Development of an artificial neural network for predicting energy absorption capability of thermoplastic commingled composites

Author(s)

Di Benedetto, R. M. ^{[1, 2]} ; Botelho, E. C. ^[1] ; Janotti, A. ^[2] ; Ancelotti Junior, A. C. ^[3] ; Gomes, G. F. ^[3]

Affiliation

^[1] Sao Paulo State Univ UNESP, Sch Engn, Mat & Technol Dept, Av Ariberto Pereira da Cunha 333, BR-333 Guaratingueta, SP - Brazil

^[2] Univ Delaware UDEL, Dept Mat Sci & Engn, 212 DuPont Hall, Newark, DE 19716 - USA

^[3] Fed Univ Itajuba UNIFEI, NTC Composite Technol Ctr, Mech Engn Inst, Av BPS, BR-1303 Itajuba, MG - Brazil

• Document type: Journal article
• Source: COMPOSITE STRUCTURES; v. 257, FEB 1 2021.
• Web of Science Citations: 4

Abstract

Soft computing techniques including artificial neural networks (ANN) and machine learning reflect new possibilities to behavior prediction models of commingled composites. This study focuses on developing an artificial neural network capable of predicting the impact energy absorption capability of thermoplastic commingled composites, in the context of crashworthiness, based on a compilation of experimental results, multiple regression analytical model and factorial design method. Furthermore, the scientific approach of this project comprises the (i) development of intelligent models for designing and manufacturing of new composite components, (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 to describe mechanical and structural properties of thermoplastic commingled composite materials and the development of an artificial neural network able to predict the energy absorption capability of these materials, considering some properties of polymer matrix, thermal degradation kinetics model and consolidation parameters. The obtained results from impact testing indicate that the proposed approach can predict the impact energy with satisfactory accuracy. The use of an analytical model database as input for the ANN is an innovative methodology to increase the reliability and accuracy of the ANNs. (AU)

• FAPESP's process: 18/24964-2 - Development of an artificial neural network for forecasting energy absorption capability of thermoplastic commingled composites: processing, characterization, and crashworthiness
• Grantee: Ricardo Mello di Benedetto
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• FAPESP's process: 17/16970-0 - Obtaining and Characterization of Nanostructured Thermoplastic Composites for Aeronautical Application
• Grantee: Edson Cocchieri Botelho
• Support Opportunities: Regular Research Grants
• FAPESP's process: 19/22173-0 - Development of an artificial neural network for predicting energy absorption capability of thermoplastic commingled composites: processing, characterization, and crashworthiness
• Grantee: Ricardo Mello di Benedetto
• Support Opportunities: Scholarships abroad - Research Internship - Post-doctor