Evaluation of the self-healing behavior of warm mix asphalt with the help of failure mechanism and in terms of induction characteristics using Artificial Neural Networks

Document Type : Original Research

Authors
I. UMAR MOHAMAD SALEH 1
M. Effati 2
M. Jalali 3
S. M. Mirabdolazimi 2
1 Master's student in civil engineering, road and transportation, GUilan University-Rasht
2 Assistant Professor, Department of Civil Engineering, Faculty of Engineering, University of Guilan
3 University of Guilan
10.22034/24.1.7
Abstract
Improving the self-healing performance of warm mix asphalt depends on several factors and parameters that are highly interdependent and have significant complexity. In this study, the self-healing performance of warm mix asphalt was investigated using artificial intelligence and artificial neural network of multi-layer perceptron and radial base with two hidden layers. To conduct this study, two additives Sasobit and Zycotherm were used. The three-point bending test was performed at two temperatures of 25 and -16 degrees Celsius and with two crack lengths of 10 and 20 mm, and the fracture toughness, fracture energy and critical load indices were determined for each of the states. Asphalt samples were subjected to induction heating at two frequencies of 87 and 88 kHz and three induction times of 60, 90 and 120 seconds. The results of sensitivity analysis in two artificial neural network models showed that in the MLP network, the fracture toughness parameter had the greatest impact on the output. It was also observed that the test temperature parameter had the highest sensitivity coefficient in the RBF network. The results showed that in the perceptron neural network with two layers in the test section, the root mean square error (RMSE) values increased from 10.46 in the first model to 4.27 in the fourth model. The results of the basic radial artificial neural network showed that the addition of input parameters reduced the root mean square error (RMSE) value of the test section from 10.56 to 4.35. The results of MLP and RBF network estimation have shown that the addition of input variables to the model has increased NS in all three parts of test, train and validation. In this way, in the MLP network, the value of NS in the test section has reached from 0.45 to 0.90 and the estimation accuracy has doubled. In the RBF network, similarly to MLP, with the addition of the NS parameter, the NS value has increased from 0.44 to 0.90. Also, the results of this study showed that in both types of MLP and RBF networks, the value of R2 in the second group was higher than the first group in all test, train and validation sections. In general, the results of this study showed that the artificial neural network has appropriate performance and accuracy due to the nature of learning and the ability to train from the previous laboratory results in estimating the self-healing ability and modeling the complex relationship of the influential input variables, and the use of the proposed intelligent model by reducing the of experiments and cost can be effective in evaluating the self-healing behavior of warm mix asphalt.

