پیش بینی مقاومت مارشال آسفالت با استفاده از الگوریتم های یادگیری ماشین نظارت شده ماشین بردار پشتیبان و جنگل تصادفی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانش آموخته کارشناسی ارشد، مهندسی عمران، موسسه آموزش عالی اقبال لاهوری، مشهد، ایران

2 دانشجوی کارشناسی ارشد، مهندسی عمران، موسسه آموزش عالی اقبال لاهوری، مشهد، ایران

3 دانش آموخته کارشناسی ارشد، مهندسی عمران، دانشگاه آزاد اسلامی، مشهد، ایران

چکیده

سازمان‌های مسئول ساخت و نگهداری راه‌ها معمولاً از برخی معیارها برای واجد شرایط بودن مخلوط‌های آسفالتی قبل از استفاده در ساخت‌وساز استفاده می‌کنند. یکی از مهم‌ترین ویژگی‌هایی که در طرح اختلاط و کنترل کیفی آسفالت سنجیده می‌شود مقاومت مارشال آسفالت می‌باشد. این مطالعه استفاده از روش‌های یادگیری ماشین را برای پیش بینی مقاومت مارشال آسفالت را بررسی می‌کند. با توجه به زمان‌بر بودن و هزینه‌بر بودن فرایند تولید و کنترل کیفی آسفالت، استفاده از روش‌های نوین در این فرایند ضرورت دارد. در این پژوهش از دو الگوریتم نظارت شده ماشین بردار پشتیبان و جنگل تصادفی که از الگوریتم‌های یادگیری ماشین محسوب می‌شوند به‌منظور پیش‌بینی مقاومت مارشال آسفالت استفاده شد. برای این منظور، نتایج آزمایشات 2000 نمونه آسفالت کارخانه آسفالت سازمان عمران شهرداری مشهد شامل دانه‌بندی مصالح، درصد شکستگی مصالح، درصد جذب قیر، وزن مخصوص قیر، وزن مخصوص حقیقی مصالح، درصد قیر مصرفی، نسبت درصد وزنی فیلر به قیر مؤثر و مقاومت مارشال آسفالت برای آموزش و ارزیابی مدل‌ها بکاررفته است. پس ساخت مدل و ارزیابی آن‌ها، مقدار R2 برای روش ماشین بردار پشتیبان برابر 5/87 و برای جنگل تصادفی 69/82 به دست آمده است. همچنین مقادیر MAPE، RMES و SDE برای SVM به ترتیب معادل 1073/3، 042/40 و 0208/0 و برای RF به ترتیب معادل 1641/3، 870/41 و 0211/0 محاسبه گشت. نتایج حاصله نشان دهنده کارآمدی مدل‌های استفاده‌شده در برابر روش‌های آزمایشگاهی برای پیش‌بینی مقاومت مارشال آسفالت است که روش SVM عملکرد مطلوب‌تری را نسبت به RF داراست. از روش‌های یادگیری ماشین می‌توان برای پیش‌بینی سایر پارامترهای طرح اختلاط آسفالت استفاده و زمان، هزینه و خطای انسانی آزمایشات را کاهش داد.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Predicting Marshall Asphalt Stability Using Supervised Machine Learning Algorithms, support vector machine and random forest

نویسندگان [English]

  • Hassan Hosseinzadeh 1
  • Alireza Hasani 2
  • Sina Arman 3
  • Amir Siavash Hejazi 3
1 M.Sc., Grad., Civil Engineering, Eqbal Lahori IHE, Mashhad, Iran.
2 M.Sc., Student, Civil Engineering, Eqbal Lahori IHE, Mashhad, Iran.
3 M.Sc., Grad., Civil Engineering, Islamic Azad University, Mashhad, Iran.
چکیده [English]

