cs.LG · 2606.21728 Copy arXiv ID · Jun 19, 2026 Save Embedding Linear Equality Constraints in Probabilistic Neural Networks for Dynamic Modelling Authors: Matthew Marsh , Benoit Chachuat , Antonio del Rio Chanona
Organizations: The Sargent Centre for Process Systems Engineering, Department of Chemical Engineering, Imperial College London, UK
Abstract Machine learning models are increasingly used to model chemical process systems, yet they often lack principled uncertainty quantification and mechanisms to enforce physical constraints. We propose a probabilistic neural network framework that guarantees satisfaction of linear equality constraints within a given tolerance, while capturing aleatoric uncertainty. Compared to state-of-the-art methods, our formulation demonstrates improved predictive accuracy, uncertainty calibration, and adherence to constraints on reduced data. It also demonstrates competitive performance, but with significantly faster training times when evaluated on large data regimes. We evaluated this on two batch reactor case studies, enforcing mass balances.
Explore similar work Jun 9, 2026 · Fateme Mohammad Mohammadi, Hector Budman, Joshua L. Pulsipher Conventional Physics-Informed Neural Networks Inequality Constraints
Apr 27, 2026 · Matthew Marsh, Benoît Chachuat, Antonio del Rio Chanona Bayesian Neural Networks Variational Inference
Apr 21, 2026 · Andrea Goertzen, Kaveh Alim, Youngjae Min +1 Inequality Constraints Structural Constraints
Jun 9, 2026 · cs.LG J/K move · Enter open · S save
Fateme Mohammad Mohammadi, Hector Budman, Joshua L. Pulsipher
Department of Chemical Engineering University of Waterloo, 200 University Ave W, Waterloo, ON N2L 3G1, Canada
While physics-informed neural networks (PINNs) have shown strong potential for process modeling, physical equations are only enforced as soft constraints during training, and thus, they do not guarantee constraint satisfaction at inference. We propose a framework, called piecewise-linear Karush--Kuhn--Tucker hard-constrained PINNs (PL-KKT-hPINNs), that strictly enforces nonlinear equality constraints through piecewise-linear projection. This extends the KKT-hPINN framewor, which exactly enforces linear equalities through the Karush--Kuhn--Tucker (KKT) conditions associated with orthogonally projecting neural network outputs onto the constraint feasible region. The method is demonstrated on a continuous stirred-tank reactor (CSTR) case study for both one and two inputs. Results show that PL-KKT-hPINN preserves predictive accuracy comparable to that of a standard neural network while achieving substantially lower constraint violations. In addition, the proposed model shows improved robustness in low-data regimes, yielding lower RMSE than the unconstrained neural network for limited training sample sizes. These results demonstrate that PL-KKT-hPINN provides a computationally efficient and physically consistent framework for surrogate modeling of nonlinear chemical engineering systems.