Predictive models for mechanical properties of expanded polystyrene (EPS) geofoam using regression analysis and artificial neural networks

No Thumbnail Available

Date

2022

Journal Title

Journal ISSN

Volume Title

Publisher

Springer London Ltd

Open Access Color

OpenAIRE Downloads

OpenAIRE Views

Research Projects

Organizational Units

Organizational Unit
Manufacturing Engineering
(2003)
Opened in 2003 with the aim to graduate experts in the field of machine-production, our Department is among the firsts in our country to offer education in English. The Manufacturing Engineering program focuses on the manufacturing technologies that shape materials from raw materials to final products by means of analytical, experimental and numerical modeling methods. First Manufacturing Engineering Program to be engineered by Müdek, our department aims to graduate creative and innovative Manufacturing Engineers that are knowledgeable in the current technology, and are able to use production resources in an effective and sustainable way that never disregards environmental facts. As the first Department to implement the Cooperative Education Program at Atılım University in coordination with institutions from the industry, the Manufacturing Engineering offers a practice-oriented approach in education with its laboratory infrastructure and research opportunities. The curriculum at our department is supported by current engineering software, and catered to creating engineers equipped to meet the needs of the production industry.

Journal Issue

Abstract

Initial elastic modulus and compressive strength are the two most important engineering properties for modeling and design of EPS geofoams, which are extensively used in civil engineering applications such as light-fill material embankments, retaining structures, and slope stabilization. Estimating these properties based on geometric and physical parameters is of great importance. In this study, the compressive strength and modulus of elasticity values are obtained by performing 356 unconfined compression tests on EPS geofoam samples with different shapes (cubic or disc), dimensions, loading rates, and density values. Using these test results, the mechanical properties of the specimens are predicted by linear regression and artificial neural network (ANN) methods. Both methods predicted the initial modulus of elasticity (E-i), 1% strain (sigma(1)), 5% strain (sigma(5)), and 10% strain (sigma(10)) strength values on a satisfactory level with a coefficient of correlation (R-2) values of greater than 0.901. The only exception was in prediction of sigma(1) and E-i in disc-shaped samples by linear regression method where the R-2 value was around 0.558. The results obtained from linear regression and ANN approaches show that ANN slightly outperform linear regression prediction for E-i and sigma(1) properties. The outcomes of the two methods are also compared with results of relevant studies, and it is observed that the calculated values are consistent with the results from the literature.

Description

Sadigh, Bahram Lotfi/0000-0002-3027-3734; Akis, Ebru/0000-0001-8417-2405

Keywords

Expanded polystyrene (EPS) geofoam, Geosynthetics, Modulus of elasticity, Compressive strength, Regression analysis, Artificial neural network (ANN)

Turkish CoHE Thesis Center URL

Fields of Science

Citation

6

WoS Q

Q2

Scopus Q

Source

Volume

34

Issue

13

Start Page

10845

End Page

10884

Collections