Neural network strength prediction of high-performance concrete with supplementary cementitious materials for sustainable construction

Abstract The Philippine construction sector is anticipated to experience significant development, particularly in infrastructure projects. With the extensive use of concrete in construction, researchers have explored optimizing its properties, leading to the development of high-performance concrete (HPC). However, this increase in demand for cement may lead to potential negative environmental impacts. As a solution, the use of supplementary cementitious materials (SCMs) as partial replacements for cement was investigated in this study. SCMs are materials with high pozzolanic properties, similar to cement, enabling them to bind and fill voids effectively due to their extremely fine particle sizes. This characteristic contributes to the improved strength and durability of concrete. The Modified Andreasen and Andersen Particle Packing Model (MAA PPM) was employed to create HPC, demonstrating that optimizing the mixture curve enhanced material packing density. Despite this advancement, accurately predicting the compressive strength of HPC remains a challenge, as it requires trial batching and extensive experimentation. To address this, an Artificial Neural Network (ANN) was used to predict HPC’s compressive strength based on input material quantities, including cement, aggregates, silica fume, and fly ash. The findings suggest that the ANN model predicts concrete strength with minimal error by capturing complex data linkages. Incorporating the MAA PPM in concrete mixtures with fly ash (FA) and silica fume (SF) as partial replacements for cement enhanced the mechanical performance and properties of the concrete, consistently demonstrating the potential to achieve a high-performance concrete mix. These findings highlight the potential of SCMs in promoting sustainable construction practices. By reducing the reliance on cement and utilizing industrial by-products, the environmental impact of concrete production can be significantly mitigated. Therefore, adopting SCMs not only enhances the performance of HPC but also contributes to the sustainability and resilience of the construction sector.

Authors

Institutions

Publication Details

Journal
IOP Conference Series Earth and Environmental Science
Published
2025-05-01
DOI
https://doi.org/10.1088/1755-1315/1500/1/012037
Primary Topic
Concrete and Cement Materials Research
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Neural network strength prediction of high-performance concrete with supplementary cementitious materials for sustainable construction

Apolonio D. Hilario, Tono Fernández Usón, Cristina P. Santos, DG Cuevas et al.
4 links
IOP Conference Series Earth and Environmental Science
Concrete and Cement Materials Research
article

Neural network strength prediction of high-performance concrete with supplementary cementitious materials for sustainable construction

Apolonio D. Hilario, Tono Fernández Usón, Cristina P. Santos, DG Cuevas, L Samudio, K Bero, T Cabangangan
article en

Abstract

Abstract The Philippine construction sector is anticipated to experience significant development, particularly in infrastructure projects. With the extensive use of concrete in construction, researchers have explored optimizing its properties, leading to the development of high-performance concrete (HPC). However, this increase in demand for cement may lead to potential negative environmental impacts. As a solution, the use of supplementary cementitious materials (SCMs) as partial replacements for cement was investigated in this study. SCMs are materials with high pozzolanic properties, similar to cement, enabling them to bind and fill voids effectively due to their extremely fine particle sizes. This characteristic contributes to the improved strength and durability of concrete. The Modified Andreasen and Andersen Particle Packing Model (MAA PPM) was employed to create HPC, demonstrating that optimizing the mixture curve enhanced material packing density. Despite this advancement, accurately predicting the compressive strength of HPC remains a challenge, as it requires trial batching and extensive experimentation. To address this, an Artificial Neural Network (ANN) was used to predict HPC’s compressive strength based on input material quantities, including cement, aggregates, silica fume, and fly ash. The findings suggest that the ANN model predicts concrete strength with minimal error by capturing complex data linkages. Incorporating the MAA PPM in concrete mixtures with fly ash (FA) and silica fume (SF) as partial replacements for cement enhanced the mechanical performance and properties of the concrete, consistently demonstrating the potential to achieve a high-performance concrete mix. These findings highlight the potential of SCMs in promoting sustainable construction practices. By reducing the reliance on cement and utilizing industrial by-products, the environmental impact of concrete production can be significantly mitigated. Therefore, adopting SCMs not only enhances the performance of HPC but also contributes to the sustainability and resilience of the construction sector.

IOP Conference Series Earth and Environmental ScienceVol. 1500(1)
Technological Institute of the Philippines (PH)
Openalex Percentile: Top 68%
Concrete and Cement Materials Research
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.