Techno Press
Tp_Editing System.E (TES.E)
Login Search
You logged in as

acc
 
CONTENTS
Volume 18, Number 4, October 2024
 

Abstract
A sophisticated machine learning (ML) strategy and a salty setting where fly ash and stone dust replace cement and sand may reveal eco-friendly lightweight foam concrete's implications that are not widely available or adequately stated in the literature. The study aims to conduct experimental programs to analyze the implications of utilizing various quantities of stone dust and fly ash as a substitute for sand and cement on foam concrete's fresh, hardened, and non-destructive testing (NDT) properties. The study explores foam concrete's compressive, splitting, permeability, pulse velocity, and microstructural properties and its potential as an alternative to conventional concrete in saline environments while integrating machine learning techniques like SVM and ANN for predicting compressive strength. The experimental study utilized three foam concrete batches with varying filler and binder proportions: Batch I with 100% sand and different fly ash percentages, Batch II with stone dust replacing sand and cement replaced by fly ash, and Batch III with 100% stone dust and different fly ash and cement ratios, all consistently using a foaming agent at 0.5% by binder weight. The study observed that replacing approximately 30% of cement with fly ash yielded the highest compressive strength, while substituting over 40% of sand with stone dust also showed promising results, achieving peak compressive strengths of 13-14 MPa. The study findings further revealed that the water absorption and permeability rate were minimal, and the rebound hammer, microstructure, and pulse velocity were ultimate when cement was replaced with roughly 30% fly ash. The experiments' outcomes are utilized to develop advanced machine learning methods for forecasting its strength. The ML technique demonstrates that an inferior regression coefficient (R2) support vector machine (SVM) contrasts dramatically with a larger R2 value for the artificial neural networks (ANN), showing an excellent projection with experimental data.

Key Words
fly ash; foam concrete; machine learning system; saline environments; stone dust; sustainable construction material

Address
(1) Iffat Haq, Shuvo Dip Datta, Md. Habibur Rahman Sobuz, Fahim Shahriyar Aditto, F.M. Tareq Rahman:
Department of Building Engineering and Construction Management, Khulna University of Engineering & Technology, Khulna-9203, Bangladeshl
(2) Md. Shahriar Abdullah:
Department of Civil and Environmental Engineering, Lamar University, TX 77705, USA;
(3) Md Azree Othuman Mydin:
School of Housing, Building and Planning, Universiti Sains Malaysia, 11800, Penang, Malaysia.

Abstract
This work describes a unique technique for forecasting the buckling behavior of functionally graded concrete (FGC) structures, with a focus on their use in sports engineering. Traditional prediction methods, which may rely on basic assumptions, fail to give the necessary accuracy for complicated material compositions. Artificial neural networks (ANNs) provide a versatile and adaptable approach to detecting complex patterns in FGC systems, particularly for sports infrastructure and equipment design. The ANN model displays versatility across different materials and structural designs, including stadium construction, sports equipment, and high-performance athletic surfaces, thanks to comprehensive training and validation on multiple FGC configurations. The ANN model exceeds standard analytical approaches in terms of speed and accuracy, demonstrating its effectiveness in anticipating crucial buckling stresses in dynamic, high-impact situations characteristic of sporting activities. This paper investigates the combination of artificial neural networks, image processing, and risk assessments, highlighting their importance in influencing design decisions. This work advances our understanding of the flexural properties of FGC structures, especially in athletic situations, allowing for the design of safer, more reliable, and performance-enhancing sports facilities. This technology offers engineers with an excellent tool for designing innovative and resilient sports-specific systems.

Key Words
artificial neural networks; buckling analysis; functionally graded concrete structures; optimization; sports structures; stability

Address
(1) Shuo Dong, Wen Pan:
Faculty of Civil Engineering and Mechanics, Kunming University of Science and Technology, Kunming 650500, Yunnan, China;
(2) Shuo Dong, Wen Pan:
Yunnan Seismic Engineering Technology Research Center, Kunming 650500, Yunnan, China;
(3) Jing Zhao:
State Key Laboratory of Energy Resources, Douai, UAE.

Abstract
In this research, a detailed analysis was conducted on the interface shear stresses in damaged reinforced concrete (RC) beams strengthened with composite material plates (P-FGM and E-FGM). Various conditions were considered, including the application of a uniformly distributed load, an arbitrarily positioned point load, and two symmetric point loads. Additionally, the effects of hygrothermal conditions were incorporated. The analysis was based on linear elastic theory. The presence of pores in the reinforcement plate was accounted for, with these pores categorized into different forms to ensure comprehensive consideration of this parameter. Comparisons between the proposed model and existing analytical solutions from the literature not only validate this new method but also demonstrate its accuracy and relevance. These results confirm the ability of the approach to provide reliable predictions and emphasize its potential for solving complex problems related to the modeling of reinforced systems, aligning with recognized theoretical outcomes. A parametric study was conducted to examine the sensitivity of interface stresses to various parameters, including plate homogeneity, porosity, plate and adhesive stiffness, plate thickness, and the damage factor. In the present model, a shear stress of 1.823 is achieved for CFRP in undamaged beams, which is within 1% of the highest value reported in other references but 8% lower than the maximum. For GFRP, the present model shows a 10% improvement over other references, reaching 1.2174. In damaged beams, steel achieves a shear stress of 2.266 in the present model, which is within 8% of the highest value in the references, while P-FGM (Al2O3) provides a balanced alternative at 1.457. This study establishes a solid foundation for future analyses of damaged reinforced concrete beams reinforced with composite plates, whether advanced or conventional, paving the way for significant advances in rehabilitation methodologies.

