مدل‌سازی پیش‌بینی حساسیت رطوبتی در مخلوط‌های آسفالتی با استفاده از یادگیری ماشین

نوع مقاله : پژوهشی اصیل (کامل)

نویسندگان
امیرحسین معتمدی 1
غلام حسین حامدی 2
فریدون مقدس نژاد 1
1 دانشکده مهندسی عمران و محیط زیست، دانشگاه صنعتی امیرکبیر، تهران، ایران
2 دانشکده مهندسی عمران، دانشگاه گیلان، رشت، ایران
10.22034/25.5.3
چکیده
حساسیت رطوبتی در مخلوط‌های آسفالتی چالشی عمده در دوام زیرساخت‌های راهسازی محسوب می‌شود. پیچیدگی این پدیده، مدل‌سازی دقیق را برای ارائه راهکارهای مؤثر ضروری می‌سازد. روش‌های آزمایشگاهی موجود، از جمله آزمون‌های مبتنی بر شاخص‌های عمومی مانند نسبت مقاومت کششی غیرمستقیم، اگرچه در ارزیابی حساسیت رطوبت کارآمد هستند، اما با محدودیت‌های قابل توجهی از نظر هزینه و زمان مواجه‌اند. در این پژوهش، با استفاده از چهار نوع سنگدانه (دو نوع آهکی و دو نوع گرانیتی) و هشت نوع قیر با درجه عملکردی مختلف، آزمایش‌هایی شامل روش اصلاح‌شده لاتمن و آزمایش کششی غیرمستقیم انجام شد. مجموعه داده‌ای متشکل از 34 نمونه و 11 متغیر برای پیش‌بینی دو شاخص کلیدی عملکرد حساسیت رطوبتی، نقطه عطف عریان‌شدگی (ISP) و شیب عریان‌شدگی (SS)، با استفاده از روش برنامه‌ریزی ژنتیک چندژنی (MGGP) مورد استفاده قرار گرفت. برخی از پارامترهای مهم مورد بررسی شامل ضخامت ظاهری لایه قیر، نفوذپذیری، انرژی جداشدگی، انرژی آزاد پیوستگی و چسبندگی بود. نتایج حاصل از مدل‌سازی نشان می‌دهد که برای پیش‌بینی ISP، مدل‌ MGGP ضریب تعیین (R2) 0.981 را ارائه می‌دهد و در مورد SS، این مقدار 0.974 می‌باشد. مدل‌ مورد استفاده در این تحقیق می‌تواند فرمول‌های ریاضی ارائه دهد که شامل پارامترهای ورودی مؤثر بر ISP و SS هستند.

کلیدواژه‌ها

موضوعات

عنوان مقاله English

Predictive Modeling of Moisture Susceptibility in Asphalt Mixtures Using Machine Learning

نویسندگان English

Amirhosein Motamedi 1
Gholam Hossein Hamedi 2
Fereidoon Moghadas Nejad 1
1 Department of Civil & Environmental Engineering, Amirkabir University of Technology, Tehran, Iran
2 Department of Civil Engineering, University of Guilan, Rasht, Iran
چکیده English

