A data-driven model for phase angle behaviour of asphalt concrete mixtures based on convolutional neural network
Source abstract
Abstract
Abstract Selection of asphalt concrete (AC) mixtures with proper knowledge of its phase angle characteristics is critical in designing flexible pavements and ensuring the maximum service life of pavements. To achieve this purpose, laborious and expensive laboratory testings are frequently performed, and the results are implied to field. To overcome this problem, models (mathematical or machine learning) are developed to predict the phase angle of AC mixtures. However, the complex and non-linear relationship of phase angle with its independent variables is hard to capture using simple mathematical (or statistical) models. As such, this study proposes a data-driven model based on Convolutional Neural Network (CNN) to capture and predict the phase angle behaviour of AC mixtures. Twenty-three AC mixtures are prepared in laboratory consisting of varying gradations, binder grades, and mix types to perform phase angle testing. The proposed modelling framework, trained using the dataset obtained from laboratory testing, captures 90% of the variance in the test data, which is a significant improvement as compared with other machine learning models as well as linear regression. The proposed model has the capability to capture the non-linearity associated with AC mixtures and can be used by transport agencies and practitioners as a surrogate to tedious laboratory testing.
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Infrastructure Maintenance and Monitoring · Asphalt Pavement Performance Evaluation · Concrete Corrosion and Durability
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (34)
Show source-provided references
1. Sensitivity analysis of dynamic response and fatigue behaviour of various asphalt concrete mixtures: dynamic Response and Fatigue Behaviour of Asphalt Concrete Mixtures10.1111/ffe.12297 ↗
2. Performance evaluation of elvaloy as a fuel-resistant polymer in asphaltic concrete airfield pavements10.1061/(ASCE)MT.1943-5533.0002018 ↗
3. Y. Ali, M. Irfan, S. Ahmed, Can Asphaltic Concrete Permanent Deformation Test Methods be used as Surrogate to Each Other?, 96th Transportation Research Board Annual Meeting, Transportation Research Broad, Washington, D.C., 2017.
4. Modelling and characterising the fatigue behaviour of asphaltic concrete mixtures10.1016/j.conbuildmat.2018.07.022 ↗
5. Evaluation of asphalt mixtures' viscoelastic properties using phase angle relationships10.1080/10298430903033354 ↗
6. Revised predictive model for dynamic (complex) modulus of asphalt mixtures10.1177/0361198196154000103 ↗
7. Rutting as a function of dynamic modulus and gradation10.1061/(ASCE)MT.1943-5533.0000309 ↗
8. Flow number predictive models from volumetric and binder properties10.1016/j.conbuildmat.2014.04.069 ↗
9. Permanent deformation prediction of asphalt concrete mixtures – A synthesis to explore a rational approach10.1016/j.conbuildmat.2017.07.105 ↗
10. A binary logistic model for predicting the tertiary stage of permanent deformation of conventional asphalt concrete mixtures10.1016/j.conbuildmat.2019.07.334 ↗
11. Prediction of fatigue life of rubberized asphalt concrete mixtures containing reclaimed asphalt pavement using artificial neural networks10.1061/(ASCE)0899-1561(2009)21:6(253) ↗
12. Improving accuracy of rutting prediction for mechanistic-empirical pavement design guide with deep neural networks10.1016/j.conbuildmat.2018.09.087 ↗
13. Stiffness modulus and marshall parameters of hot mix asphalts: laboratory data modeling by artificial neural networks characterized by cross-validation10.3390/app9173502 ↗
14. Neural network model for asphalt concrete permeability10.1061/(ASCE)0899-1561(2005)17:1(19) ↗
15. Characterization and identification of asphalt mixtures based on Convolutional Neural Network methods using X-ray scanning images10.1016/j.conbuildmat.2018.04.083 ↗
16. Recognition of asphalt pavement crack length using deep convolutional neural networks10.1080/14680629.2017.1308265 ↗
17. Deep convolutional neural networks with transfer learning for computer vision-based data-driven pavement distress detection10.1016/j.conbuildmat.2017.09.110 ↗
18. Convolutional neural network for asphalt pavement surface texture analysis: convolutional neural network10.1111/mice.12406 ↗
19. Z. Fan, Y. Wu, J. Lu, W. Li, Automatic pavement crack detection based on structured prediction with the convolutional neural network, arXiv preprint arXiv:1802.02208 (2018).
20. Wang · 2017 · 166
21. W. Ye, W. Jiang, Z. Tong, D. Yuan, J. Xiao, Convolutional neural network for pothole detection in asphalt pavement, Road Materials and Pavement Design (2019) 1-17.10.1080/14680629.2019.1615533 ↗
22. R. Roberts, G. Giancontieri, L. Inzerillo, G. Di Mino, Towards low-cost pavement condition health monitoring and analysis using deep learning, Applied Sciences 10(1) (2020) 319.10.3390/app10010319 ↗
23. Pavement image datasets: a new benchmark dataset to classify and densify pavement distresses10.1177/0361198120907283 ↗
24. Autonomous microscopic bunch inspection using region-based deep learning for evaluating graphite powder dispersion10.1016/j.conbuildmat.2018.04.050 ↗
25. Characterization of various plant-produced asphalt concrete mixtures using dynamic modulus test10.1155/2016/5618427 ↗
26. Effect of binder grade on performance parameters of asphaltic concrete paving mixtures10.1016/j.ijprt.2017.11.006 ↗
27. Investigation of factors affecting dynamic modulus and phase angle of various asphalt concrete mixtures10.1617/s11527-015-0544-3 ↗
28. ASTM, Standard Practice for Preparation of Bituminous Specimens Using Marshall Apparatus, ASTM D6926, ASTM International, West Conshohocken, PA., 2010.
29. NHA, “General Specification.” Surface Courses and Pavement, 305/1-6, National Highway Authority, Revised specification for improvement of asphalt mixture design in Pakistan, 2015.
30. Rutting evaluation of asphalt mixtures using static, dynamic, and repeated creep load tests10.1007/s13369-017-2982-4 ↗
31. AASHTO TP 62-07, Standard test method for determining the dynamic modulus of hot mix asphalt (HMA), American Association of State Highway and Transportation Officials, Washington DC (2007).
32. Enhanced features ranking and selection using recursive feature elimination (RFE) and k-nearest neighbor algorithms in support vector machine for intrusion detection system
33. Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms10.1162/089976698300017197 ↗
34. A hazard-based duration model to quantify the impact of connected driving environment on safety during mandatory lane-changing10.1016/j.trc.2019.07.015 ↗