Developing a prediction model for low-temperature fracture energy of asphalt mixtures using machine learning approach

被引:12
作者
Mirzaiyanrajeh, Danial [1 ]
Dave, Eshan, V [1 ]
Sias, Jo E. [1 ]
Ramsey, Philip [1 ]
机构
[1] Univ New Hampshire, Durham, NH 03824 USA
关键词
Mixture properties; mixture performance; fracture cracking; performance prediction; machine learning; NEURAL-NETWORK; PERFORMANCE; CONCRETE;
D O I
10.1080/10298436.2021.2024185
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
This paper presents an augmented full quadratic model (AFQM), artificial neural network (ANN) and an innovative machine learning technique called self-validated ensemble modelling (SVEM) approaches to predict low-temperature fracture energy of asphalt mixtures. An experimental database including 852 fracture energy values obtained from low temperature disk-shaped compact tension (DCT) testing was utilised to develop the prediction models. The fracture energy was predicted in terms of several variables that are available during the mix design process. The collected data were categorised into three groups based on the availability of the data at different points during the mix design process. A sensitivity analysis was conducted to assess the impact of the design variables on fracture energy. Based on the model development results, both ANN and SVEM methods showed higher prediction accuracy than AFQM. Prediction models based on the ANN were time-consuming and computationally expensive due to the optimum model architecture. The SVEM technique was found to be a reliable prediction method with high prediction reliability even with a limited amount of data. Based on the sensitivity analysis, design traffic level, PG low temperature (PGLT) binder grade, amount of aggregate passing 9.5 mm sieve, and the voids in mineral aggregate (VMA) are the most effective factors impacting low-temperature asphalt mixture fracture energy. A web-based prediction model platform was developed using prediction models based on the SVEM technique which can be utilised as a predesign tool to evaluate low-temperature fracture energy of asphalt mixtures when laboratory testing is not feasible.
引用
收藏
页数:12
相关论文
共 44 条
[1]   A robust data mining approach for formulation of geotechnical engineering systems [J].
Alavi, Amir Hossein ;
Gandomi, Arnir Hossein .
ENGINEERING COMPUTATIONS, 2011, 28 (3-4) :242-274
[2]   The influence of natural and synthetic fibers on low temperature mixed mode I plus II fracture behavior of warm mix asphalt (WMA) materials [J].
Aliha, M. R. M. ;
Razmi, A. ;
Mansourian, A. .
ENGINEERING FRACTURE MECHANICS, 2017, 182 :322-336
[3]   A novel test specimen for investigating the mixed mode I plus III fracture toughness of hot mix asphalt composites - Experimental and theoretical study [J].
Aliha, M. R. M. ;
Bahmani, A. ;
Akhondi, Sh. .
INTERNATIONAL JOURNAL OF SOLIDS AND STRUCTURES, 2016, 90 :167-177
[4]  
[Anonymous], 2013, D731313 ASTM ASTM IN
[5]   Effects of Recycled Asphalt Pavement Amounts on Low-Temperature Cracking Performance of Asphalt Mixtures Using Acoustic Emissions [J].
Behnia, Behzad ;
Dave, Eshan V. ;
Ahmed, Sarfraz ;
Buttlar, William G. ;
Reis, Henrique .
TRANSPORTATION RESEARCH RECORD, 2011, (2208) :64-71
[6]   Evaluation of the DC(T) test in discerning the variations in cracking properties of asphalt mixtures [J].
Blankenship, Phillip B. ;
Zeinali, Alireza .
ROAD MATERIALS AND PAVEMENT DESIGN, 2017, 18 :426-449
[7]  
Bose A., 2018, U-statistics, Mm-estimators and Resampling
[8]   ON THE EXPERIMENTAL ATTAINMENT OF OPTIMUM CONDITIONS [J].
BOX, GEP ;
WILSON, KB .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 1951, 13 (01) :1-45
[9]  
Buttlar W., 2018, Asphalt Mixtures, V51
[10]   Performance space diagram for the evaluation of high- and low-temperature asphalt mixture performance [J].
Buttlar, William G. ;
Hill, Brian C. ;
Wang, He ;
Mogawer, Walaa .
ROAD MATERIALS AND PAVEMENT DESIGN, 2017, 18 :336-358