A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Resilient modulus prediction of asphalt mixtures containing Recycled Concrete Aggregate using an adaptive neuro-fuzzy methodology
Highlights Resilient modulus prediction. Series of measurements of Recycled Concrete Aggregates (RCA). Content in Hot Mix Asphalt (HMA) and Stone Mastic Asphalt (SMA) mixtures.
Abstract In this paper, the accuracy of a soft computing technique was employed for resilient modulus prediction based on a series of measurements of Recycled Concrete Aggregates (RCA) content in Hot Mix Asphalt (HMA) and Stone Mastic Asphalt (SMA) mixtures. The main goal was to simulate the resilient modulus with adaptive neuro-fuzzy inference system (ANFIS). The inputs were RCA content and test temperatures. The ANFIS results were compared with the experimental results using root-mean-square error (RMSE), coefficient of determination, and the Pearson coefficient. The effectiveness of the proposed strategies was verified based on the simulation results. The experimental results indicate that the best predictive accuracy and capability of generalization was achieved for SMA containing Mixed RCA (RMSE=25.20119) while the worst predictive accuracy and capability of generalization was achieved for HMA containing Coarse RCA (RMSE=35.56637).
Resilient modulus prediction of asphalt mixtures containing Recycled Concrete Aggregate using an adaptive neuro-fuzzy methodology
Highlights Resilient modulus prediction. Series of measurements of Recycled Concrete Aggregates (RCA). Content in Hot Mix Asphalt (HMA) and Stone Mastic Asphalt (SMA) mixtures.
Abstract In this paper, the accuracy of a soft computing technique was employed for resilient modulus prediction based on a series of measurements of Recycled Concrete Aggregates (RCA) content in Hot Mix Asphalt (HMA) and Stone Mastic Asphalt (SMA) mixtures. The main goal was to simulate the resilient modulus with adaptive neuro-fuzzy inference system (ANFIS). The inputs were RCA content and test temperatures. The ANFIS results were compared with the experimental results using root-mean-square error (RMSE), coefficient of determination, and the Pearson coefficient. The effectiveness of the proposed strategies was verified based on the simulation results. The experimental results indicate that the best predictive accuracy and capability of generalization was achieved for SMA containing Mixed RCA (RMSE=25.20119) while the worst predictive accuracy and capability of generalization was achieved for HMA containing Coarse RCA (RMSE=35.56637).
Resilient modulus prediction of asphalt mixtures containing Recycled Concrete Aggregate using an adaptive neuro-fuzzy methodology
Pourtahmasb, Mohammad Saeed (author) / Karim, Mohamed Rehan (author) / Shamshirband, Shahaboddin (author)
Construction and Building Materials ; 82 ; 257-263
2015-02-18
7 pages
Article (Journal)
Electronic Resource
English
ANFIS , Estimation , HMA , SMA , RCA , Resilient modulus
| British Library Online Contents | 2015
Resilient Modulus of Recycled Asphalt Pavement and Recycled Concrete Aggregate
| British Library Conference Proceedings | 2012
ASPHALT MIXTURES USING RECYCLED CONCRETE AGGREGATE
| British Library Conference Proceedings | 2004