Solving PDE-constrained Control Problems Using Operator Learning

• URL: http://arxiv.org/abs/2111.04941v3
• Date: Tue, 26 Dec 2023 08:22:24 GMT
• Title: Solving PDE-constrained Control Problems Using Operator Learning
• Authors: Rakhoon Hwang, Jae Yong Lee, Jin Young Shin, Hyung Ju Hwang
• Abstract summary: We introduce surrogate models for PDE solution operators with special regularizers. Our framework can be applied to both data-driven and data-free cases.
• Score: 14.30832827446317
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The modeling and control of complex physical systems are essential in real-world problems. We propose a novel framework that is generally applicable to solving PDE-constrained optimal control problems by introducing surrogate models for PDE solution operators with special regularizers. The procedure of the proposed framework is divided into two phases: solution operator learning for PDE constraints (Phase 1) and searching for optimal control (Phase 2). Once the surrogate model is trained in Phase 1, the optimal control can be inferred in Phase 2 without intensive computations. Our framework can be applied to both data-driven and data-free cases. We demonstrate the successful application of our method to various optimal control problems for different control variables with diverse PDE constraints from the Poisson equation to Burgers' equation.

Related papers

• Control and optimization for Neural Partial Differential Equations in Supervised Learning [0.0]
  We aim to initiate a line of research in control theory focused on optimizing and controlling the coefficients of parabolic and hyperbolic operators.<n>In supervised learning, the primary objective is to transport initial data toward target data through the layers of a neural network.<n>We propose a novel perspective: neural networks can be interpreted as partial differential equations (PDEs)
  arXiv  Detail & Related papers  (2025-06-25T18:54:48Z)
• Physics-Informed Neural Networks for Control of Single-Phase Flow Systems Governed by Partial Differential Equations [4.776073133338117]
  We extend the Physics-Informed Neural Nets for Control (PINC) framework to integrate neural networks with physical conservation laws.<n>The PINC model for PDEs is structured into two stages: a steady-state network, which learns equilibrium solutions for a wide range of control inputs, and a transient network, which captures dynamic responses under time-varying boundary conditions.<n>We validate our approach through numerical experiments, demonstrating that the PINC model, which is trained exclusively using physical laws, accurately represents flow dynamics and enables real-time control applications.
  arXiv  Detail & Related papers  (2025-06-06T15:50:19Z)
• CodePDE: An Inference Framework for LLM-driven PDE Solver Generation [57.15474515982337]
  Partial differential equations (PDEs) are fundamental to modeling physical systems.<n>Traditional numerical solvers rely on expert knowledge to implement and are computationally expensive.<n>We introduce CodePDE, the first inference framework for generating PDE solvers using large language models.
  arXiv  Detail & Related papers  (2025-05-13T17:58:08Z)
• Paving the way for scientific foundation models: enhancing generalization and robustness in PDEs with constraint-aware pre-training [49.8035317670223]
  A scientific foundation model (SciFM) is emerging as a promising tool for learning transferable representations across diverse domains. We propose incorporating PDE residuals into pre-training either as the sole learning signal or in combination with data loss to compensate for limited or infeasible training data. Our results show that pre-training with PDE constraints significantly enhances generalization, outperforming models trained solely on solution data.
  arXiv  Detail & Related papers  (2025-03-24T19:12:39Z)
• Interpretable and Efficient Data-driven Discovery and Control of Distributed Systems [1.5195865840919498]
  Reinforcement Learning (RL) has emerged as a promising control paradigm for systems with high-dimensional, nonlinear dynamics. We propose a data-efficient, interpretable, and scalable framework for PDE control.
  arXiv  Detail & Related papers  (2024-11-06T18:26:19Z)
• Unisolver: PDE-Conditional Transformers Are Universal PDE Solvers [55.0876373185983]
  We present the Universal PDE solver (Unisolver) capable of solving a wide scope of PDEs. Our key finding is that a PDE solution is fundamentally under the control of a series of PDE components. Unisolver achieves consistent state-of-the-art results on three challenging large-scale benchmarks.
