人工智能与塑性：综合综述

AI Meets Plasticity: A Comprehensive Survey Hadi Bakhshan, Sima Farshbaf, Junior Ramirez Machado, Fernando Rastellini Canela, Josep Maria Carbonell AI Meets Plasticity: A Comprehensive Survey Hadi Bakhshana,1, Sima Farshbafa,b,2, Junior Ramirez Machadoa,b, Fernando Rastellini Canelaa, Josep MariaCarbonella,c aCentre Internacional de Mètodes Numèrics a l’Enginyeria (CIMNE), Campus Norte UPC, 08034 Barcelona, SpainbUniversitat Politècnica de Catalunya (UPC), Campus Norte UPC, 08034 Barcelona, SpaincMechatronics and Modelling Applied on Technology of Materials (MECAMAT) group. Universitat de Vic-Universitat Central de Catalunya(UVic-UCC), C. de la Laura 13, 08500 Vic, Spain Abstract Artificial intelligence (AI) is rapidly emerging as a new paradigm of scientific discovery, namely data-driven sci-ence, across nearly all scientific disciplines. In materials science and engineering, AI has already begun to exert atransformative influence, making it both timely and necessary to examine its interaction with materials plasticity. Inthis study, we present a holistic survey of the convergence between AI and plasticity, highlighting state-of-the-art AImethodologies employed to discover, construct surrogate models for, and emulate the plastic behavior of materials.From a materials science perspective, we examine cause-and-effect relationships governing plastic deformation, in-cluding microstructural characterization and macroscopic responses described through plasticity constitutive models.From the perspective of AI methodology, we review a broad spectrum of applied approaches, ranging from frequentisttechniques such as classical machine learning (ML), deep learning (DL), and physics-informed models to probabilisticframeworks that incorporate uncertainty quantification and generative AI methods. These data-driven approaches arediscussed in the context of materials characterization and plasticity-related applications. The primary objective of thissurvey is to develop a comprehensive and well-organized taxonomy grounded in AI methodologies, with particularemphasis on distinguishing critical aspects of these techniques, including model architectures, data requirements, andpredictive performance within the specific domain of materials plasticity. By doing so, this work aims to provide aclear road map for researchers and practitioners in the materials community, while offering deeper physical insightand intuition into the role of AI in advancing materials plasticity and characterization, an area of growing importancein the emerging AI-driven era. Keywords:Artificial intelligence (AI), Machine learning (ML), Deep learning (DL), Generative AI, Material plasticity, Microstructure characterization Contents Nomenclature5 1Introduction7 1.1Taxonomy and terminology . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .71.2Earlier reviews. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .81.3Objective and organization of the paper. . . . . . . . . . . . . . . . . . . . . . . . . . . .8 2Datasets: Types, sources and sampling strategies9 3Classical machine learning (ML) methods113.1Polynomials and nonlinear regressions . . . . . . . . . . . . . . . . . . . . . . . . . . . . .11 3.2Support vector machines (SVMs) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .123.2.1SVM-based yield function (YF) surrogate . . . . . . . . . . . . . . . . . . . . . . .133.2.2SVM-based constitutive model (CM) surrogate. . . . . . . . . . . . . . . . . . . .143.3Decision tree-based methods. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .153.3.1Bootstrap aggregating (bagging) . . . . . . . . . . . . . . . . . . . . . . . . . . . .163.3.2Boosting. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .173.4Symbolic regression (SR) for model discovery . . . . . . . . . . . . . . . . . . . . . . . . .183.5Summary. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .20 4Deep learning (DL) methods20 4.1Artificial neural networks (ANNs). . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .214.1.1ANN-based YF surrogate. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .22 4.1.2ANN-based CM parameter identification. . . . . . . . . . . . . . . . . . . . . . .234.1.3ANNs for plasticity . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .234.1.4ANNs for viscoplasticity, thermoviscoplasticity and hypoplasticity . . . . . . . . . .244.1.5ANNs for crystal plasticity (CP) . . . . . . . . . . . . . . . . . . . . . . . . . . . .25 4.2Convolutional neural networks (CNNs). . . . . . . . . . . . . . . . . . . . . . . . . . . .264.2.1CNNs for microstructure characterization. . . . . . . . . . . . . . . . . . . . . . .29 4.2.2CNNs for mechanical property prediction . . . . . . . . . . . . . . . . . . . . . . .304.2.3CNNs for mechanical response prediction . . . . . . . . . . . . . . . . . . . .