Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Compressive strength of concrete formulated with waste materials using neural networks
The cement production process contributes significantly to climate change by releasing continuous carbon dioxide emissions, a potent greenhouse gas. This study focuses on replacing cement in concrete with three alternative materials: eggshell powder (ESP), red mud (RM), and Construction and Demolition (C&D) waste. Thorough material assessments confirm their suitability for concrete use. Extensive testing shows that all three waste materials can effectively replace cement while maintaining concrete's strength. Artificial Neural Network (ANN) models validate the findings, with an impressive R2 score of 0.99183, representing the model's ability to predict concrete strength influenced by ESP, RM, and C&D waste. This research underscores the potential of ANN models in predicting eco-friendly concrete properties and validates predictions through empirical evidence. The compressive strength of concrete using such waste materials were presented through experimental work. Substituting SCMs up to 15% consistently improves strength-related attributes. Microstructural analysis was also conducted through scanning electron microscopy and X-ray diffractions.
Compressive strength of concrete formulated with waste materials using neural networks
The cement production process contributes significantly to climate change by releasing continuous carbon dioxide emissions, a potent greenhouse gas. This study focuses on replacing cement in concrete with three alternative materials: eggshell powder (ESP), red mud (RM), and Construction and Demolition (C&D) waste. Thorough material assessments confirm their suitability for concrete use. Extensive testing shows that all three waste materials can effectively replace cement while maintaining concrete's strength. Artificial Neural Network (ANN) models validate the findings, with an impressive R2 score of 0.99183, representing the model's ability to predict concrete strength influenced by ESP, RM, and C&D waste. This research underscores the potential of ANN models in predicting eco-friendly concrete properties and validates predictions through empirical evidence. The compressive strength of concrete using such waste materials were presented through experimental work. Substituting SCMs up to 15% consistently improves strength-related attributes. Microstructural analysis was also conducted through scanning electron microscopy and X-ray diffractions.
Compressive strength of concrete formulated with waste materials using neural networks
Asian J Civ Eng
Gulati, Ritu (Autor:in) / Bano, Samreen (Autor:in) / Bano, Farheen (Autor:in) / Singh, Sumit (Autor:in) / Singh, Vikash (Autor:in)
Asian Journal of Civil Engineering ; 25 ; 4657-4672
01.09.2024
16 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Compressive strength of concrete formulated with waste materials using neural networks
| Springer Verlag | 2024
| British Library Online Contents | 2013
Prediction of compressive strength of concrete by neural networks
| British Library Online Contents | 2000