Prediction of Bending Beam Rheometer Test Outputs Using Artificial Neural Networks

Abstract:

The major objective of this study is to investigate the possibility of using Artificial Neural Networks in creating prediction models capable of estimating Bending Beam Rheometer outputs; namely creep stiffness, and m-value based on test temperature, modifier content; in our case waste vegetable oil, and testing time interval. A feedforward backpropagation neural network with Bayesian Regulation training algorithm and an SSE performance function was implemented. It was found that the neural network model shows high predictive powers with training and testing performance of 99.8% and 99.2% respectively. Plots between laboratory obtained values and neural network predicted outputs were also considered, and a strong correlation between the two methods was concluded. Therefore, it was reasonable to state that using neural networks to build prediction models in order to find BBR test values is justified.

• Periodical: Key Engineering Materials (Volume 821)
• Pages: 500-505
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.821.500
• Online since: September 2019
• Authors: Mohammad Fuad Aljarrah, Mohammad Ali Khasawneh*, Aslam Ali Al-Omari, Mohammad Emad Alshorman
• Keywords: Artificial Neural Networks, Bending Beam Rheometer, Creep Stiffness, m-Value, Waste Vegetable Oil

References

[1] Terrel, Ronald L., and Jon A. Epps. Using additives and modifiers in hot mix asphalt. National Asphalt Association, (1993).

[2] Khedaywi, T. S., and S. T. Abu-Orabi. Effect of oil shale ash, rubber ash, husk ash, and polyethylene on properties of asphalt cement., J Petroleum 8, no. 2 (1989): 193-206.

[3] Sun, Zhaojie, Junyan Yi, Yudong Huang, Decheng Feng, and Chaoyang Guo. Properties of asphalt binder modified by bio-oil derived from waste cooking oil., Construction and Building Materials 102 (2016): 496-504.

DOI: 10.1016/j.conbuildmat.2015.10.173

[4] Chen, Meizhu, Binbin Leng, Shaopeng Wu, and Yang Sang. Physical, chemical and rheological properties of waste edible vegetable oil rejuvenated asphalt binders., Construction and Building materials 66 (2014): 286-298.

DOI: 10.1016/j.conbuildmat.2014.05.033

[5] Chen, Meizhu, Feipeng Xiao, Bradley Putman, Bingbing Leng, and Shaopeng Wu. High temperature properties of rejuvenating recovered binder with rejuvenator, waste cooking and cotton seed oils., Construction and Building Materials 59 (2014): 10-16.

DOI: 10.1016/j.conbuildmat.2014.02.032

[6] Al-Omari, Aslam A., Taisir S. Khedaywi, and Mohammad A. Khasawneh. Laboratory characterization of asphalt binders modified with waste vegetable oil using SuperPave specifications., International Journal of Pavement Research and Technology 11, no. 1 (2018): 68-76.

DOI: 10.1016/j.ijprt.2017.09.004

[7] Dai, Qingli, and Zhanping You. Prediction of creep stiffness of asphalt mixture with micromechanical finite-element and discrete-element models., Journal of Engineering Mechanics133, no. 2 (2007): 163-173.

DOI: 10.1061/(asce)0733-9399(2007)133:2(163)

[8] Khasawneh, Mohammad. The Prediction of LWST Values from DFT and CTM Measurements Using Linear and Nonlinear Regression Analyses., Jordan Journal of Civil Engineering 9, no. 4 (2015).

DOI: 10.14525/jjce.9.4.3121

[9] Demuth, Howard B., Mark H. Beale, Orlando De Jess, and Martin T. Hagan. Neural network design. Martin Hagan, (2014).

[10] Shafabakhsh, G. H., O. Jafari Ani, and M. Talebsafa. Artificial neural network modeling (ANN) for predicting rutting performance of nano-modified hot-mix asphalt mixtures containing steel slag aggregates., Construction and Building Materials 85 (2015): 136-143.

DOI: 10.1016/j.conbuildmat.2015.03.060

[11] Xiao, Feipeng, Serji Amirkhanian, and C. Hsein Juang. Prediction of fatigue life of rubberized asphalt concrete mixtures containing reclaimed asphalt pavement using artificial neural networks., Journal of Materials in Civil Engineering 21, no. 6 (2009): 253-261.

DOI: 10.1061/(asce)0899-1561(2009)21:6(253)

[12] Xiao, Feipeng, and Serji N. Amirkhanian. Artificial neural network approach to estimating stiffness behavior of rubberized asphalt concrete containing reclaimed asphalt pavement., Journal of Transportation Engineering 135, no. 8 (2009): 580-589.

DOI: 10.1061/(asce)te.1943-5436.0000014

[13] Owusu‐Ababio, Sam. Effect of neural network topology on flexible pavement cracking prediction., Computer‐Aided Civil and Infrastructure Engineering 13, no. 5 (1998): 349-355.

DOI: 10.1111/0885-9507.00113

[14] Lou, Z., M. Gunaratne, J. J. Lu, and B. Dietrich. Application of neural network model to forecast short-term pavement crack condition: Florida case study., Journal of infrastructure systems 7, no. 4 (2001): 166-171.

DOI: 10.1061/(asce)1076-0342(2001)7:4(166)

[15] Gajewski, Jakub, and Tomasz Sadowski. Sensitivity analysis of crack propagation in pavement bituminous layered structures using a hybrid system integrating Artificial Neural Networks and Finite Element Method., Computational Materials Science 82 (2014): 114-117.

DOI: 10.1016/j.commatsci.2013.09.025

[16] Yang, Jidong, Jian Lu, Manjriker Gunaratne, and Bruce Dietrich. Modeling crack deterioration of flexible pavements: comparison of recurrent Markov chains and artificial neural networks., Transportation Research Record: Journal of the Transportation Research Board 1974 (2006): 18-25.

DOI: 10.1177/0361198106197400103

[17] American Society for Testing and Materials. Standard Test Method for Determining the Flexural Creep Stiffness of Asphalt Binder Using the Bending Beam Rheometer (BBR),, ASMT Standard Test Method D 1298, Book of ASTM Standards, Volume 04.03 (2005), Philadelphia, PA.

DOI: 10.1520/d6648-08r16