ASSESSMENT OF THE TRANSPORT AND OPERATIONAL CONDITION OF ROADS BASED ON MOBILE LABORATORY DATA USING MACHINE LEARNING METHODS

Victoria Shamraeva

Abstract


The subject of the study is the prediction of traffic intensity and pavement condition at a linear road section. The paper addresses a model of a neural network used to assess the usability of a road section and its transport and operational performance. The object of the study is a section of the M-1 Belarus road, 86th km, for the period from 2014 to 2023. The purpose of the study was to describe possible future scenarios of the road condition based on predicted traffic intensity and road quality condition metrics as part of the assessment of its usability with account for the International Roughness Index (IRI). In the course of the study, the following methods were used: Data Science (analysis of data collected from mobile laboratories) and machine learning algorithms (linear regression, gradient boosting, random forest, and neural networks based on long short-term memory (LSTM)). The output is a trained neural network capable of predicting the traffic intensity on the 86th km of the M-1 Belarus road. These methods reveal hidden patterns in the data and provide high-accuracy predictions. Results: The implementation of the deep learning model using the assessment of the condition of a linear road section will make it possible to address the main issues of road maintenance — to optimize time and reduce expenditures when planning and introducing measures at the stage of operation of transport infrastructure facilities, to take into account possible risks of road condition quality loss during re-pavement and design of new elements.


Keywords


transportation infrastructure; road diagnostics; defects; machine learning; Data Science; road information model

Full Text:

PDF

References


Apestin, V. K. (2011). About divergence between design and normative interrepair periods of road pavement service. Science and Engineering for Highways, No. 1, pp. 18–20.

Avtodor (2016). Avtodor State Company Standard. Predicting the condition of operated roads of the Avtodor State Company. Organization Standard AVTODOR 2.28-2016. Moscow: Avtodor, 26 p.

Cano-Ortiz, S., Pascual-Muñoz, P., and Castro-Fresno, D. (2022). Machine learning algorithms for monitoring pavement performance. Automation in Construction. Vol. 139, 104309. DOI: 10.1016/j.autcon.2022.104309.

Cha, Y.-J., Choi, W., and Büyüköztürk, O. (2017). Deep learning-based crack damage detection using convolutional neural networks. Computer-Aided Civil and Infrastructure Engineering, Vol. 32, Issue 5, pp. 361–378. DOI: 10.1111/mice.12263.

Gazarov, A. R. (2020). Advantages of using artificial intelligence in the field of construction. News of the Tula State University. Technical Sciences, No. 4, pp. 136–139.

Goodfellow, I., Bengio, Y., and Courville, A. (2018). Deep learning. 2nd edition. Moscow: DMK Press, 652 p.

Hosmer Jr., D. W., Lemeshov, S., and Sturdivant, R. X. (2013). Applied logistic regression. 3rd edition. New York: John Wiley & Sons, 528 p.

Iliopolov, S. K., Seleznev, M. G., and Uglova, Ye. V. (2002). Dynamics of road structures. Rostov-on-Don: Rostov State University of Civil Engineering, 258 p.

Interstate Council for Standardization, Metrology and Certification (ISC) (2016). GOST 33388-2015. Automobile roads of the general use. Requirements to conducting diagnostics and certification. Moscow: Standartinform, 11 p.

Lasisi, A. and Attoh-Okine, N. (2018). Principal components analysis and track quality index: a machine learning approach. Transportation Research Part C: Emerging Technologies, Vol. 91, pp. 230–248. DOI: 10.1016/j.trc.2018.04.001.

Marcelino, P., de Lurdes Antunes, M., Fortunato, E., and Castilho Gomes, M. (2019). Machine learning approach for pavement performance prediction. International Journal of Pavement Engineering, Vol. 22, Issue 3, pp. 341–354. DOI: 10.1080/10298436.2019.1609673.

Panthi, K. (2009). A methodological framework for modeling pavement maintenance costs for projects with performance-based contracts. PhD Thesis in Civil Engineering. DOI: 10.25148/etd.FI09120824.

Pugachev, I. N., Sheshera, N. G., Grigorov, D. E., and Evtyukov, S. S. (2024).

Forecast of traffic flow intensity. Training with a teacher. Random tree method. T-Comm, Vol. 18, No. 4, pр. 36–47. DOI: 10.36724/2072-8735-2024-18-4-36-47.

Robinson, R., Danielson, U., and Snaith, M. (1998). Road maintenance management: concepts and systems. London: Red Globe Press, 312 p. DOI: 10.1007/978-1-349-14676-5.

Rosavtodor (2018). Industry road guidance document. Recommendations on diagnostics and assessment of the technical condition of motor roads. ODM 218.4.039-2018. Moscow: Rosavtodor, 59 p.

Shamraeva, V. V. (2020). Economic efficiency of operation of elements of civil buildings taking into account residual resource: probabilistic-statistical approach. Modern Science: Actual Problems of Theory and Practice. Series: Economics and Law, No. 2, pp. 61–68.

Shamraeva, V. V. (2024). Mathematical methods for forecasting stock price changes and their implementation using machine learning methods. Fundamental Research, No. 11, pp. 88–96. DOI: 10.17513/fr.43718.

Shamraeva, V. and Savinov, E. (2021). INFRA-BIM for business processes’ management in road construction and operation. Architecture and Engineering, Vol. 6, No. 3, pp. 19–28. DOI: 10.23968/2500-0055-2021-6-3-19-28.

Stolbov, Yu. V., Stolbova, S. Yu., Pronina, L. A., and Uvarov, A. I. (2017). The provision of the inspections’ control accuracy on the IV, V category road basics and coverings by the application of H-3 type niveliers. Russian Automobile and Highway Industry Journal, No. 6 (58), pp. 125–132.

Vasilyev, A.P. (2013). Operation of motor roads. In 2 volumes. Vol. 2. 3rd edition. Moscow: Academia Publishing Center, 320 p.

Ziari, H., Sobhani, J., Ayoubinejad, J., and Hartmann, T. (2015). Prediction of IRI in short and long terms for flexible pavements: ANN and GMDH methods. International Journal of Pavement Engineering, Vol. 17, Issue 9, pp. 776–788. DOI: 10.1080/10298436.2015.1019498.

Znobishchev, S. and Shamraeva, V. (2019). Practical use of BIM modeling for road infrastructure facilities. Architecture and Engineering, Vol. 4, No. 3, pp. 49–54. DOI: 10.23968/2500-0055-2019-4-3-49-54.


Refbacks

  • There are currently no refbacks.




     

ISSN: 2500-0055