Development of an artificial neural network for predicting energy absorption capability of thermoplastic commingled composites: processing, characterization, and crashworthiness

• Grant number: 19/22173-0
• Support Opportunities: Scholarships abroad - Research Internship - Post-doctor
• Start date: October 28, 2020
• End date: October 10, 2021
• Field of knowledge: Engineering - Materials and Metallurgical Engineering - Nonmetallic Materials
• Principal Investigator: Edson Cocchieri Botelho
• Grantee: Ricardo Mello di Benedetto
• Supervisor: Anderson Janotti
• Host Institution: Faculdade de Engenharia (FEG). Universidade Estadual Paulista (UNESP). Campus de Guaratinguetá. Guaratinguetá , SP, Brazil
• Institution abroad: University of Delaware (UD), United States
• Associated to the scholarship: 18/24964-2 - Development of an artificial neural network for forecasting energy absorption capability of thermoplastic commingled composites: processing, characterization, and crashworthiness, BP.PD

Abstract

The development and use of intelligent computational system methodologies in area of structural composite materials is an innovative and promising research topic in both academic and industry sectors. Soft computing techniques, including artificial neural networks (ANN) and machine learning, can be used in behavior prediction models to engineer new materials and aid materials process decision making. Such prediction models will be used in the design and manufacturing phases of new materials and components. The proposed project focuses on developing an artificial neural network capable of predicting the impact energy absorption capability of commingled thermoplastic composites, in the context of crashworthiness, based on a compilation of experimental results obtained during the postdoctoral period and from literature. It will also incorporate atomistic scale simulations that link composition and structure to materials properties. International support in this project comprises (i) the development of intelligent models for design and manufacture of a new component, (ii) application of computational methods to predict material performance and behavior, and (iii) optimization of manufacturing processes. The innovativeness of this proposal is to initiate the use of computational methods that describe mechanical and structural properties of materials of interest based on fundamental interatomic interactions, extracted from the density functional theory (DFT) and empirical interatomic potential calculations, an area of expertise of the overseas supervisor. The main goal is to develop of a fundamental understanding of the phenomena that occur at the atomistic level and to translate them into mechanical and thermomechanical properties of structural composite materials. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

DI BENEDETTO, R. M.; BOTELHO, E. C.; JANOTTI, A.; ANCELOTTI JUNIOR, A. C.; GOMES, G. F.. Development of an artificial neural network for predicting energy absorption capability of thermoplastic commingled composites. COMPOSITE STRUCTURES, v. 257, FEB 1 2021. (18/24964-2, 17/16970-0, 19/22173-0)

BENEDETTO, RICARDO MELLO DI; JANOTTI, ANDERSON; GOMES, GUILHERME FERREIRA; JUNIOR, ANTONIO CARLOS ANCELOTTI; BOTELHO, EDSON COCCHIERI. Development of hybrid steel-commingled composites CF/PEEK/BwM by filament winding and thermoforming. COMPOSITES SCIENCE AND TECHNOLOGY, v. 218, FEB 8 2022. (17/16970-0, 18/24964-2, 19/22173-0)

DI BENEDETTO, RICARDO MELLO; GOMES, GUILHERME FERREIRA; JANOTTI, ANDERSON; ANCELOTTI JUNIOR, ANTONIO CARLOS; BOTELHO, EDSON COCCHIERI. Statistical approach to optimize crashworthiness of thermoplastic commingled composites. MATERIALS TODAY COMMUNICATIONS, v. 31, p. 10-pg., 2022-05-12. (18/24964-2, 19/22173-0, 17/16970-0)