車轍為鋪面的主要破壞之一，鋪面的車轍的來源之一為瀝青混凝土材料產生了永久變形，而瀝青混凝土材料之永久變形與其材料之抗剪強度高度相關，因此如何設計出具有高抗車轍效果的瀝青混凝土，為工程師長期來追求的目標，車轍不僅影響鋪面的壽命和性能，還可能對道路使用者的安全造成威脅，因此針對它的預測和治理尤為重要。透過這些方法，可以減少評估的成本和時間，從而更有效地確保鋪面的安全和持久性。為了解決這樣的問題，需要建立一套可以快速且有效地預測鋪面車轍形成的模型。研究遇到的問題在於如何利用級配曲線、初始粒料含量、回收粒料含量及瀝青含油量的資料，預測漢堡輪跡車轍成效試驗的車轍深度值。於是本研究建立一套基於資料驅動的機器學習神經網路模型，以預測並評估瀝青混凝土試體在漢堡輪跡車轍成效試驗的車轍深度值。本研究使用神經網路演算法處理已收集之資料。漢堡輪跡車轍成效試驗的條件為每分鐘52次頻率下，以50度C溫度進行往返滾壓，直到車轍深度達到12.5mm或循環次數達20,000次。該模型不僅成功預測漢堡輪跡車轍試驗的結果，在訓練流程最好的表現指標R2值為0.928，最佳化模型有著2層隱藏層，每層隱藏層40個神經元節點，應用ReLU活化函數，搭配lbfgs優化器，MSE收斂函數。在未經訓練的數據集也有準確預測的潛力，期望在未來能取代實際的漢堡輪跡車轍試驗。

Predicting the permanent deformation of asphalt paving accurately is difficult due to the complex behavior of asphalt paving materials under various loading conditions, pavement structures, and environmental conditions. To make predictions, one needs to find the mathematical relationship between input and output data and use a method that is both accurate and simple. Studying the behavior of asphalt pavements under the influence of various environmental and structural parameters will greatly help engineers in the design and maintenance of asphalt pavements. In this regard, the use of artificial neural networks can greatly simplify operations in data engineering science, while ensuring that comprehensive studies cover all or most of the parameters affecting pavement behavior. As the main damage to pavement, rutting not only affects the life and performance of pavement, but also may pose a threat to the safety of road users, so its prediction and treatment are particularly important. Through these methods, we can reduce the cost and time of assessment, so as to ensure the safety and durability of pavement more effectively. In order to solve such problems, it is necessary to establish a set of models that can quickly and effectively predict the formation of pavement ruts. The problem encountered in the research is how to use the data of gradation curve, initial aggregate content, recycled aggregate content and asphalt oil content to predict the rut depth value of the Hamburg wheel track test. Therefore, this study established a set of data-driven machine learning neural network models to predict and evaluate the rut depth value of asphalt concrete specimens in the Hamburg Wheel Track Test. This study uses a neural network algorithm to process the collected data. The condition of Hamburg wheel track test is 52 times per minute, reciprocating rolling at 50 degrees C until the rut depth reaches 12.5mm or the number of cycles reaches 20,000 times. The model not only successfully predicted the results of the Hamburg rutting and wheel track test, but also had the best performance index R2 value of 0.928 in the training process. The optimized model has 2 hidden layers, each hidden layer has 40 neuron nodes, and the ReLU activation function is applied. , with lbfgs optimizer, MSE convergence function. There is also potential for accurate predictions on the untrained dataset, which is expected to replace the actual Hamburg rutting test in the future.

Cano-Ortiz, S., Pascual-Munoz, P., and Castro-Fresno, D. (2022). "Machine learning algorithms for monitoring pavement performance." Autom. Constr., 139, 16.
Majidifard, H., Jahangiri, B., Buttlar, W. G., and Alavi, A. H. (2019). "New machine learning-based prediction models for fracture energy of asphalt mixtures." Measurement, 135, 438-451.
Rahman, S., Bhasin, A., and Smit, A. (2021). "Exploring the use of machine learning to predict metrics related to asphalt mixture performance." Constr. Build. Mater., 295, 11.
Upadhya, A., Thakur, M. S., Mashat, A., Gupta, G., and Abdo, M. S. (2022). "Prediction of Binder Content in Glass Fiber Reinforced Asphalt Mix Using Machine Learning Techniques." IEEE Access, 10, 33866-33881.