Moisture damage in asphalt mixtures poses significant challenges to infrastructure durability, necessitating accurate modeling for effective mitigation strategies due to the complex nature of moisture susceptibility. Current tests, such as those utilizing general indicators like the indirect tensile strength ratio, examine moisture susceptibility in asphalt mixtures. However, these tests incur substantial costs and require considerable time. Therefore, this study aims to develop moisture susceptibility prediction models using Multi-Gene Genetic Programming (MGGP). The research utilized four types of aggregates (two limestone and two granite types) and eight different Performance Grade (PG) bitumen types. The modified Lottman test method (AASHTO T283) was employed for moisture susceptibility assessment, with samples subjected to specific conditioning protocols including vacuum saturation (13-67 kPa absolute pressure), freeze-thaw cycles (-18°C for 16 hours), and hot water conditioning (60°C for 24 hours). Indirect tensile strength tests were conducted under controlled loading conditions (2 Hz frequency, 0.1s loading time, 0.4s rest period) at 25°C. The dataset comprised 34 samples and 11 variables to predict two key indicators: Inflection Stripping Point (ISP) and Stripping Slope (SS). The MGGP model demonstrated remarkable performance in predicting both ISP and SS, achieving R2 values of 0.981 and 0.974 for the test data, respectively. Several crucial parameters were analyzed, including the apparent film thickness (AFT) calculated using aggregate specific surface area, permeability measured through falling head test method (ASTM PS 129-01), and surface free energy components. The surface energy analysis incorporated both cohesive free energy (CFE) and adhesive free energy (AFE), with special attention to the acid-base theory components: Lifshitz-van der Waals (LW), Lewis acid (Γ+), and Lewis base (Γ-) components. For ISP prediction, the MGGP model identified key variables including the ratio of base to acid surface free energy (SFE), asphalt-water adhesion (ΓAsphalt-Water), cohesive free energy (CFE), adhesive free energy (AFE), permeability of asphalt mixture (PAM), asphalt film thickness (AFT), and degree of saturation (DS). The model for SS prediction emphasized the importance of ΓAsphalt-Water, aggregate-water adhesion (ΓAggregate-Water), wettability, specific surface area (SSA), PAM, and DS. The study employed various performance metrics to evaluate the MGGP models. For ISP predictions, the model achieved RMSE, MSE, and MAE values of 5.228, 27.337, and 3.843, respectively. For SS predictions, these values were 0.294, 0.086, and 0.231, respectively, indicating high accuracy and low error rates. These results surpass those of previous studies employing traditional Genetic Programming (GP) methods, highlighting the potential of MGGP as a powerful tool in modeling asphalt moisture susceptibility. The practical implications of this research are significant for improving asphalt mixture durability, reducing maintenance costs, and enhancing road safety. Future research could focus on validating the models across a broader range of asphalt mixtures and environmental conditions.

کلیدواژه‌ها English

Asphalt Mixture
Moisture Susceptibility
Machine learning
Multi-Gene Genetic Programming
[1] J. Grenfell, N. Ahmad, Y. Liu, A. Apeagyei, D. Large, and G. Airey, "Assessing asphalt mixture moisture susceptibility through intrinsic adhesion, bitumen stripping and mechanical damage," Road Materials and Pavement Design, vol. 15, no. 1, pp. 131-152, 2014.
[2] R. A. Tarefder and M. Ahmad, "Evaluating the relationship between permeability and moisture damage of asphalt concrete pavements," Journal of Materials in Civil Engineering, vol. 27, no. 5, p. 04014172, 2015.
[3] S. Caro, E. Masad, A. Bhasin, and D. N. Little, "Moisture susceptibility of asphalt mixtures, Part 2: characterisation and modelling," International Journal of Pavement Engineering, vol. 9, no. 2, pp. 99-114, 2008.
[4] S. Caro, E. Masad, A. Bhasin, and D. N. Little, "Moisture susceptibility of asphalt mixtures, Part 1: mechanisms," International Journal of Pavement Engineering, vol. 9, no. 2, pp. 81-98, 2008.
[5] A. Diab, Z. You, X. Yang, and M. R. Mohd Hasan, "Towards an alternate evaluation of moisture-induced damage of bituminous

