Enregistré dans:
Détails bibliographiques
Auteurs principaux: Iftakher, Ashfaq, Golder, Rahul, Roy, Bimol Nath, Hasan, M. M. Faruque
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2507.08124
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909746256150528
author Iftakher, Ashfaq
Golder, Rahul
Roy, Bimol Nath
Hasan, M. M. Faruque
author_facet Iftakher, Ashfaq
Golder, Rahul
Roy, Bimol Nath
Hasan, M. M. Faruque
contents Traditional physics-informed neural networks (PINNs) do not guarantee strict constraint satisfaction. This is problematic in engineering systems where minor violations of governing laws can degrade the reliability and consistency of model predictions. In this work, we introduce KKT-Hardnet, a neural network architecture that enforces linear and nonlinear equality and inequality constraints up to machine precision. It leverages a differentiable projection onto the feasible region by solving Karush-Kuhn-Tucker (KKT) conditions of a distance minimization problem. Furthermore, we reformulate the nonlinear KKT conditions via a log-exponential transformation to construct a sparse system with linear and exponential terms. We apply KKT-Hardnet to nonconvex pooling problem and a real-world chemical process simulation. Compared to multilayer perceptrons and PINNs, KKT-Hardnet achieves strict constraint satisfaction. It also circumvents the need to balance data and physics residuals in PINN training. This enables the integration of domain knowledge into machine learning towards reliable hybrid modeling of complex systems.
format Preprint
id arxiv_https___arxiv_org_abs_2507_08124
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Physics-Informed Neural Networks with Hard Nonlinear Equality and Inequality Constraints
Iftakher, Ashfaq
Golder, Rahul
Roy, Bimol Nath
Hasan, M. M. Faruque
Machine Learning
Traditional physics-informed neural networks (PINNs) do not guarantee strict constraint satisfaction. This is problematic in engineering systems where minor violations of governing laws can degrade the reliability and consistency of model predictions. In this work, we introduce KKT-Hardnet, a neural network architecture that enforces linear and nonlinear equality and inequality constraints up to machine precision. It leverages a differentiable projection onto the feasible region by solving Karush-Kuhn-Tucker (KKT) conditions of a distance minimization problem. Furthermore, we reformulate the nonlinear KKT conditions via a log-exponential transformation to construct a sparse system with linear and exponential terms. We apply KKT-Hardnet to nonconvex pooling problem and a real-world chemical process simulation. Compared to multilayer perceptrons and PINNs, KKT-Hardnet achieves strict constraint satisfaction. It also circumvents the need to balance data and physics residuals in PINN training. This enables the integration of domain knowledge into machine learning towards reliable hybrid modeling of complex systems.
title Physics-Informed Neural Networks with Hard Nonlinear Equality and Inequality Constraints
topic Machine Learning
url https://arxiv.org/abs/2507.08124