A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Mathematical modeling techniques to predict the compressive strength of pervious concrete modified with waste glass powders
As a result of the ongoing climate change and the subsequent rise in flood risks across numerous countries, there has been a notable surge in the adoption of pervious concrete as a viable solution to manage water accumulation underground. Pervious concrete is particularly beneficial in low-loaded areas, where its implementation can effectively mitigate flooding concerns. Nevertheless, researchers are faced with a significant challenge in this context: devising a method to create eco-friendly pervious concrete by incorporating waste materials into its composition. This endeavor aims to not only enhance the overall sustainability of the construction industry but also address environmental concerns associated with waste disposal. This article focuses on suggesting various mathematical models, such as linear regression (LR), non-linear regression (NLR), and artificial neural network (ANN) models for predicting the compressive strength of pervious concrete when waste glass powder is used as a partial replacement for cement. According to the findings, the ANN model outperforms both LR and NLR models in terms of accuracy and efficiency. The scatter index (SI) value of the ANN model is lower than 0.1, and its coefficient of determination (R2) is 22% higher than that of LR and 17% higher than that of NLR.
Mathematical modeling techniques to predict the compressive strength of pervious concrete modified with waste glass powders
As a result of the ongoing climate change and the subsequent rise in flood risks across numerous countries, there has been a notable surge in the adoption of pervious concrete as a viable solution to manage water accumulation underground. Pervious concrete is particularly beneficial in low-loaded areas, where its implementation can effectively mitigate flooding concerns. Nevertheless, researchers are faced with a significant challenge in this context: devising a method to create eco-friendly pervious concrete by incorporating waste materials into its composition. This endeavor aims to not only enhance the overall sustainability of the construction industry but also address environmental concerns associated with waste disposal. This article focuses on suggesting various mathematical models, such as linear regression (LR), non-linear regression (NLR), and artificial neural network (ANN) models for predicting the compressive strength of pervious concrete when waste glass powder is used as a partial replacement for cement. According to the findings, the ANN model outperforms both LR and NLR models in terms of accuracy and efficiency. The scatter index (SI) value of the ANN model is lower than 0.1, and its coefficient of determination (R2) is 22% higher than that of LR and 17% higher than that of NLR.
Mathematical modeling techniques to predict the compressive strength of pervious concrete modified with waste glass powders
Asian J Civ Eng
Ahmad, Soran Abdrahman (author) / Rafiq, Serwan Khwrshid (author) / Hilmi, Hozan Dlshad M. (author) / Ahmed, Hemn Unis (author)
Asian Journal of Civil Engineering ; 25 ; 773-785
2024-01-01
13 pages
Article (Journal)
Electronic Resource
English
Predictive modeling of compressive strength in glass powder blended pervious concrete
| Springer Verlag | 2025
Predictive modeling of compressive strength in glass powder blended pervious concrete
| Springer Verlag | 2025
High-strength pervious concrete admixture and pervious concrete
| European Patent Office | 2021