Road construction and maintenance organizations usually use certain criteria to qualify asphalt mixtures before use in construction. One of the most important features that is measured in the asphalt mixing and quality control plan is the Marshall asphalt stability. This study examines the use of machine learning techniques to predict Marshall asphalt stability. Due to the time-consuming and costly process of asphalt production and quality control, it is necessary to use new methods in this process. In this research, two supervised support vector machine and random forest algorithms, which are machine learning algorithms, were used to predict the marshal asphalt stability. For this purpose, the test results of 2000 asphalt samples including Granulation of aggregate, Fracture percentage, bitumen adsorption, bitumen specific gravity, actual specific gravity of materials, bitumen consumption percentage, dust to effective binder ratio and Marshall asphalt stability for training and evaluation Models were used. After modeling and evaluation, the value of R2 is 87.5 for the support vector machine method and 82.69 for the random forest. Also, MAPE, RMES and SDE values for SVM were 3.1073, 40.042 and 0.0208, respectively, and for RF were 3.1641, 41.870 and 0.0211, respectively. The results show the efficiency of the models used against laboratory methods for predicting marshal asphalt stability, which SVM method has a better performance than RF. Machine learning methods can be used to predict other parameters of the asphalt mixing plan and reduce the time, cost and human error of the tests.

کلیدواژه‌ها [English]

  • Asphalt
  • machine learning
  • Random forest
  • Support vector machine
  • Marshal stability