Key Words
composite plate; damaged RC beam; hygrothermal effects; interfacial stresses; porosity; reinforcement

Address
(1) Mokhtar Nebab, Zahira Sadoun, Riadh Bennai, Hassen Ait Atmane, Rezki Amara:
Laboratory of Structures, Geotechnics and Risks, Department of Civil Engineering, Hassiba Benbouali University of Chlef, Algeria;
(2) Mokhtar Nebab:
Department of Civil Engineering, Faculty of Technology, University of M'Hamed Bougara Boumerdes, Algeria;
(3) Zahira Sadoun, Riadh Bennai, Hassen Ait Atmane, Rezki Amara:
Department of Civil Engineering, Faculty of Civil Engineering and Architecture, University Hassiba Benbouali of Chlef, Algeria.

Abstract
The construction and materials sector is actively striving to mitigate the environmental consequences of cement production in concrete by integrating alternative and supplemental cementitious materials while reducing carbon emissions. Because of their pozzolanic reactions, natural pozzolans (NPs) have become prominent in this area. The aim of this research is to accurately predict the compressive strength of normal-weight concrete that contains NP by investigating the impact of several elements, including cement, NP content, water and aggregate quantity, and superplasticizer content. For doing this, the research examined data gathered from various sources, which led to the creation of a dataset consisting of 496 mix ratios with strengths. A comprehensive analysis was conducted using numerous advanced machine learning (ML) algorithms, including extreme gradient boosting (XGB), adaptive boosting (ADB), and bagging regressor (BAG), as well as hybrid ML techniques such as XGB-ADB and XGB-BAG. The purpose was to extensively examine the concrete mix materials and evaluate their influence on strength. The collected dataset was divided into two groups: training and testing. Statistical tests were conducted to ascertain the correlations between the input parameters and strength. Furthermore, the algorithms' performance was assessed using four separate statistical assessment criteria. The hybrid XGB-BAG model exhibited superior accuracy (test R2 = 0.901) in comparison to other models. All other models also demonstrate adequate performance (R2 greater than 0.80) for the use of predicting the compressive strength of NP-concrete. In addition, the SHapley Additive Explanations (SHAP) study indicated that cement, NPs, and superplasticizers had a beneficial impact on strength. In summary, the research indicates that the hybrid XGBADB model, when combined with the indicated input parameters, can effectively forecast the compressive strength of NPconcrete.

Key Words
compressive strength; eco-friendly concrete; hybrid machine learning; natural pozzolans; parametric analysis

Address
Department of Civil Engineering, Faculty of Engineering, University of Tabuk, P.O. Box 741, Tabuk 71491, Saudi Arabia.


Abstract
Vertical members such as columns and shear walls undergo time-dependent deformations in multi-story buildings due to creep and shrinkage. This causes columns and shear walls to shorten unevenly, especially if their cross-sectional areas, reinforcement ratios, or loading conditions differ. Differential shortening throughout the structure may result from this over time. This can result in unexpected seismic drift, affecting the building's ability to withstand lateral displacements caused by earthquakes. This study examines the impact of vertical member shortening, caused by creep and shrinkage during construction, on the seismic performance of RC buildings. It also evaluates the suitability of the Static Equivalent Lateral Force (SELF) methods, as outlined in the IBC-2000 (US) and Euro Code 8 (Europe), for RC structures experiencing such shortening under seismic conditions. Two real earthquakes, 1940 EL-Centro and Parkfield, were analyzed across two categories of RC buildings: moment-resisting frames and those with shear walls, designed per ACI 318-19 standards and simulated via Midas Gen's finite element method. Each category included buildings of six, nine, and twelve stories. The investigation involved two scenarios: SCAT, which accounts for creep and shrinkage, and SCAN, which does not. The results indicate that in the case of momentresisting frame buildings, the maximum column shortening resulting from SCAT exceeds that obtained from SCAN by 68-128%, while in the case of shear wall buildings, the maximum vertical member shortening increases by 40-82%. Under the 1940 EL-Centro earthquake, SCAT's maximum story drift was higher than SCAN's by 9-15% in multi-story building frames and 3-8% in shear walls. Also, the limits of the fundamental period of vibration estimated by IBC-2000 and EC-8 are conservative for both cases of SCAN and SCAT. Additionally, the study revealed that IBC-2000's base shear estimations could be nonconservative for the 1940 EL-Centro earthquake, while EC-8's predictions were generally conservative for both SCAT and SCAN scenarios.

Key Words
column shortening; construction stages; creep and shrinkage effect; earthquakes; non-linear analysis

Address
(1) Mahmoud A. El-Mandouh:
Civil Engineering Department, Faculty of Engineering, Beni-Suef University, Beni-Suef 62511, Egypt;
(2) Ahmed S. Abd El-Maula:
Civil Engineering Department, Shoubra Faculty of Engineering, Benha University, Benha 13511, Egypt;
(3) Ahmed S. Abd El-Maula, Mohamed A. Farouk:
Civil Engeering Department, Faculty of Engineering, Delta University for Science and Technology, Gamasa 35712, Egypt;
(4) Talal O. Alshammari, Ahmed M. Yosri:
Department of Civil Engineering, College of Engineering, Jouf University, Sakaka 72341, King Saudi Arabia;
(5) Mohamed A. Farouk:
Department of Civil Engineering, Faculty of Engineering, Sphinx University, New Assuit, Egypt.

Techno-Press: Publishers of international journals and conference proceedings.       Copyright © 2025 Techno-Press ALL RIGHTS RESERVED.
P.O. Box 33, Yuseong, Daejeon 34186 Korea, Email: admin@techno-press.com