materials," Applied Sciences, vol. 7, no. 10, p. 1049, 2017.
[6] R. K. Veeraragavan, N. M. Kottayi, R. B. Mallick, M. K. Nirala, and S. Sarkar, "Application of artificial intelligence to predict moisture damage of hot-mix asphalt mixes," in Proceedings of the Institution of Civil Engineers-Transport, 2021, vol. 174, no. 3: Thomas Telford Ltd, pp. 197-206.
[7] C. Ling, "Developing evaluation method of moisture susceptibility for cold mix asphalt," 2013.
[8] R. K. Veeraragavan, N. MK, and R. B. Mallick, "Accurate identification of pavement materials that are susceptible to moisture damage with the
use of advanced conditioning and test methods and the use of machine learning techniques," SN Applied Sciences, vol. 1, pp. 1-7, 2019.
[9] M. G. Zamani, K. Saniei, B. Nematollahi, Z. Zahmatkesh, M. M. Poor, and M. R. Nikoo, "Developing sustainable strategies by LID optimization in response to annual climate change impacts," Journal of Cleaner Production, vol. 416, p. 137931, 2023.
[10] S. Ranjbar, F. M. Nejad, H. Zakeri, and A. H. Gandomi, "Computational intelligence for modeling of asphalt pavement surface distress," in New Materials in Civil Engineering: Elsevier, 2020, pp. 79-116.
[11] R. B. Mallick, N. Madankara Kottayi, R. K. Veeraragavan, E. Dave, C. DeCarlo, and J. E. Sias, "Suitable tests and machine learning approach to predict moisture susceptibility of hot-mix asphalt," Journal of Transportation Engineering, Part B: Pavements, vol. 145, no. 3, p. 04019030, 2019.
[12] R. Sezavar, G. Shafabakhsh, and S. Mirabdolazimi, "New model of moisture susceptibility of nano silica-modified asphalt concrete using GMDH algorithm," Construction and Building Materials, vol. 211, pp. 528-538, 2019.
[13] N. D. Lagaros, "Artificial neural networks applied in civil engineering," vol. 13, ed: MDPI, 2023, p. 1131.
[14] R. Babagoli and M. Rezaei, "Development of prediction models for moisture susceptibility of asphalt mixture containing combined SBR, waste CR and ASA using support vector regression and artificial neural network methods," Construction and Building Materials, vol. 322, p. 126430, 2022.
[15] R. Babagoli and M. Rezaei, "Using Artificial Neural Network Methods for Modeling Moisture Susceptibility of Asphalt Mixture Modified by Nano TiO 2," Journal of Materials in Civil Engineering, vol. 34, no. 6, p. 04022108, 2022.
[16] F. J. Rebelo, F. F. Martins, H. M. Silva, and J. R. Oliveira, "Use of data mining techniques to explain the primary factors influencing water sensitivity of asphalt mixtures," Construction and Building Materials, vol. 342, p. 128039, 2022.
[17] Q. Cao, I. L. Al-Qadi, and L. Abufares, "Pavement moisture content prediction: A deep residual neural network approach for analyzing ground penetrating radar," IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1-11, 2022.
[18] H. Majidifard, B. Jahangiri, W. G. Buttlar, and A. H. Alavi, "New machine learning-based prediction models for fracture energy of asphalt mixtures," Measurement, vol. 135, pp. 438-451, 2019.
[19] V. N. M. Gilani, S. M. Hosseinian, H. Behbahani, and G. H. Hamedi, "Prediction and pareto-based multi-objective optimization of moisture and fatigue damages of asphalt mixtures modified with nano hydrated lime," Construction and Building Materials, vol. 261, p. 120509, 2020.
[20] H. Behbahani, G. H. Hamedi, and V. N. M. Gilani, "Predictive model of modified asphalt mixtures with nano hydrated lime to increase resistance to moisture and fatigue damages by the use of deicing agents," Construction and Building Materials, vol. 265, p. 120353, 2020.
[21] N. Esmaeili, G. H. Hamedi, and M. Khodadadi, "Determination of the stripping process of asphalt mixtures and the effective mix design and SFE parameters on its different phases," Construction and Building Materials, vol. 213, pp. 167-181, 2019.
[22] ASTM International, “Astm D4318-17,” Stand. Test Methods Liq. Limit, Plast. Limit, Plast. Index Soils, pp. 1–10, 2017, doi: 10.1520/D4318-17E01.1.9.
[23] T. AASHTO, “283; Standard Method of Test for Resistance of Compacted Asphalt Mixtures to Moisture-Induced Damage,” Am. Assoc. State Highw. Transp. Off. Washington, DC, USA, 2014.
