Mechanical performance prediction of asphalt mixtures: a baseline study of linear and non-linear regression compared with neural network modeling

• Autorzy: Baldo Nicola , Rondinella Fabio , Daneluz Fabiola , Vacková Pavla , Valentin Jan , Gajewski Marcin , Król Jan

Identyfikatory

DOI

10.7409/rabdim.025.001

Warianty tytułu

PL

Przewidywanie właściwości mechanicznych mieszanek mineralno-asfaltowych: badanie modelowania sieciami neuronowymi w porównaniu z metodami referencyjnymi regresji liniowej i nieliniowej

• Języki publikacji: EN

Abstrakty

EN

Accurate predictions of asphalt mixtures’ mechanical performance are crucial to improve the conventional mix-design procedures and to optimize both pavements’ performance and service life. This research explores this issue by means of a comparative analysis between different modeling approaches: conventional regressions, both linear and non-linear, and artificial neural networks. The former are widely used but may lack the flexibility to capture complex relationships between testing conditions and the corresponding mechanical behavior. The latter represent promising alternatives due to their capability to successfully model non-linear interactions between variables. This research compares the predictive accuracy of these different modeling approaches using experimental data resulting from 4-point bending tests carried out under several temperatures and loading frequencies. The outcomes suggest that neural networks outperform conventional regression models in capturing complex relationships, highlighting the strengths and limitations of each modeling approach and providing insights for selecting optimal models in road pavement engineering applications.

PL

Dokładne przewidywanie właściwości mechanicznych mieszanek mineralno-asfaltowych jest kluczowe w doskonaleniu konwencjonalnych procedur projektowania mieszanek oraz optymalizacji ich właściwości i trwałości nawierzchni. Niniejsze badania dotyczą pogłębionej analizy tego zagadnienia z wykorzystaniem analizy porównawczej dwóch różnych podejść do modelowania: konwencjonalnymi metodami regresji liniowej i nieliniowej oraz metodą sztucznych sieci neuronowych. Pierwsze podejście z konwencjonalnymi metodami regresyjnymi jest szeroko stosowane, ale może mieć pewne ograniczenia co do zastosowania, szczególnie tam, gdzie należy uwzględnić złożone zależności między warunkami badania, a odpowiadającymi im wyjściowymi właściwościami mechanicznymi. Drugie podejście stanowi obiecującą alternatywę, ze względu na przydatność sztucznych sieci neuronowych w modelowaniu nieliniowych interakcji między zmiennymi. Niniejsze badania porównują dokładność przewidywania różnymi metodami predykcyjnymi właściwości mechanicznych mieszanek mineralno-asfaltowych, wykorzystując dane eksperymentalne uzyskane w badaniu cztero-punktowego zginania przeprowadzonych w różnych temperaturach i częstotliwościach obciążenia. Wyniki analiz wskazują na przewagę sieci neuronowych nad konwencjonalnymi metodami modeli regresyjnych ze względu na złożoność analizowanych zależności. Dodatkowymi efektami przeprowadzonych badań jest wskazanie mocnych i słabych strony każdego podejścia do modelowania oraz praktyczne rekomendacje dotyczące wyboru optymalnych modeli do zastosowania w praktyce inżynierskiej budownictwa drogowego.

Słowa kluczowe

EN

artificial neural networks; asphalt mixtures; linear regression; machine learning; mechanical behaviour; non-linear regression

PL

sztuczne sieci neuronowe; mieszanka mineralno-asfaltowa; regresja liniowa; uczenie maszynowe; właściwości mechaniczne; regresja nieliniowa

• Wydawca: Instytut Badawczy Dróg i Mostów
• Czasopismo: Roads and Bridges - Drogi i Mosty
• Rocznik: 2025
• Tom: Vol. 24, no. 1
• Strony: 27--35
• Opis fizyczny: Bibliogr. 40 poz., rys., tab.

