Tehnički vjesnik, Vol. 33 No. 6, 2026.
Izvorni znanstveni članak
https://doi.org/10.17559/TV-20251231003252
Using of Rebound Materials during Shotcrete Application as a Concrete Pave and Prediction by Machine Learning
Melda Alkan Çakiroğlu
; Isparta University of Applied Sciences, Faculty of Technology, Department of Civil Engineering, Isparta, Türkiye
Cengiz Özel
; Isparta University of Applied Sciences, Faculty of Technology, Department of Civil Engineering, Isparta, Türkiye
Ahmet Ali Süzen
; Isparta University of Applied Sciences, Faculty of Technology, Department of Civil Engineering, Isparta, Türkiye
*
Ozan Çimen
; Suleyman Demirel University, Graduate School of Natural and Applied Sciences, Isparta, Türkiye
* Dopisni autor.
Sažetak
One of the most significant challenges in shotcrete application is the rebound of material that fails to adhere to the substrate or the previously sprayed layer. This rebound material is traditionally excluded from the primary mix and managed as waste. In this study, the rebounded waste material was utilized to manufacture concrete paving blocks. Three series of dry-mix shotcrete mixtures were prepared, including plain mixtures, mixtures with 5 kg/m³ of polypropylene fibers, and mixtures with 9 kg/m³ of polypropylene fibers. The rebounded material collected during the spraying process was used to produce a total of 30 concrete paving block samples, with 10 samples in each series. The produced paving stone samples were evaluated in terms of dimensions and subjected to splitting tensile strength and abrasion resistance tests. In addition, using the data obtained from the experimental study, the amount of rebound was predicted with five different machine learning algorithms. The highest bounce prediction accuracy was obtained in the Extra Tree model with 99.99%. The results demonstrate that rebounded material from shotcrete application can be effectively used in the production of concrete paving blocks, thereby reducing the environmental impact of this inactive material and providing economic benefits.
Ključne riječi
rebound; dry-mix shotcrete; concrete pave; waste; extra tree; machine learning; prediction.
Hrčak ID:
353101
URI
Datum izdavanja:
7.11.2026.
Posjeta: 0 *