Empowering Materials Processing and Performance from Data and AI

• Autore: Chinesta Francisco
• Pubblicazione: Basel, Switzerland, : MDPI - Multidisciplinary Digital Publishing Institute, 2021
• Descrizione fisica: 1 electronic resource (156 p.)
• Soggetto topico: Technology: general issues
• Soggetto non controllato: plasticity; machine learning; constitutive modeling; manifold learning; topological data analysis; GENERIC; soft living tissues; hyperelasticity; computational modeling; data-driven mechanics; TDA; Code2Vect; nonlinear regression; effective properties; microstructures; model calibration; sensitivity analysis; elasto-visco-plasticity; Gaussian process; high-throughput experimentation; additive manufacturing; Ti-Mn alloys; spherical indentation; statistical analysis; Gaussian process regression; nanoporous metals; open-pore foams; FE-beam model; data mining; mechanical properties; hardness; principal component analysis; structure-property relationship; microcompression; nanoindentation; analytical model; finite element model; artificial neural networks; model correction; feature engineering; physics based; data driven; laser shock peening; residual stresses; data-driven; multiscale; nonlinear; stochastics; neural networks
• Persona (resp. second.): CuetoElías; KlusemannBenjamin; ChinestaFrancisco
• Sommario/riassunto: Third millennium engineering address new challenges in materials sciences and engineering. In particular, the advances in materials engineering combined with the advances in data acquisition, processing and mining as well as artificial intelligence allow for new ways of thinking in designing new materials and products. Additionally, this gives rise to new paradigms in bridging raw material data and processing to the induced properties and performance. This present topical issue is a compilation of contributions on novel ideas and concepts, addressing several key challenges using data and artificial intelligence, such as:- proposing new techniques for data generation and data mining;- proposing new techniques for visualizing, classifying, modeling, extracting knowledge, explaining and certifying data and data-driven models;- processing data to create data-driven models from scratch when other models are absent, too complex or too poor for making valuable predictions;- processing data to enhance existing physic-based models to improve the quality of the prediction capabilities and, at the same time, to enable data to be smarter; and- processing data to create data-driven enrichment of existing models when physics-based models exhibit limits within a hybrid paradigm.
• Titolo autorizzato: Empowering Materials Processing and Performance from Data and AI
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910557717703321
• Lo trovi qui: Univ. Federico II