Twórcy

autor

Baldo Nicola

• University of Udine, Polytechnic Department of Engineering and Architecture, Via del Cotonificio 114, 33100 Udine, Italy

• https://orcid.org/0000-0002-5627-9763

autor

Rondinella Fabio

• University of Udine, Polytechnic Department of Engineering and Architecture, Via del Cotonificio 114, 33100 Udine, Italy

• https://orcid.org/0000-0002-8702-5555

autor

Daneluz Fabiola

• University of Udine, Polytechnic Department of Engineering and Architecture, Via del Cotonificio 114, 33100 Udine, Italy

• https://orcid.org/0000-0002-8305-3911

autor

Vacková Pavla

• Czech Technical University, Faculty of Civil Engineering, Thákurova 7, 166 29 Prague, Czech Republic

• https://orcid.org/0000-0003-4636-8356

autor

Valentin Jan

• Czech Technical University, Faculty of Civil Engineering, Thákurova 7, 166 29 Prague, Czech Republic

• https://orcid.org/0000-0001-9155-1921

autor

Gajewski Marcin

• Warsaw University of Technology, Faculty of Civil Engineering, 16 Armii Ludowej Av., 00-637 Warsaw, Poland

• https://orcid.org/0000-0002-3171-8504

autor

Król Jan

• Warsaw University of Technology, Faculty of Civil Engineering, 16 Armii Ludowej Av., 00-637 Warsaw, Poland

