Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Using Random Forest for Predicting Compressive Strength of Self-compacting Concrete
Self-compacting concrete (SCC) is a high-strength and high-efficiency concrete that can get compacted without the need for mechanical vibration. SCC can flow due to the self-weight effect to compact and still ensure uniformity. Thanks to these advantages, self-compacting concrete has been considered an outstanding application in construction. One of the most important properties of self-compacting concrete is compressive strength. In this paper, the application of random forest (RF) to predict the SCC compressive strength has been investigated. Eight RF architectures with different number of trees were fully evaluated in terms of performance and prediction capability over statistical results of 50 simulations for each case. The results showed that a combination of 500 trees performed best and the RF algorithm was a good tool, might be useful for engineers to avoid time-consuming experiments for predicting the compressive strength of SCC. Furthermore, the sensitivity of the input variables was also evaluated in this study.
Using Random Forest for Predicting Compressive Strength of Self-compacting Concrete
Self-compacting concrete (SCC) is a high-strength and high-efficiency concrete that can get compacted without the need for mechanical vibration. SCC can flow due to the self-weight effect to compact and still ensure uniformity. Thanks to these advantages, self-compacting concrete has been considered an outstanding application in construction. One of the most important properties of self-compacting concrete is compressive strength. In this paper, the application of random forest (RF) to predict the SCC compressive strength has been investigated. Eight RF architectures with different number of trees were fully evaluated in terms of performance and prediction capability over statistical results of 50 simulations for each case. The results showed that a combination of 500 trees performed best and the RF algorithm was a good tool, might be useful for engineers to avoid time-consuming experiments for predicting the compressive strength of SCC. Furthermore, the sensitivity of the input variables was also evaluated in this study.
Using Random Forest for Predicting Compressive Strength of Self-compacting Concrete
Lecture Notes in Civil Engineering
Ha-Minh, Cuong (Herausgeber:in) / Tang, Anh Minh (Herausgeber:in) / Bui, Tinh Quoc (Herausgeber:in) / Vu, Xuan Hong (Herausgeber:in) / Huynh, Dat Vu Khoa (Herausgeber:in) / Mai, Hai-Van Thi (Autor:in) / Tran, Van Quan (Autor:in) / Nguyen, Thuy-Anh (Autor:in)
CIGOS 2021, Emerging Technologies and Applications for Green Infrastructure ; Kapitel: 196 ; 1937-1944
28.10.2021
8 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Predicting the compressive strength of self compacting concrete using artificial neural network
| British Library Conference Proceedings | 2009
Low Strength Self Compacting Concrete Compressive Strength Test
| Trans Tech Publications | 2013
XGB-Northern Goshawk Optimization: Predicting the Compressive Strength of Self-Compacting Concrete
| Springer Verlag | 2024
In-situ compressive strength of self-compacting concrete
| British Library Online Contents | 2002
| Springer Verlag | 2024