The Flexural Strength Prediction of Carbon Fiber/Epoxy Composite Using Artificial Neural Network Approach
Materials · 28.07.2023 · 16 (15) · 5301
DOI: 10.3390/ma16155301 ↗Kurz gefasst
Fachartikel in der Zeitschrift Materials, online erschienen am 28.07.2023. Verfasst von Veena Phunpeng und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical Engineering, Institute of Engineering, Suranaree University of Technology, 111 Maha Witthayalai Rd., Suranaree Sub-District, Mue…. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Suranaree University of Technology, Thailand Science Research and Innovation (TSRI), and National Science, Research, and Innovation Fund (NSRF), Suranaree University of Technology, Thailand Science Research and Innovation (TSRI).
Abstract (Originalsprache)
There is a developing demand for natural resources because of the growing population. Alternative materials have been developed to address these shortages, concentrating on characteristics such as durability and lightness. By researching composite materials, natural materials can be replaced. It is vital to consider the mechanical properties of composite materials when selecting them for a specific application. This study aims to measure the flexural strength of carbon fiber/epoxy composites. However, the cost of forming these composites is relatively high, given the expense of composite materials. Consequently, this study seeks to reduce molding costs by predicting flexural strength. Conducting many tests for each case is costly; therefore, it is necessary to discover an economical method. To accomplish this, the flexural strength of carbon fiber/epoxy composites was investigated using an artificial neural network (ANN) technique to reduce the expense of material testing. The output parameter investigated was flexural strength, while input parameters included ply orientation, manufacturing, width, thickness, and graphite filler percentage. The scope alternative was determined by identifying the values of variables that substantially affect the flexural strength. The prediction of flexural strength was deemed acceptable if the mean squared error (MSE) value was less than 0.001, and the coefficient of determination (R2) was greater than or equal to 0.95. The obtained results demonstrated an MSE of 0.003039 and an R2 value of 0.95274, indicating a low prediction error and high prediction accuracy for all flexural strength data. Thus, the outcomes of this study provide accurate predictions of flexural strength in the composite materials.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Mechanical Engineering, Institute of Engineering, Suranaree University of Technology, 111 Maha Witthayalai Rd., Suranaree Sub-District, Mueang Nakhon Ratchasima District, Nakhon Ratchasima 30000, Thailand.
- Department of Electrical Engineering, Faculty of Engineering, Kasetsart University, 50 Ngamwongwan Rd., Chatuchak, Bangkok 10900, Thailand.
ORCID-Profile: Veena Phunpeng, Thongchart Kerdphol
Förderung
- Suranaree University of Technology
- Thailand Science Research and Innovation (TSRI), and National Science, Research, and Innovation Fund (NSRF)
- Suranaree University of Technology, Thailand Science Research and Innovation (TSRI)
- NRIIS
Zitieren
APA
Phunpeng, V., Saensuriwong, K., Kerdphol, T., & Uangpairoj, P. (2023). The Flexural Strength Prediction of Carbon Fiber/Epoxy Composite Using Artificial Neural Network Approach. Materials, 16(15), 5301. https://doi.org/10.3390/ma16155301
Vancouver
Phunpeng V, Saensuriwong K, Kerdphol T, Uangpairoj P. The Flexural Strength Prediction of Carbon Fiber/Epoxy Composite Using Artificial Neural Network Approach. Materials. 2023;16(15):5301. doi:10.3390/ma16155301
BibTeX
@article{Phunpeng2023,
author = {Phunpeng, Veena and Saensuriwong, Karunamit and Kerdphol, Thongchart and Uangpairoj, Pichitra},
title = {The Flexural Strength Prediction of Carbon Fiber/Epoxy Composite Using Artificial Neural Network Approach},
journal = {Materials},
year = {2023},
volume = {16},
number = {15},
pages = {5301},
doi = {10.3390/ma16155301}
}
EUVIMED