  arXiv  Detail & Related papers  (2024-05-27T15:34:35Z)
• Two-Stage ML-Guided Decision Rules for Sequential Decision Making under Uncertainty [55.06411438416805]
  Sequential Decision Making under Uncertainty (SDMU) is ubiquitous in many domains such as energy, finance, and supply chains. Some SDMU are naturally modeled as Multistage Problems (MSPs) but the resulting optimizations are notoriously challenging from a computational standpoint. This paper introduces a novel approach Two-Stage General Decision Rules (TS-GDR) to generalize the policy space beyond linear functions. The effectiveness of TS-GDR is demonstrated through an instantiation using Deep Recurrent Neural Networks named Two-Stage Deep Decision Rules (TS-LDR)
  arXiv  Detail & Related papers  (2024-05-23T18:19:47Z)
• BiLO: Bilevel Local Operator Learning for PDE inverse problems [10.082649871368409]
  We propose a new neural network based method for solving inverse problems for partial differential equations (PDEs) At the upper level, we minimize the data loss with respect to the PDE parameters. At the lower level, we train a neural network to locally approximate the PDE solution operator in the neighborhood of a given set of PDE parameters.
  arXiv  Detail & Related papers  (2024-04-27T06:06:41Z)
• Policy Optimization for PDE Control with a Warm Start [3.0811185425377743]
  Dimensionality reduction is crucial for controlling nonlinear partial differential equations (PDE) We augment the reduce-then-design procedure with a policy optimization step to compensate for the modeling error from dimensionality reduction. Our approach offers a cost-effective alternative to PDE control using end-to-end reinforcement learning.
  arXiv  Detail & Related papers  (2024-03-01T22:03:22Z)
• Double Duality: Variational Primal-Dual Policy Optimization for Constrained Reinforcement Learning [132.7040981721302]
  We study the Constrained Convex Decision Process (MDP), where the goal is to minimize a convex functional of the visitation measure. Design algorithms for a constrained convex MDP faces several challenges, including handling the large state space.
  arXiv  Detail & Related papers  (2024-02-16T16:35:18Z)
• Learning differentiable solvers for systems with hard constraints [48.54197776363251]
  We introduce a practical method to enforce partial differential equation (PDE) constraints for functions defined by neural networks (NNs) We develop a differentiable PDE-constrained layer that can be incorporated into any NN architecture. Our results show that incorporating hard constraints directly into the NN architecture achieves much lower test error when compared to training on an unconstrained objective.
  arXiv  Detail & Related papers  (2022-07-18T15:11:43Z)
• Physics-informed neural networks for PDE-constrained optimization and control [0.0]
  Control Physics-Informed Neural Networks simultaneously solve a given system state, and its respective optimal control. The success of Control PINNs is demonstrated by solving the following open-loop optimal control problems.
  arXiv  Detail & Related papers  (2022-05-06T17:22:36Z)
• Fast PDE-constrained optimization via self-supervised operator learning [0.0]
  Design and optimal control problems are among the fundamental, ubiquitous tasks we face in science and engineering. In this work we leverage physics-informed deep operator networks (DeepONets) to build fast and differentiable surrogates for rapidly solving PDE-constrained optimization problems. DeepONets can minimize high-dimensional cost functionals in a matter of seconds, yielding a significant speed up compared to traditional adjoint PDE solvers.
  arXiv  Detail & Related papers  (2021-10-25T22:17:15Z)
• Combining Deep Learning and Optimization for Security-Constrained Optimal Power Flow [94.24763814458686]
  Security-constrained optimal power flow (SCOPF) is fundamental in power systems. Modeling of APR within the SCOPF problem results in complex large-scale mixed-integer programs. This paper proposes a novel approach that combines deep learning and robust optimization techniques.
  arXiv  Detail & Related papers  (2020-07-14T12:38:21Z)
• Learning to Control PDEs with Differentiable Physics [102.36050646250871]
  We present a novel hierarchical predictor-corrector scheme which enables neural networks to learn to understand and control complex nonlinear physical systems over long time frames. We demonstrate that our method successfully develops an understanding of complex physical systems and learns to control them for tasks involving PDEs.
  arXiv  Detail & Related papers  (2020-01-21T11:58:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.