Keywords

Subjects

1) Cheraghian, G., Falchetto, A.C., You, Z., Chen, S., Kim, Y.S., Westerhoff, J., Moon, K.H. and Wistuba, M.P., 2020. Warm mix asphalt technology: An up to date review. Journal of Cleaner Production, 268, p.122128.
2) Kim Y. R., Little D. N., & Lytton R. L. (2001). Evaluation of microdamage, healing, and heat dissipation of asphalt mixtures, using a dynamic mechanical analyzer. Transportation Research Record, 1767(1), 60-66
3) Aliha, M.R.M., Bahmani, A. and Akhondi, S., 2015. Determination of mode III fracture toughness for different materials using a new designed test configuration. Materials & Design, 86, pp.863-871.
4) Griffith, A.A., 1921. VI. The phenomena of rupture and flow in solids. Philosophical transactions of the royal society of london. Series A, containing papers of a mathematical or physical character, 221(582-593), pp.163-198.
5) Gómez-Meijide B., Ajam H., Garcia A., & Vansteenkiste S. (2018). Effect of bitumen properties in the induction healing capacity of asphalt mixes. Construction and Building Materials, 190, 131-139
6) García, Á., Schlangen, E., van de Ven, M. and Liu, Q., 2012. A simple model to define induction heating in asphalt mastic. Construction and Building Materials, 31, pp.38-46.
7) Kargari, A., Arabani, M. and Mirabdolazimi, S.M., 2022. Effect of palm oil capsules on the self-healing properties of aged and unaged asphalt mixtures gained by resting period and microwave heating. Construction and Building Materials, 316, p.125901.
8) Adeli H. (2001). Neural networks in civil engineering: 1989–2000. Computer‐Aided Civil and Infrastructure Engineering, 16(2), 126-142
9) Sezavar, R., Shafabakhsh, G. and Mirabdolazimi, S.M., 2019. New model of moisture susceptibility of nano silica-modified asphalt concrete using GMDH algorithm. Construction and Building Materials, 211, pp.528-538.
10) Ozturk H. I., & Kutay, M. E. (2014). An artificial neural network model for virtual Superpave asphalt mixture design. International Journal of Pavement Engineering, 15(2), 151-162.
11) Domitrović J., Dragovan H., Rukavina T., & Dimter S. (2018). Application of an artificial neural network in pavement management system. Tehnički vjesnik, 25 (Supplement 2), 466-473
12) Baldo N., Manthos E., & Pasetto M. (2018). Analysis of the mechanical behaviour of asphalt concretes using artificial neural networks. Advances in Civil Engineering.
13) Nguyen H. L., Le T. H., Pham C. T., Le T. T., Ho L. S., Le V. M., & Ly H. B. (2019). Development of hybrid artificial intelligence approaches and a support vector machine algorithm for predicting the marshall parameters of stone matrix asphalt. Applied Sciences, 9(15), 3172.
14) Kie Badroodi S., Keymanesh M. R., & Shafabakhsh G (2020). Laboratory Study and Investigation on Significance Level of Fatigue Phenomenon in Warm Mix Asphalt Modified with Nano-Silica. Journal of Rehabilitation in Civil Engineering, 8(2), 92-113.
15) Mirabdolazimi, S.M. and Shafabakhsh, G., 2017. Rutting depth prediction of hot mix asphalts modified with forta fiber using artificial neural networks and genetic programming technique. Construction and Building Materials, 148, pp.666-674.
16) Hamid A., Baaj H., & El-Hakim M. (2022). Predicting the Recovery and Nonrecoverable Compliance Behaviour of Asphalt Binders Using Artificial Neural Networks. Processes, 10(12), 2633.
17) " نشریه 234 - آیین نامه روسازی آسفالتی راه های ایران "، سازمان برنامه و بودجه کشور، 1390
18) Xu S., García A., Su J., Liu Q., Tabaković A., & Schlangen E. (2018). Self‐Healing Asphalt Review: From Idea to Practice. Advanced Materials Interfaces, 5(17), 1800536
19) Qiu J., Van de Ven M. F. C., Wu S., Yu J., & Molenaar, A. A. A. (2009). Investigating the self-healing capability of bituminous binders. Road Materials and Pavement Design, 10(sup1), 81-94.
20) Ziari H., Aliha M., Moniri A., & Saghafi Y. (2020). Crack resistance of hot mix asphalt containing different percentages of reclaimed asphalt pavement and glass fiber. Construction and Building Materials, 230, 117015.
21) Bayat H., Ebrahimi E., & Fallah, M. (2018). Estimation of soil moisture using confined compression curve parameters. Geoderma, 318, 64-77.
22) Rezaki M., & Sadeghian M. (2022). Asphalt mixture design using artificial neural network and genetic algorithm. The 13th National Conference and Exhibition of Bitumen, Asphalt and Machinery. (In Persian)
23) Liang B., Lan F., Shi K., Qian G., Liu Z., & Zheng J. (2021). Review on the self-healing of asphalt materials: Mechanism, affecting factors, assessments and improvements. Construction and Building Materials, 266, 120453.
24) Liu Q., Schlangen E., & Ven M. (2013). Induction Healing of Porous Asphalt Concrete Beams on an Elastic Foundation. Journal of Materials in Civil Engineering, 25(7), 880-5.
25) Menozzi A., Garcia A., Partl M., Tebaldi G., & Schuetz P. (2015). Induction healing of fatigue damage in asphalt test samples. Construction and Building Materials, 74, 162-8.
26) Behbahani H., Mohammad Aliha M. R., Fazaeli H., & Aghajani S. (2013). Experimental fracture toughness study for some modified asphalt mixtures. In Advanced Materials Research. Trans Tech Publications Ltd, 723, 337-344.
27) Podolsky J. H., Buss A., Williams R. C., & Cochran E. (2016). Comparative performance of bio-derived/chemical additives in warm mix asphalt at low temperature. Materials and Structures, 49(1), 563-575.
28) Aliha M. R. M., Behbahani H., Fazaeli H., & Rezaifar M. H. (2015). Experimental study on mode I fracture toughness of different asphalt mixtures. Scientia Iranica A, 22(1), 120-130.
29) Ameri M., Molayam M. (2006). The use of artificial neural networks for the analysis of flexible pavements. International Journal of Engineering Sciences, 5(17), 53-60. (In Persian)
30) Shafabakhsh G. A., Naderpour H., & Fasihi F. (2010). Choosing the optimal neural network algorithm in the analysis of flexible road pavements. Journal of Modeling in Engineering, 8(21), 45-57. (In Persian)
31) Taherkhani H., & Posht-Panah A. (2013). Predicting the dynamic modulus of hot asphalt concrete using the neural network method. Transportation research paper, 10th year. 3, 281-290. (In Persian)
32) Bayat H., Ebrahimi E., Ersahin S., Hepper E. N., Singh D. N., Amer A. M. M., & Yukselen-Aksoy Y. (2015). Analyzing the effect of various soil properties on the estimation of soil specific surface area by different methods. Applied Clay Science, 116, 129-140.
Modares Civil Engineering journal
Volume 24, Issue 1
March and April 2024
Pages 7-23