactly through a composite cubic-and-mask ansatz, and an unconstrained control network. The composite loss combines the physics residual at the collocation points with a trapezoidal approximation of the cost functional, weighted by a single scalar hyperparameter. On the benchmark considered, the PINN reproduces the classical optimal cost to four significant digits, satisfies the terminal state constraints exactly by construction, and produces pointwise state and control errors that fall within the spread of the two classical references. Training is approximately two orders of magnitude slower than classical shooting on this benchmark, which is honestly reported. The contribution is methodological clarity rather than methodological novelty: the formulation and the accompanying Google Colab implementation are intended to lower the barrier to entry for practitioners exploring PINN-based optimal control without prior exposure to adjoint methods or two-point boundary value problems.

22 pages, 6 figures. Reproducible benchmark study of dual-network Physics-Informed Neural Networks (PINNs) for optimal control of a mass-spring-damper system. Includes comparison with Pontryagin's Minimum Principle and direct transcription methods and accompanying Google Colab implementation

Optimization and Control (math.OC); Machine Learning (cs.LG)

arXiv:2606.15271 [math.OC]

(or arXiv:2606.15271v1 [math.OC] for this version)

https://doi.org/10.48550/arXiv.2606.15271 arXiv-issued DOI via DataCite (pending registration)