0% Complete
|
Sign in
|
Sign Up
Home
/
15th International Fiber and Polymer Research Symposium
Prediction of Marshall Strength in Polymer-Modified Thin-Layer Asphalt Using Decision Tree Regression and Bayesian Optimization
Authors :
Uğur ÖZVEREN
1
Ozan Derya KAYA
2
Ayserin Pelin YILMAZ
3
Burce PEKER
4
Idil Sena BAYRAK
5
Kabil Bilgic
6
1- Marmara University, Department of Engineering Faculty
2- Marmara University, Department of Engineering Faculty
3- Marmara University, Department of Engineering Faculty
4- Marmara University, Department of Engineering Faculty
5- Marmara University, Department of Engineering Faculty
6- Marmara University, Department of Engineering Faculty
Keywords :
Polymer-Modified Asphalt،Marshall Strength Prediction،Machine Learning،Decision Tree Regression،Hyperparameter Optimization
Abstract :
This study presents a machine learning approach for predicting the Marshall Strength of polymer-modified thin-layer asphalt mixtures using Decision Tree regression with Bayesian optimization. The research utilized a dataset of 45 samples with varying aggregate crushing strengths (80-100) and polymer percentages (5-15%), designed according to EN13108-2 standards. The model achieved exceptional accuracy with R² values of 0.9985 and 0.9214 for training and test sets, respectively. Feature importance analysis revealed that polymer percentage has a dominant influence (57.66%) on Marshall Strength compared to aggregate crushing strength (42.34%). The comprehensive evaluation using multiple regression metrics demonstrated the model's strong predictive capabilities, despite some evidence of overfitting indicated by the differences between training and test metrics (Training RMSE: 6.9572, Test RMSE: 48.2378). This approach provides a practical tool for optimizing asphalt mixture designs, potentially reducing the need for extensive laboratory testing while maintaining prediction accuracy. The methodology offers significant implications for the development of more durable and cost-effective pavement solutions, particularly in regions with varying climate conditions and heavy traffic loads.
Papers List
List of archived papers
Development of recycled lightweight fiber reinforced polymeric composite parts by using manufacturing waste glass fibers and PET powder materials
Gülnur Başer - Rümeysa Zeynep Kabaca
Poly(2-Hydroxyethyl Methacrylate) modified cellulose nanocrystals and their PBAT - based nanocomposites
EDA JAN YILMAZ ARIKAN - YONCA ALKAN GOKSU - AYLIN ALTINBAY - MOHAMMADREZA NOFAR
Sustainable Production of Yarn Incorporating recycled fiber extracted from hard waste to Promote Sustainability
Ahsan Habib - Md. Abdullah Al Mamun - Osman Babaarslan
Development of PLGA Nanofibers Enhanced with Curcumin/Ag Nanoparticles
Fatma Ahsen Oktemer - Cansu Gunes - M. Mert Kurdis - Ahmet Avci
Migration of Phthalate Derivatives Found in PVC Based Wastes into Soil
Semra Karaoğlan - Ayşe Pınar Tüzüm Demir
Uranium (VI) Adsorption by Al-Doped ZnO/PVDF Fiber Composite: Response Surface Methodology (RSM)
Ikbal Gozde Kaptanoglu - Sabriye Yusan - Sermin Cam Kaynar - Umit Huseyin Kaynar
A new sustainability concept in PLA/PBAT blends: Smart Recycling
Berk Baykan - M. Reza Nofar
INVESTIGATION OF CAPACITIVE PROPERTIES OF ALD THIN FILM COATED FABRICS
Aleyna NİŞANCI - Halil İbrahim AKYILDIZ
Effect of vulcanization time on crosslinking of EPDM rubber
Alara Meryem Ayaz - Omer Yunus Gumus - Muhammet Kara
Bigbag üretiminde kullanılan dikiş iplerinin geri dönüştürülmüş plastik kaynaklarından üretilmesi ve uygulanabilirliği
Betül Gülgeç - Mehmet Zeybek - Erhan Demircan
more
Samin Hamayesh - Version 41.7.5