Physics-Informed Machine Learning for Modeling and Control of Dynamical Systems
Physics-Informed Machine Learning for Modeling and Control of Dynamical Systems
复制标题
DOI：
10.23919/acc55779.2023.10155901
复制
发表时间：
2023-05
期刊：
影响因子：
--
通讯作者：
Truong X. Nghiem;Ján Drgoňa;Colin N. Jones;Zoltán Nagy;Roland Schwan;Biswadip Dey;A. Chakrabarty
中科院分区：
文献类型：
--
作者：
Truong X. Nghiem;Ján Drgoňa;Colin N. Jones;Zoltán Nagy;Roland Schwan;Biswadip Dey;A. Chakrabarty
物理信息机器学习（Physics-informed machine learning，PIML）是一组将机器学习（ML）算法与科学和工程领域开发的物理约束和抽象数学模型系统集成的方法和工具。与纯粹的数据驱动方法相反，PIML模型可以从通过执行物理定律（如能量和质量守恒）获得的额外信息中进行训练。更广泛地说，PIML模型可以包括抽象属性和条件，如稳定性，凸性或不变性。PIML的基本前提是ML和物理的集成可以产生更有效，物理一致和数据高效的模型。本文的目的是提供一个教程般的概述PIML的动态系统建模和控制的最新进展。具体而言，本文概述了以下主题的理论，基本概念和方法，工具和应用：1）用于系统识别的物理信息学习; 2）用于控制的物理信息学习; 3）PIML模型的分析和验证;以及4）物理信息数字孪生。本文的结论是开放的挑战和未来的研究机会的角度。
Physics-informed machine learning (PIML) is a set of methods and tools that systematically integrate machine learning (ML) algorithms with physical constraints and abstract mathematical models developed in scientific and engineering domains. As opposed to purely data-driven methods, PIML models can be trained from additional information obtained by enforcing physical laws such as energy and mass conservation. More broadly, PIML models can include abstract properties and conditions such as stability, convexity, or invariance. The basic premise of PIML is that the integration of ML and physics can yield more effective, physically consistent, and data-efficient models. This paper aims to provide a tutorial-like overview of the recent advances in PIML for dynamical system modeling and control. Specifically, the paper covers an overview of the theory, fundamental concepts and methods, tools, and applications on topics of: 1) physics-informed learning for system identification; 2) physics-informed learning for control; 3) analysis and verification of PIML models; and 4) physics-informed digital twins. The paper is concluded with a perspective on open challenges and future research opportunities.