Innovative optimization of seashell ash-based lightweight foamed concrete: Enhancing physicomechanical properties through ANN-GA hybrid approach

Abstract This study presents a novel approach to sustainable construction by utilizing three types of seashell ashes, namely, oyster shell ash (OSA), scallop shell ash (SSA), and mussel shell ash (MSA), as partial replacements for cement in lightweight foamed concrete (LFC). This novel application of aquaculture waste as an additive enhances the creation of more sustainable and resilient construction materials for urban settings. The physicomechanical properties of LFC, such as compressive strength (CS), flexural strength (FS), split tensile strength (STS), water absorption (WA), and porosity ( P ), were assessed utilizing response surface methodology (RSM) and artificial neural network (ANN) with K -fold cross-validation. The research examines the influence of additive type (OSA, SSA, MSA), curing duration (7–28 days), and additive concentration (0–30%) on the characteristics of LFC. Analysis of variance indicated that curing time exerted the most substantial effect on CS, FS, and STS, but additive content had a more pronounced impact on WA and P . The findings indicated favorable enhancements in CS, FS, and STS with curing durations of 28 days and additive concentrations between 4 and 20%. Replacing cement with OSA, SSA, and MSA showed favorable benefits on LFC characteristics. The predictive effectiveness of the DNN-IGWO, ANN, RSM, and Support vector machine models was evaluated using several error metrics, including mean absolute deviation, mean absolute percentage error, root mean square error, and coefficient of determination ( R 2 ). The results showed that the hybrid DNN-IGWO model outperformed all other approaches, providing significantly higher accuracy across all attributes studied. Moreover, the incorporation of evolutionary algorithms utilizing DNN-IGWO models facilitated the discovery of optimal solutions for the multi-objective optimization of LFC properties. The optimization exposed intrinsic trade-offs between targets, such as CS vs WA and CS vs P , underscoring the necessity for meticulous equilibrium in the optimization process. This study constitutes a notable advancement in sustainable development goals in construction materials by improving concrete characteristics through the incorporation of seashell ash and sophisticated optimization methods.

Authors

Institutions

Publication Details

Journal
REVIEWS ON ADVANCED MATERIALS SCIENCE
Published
2025-01-01
DOI
https://doi.org/10.1515/rams-2025-0131
Citations
1
Primary Topic
BIM and Construction Integration
Type
article
Field-Weighted Citation Impact
1.01
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Innovative optimization of seashell ash-based lightweight foamed concrete: Enhancing physicomechanical properties through ANN-GA hybrid approach

Mohammed M. Bait‐Suwailam, Yazan Issa Abu Aisheh, Maaz Osman Bashir, Aissa Laouissi et al.
1 citations
REVIEWS ON ADVANCED MATERIALS SCIENCE
BIM and Construction Integration
1.01
article

Innovative optimization of seashell ash-based lightweight foamed concrete: Enhancing physicomechanical properties through ANN-GA hybrid approach

Mohammed M. Bait‐Suwailam, Yazan Issa Abu Aisheh, Maaz Osman Bashir, Aissa Laouissi, Yazid Chetbani, Bassam A. Tayeh
article en
1 citations

Abstract

Abstract This study presents a novel approach to sustainable construction by utilizing three types of seashell ashes, namely, oyster shell ash (OSA), scallop shell ash (SSA), and mussel shell ash (MSA), as partial replacements for cement in lightweight foamed concrete (LFC). This novel application of aquaculture waste as an additive enhances the creation of more sustainable and resilient construction materials for urban settings. The physicomechanical properties of LFC, such as compressive strength (CS), flexural strength (FS), split tensile strength (STS), water absorption (WA), and porosity ( P ), were assessed utilizing response surface methodology (RSM) and artificial neural network (ANN) with K -fold cross-validation. The research examines the influence of additive type (OSA, SSA, MSA), curing duration (7–28 days), and additive concentration (0–30%) on the characteristics of LFC. Analysis of variance indicated that curing time exerted the most substantial effect on CS, FS, and STS, but additive content had a more pronounced impact on WA and P . The findings indicated favorable enhancements in CS, FS, and STS with curing durations of 28 days and additive concentrations between 4 and 20%. Replacing cement with OSA, SSA, and MSA showed favorable benefits on LFC characteristics. The predictive effectiveness of the DNN-IGWO, ANN, RSM, and Support vector machine models was evaluated using several error metrics, including mean absolute deviation, mean absolute percentage error, root mean square error, and coefficient of determination ( R 2 ). The results showed that the hybrid DNN-IGWO model outperformed all other approaches, providing significantly higher accuracy across all attributes studied. Moreover, the incorporation of evolutionary algorithms utilizing DNN-IGWO models facilitated the discovery of optimal solutions for the multi-objective optimization of LFC properties. The optimization exposed intrinsic trade-offs between targets, such as CS vs WA and CS vs P , underscoring the necessity for meticulous equilibrium in the optimization process. This study constitutes a notable advancement in sustainable development goals in construction materials by improving concrete characteristics through the incorporation of seashell ash and sophisticated optimization methods.

REVIEWS ON ADVANCED MATERIALS SCIENCEVol. 64(1)
Al-Ahliyya Amman University (JO), Prince Sattam Bin Abdulaziz University (SA), University of Waterloo (CA), Islamic University of Gaza (PS), Omdurman Islamic University (SD), Centre de Recherche sur l'Information Scientifique et Technique (DZ), University Mohamed El Bachir El Ibrahimi of Bordj Bou Arreridj (DZ), Amar Telidji University of Laghouat (DZ)
Openalex Percentile: Top 20%
BIM and Construction Integration
1.01
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.