[24] G. H. Hamedi and F. Moghadas Nejad, "Using energy parameters based on the surface free energy concept to evaluate the moisture susceptibility of hot mix asphalt," Road Materials and Pavement Design, vol. 16, no. 2, pp. 239-255, 2015.
[25] D. W. Christensen and R. F. Bonaquist, Volumetric requirements for Superpave mix design. Transportation Research Board, 2006.
[26] G. H. Hamedi and F. Moghadas Nejad, "Evaluating the effect of mix design and thermodynamic parameters on moisture sensitivity of hot mix asphalt," Journal of Materials in Civil Engineering, vol. 29, no. 2, p. 04016207, 2017.
[27] B. Huang, L. N. Mohammad, A. Raghavendra, and C. Abadie, "Fundamentals of permeability in asphalt mixtures," Journal of the Association of Asphalt Paving Technologists, vol. 68, 1999.
[28] A. W. Hefer, Adhesion in bitumen-aggregate systems and quantification of the effects of water on the adhesive bond. Texas A&M University, 2004.
[29] C. J. Van Oss, M. K. Chaudhury, and R. J. Good, "Interfacial Lifshitz-van der Waals and polar interactions in macroscopic systems," Chemical reviews, vol. 88, no. 6, pp. 927-941, 1988.
[30] M. N. Yalghouzaghaj, A. Sarkar, G. H. Hamedi, and P. Hayati, "Application of the surface free energy method on the mechanism of low-temperature cracking of asphalt mixtures," Construction and Building Materials, vol. 268, p. 121194, 2021.
[31] D. Cheng, D. N. Little, R. L. Lytton, and J. C. Holste, "Surface energy measurement of asphalt and its application to predicting fatigue and healing in asphalt mixtures," Transportation Research Record, vol. 1810, no. 1, pp. 44-53, 2002.
[32] R. J. Good and C. J. van Oss, "The modern theory of contact angles and the hydrogen bond components of surface energies," in Modern approaches to wettability: theory and applications: Springer, 1992, pp. 1-27.
[33] A. Bhasin, "Development of methods to quantify bitumen-aggregate adhesion and loss of adhesion due to water," Texas A&M University, 2007.
[34] G. H. Hamedi, A. H. Asadi, and J. Zarrinfam, "Investigating the effect of fundamental properties of materials on the mechanisms of thermal cracking of asphalt mixtures," Construction and Building Materials, vol. 411, p. 134426, 2024.
[35] H. Naseri, H. Jahanbakhsh, F. Moghadas Nejad, and A. Golroo, "Developing a novel machine learning method to predict the compressive strength of fly ash concrete in different ages," َ
AUT Journal of Civil Engineering, vol. 4, no. 4, pp. 423-436, 2020.
[36] M. Ehsani, M. Ostovari, S. Mansouri, H. Naseri, H. Jahanbakhsh, and F. M. Nejad, "Machine learning for predicting concrete carbonation depth: A comparative analysis and a novel feature selection," Construction and Building Materials, vol. 417, p. 135331, 2024.
[37] S. Ranjbar, F. M. Nejad, and H. Zakeri, "Image-based severity analysis of Asphalt pavement bleeding using a metaheuristic-boosted fuzzy classifier," Automation in Construction, vol. 166, p. 105655, 2024.
[38] M. Dargi, E. Khamehchi, and J. Mahdavi Kalatehno, "Optimizing acidizing design and effectiveness assessment with machine learning for predicting post-acidizing permeability," Scientific Reports, vol. 13, no. 1, p. 11851, 2023.
[39] A. Lissovoi and P. S. Oliveto, "Computational complexity analysis of genetic programming," Theory of Evolutionary Computation: Recent Developments in Discrete Optimization, pp. 475-518, 2020.
[40] D. Searson, "GPTIPS genetic programming & symbolic regression for MATLAB user guide," ed: Natick, MA: MathWorks, 2009.
[41] D. P. Searson, D. E. Leahy, and M. J. Willis, "GPTIPS: an open source genetic programming toolbox for multigene symbolic regression," in Proceedings of the International multiconference of engineers and computer scientists, 2010, vol. 1: Citeseer, pp. 77-80.
[42] B. Choubane, G. C. Page, and J. A. Musselman, "Effects of water saturation level on resistance of compacted hot-mix asphalt samples to moisture-induced damage," Transportation Research Record, vol. 1723, no. 1, pp. 97-106, 2000.
[43] H. A. Omar, N. I. M. Yusoff, M. Mubaraki, and H. Ceylan, "Effects of moisture damage on asphalt mixtures," Journal of Traffic and Transportation Engineering (English Edition), vol. 7, no. 5, pp. 600-628, 2020.
[44] B. Sengoz and E. Agar, "Effect of asphalt film thickness on the moisture sensitivity characteristics of hot-mix asphalt," Building and environment, vol. 42, no. 10, pp. 3621-3628, 2007.