• https://orcid.org/0000-0001-8728-3530

Bibliografia

• 1. Gandomi A.H., Alavi A.H., Mirzahosseini M.R., Nejad F.M.: Nonlinear genetic-based models for prediction of flow number of asphalt mixtures. Journal of Materials in Civil Engineering, 23, 2011, 248-263, DOI: 10.1061/(ASCE)MT.1943-5533.0000154
• 2. Alavi A.H., Ameri M., Gandomi A.H., Mirzahosseini M.R.: Formulation of flow number of asphalt mixes using a hybrid computational method. Construction and Building Materials, 25, 2011, 1338-1355, DOI: 10.1016/j.conbuildmat.2010.09.010
• 3. Dias J.L.F., Picado-Santos L., Capitão S.: Mechanical performance of dry process fine crumb rubber asphalt mixtures placed on the Portuguese road network. Construction and Building Materials, 73, 2014, 247-254, DOI: 10.1016/j.conbuildmat.2014.09.110
• 4. Pasandín A., Pérez I.: Overview of bituminous mixtures made with recycled concrete aggregates. Construction and Building Materials, 74, 2015, 151-161, DOI: 10.1016/j.conbuildmat.2014.10.035
• 5. Masad E., Tashman L., Little D., Zbib H.: Viscoplastic modeling of asphalt mixes with the effects of anisotropy, damage and aggregate characteristics. Mechanics of Materials, 37, 12, 2005, 1242-1256, DOI: 10.1016/j.mechmat.2005.06.003
• 6. Giunta M., Pisano A.A.: One dimensional viscoelastoplastic constitutive model for asphalt concrete. Multidiscipline Modeling in Materials and Structures, 2, 2, 2006, 247-264, DOI: 10.1163/157361106776240761
• 7. Erkens S.M.J.G., Liu X., Scarpas A.: 3D finite element model for asphalt concrete response simulation. International Journal of Geomechanics, 2, 3, 2002, 305-330, DOI: 10.1061/(ASCE)1532-3641(2002)2:3(305)
• 8. Costanzi M., Cebon D.: Generalized phenomenological model for the viscoelasticity of idealized asphalts. Journal of Materials in Civil Engineering, 26, 3, 2014, 399-410, DOI: 10.1061/(ASCE)MT.1943-5533.0000842
• 9. Collop A.C., McDowell G.R., Lee Y.: Use of the distinct element method to model the deformation behavior of an idealized asphalt mixture. International Journal of Pavement Engineering, 5, 1, 2004, 1-7, DOI: 10.1080/10298430410001709164
• 10. Abbas A., Masad E., Papagiannakis T., Harman T.: Micromechanical modelling of the viscoelastic behavior of asphalt mixtures using the discrete-element method. International Journal of Geomechanics, 7, 2, 2007, 131-139, DOI: 10.1061/(ASCE)1532-3641(2007)7:2(131)
• 11. Dondi G., Simone A., Vignali V., Manganelli G.: Numerical and experimental study of granular mixes for asphalts. Powder Technology, 232, 2012, 31-40, DOI: 10.1016/j.powtec.2012.07.057
• 12. Majidifard H., Jahangiri B., Buttlar W.G., Alavi A.H.: New machine learning-based prediction models for fracture energy of asphalt mixtures. Measurement, 135, 2019, 438-451, DOI: 10.1016/j.measurement.2018.11.081
• 13. Ghafari S., Ehsani M., Nejad F.M.: Prediction of low-temperature fracture resistance curves of unmodified and crumb rubber modified hot mix asphalt mixtures using a machine learning approach. Construction and Building Materials, 314, 2022, Article ID: 125332. DOI: 10.1016/j.conbuildmat.2021.125332
• 14. Friedman J., Hastie T., Tibshirani R.: Regularization Paths for Generalized Linear Models via Coordinate Descent. Journal of Statistical Software, 33, 1, 2008, 1-22, DOI: 10.18637/jss.v033.i01
• 15. Li Z., Liu F., Yang W., Peng S., Zhou J.: A survey of convolutional neural networks: analysis, applications, and prospects. IEEE Transactions on Neural Networks and Learning Systems, 33, 12, 2021, 6999-7019, DOI: 10.1109/TNNLS.2021.3084827
• 16. Aizenbud Y., Sober B.: Approximating the span of principal components via iterative least-squares. Applied and Computational Harmonic Analysis (ACHA), 63, 2023, 84-92, DOI: 10.1016/j.acha.2022.11.006
• 17. Meng K., Gai Y., Wang X., Yao M., Sun X.: Transfer learning for high-dimensional linear regression via the elastic net. Knowledge-Based Systems, 304, 2024, Article ID: 112525, DOI: 10.1016/j.knosys.2024.112525
• 18. Seno M.E., Zeini H.A., Imran H., Noori M., Henedy S.N., Ghazaly N.M.: Advancing in creep index of soil prediction: A groundbreaking machine learning approach with Multivariate Adaptive Regression Splines. Results in Materials, 24, 2024, Article ID: 100641, DOI: 10.1016/j.rinma.2024.100641
• 19. Rondinella F., Oreto C., Abbondati F., Baldo N.: Laboratory Investigation and Machine Learning Modeling of Road Pavement Asphalt Mixtures Prepared with Construction and Demolition Waste and RAP. Sustainability, 15, 23, 2023, Article ID: 16337, DOI: 10.3390/su152316337
