Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Compressive Strength Prediction of Aluminosilicate Precursors Based Geopolymers Through Artificial Neural Network (ANN)
The need for the present decade is an environmentally friendly approach to the utilization of building materials. Geopolymers which are produced from 100% aluminosilicate-based waste materials have the potential to pave the path for sustainable development and construction practices. But many factors affect the compressive strength of geopolymers that needs to be evaluated before its utilization in any field practices. Hence the purpose of this article is to formulate a model by employing Artificial Neural Network (ANN) for prediction of compressive strength. Seven input parameters were taken into consideration which influences the compressive strength of geopolymers, to develop four different ANN models. A total of 396 sets of data were analyzed in training, validation, and testing phases to estimate the geopolymeric potential of different aluminosilicate-based precursors. The best performing model with an R2 value of 0.9994 is Model—4 which contains two hidden layers with 14 artificial neurons. Finally, ANN showed strong potential in predicting the compressive strength of geopolymers within the considered range.
Compressive Strength Prediction of Aluminosilicate Precursors Based Geopolymers Through Artificial Neural Network (ANN)
The need for the present decade is an environmentally friendly approach to the utilization of building materials. Geopolymers which are produced from 100% aluminosilicate-based waste materials have the potential to pave the path for sustainable development and construction practices. But many factors affect the compressive strength of geopolymers that needs to be evaluated before its utilization in any field practices. Hence the purpose of this article is to formulate a model by employing Artificial Neural Network (ANN) for prediction of compressive strength. Seven input parameters were taken into consideration which influences the compressive strength of geopolymers, to develop four different ANN models. A total of 396 sets of data were analyzed in training, validation, and testing phases to estimate the geopolymeric potential of different aluminosilicate-based precursors. The best performing model with an R2 value of 0.9994 is Model—4 which contains two hidden layers with 14 artificial neurons. Finally, ANN showed strong potential in predicting the compressive strength of geopolymers within the considered range.
Compressive Strength Prediction of Aluminosilicate Precursors Based Geopolymers Through Artificial Neural Network (ANN)
Lecture Notes in Civil Engineering
Das, B. B. (Herausgeber:in) / Gomez, Christy P. (Herausgeber:in) / Mohapatra, Benu. G. (Herausgeber:in) / Das, Sourav Kumar (Autor:in) / Shrivastava, Sandeep (Autor:in)
25.04.2022
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Systematic Mix Design Study on Geopolymers—Prediction of Compressive Strength
| DOAJ | 2023
Application of fuzzy logic for prediction compressive strength of OPC based geopolymers
| British Library Online Contents | 2012
Prediction of concrete compressive strength through artificial neural networks
| DOAJ | 2020
Factors influencing the compressive strength of fly ash based geopolymers
| Online Contents | 2016