Learning stable reduced-order models for hybrid twins
نویسندگان
چکیده
Abstract The concept of “hybrid twin” (HT) has recently received a growing interest thanks to the availability powerful machine learning techniques. This twin combines physics-based models within model order reduction framework—to obtain real-time feedback rates—and data science. Thus, main idea HT is develop on-the-fly data-driven correct possible deviations between measurements and predictions. paper focused on computation stable, fast, accurate corrections in framework. Furthermore, regarding delicate important problem stability, new approach proposed, introducing several subvariants guaranteeing low computational cost as well achievement stable time-integration.
منابع مشابه
Stable Galerkin reduced order models for linearized compressible flow
Article history: Received 28 February 2008 Received in revised form 19 September 2008 Accepted 15 November 2008 Available online 27 November 2008
متن کاملA Hybrid Optimization Algorithm for Learning Deep Models
Deep learning is one of the subsets of machine learning that is widely used in Artificial Intelligence (AI) field such as natural language processing and machine vision. The learning algorithms require optimization in multiple aspects. Generally, model-based inferences need to solve an optimized problem. In deep learning, the most important problem that can be solved by optimization is neural n...
متن کاملA Hybrid Optimization Algorithm for Learning Deep Models
Deep learning is one of the subsets of machine learning that is widely used in Artificial Intelligence (AI) field such as natural language processing and machine vision. The learning algorithms require optimization in multiple aspects. Generally, model-based inferences need to solve an optimized problem. In deep learning, the most important problem that can be solved by optimization is neural n...
متن کاملConstruction of energy-stable projection-based reduced order models
An approach for building energy-stable Galerkin reduced order models (ROMs) for linear hyperbolic or incompletely parabolic systems of partial differential equations (PDEs) using continuous projection is developed. This method is an extension of earlier work by the authors specific to the equations of linearized compressible inviscid flow. The key idea is to apply to the PDEs a transformation i...
متن کاملReduced-Order Models for Data-Limited Reinforcement Learning
Often in reinforcement learning we are confronted with planning in a domain with an unknown dynamics model. In poorly understood domains where an exact model of either the dynamics, value function, or policy is unavailable we commonly choose to use large models, consisting of many parameters. Unfortunately, these large models can require a prohibitively large amount of training in realworld dom...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Data-centric engineering
سال: 2021
ISSN: ['2632-6736']
DOI: https://doi.org/10.1017/dce.2021.16