Midtfjord, A. D., De Bin, R., and Huseby, A. B. (2022). "A decision support system for safer airplane landings: Predicting runway conditions using XGBoost and explainable AI." Cold Reg. Sci. Tech., 199, 15.
Dutta, B. (2021). "A Classification and Regression Tree (CART) Algorithm." <https://www.analyticssteps.com/blogs/classification-and-regression-tree-cart-algorithm>.
Xu, Y., and Zhang, Z. M. (2022). "Review of Applications of Artificial Intelligence Algorithms in Pavement Management." J. Transp. Eng. Pt. B-Pavements, 148(3), 18.
Sholevar, N., Golroo, A., and Esfahani, S. R. (2022). "Machine learning techniques for pavement condition evaluation." Autom. Constr., 136, 17.
Singhal, N., and Prasad, L. (2022). "Sensor based vehicle detection and classification - a systematic review." Int. J. Eng. Syst. Model. Simul., 13(1), 38-60.
Cano-Ortiz, S., Pascual-Munoz, P., and Castro-Fresno, D. (2022). "Machine learning algorithms for monitoring pavement performance." Autom. Constr., 139, 16.
Probst, P., Boulesteix, A.-L., and Bischl, B. (2019). "Tunability: Importance of hyperparameters of machine learning algorithms." The Journal of Machine Learning Research, 20(1), 1934-1965.
Bergstra, J., and Bengio, Y. (2012). "Random search for hyper-parameter optimization." J. Mach. Learn. Res., 13(null), 281–305.
Justo-Silva, R., Ferreira, A., and Flintsch, G. (2021). "Review on Machine Learning Techniques for Developing Pavement Performance Prediction Models." Sustainability, 13(9), 5248.

Shafabakhsh, G. H., Ani, O. J., and Talebsafa, M. (2015). "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, 136-143.
Azarhoosh, A. R., Hamedi, G. H., and Abandansari, H. F. (2018). "Providing Laboratory Rutting Models for Modified Asphalt Mixes with Different Waste Materials." Periodica Polytechnica-Civil Engineering, 62(2), 308-317.
Kamboozia, N., Ziari, H., and Behbahani, H. (2018). "Artificial neural networks approach to predicting rut depth of asphalt concrete by using of visco-elastic parameters." Construction and Building Materials, 158, 873-882.
Probst, P., Boulesteix, A.-L., and Bischl, B. (2019). "Tunability: Importance of hyperparameters of machine learning algorithms." The Journal of Machine Learning Research, 20(1), 1934-1965.
Azari, D. H., Laboratory, A. M. R., and Gaithersburg, M. (2014). "PRECISION ESTIMATES OF AASHTO T 324,“HAMBURG WHEELTRACK TESTING OFCOMPACTED HOT MIX ASPHALT (HMA)” ", 48.
Awed, A. M., Tarbay, E. W., El-Badawy, S. M., and Azam, A. M. (2022). "Performance characteristics of asphalt mixtures with industrial waste/by-product materials as mineral fillers under static and cyclic loading." Road Materials and Pavement Design, 23(2), 335-357.
Zhou, F., Im, S., Sun, L., and Scullion, T. (2017). "Development of an IDEAL cracking test for asphalt mix design and QC/QA." Road Materials and Pavement Design, 18(sup4), 405-427.
Lv, Q., Huang, W., Zheng, M., Sadek, H., Zhang, Y., and Yan, C. (2020). "Influence of gradation on asphalt mix rutting resistance measured by Hamburg Wheel Tracking test." Construction and Building Materials, 238, 117674.
Hasan, M. M., Ahmad, M., Hasan, M. A., Faisal, H. M., and Tarefder, R. A. (2019). "Laboratory performance evaluation of fine and coarse-graded asphalt concrete mix." Journal of Materials in Civil Engineering, 31(11), 04019259.
Sreedhar, S., and Coleri, E. (2018). "Effects of binder content, density, gradation, and polymer modification on cracking and rutting resistance of asphalt mixtures used in Oregon." Journal of Materials in Civil Engineering, 30(11), 04018298.
Amelian, S., Abtahi, S. M., and Hejazi, S. M. (2014). "Moisture susceptibility evaluation of asphalt mixes based on image analysis." Construction and Building Materials, 63, 294-302.
Zhou, F., Hu, S., and Newcomb, D. (2020). "Development of a performance-related framework for production quality control with ideal cracking and rutting tests." Construction and Building Materials, 261, 120549.
