A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Compressive strength prediction of fly ash and blast furnace slag-based geopolymer concrete using convolutional neural network
The production of cement concrete has significant environmental impacts, including ecological imbalances, the greenhouse effect, and the depletion of natural resources. To address these issues, this paper proposes a systematic approach for selecting mix proportions in geopolymer concrete, which uses fly ash and GGBS as alternatives to traditional cement. Geopolymer concrete (GPC) offers a more sustainable option as it reduces the demand for cement and utilizes industrial by-products. The study evaluates tree-based models like random forest (RF) and support vector machine (SVM), along with a network-based model called convolutional neural network (CNN), to predict and optimize the mix proportions of geopolymer concrete. These machine-learning (ML) models were utilized to improve the accuracy of the concrete mix design process and optimize the use of fly ash and GGBS. Experimental data were gathered and employed for the study, involving various GPC mixtures to assess mechanical properties. The paper conducts a comparative study of the models’ performance and concludes that the CNN model outperforms RF and SVM in predicting the optimal mix proportions for GPC.
Compressive strength prediction of fly ash and blast furnace slag-based geopolymer concrete using convolutional neural network
The production of cement concrete has significant environmental impacts, including ecological imbalances, the greenhouse effect, and the depletion of natural resources. To address these issues, this paper proposes a systematic approach for selecting mix proportions in geopolymer concrete, which uses fly ash and GGBS as alternatives to traditional cement. Geopolymer concrete (GPC) offers a more sustainable option as it reduces the demand for cement and utilizes industrial by-products. The study evaluates tree-based models like random forest (RF) and support vector machine (SVM), along with a network-based model called convolutional neural network (CNN), to predict and optimize the mix proportions of geopolymer concrete. These machine-learning (ML) models were utilized to improve the accuracy of the concrete mix design process and optimize the use of fly ash and GGBS. Experimental data were gathered and employed for the study, involving various GPC mixtures to assess mechanical properties. The paper conducts a comparative study of the models’ performance and concludes that the CNN model outperforms RF and SVM in predicting the optimal mix proportions for GPC.
Compressive strength prediction of fly ash and blast furnace slag-based geopolymer concrete using convolutional neural network
Asian J Civ Eng
Kumar, Pramod (author) / Pratap, Bheem (author) / Sharma, Sanjay (author) / Kumar, Indra (author)
Asian Journal of Civil Engineering ; 25 ; 1561-1569
2024-02-01
9 pages
Article (Journal)
Electronic Resource
English