• 20. Rondinella F., Daneluz F., Vacková P., Valentin J., Baldo N.: Volumetric Properties and Stiffness Modulus of Asphalt Concrete Mixtures Made with Selected Quarry Fillers: Experimental Investigation and Machine Learning Prediction. Materials, 16, 3, 2023, Article ID: 1017, DOI: 10.3390/ma16031017
• 21. Liu J., Liu F., Zheng C., Fanijo E.O., Wang L.: Improving asphalt mix design considering international roughness index of asphalt pavement predicted using autoencoders and machine learning. Construction and Building Materials, 360, 2022, Article ID: 129439, DOI: 10.1016/j.conbuildmat.2022.129439
• 22. Pattanaik M.L., Kumar S., Choudhary R., Agarwal M., Kumar B.: Predicting the abrasion loss of open-graded friction course mixes with EAF steel slag aggregates using machine learning algorithms. Construction and Building Materials, 321, 2022, Article ID: 126408, DOI: 10.1016/j.conbuildmat.2022.126408
• 23. Tiwari N., Rondinella F., Satyam N., Baldo N.: Alternative Fillers in Asphalt Concrete Mixtures: Laboratory Investigation and Machine Learning Modeling towards Mechanical Performance Prediction. Materials, 16, 2, 2023, Article ID: 807, DOI: 10.3390/ma16020807
• 24. Wang J., Zhang R., Wang R., Bahia H., Huang W., Wang D., Cai W.: Prediction of the fundamental viscoelasticity of asphalt mixtures using ML algorithms. Construction and Building Materials, 442, 2024, Article ID: 137573. DOI: 10.1016/j.conbuildmat.2024.137573
• 25. SIST EN 12591: 2009 Bitumen and Bituminous Binders – Specifications for Paving Grade Bitumens. European Committee for Standardization: Brussels, Belgium
• 26. ČSN 73 6121 (736121): 2019 Stavba Vozovek – Hutněné Asfaltové Vrstvy – Provádění a Kontrola Shody. Česká Technická Norma: Prague, Czech Republic
• 27. SIST EN 12697: 2019 Part 26, Bituminous Mixtures – Test Methods for Hot Mix Asphalt-Stiffness. European Committee for Standardization: Brussels, Belgium
• 28. James G., Witten D., Hastie T., Tibshirani R.: An Introduction to Statistical Learning with Applications in R. Springer: New York, NY, USA, 2013
• 29. Dismuke C., Lindrooth R.: Ordinary least squares. Methods and designs for outcomes research, 93, 1, 2006, 93-104
• 30. Melkumova L.E., Shatskikh S.Y.: Comparing Ridge and LASSO estimators for data analysis. Procedia Engineering, 201, 2017, 746-755, DOI: 10.1016/j.proeng.2017.09.615
• 31. Heiberger R.M., Neuwirth E.: Polynomial regression. R Through Excel: A Spreadsheet Interface for Statistics, Data Analysis, and Graphics, 2009, 269-284, DOI: 10.1007/978-1-4419-0052-4
• 32. McCulloch W.S., Pitts W.: A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics, 5, 1943, 115-133, DOI: 10.1007/BF02478259
• 33. Moayedi H., Mosallanezhad M., Rashid A.S.A., Jusoh W.A.W., Muazu M.A.: A systematic review and meta-analysis of artificial neural network application in geotechnical engineering: Theory and applications. Neural Computing and Applications, 32, 2020, 495-518, DOI: 10.1007/s00521-019-04109-9
• 34. Rondinella F., Oreto C., Abbondati F., Baldo N.: A Deep Neural Network Approach towards Performance Prediction of Bituminous Mixtures Produced Using Secondary Raw Materials. Coatings, 14, 8, 2024, Article ID: 922, DOI: 10.3390/coatings14080922
• 35. Berahas A.S., Nocedal J., Takác M.: A multi-batch L-BFGS method for machine learning. Advances in Neural Information Processing Systems, 29, 2016, 1055-1063, DOI: 10.48550/arXiv.1605.06049
• 36. Rumelhart D.E., Hinton G.E., Williams R.J.: Learning representations by back-propagating errors. Nature, 323, 1986, 533-536, DOI: 10.1038/323533a0
• 37. Kingma D.P., Ba J.: Adam: A Method for Stochastic Optimization. arXiv, 1412.6980, 2014, DOI: 10.48550/arXiv.1412.6980
• 38. Kearns M., Valiant L.: Cryptographic limitations on learning boolean formulae and finite automata. Journal of the ACM (JACM), 41, 1, 1994, 67-95, DOI: 10.1145/174644.174647
• 39. Al-Obeidat F., Spencer B., Alfandi O.: Consistently accurate forecasts of temperature within buildings from sensor data using ridge and lasso regression. Future Generation Computer Systems, 110, 2020, 382-392, DOI: 10.1016/j.future.2018.02.035
• 40. Rondinella F., Daneluz F., Hofko B., Baldo N.: Improved predictions of asphalt concretes’ dynamic modulus and phase angle using decision-tree based categorical boosting model. Construction and Building Materials, 400, 2023, Article ID: 132709, DOI: 10.1016/j.conbuildmat.2023.132709