A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Assessment of Soft Computing-Based Techniques for the Prediction of Marshall Stability of Asphalt Concrete Reinforced with Glass Fiber
https://orcid.org/http://orcid.org/0000-0002-7761-0603
The Stability of asphalt concrete is necessary in the design of flexible pavement. Many methods and additives are being successfully used to enhance the crack resistance of asphalt. Fiber reinforcement is a constructive approach to improve the performance of asphalt pavement. In this investigation, Marshall Stability of asphalt concrete reinforced with glass fiber is predicted using soft computing techniques such as Artificial Neural Network (ANN), Random Forest (RF), Random Tree (RT) and Adaptive Neuro-Fuzzy Inference System (ANFIS). For this, data set was collected from experiments and various creditable research papers. The performances of applied models were evaluated using five statistical indices such as coefficient of correlation (CC), Root Mean Square Error (RMSE), Willmott’s index (WI), Nash–Sutcliffe coefficient (NSE) and Mean absolute error (MAE). Performance of Trapezoidal membership function-based ANFIS model is outperforming among all applied models with CC value as 0.8347, RMSE value as 2.7254, WI value as 0.7310, NSE value as 0.6951 and MAE value as 1.8756. The sensitivity analysis was also carried out using best performing model (Trapezoidal membership function-based ANFIS) with this data set, which suggest that Bitumen Grade (VG) has a major influence in predicting the Marshall Stability of asphalt concrete. This study suggests that the glass fiber (%) and Bitumen content (%) has also significant factor for the predicting the Marshall Stability of single-factor ANOVA outcomes suggest that there is no significant variation among actual and predicted values using various applied models.
Assessment of Soft Computing-Based Techniques for the Prediction of Marshall Stability of Asphalt Concrete Reinforced with Glass Fiber
https://orcid.org/http://orcid.org/0000-0002-7761-0603
The Stability of asphalt concrete is necessary in the design of flexible pavement. Many methods and additives are being successfully used to enhance the crack resistance of asphalt. Fiber reinforcement is a constructive approach to improve the performance of asphalt pavement. In this investigation, Marshall Stability of asphalt concrete reinforced with glass fiber is predicted using soft computing techniques such as Artificial Neural Network (ANN), Random Forest (RF), Random Tree (RT) and Adaptive Neuro-Fuzzy Inference System (ANFIS). For this, data set was collected from experiments and various creditable research papers. The performances of applied models were evaluated using five statistical indices such as coefficient of correlation (CC), Root Mean Square Error (RMSE), Willmott’s index (WI), Nash–Sutcliffe coefficient (NSE) and Mean absolute error (MAE). Performance of Trapezoidal membership function-based ANFIS model is outperforming among all applied models with CC value as 0.8347, RMSE value as 2.7254, WI value as 0.7310, NSE value as 0.6951 and MAE value as 1.8756. The sensitivity analysis was also carried out using best performing model (Trapezoidal membership function-based ANFIS) with this data set, which suggest that Bitumen Grade (VG) has a major influence in predicting the Marshall Stability of asphalt concrete. This study suggests that the glass fiber (%) and Bitumen content (%) has also significant factor for the predicting the Marshall Stability of single-factor ANOVA outcomes suggest that there is no significant variation among actual and predicted values using various applied models.
Assessment of Soft Computing-Based Techniques for the Prediction of Marshall Stability of Asphalt Concrete Reinforced with Glass Fiber
https://orcid.org/http://orcid.org/0000-0002-7761-0603
The Stability of asphalt concrete is necessary in the design of flexible pavement. Many methods and additives are being successfully used to enhance the crack resistance of asphalt. Fiber reinforcement is a constructive approach to improve the performance of asphalt pavement. In this investigation, Marshall Stability of asphalt concrete reinforced with glass fiber is predicted using soft computing techniques such as Artificial Neural Network (ANN), Random Forest (RF), Random Tree (RT) and Adaptive Neuro-Fuzzy Inference System (ANFIS). For this, data set was collected from experiments and various creditable research papers. The performances of applied models were evaluated using five statistical indices such as coefficient of correlation (CC), Root Mean Square Error (RMSE), Willmott’s index (WI), Nash–Sutcliffe coefficient (NSE) and Mean absolute error (MAE). Performance of Trapezoidal membership function-based ANFIS model is outperforming among all applied models with CC value as 0.8347, RMSE value as 2.7254, WI value as 0.7310, NSE value as 0.6951 and MAE value as 1.8756. The sensitivity analysis was also carried out using best performing model (Trapezoidal membership function-based ANFIS) with this data set, which suggest that Bitumen Grade (VG) has a major influence in predicting the Marshall Stability of asphalt concrete. This study suggests that the glass fiber (%) and Bitumen content (%) has also significant factor for the predicting the Marshall Stability of single-factor ANOVA outcomes suggest that there is no significant variation among actual and predicted values using various applied models.
Assessment of Soft Computing-Based Techniques for the Prediction of Marshall Stability of Asphalt Concrete Reinforced with Glass Fiber
Int. J. Pavement Res. Technol.
Upadhya, Ankita (author) / Thakur, M. S. (author) / Sharma, Nitisha (author) / Sihag, Parveen (author)
International Journal of Pavement Research and Technology ; 15 ; 1366-1385
2022-11-01
20 pages
Article (Journal)
Electronic Resource
English
Study on Short Carbon Fiber Asphalt Concrete Marshall
| Trans Tech Publications | 2012