Physics-Based Active Learning for Design Space Exploration and Surrogate Construction for Multiparametric Optimization

扫码查看

原文链接

NETL
NSTL
万方数据

外文摘要：The sampling of the training data is a bottleneck in the development of artificial intelli-gence(AI)models due to the processing of huge amounts of data or to the difficulty of access to the data in industrial practices.Active learning(AL)approaches are useful in such a context since they maximize the performance of the trained model while minimiz-ing the number of training samples.Such smart sampling methodologies iteratively sample the points that should be labeled and added to the training set based on their informative-ness and pertinence.To judge the relevance of a data instance,query rules are defined.In this paper,we propose an AL methodology based on a physics-based query rule.Given some industrial objectives from the physical process where the AI model is implied in,the physics-based AL approach iteratively converges to the data instances fulfilling those objectives while sampling training points.Therefore,the trained surrogate model is accu-rate where the potentially interesting data instances from the industrial point of view are,while coarse everywhere else where the data instances are of no interest in the industrial context studied.

外文关键词：

Active learning(AL)Artificial intelligence(AI)OptimizationPhysics based

作者：

Sergio Torregrosa、Victor Champaney、Amine Ammar、Vincent Herbert、Francisco Chinesta

展开 >

作者单位：

PIMM,Arts et Métiers Institute of Technology,151 Boulevard de l'Hopital,75013 Paris,France

STELLANTIS,Route de Gisy,78140 Vélizy-Villacoublay,France

ESI Chair,PIMM,Arts et Métiers Institute of Technology,151 Boulevard de l'Hopital,75013 Paris,France

ESI Chair,LAMPA,Arts et Métiers Institute of Technology,2 Boulevard du Ronceray,49035 Angers,France

展开 >

出版年：

2024

DOI：

10.1007/s42967-023-00329-y

应用数学与计算数学学报

上海大学

应用数学与计算数学学报

影响因子：0.165

ISSN：1006-6330

年,卷(期)：2024.6(3)