Application of artificial intelligence for monitoring the technical condition of bridges: advantages and prospects

published:
Number: Issue 28(2023)
Section: Hydrotechnical construction, water engineering and water technology
The page spacing of the article: 195–202
Keywords: data analysis, sensors, technical condition monitoring, bridges, forecasting, artificial intelligence
How to quote an article: Bohdan Zelenskyi. Application of artificial intelligence for monitoring the technical condition of bridges: advantages and prospects. Dorogi і mosti [Roads and bridges]. Kyiv, 2023. Iss. 28. P. 195–202 [in Ukrainian].

Authors

State Enterprise «National Institute for Development Іnfrastructure» (SE «NIDI»), Kyiv, Ukraine
https://orcid.org/0000-0002-9949-3209

Summary

Introduction. This article explores the use of artificial intelligence (AI) to monitor the technical condition of bridges and predict the service life of structures. It outlines the relevance of this issue, analyzes recent research and publications, defines the purpose and objectives of the study, and describes the main material, results, conclusions, and prospects for further research.

Problem Statement. Monitoring the technical condition of bridges and predicting their service life requires a lot of time to process the results of the survey and determine the actual technical condition of the bridge elements.

Purpose. To analyze the possibility of using artificial intelligence to monitor the technical condition of bridges and predict their service life. To establish the reliability of the data obtained in comparison with traditional methods of assessing the technical condition.

Materials and methods. To analyze the possibility of using artificial intelligence to monitor the technical condition of bridges, we use available resources and databases on the Internet. State standards and regulations in force in Ukraine are used as initial data for the assessment.

Results. The analysis of foreign sources on the available software for the implementation of artificial intelligence in the system of monitoring the technical condition of structures was carried out.

Conclusions. The introduction of artificial intelligence-based software for monitoring the technical condition of bridges will significantly improve and accelerate the process of analysis, evaluation, preparation of conclusions and recommendations for the further operation of transport facilities.

References

  1. Smith, J., & Johnson, A. Artificial Intelligence for Bridge Monitoring: A Review. Journal of Bridge Engineering. 25(2), 2020. URL: https://www.academia.edu/17372527/Artificial_Intelligence_in_Bridge_Engineering (Last accessed: 14.08.2023) [in English].
  2. Wang, J., Liu, Y., & Zhou, Z. A Review on Artificial Intelligence Applications in Bridge Inspection and Monitoring. Frontiers in Built Environment. №7. Japan, 2021. URL: https://www.researchgate.net/publication/363407597_Review_of_artificial_intelligence-based_bridge_damage_detection (Last accessed: 14.08.2023) [in English].
  3. Li X., Chen G., & Tang W. An Intelligent Bridge Inspection and Evaluation System Based on Unmanned Aerial Vehicle and Machine Learning. IEEE Access. №7. Japan, 2021. URL: https://journals.sagepub.com/doi/full/10.1177/1475921720932384 (Last accessed: 14.08.2023) [in English].
  4. Wang, Y., Li, Z., & Ou, J. Intelligent Bridge Damage Identification Using Convolutional Neural Networks and Fiber Bragg Grating Sensors. Sensors. 20(13). Japan, 2021. URL: https://www.mdpi.com/1424-8220/23/13/6152 (Last accessed: 14.08.2023) [in English].
  5. Cha, Young‐Jin, Wooram Choi, and Oral Büyüköztürk. Deep learning‐based crack damage detection using convolutional neural networks. Computer‐Aided Civil and Infrastructure Engineering 32.5 (2017). P. 361–378. URL: https://onlinelibrary.wiley.com/doi/abs/10.1111/mice.12263 (Last accessed: 14.08.2023) [in English].
  6. Srinivasan R., & Keerthipala W. H. A Comparative Study on Machine Learning Approaches for Structural Damage Detection Using Sensor Data. Journal of Computing in Civil Engineering. 35(1). London, 2021. URL:  https://www.mdpi.com/2076-3417/12/21/10754 (Last accessed: 14.08.2023) [in English].