مراجع

-Aggarwal, C. C., (2017), "An introduction to outlier analysis", In Outlier analysis, Springer. pp. 1-3
-Ali, N. S., (2006), "Flexural Behavior Compared with Marshall Stability of Asphalt Paving Mixtures", Journal of Zankoy Sulaimani, 9.
-Aljassar, A. H., Metwali, S., & Ali, M. A., (2004), "Effect of filler types on Marshall stability and retained strength of asphalt concrete", International Journal of Pavement Engineering, 5(1), pp.47-51.
-Amershi, S., Begel, A., Bird, C., DeLine, R., Gall, H., Kamar, E., Nagappan, N., Nushi, B., & Zimmermann, T., (2019), "Software engineering for machine learning: A case study", IEEE/ACM 41st International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP),
-Andrew, A. M., (2001), "An introduction to support vector machines and other kernel based learning methods", Kybernetes.
-Aroef, C., Rivan, Y., & Rustam, Z., (2020), "Comparing random forest and support vector machines for breast cancer classification. Telkomnika, 18(2), pp.815-821.
-ASTM D5444-15, "Standard Test Method for Mechanical Size Analysis of Extracted Aggregate", ASTM International, West Conshohocken, PA, 2015, www.astm.org.
-ASTM D5821-13, (2017), "Standard Test Method for Determining the Percentage of Fractured Particles in Coarse Aggregate", ASTM International, West Conshohocken, PA, www.astm.org.
-ASTM D4469-17, (2017), "Standard Practice for Calculating Percent Asphalt Absorption by the Aggregate in Asphalt Mixtures", ASTM International, West Conshohocken, PA, www.astm.org.
-ASTM D70 / D70M-21, (2021), "Standard Test Method for Specific Gravity and Density of Semi-Solid Asphalt Binder (Pycnometer Method)", ASTM International, West Conshohocken, PA, www.astm.org.
-ASTM C29 / C29M-17a, (2017), "Standard Test Method for Bulk Density, (“Unit Weight”) and Voids in Aggregate, ASTM International, West Conshohocken, PA, www.astm.org.
-ASTM D2172 / D2172M-17e1, (2017), "Standard Test Methods for Quantitative Extraction of Asphalt Binder from Asphalt Mixtures", ASTM International, West Conshohocken, PA, www.astm.org.
-ASTM D6927-15, (2015), "Standard Test Method for Marshall Stability and Flow of Asphalt Mixtures", ASTM International, West Conshohocken, PA, www.astm.org
-ASTM D3515-01, (2017), "Standard Specification for Hot-Mixed", Hot-Laid Bituminous Paving Mixtures.
-Breiman, L., Cutler, A., Liaw, A., & Wiener, M., (2015), "Package random forest version 4, pp.6–12.
-Burkov, A., (2020), "Machine Learning Engineering", True Positive Inc.
-Cansiz, O. F., & Askar, D. D., (2018), "Developing Multi Linear Regression Models for Estimation of Marshall Stability", International Journal of Advanced Engineering Research and Science, 5, 6.
-Cardoso-Fernandes, J., Teodoro, A., Lima, A., & Roda-Robles, E., (2019), "Evaluating the performance of support vector machines (SVMs) and random forest (RF) in
Li-pegmatite mapping: Preliminary results", Earth Resources and Environmental Remote Sensing/GIS Applications X.
-Chicco, D., Warrens, M. J., & Jurman, G., (2021), "The coefficient of determination
R-squared is more informative than SMAPE", MAE, MAPE, MSE and RMSE in regression analysis evaluation, PeerJ Computer Science, 7, e623.
-Choubane, B., Page, G. C., & Musselman, J. A., (2000), "Suitability of asphalt pavement analyzer for predicting pavement rutting", Transportation Research Record, 1723(1), pp.107-115.
-Chourasiya, S., & Jain, S., (2019), "A Study Review On Supervised Machine Learning Algorithms", SSRG International Journal of Computer Science and Engineering (SSRG-IJCSE), 6.
-Cortes, C., & Vapnik, V., (1995), "Support vector networks. Machine learning, 20(3), pp.273-297.
-Devore, J. L., (2011), "Probability and Statistics for Engineering and the Sciences", Cengage learning.
-Filzmoser, P., Garrett, R. G., & Reimann, C., (2005), "Multivariate outlier detection in exploration geochemistry", Computers & geosciences, 31(5), pp.579-587.
-Gareth, J., Daniela, W., Trevor, H., & Robert, T., (2013), "An introduction to statistical learning: with applications in R. Spinger.
-Ghorbanzadeh, O., Rostamzadeh, H., Blaschke, T., Gholaminia, K., & Aryal, J., (2018), "A new GIS-based data mining technique using an adaptive neuro-fuzzy inference system (ANFIS) and k-fold cross-validation approach for land subsidence susceptibility mapping", Natural Hazards, 94(2), pp.497-517.
-Goodfellow, I., Bengio, Y., & Courville, A., (2016), "Machine learning basics", Deep learning, 1(7), pp.98-164.
-Han, H., Guo, X., & Yu, H., (2016), "Variable selection using mean decrease accuracy and mean decrease gini based on random forest", 2016 7th ieee international conference on software engineering and service science (icsess).
-Harris, J., & Grunsky, E. C., (2015), "Predictive lithological mapping of Canada's North using Random Forest classification applied to geophysical and geochemical data", Computers & geosciences, 80, pp.9-25.