Apeagyei, A., Buttlar, W., and Dempsey, B. "Moisture damage evaluation of asphalt mixtures using AASHTO T283 and DC (T) fracture test." Proc., Proceedings of the 10th International Conference on Asphalt Pavements (CD-ROM).
Kusam, A., Malladi, H., Tayebali, A. A., and Khosla, N. P. (2017). "Laboratory evaluation of workability and moisture susceptibility of warm-mix asphalt mixtures containing recycled asphalt pavements." Journal of Materials in Civil Engineering, 29(5), 04016276.
Mogawer, W. S., Stuart, K., Austerman, A. J., and Soliman, A. A. (2018). "Investigating the Performances of Plant-Produced High-Reclaimed Asphalt Pavement Content Warm Mix Asphalts." Transportation Research Record, 2672(28), 130-142.
Afaf, A. (2014). "Effect of aggregate gradation and type on hot asphalt concrete mix properties." Journal of Engineering Sciences, 42(3), 567-574.
Radhakrishnan, V., Chowdari, G. S., Reddy, K. S., and Chattaraj, R. (2019). "Evaluation of wheel tracking and field rutting susceptibility of dense bituminous mixes." Road Materials and Pavement Design, 20(1), 90-109.
Mohammad, L. N., Wu, Z., Obulareddy, S., Cooper, S., and Abadie, C. (2006). "Permanent deformation analysis of hot-mix asphalt mixtures with simple performance tests and 2002 mechanistic–empirical pavement design software." Transportation Research Record, 1970(1), 133-142.
Korayem, A. H., Ziari, H., Hajiloo, M., Abarghooie, M., and Karimi, P. (2020). "Laboratory evaluation of stone mastic asphalt containing amorphous carbon powder as filler material." Construction and Building Materials, 243, 118280.
Arshad, A. K., Masri, K. A., Ahmad, J., and Samsudin, M. S. (2017). "Investigation on Moisture Susceptibility and Rutting Resistance of Asphalt Mixtures incorporating Nanosilica Modified Binder." Pertanika Journal of Science & Technology, 25.
Kok, B. V., and Kuloglu, N. (2007). "The effects of different binders on mechanical properties of hot mix asphalt." International Journal of Science & Technology, 2(1), 41-48.
Kumar, P., and Anand, P. (2012). "Laboratory study on moisture susceptibility of dense graded mixes." Journal of transportation engineering, 138(1), 105-113.
Safazadeh, F., Romero, P., Mohammad Asib, A. S., and VanFrank, K. (2022). "Methods to evaluate intermediate temperature properties of asphalt mixtures by the semi-circular bending (SCB) test." Road Materials and Pavement Design, 23(7), 1694-1706.
Nair, H., Seitllari, A., and McGhee, K. K. (2021). "Laboratory cracking performance evaluation of SM-4.75 asphalt mixtures." International Journal of Pavement Research and Technology, 14, 638-645.
Zhou, Z., Gu, X., Dong, Q., Ni, F., and Jiang, Y. (2020). "Low-and intermediate-temperature behaviour of polymer-modified asphalt binders, mastics, fine aggregate matrices, and mixtures with reclaimed asphalt pavement material." Road Materials and Pavement Design, 21(7), 1872-1901.
Seitllari, A., Boz, I., Habbouche, J., and Diefenderfer, S. D. (2022). "Assessment of cracking performance indices of asphalt mixtures at intermediate temperatures." International Journal of Pavement Engineering, 23(1), 70-79.
Etheridge, R. A., Wang, Y. D., Kim, S. S., and Kim, Y. R. (2019). "Evaluation of fatigue cracking resistance of asphalt mixtures using apparent damage capacity." Journal of Materials in Civil Engineering, 31(11), 04019257.
Ghuzlan, K. A., Bara'W, A.-M., and Al-Momani, A. S. (2020). "Rutting performance of asphalt mixtures with gradations designed using Bailey and conventional Superpave methods." Construction and Building Materials, 261, 119941.
Junaid, M., Shah, M. Z. A., Yaseen, G., Awan, H. H., Khan, D., and Jawad, M. (2022). "Investigating the Effect of Gradation, Temperature and Loading Duration on the Resilient Modulus of Asphalt Concrete." Civil Engineering Journal, 8(02).
Xiao, F., Herndon, D. A., Amirkhanian, S., and He, L. (2015). "Aggregate gradations on moisture and rutting resistances of open graded friction course mixtures." Construction and Building Materials, 85, 127-135.