-Hawkins, D., (1980), "A single outlier in normal samples", In Identification of Outliers Springer, pp. 27-41.
-Jakkula, V., (2006), "Tutorial on support vector machine (svm)", School of EECS, Washington State University, 37.
-Jayalakshmi, T., & Santhakumaran, A. (2011), "Statistical normalization and back propagation for classification", International Journal of Computer Theory and Engineering, 3(1), pp.1793-8201.
-Jordan, M. I., & Mitchell, T. M., (2015), "Machine learning: Trends, perspectives, and prospects", Science, 349(6245), pp.255-260.
-Kanevski, M., (2009), "Machine learning for spatial environmental data: theory, applications, and software", EPFL press.
-Karahancer, S., Capali, B., Eriskin, E., Morova, N., Serin, S., Saltan, M., Terzi, S., & Kucukcapraz, D. O., (2016), "Marshall stability estimating using artificial neural network with polyparaphenylene terephtalamide fibre rate", International Symposium on INnovations in Intelligent SysTems and Applications (INISTA).
-Lary, D. J., Alavi, A. H., Gandomi, A. H., & Walker, A. L., (2016), "Machine learning in geosciences and remote sensing", Geoscience Frontiers, 7(1), pp.3-10.
-Liaw, A., & Wiener, M., (2002), "Classification and regression by random Forest. R news, 2(3), pp.18-22.
-Liu, H., & Motoda­, H., (2012), "Feature selection for knowledge discovery and data mining, Vol. 454, Springer Science & Business Media.
-Liu, X., (1998), "Strategies for outlier analysis", IEE Colloquium on Knowledge Discovery and Data Mining, Digest No. 1998/310.
-Longjun, D., Xibing, L., Ming, X., & Qiyue, L., (2011), "Comparisons of random forest and support vector machine for predicting blasting vibration characteristic parameters", Procedia Engineering, 26, pp.1772-1781.
-Majidifard, H., Adu-Gyamfi, Y., & Buttlar, W. G., (2020), "Deep machine learning approach to develop a new asphalt pavement condition index", Construction and building materials, 247, 118513.
-Meyer, D., Dimitriadou, E., Hornik, K., Weingessel, A., Leisch, F., Chang, C. C., Lin, C. C., & Meyer, M. D., (2019), "Package ‘e1071’, The R Journal.
-Mitchell, T. M., (1997), "Machine Learning, Burr Ridge, IL:MCGraw Hill.
-Mohamad, I. B., & Usman, D., (2013), "Standardization and its effects on K-means clustering algorithm", Research Journal of Applied Sciences, Engineering and Technology, 6(17), pp.3299-3303.
-Mohri, M., Rostamizadeh, A., & Talwalkar, A., (2018), "Foundations of Machine Learning. Adaptive Computation and Machine Learning series", In: MIT Press.
-Ogundipe, O. M., (2016), "Marshall stability and flow of lime-modified asphalt concrete. Transportation Research Procedia", 14, pp.685-693.
-Oshiro, T. M., Perez, P. S., & Baranauskas, J. A., (2012), "How many trees in a random forest? International workshop on machine learning and data mining in pattern recognition".
-Ozgan, E., (2009)," Fuzzy logic and statistical-based modelling of the Marshall Stability of asphalt concrete under varying temperatures and exposure times", Advances in engineering software, 40(7), pp.527-534.
-Özgan, E., & Saruhan, H., (2010), "Modeling of asphalt concrete via simulated annealing", Advances in Engineering Software, 41(4), pp.680-683.
-Rashwan, N. K., (2015), "Evaluation of aggregate and mineral filler types on characteristics of hot mix aspha", International Journal of Civil Engineering and Technology, 6.
-Refaeilzadeh, P., Tang, L., & Liu, H., (2009), "Cross-validation, Encyclopedia of database systems", 5, pp.532-538.
-Shabankareh, M., & Hezarkhani, A., (2017), "Application of support vector machines for copper potential mapping in Kerman region", Iran. Journal of African Earth Sciences, 128, pp.116-126.
-Shawe-Taylor, J., & Cristianini, N., (2000), "An introduction to support vector machines and other kernel-based learning methods,Vol. 204.
-Tiwari, S., Babbar, R., & Kaur, G., (2018), "Performance evaluation of two ANFIS models for predicting water quality Index of River Satluj (India)", Advances in Civil Engineering.
-Wang, H., Ma, C., & Zhou, L., (2009), "A brief review of machine learning and its application, 2009 international conference on information engineering and computer science,
-Wellmer, F. W., (2012), "Statistical evaluations in exploration for mineral deposits", Springer Science & Business Media.
-Yang, Q., Li, X., & Shi, X., (2008), "Cellular automata for simulating land use changes based on support vector machines", Computers & geosciences, 34(6), pp.592-602.
-Zhang, R., Zhou, M., Gong, X., He, X., Qian, W., Qin, S., & Zhou, A., (2015), "Detecting anomaly in data streams by fractal model", World Wide Web, 18(5), pp.1419-1441.
-Zhang, X. D., (2020), "Machine learning, In A Matrix Algebra Approach to Artificial Intelligence", Springer, pp. 223-440.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

فایل ها

هم رسانی

ارجاع به این مقاله

آمار