Application of Machine Learning in Bridge Inspection Technology

Lijie Ma; Jie Li

doi:10.6919/ICJE.202507_11(7).0012

Authors

Lijie Ma
Jie Li

DOI:

https://doi.org/10.6919/ICJE.202507_11(7).0012

Keywords:

Bridge Inspection; Machine Learning; Deep Learning; Artificial Intelligence.

Abstract

The traditional bridge inspection technology mainly relies on visual inspection, which can meet the needs of bridge inspection to a certain extent, but with the development of science and technology and the increasing demand for bridge construction, the traditional inspection technology is also facing many challenges and limitations. Intelligent bridge inspection technology realizes comprehensive, efficient and accurate inspection and evaluation of bridge structural status by deeply integrating sensor technology, data analysis and artificial intelligence technology. It mainly introduces the existing bridge inspection technology, the application of machine learning in bridge inspection technology, and summarizes the advantages and prospects of combining bridge inspection technology with artificial intelligence.

Downloads

Download data is not yet available.

References

[1] Zheng Y, Wang S, Zhang P, et al. Application of nondestructive testing technology in quality evaluation of plain concrete and RC structures in bridge engineering: A review[J]. Buildings, 2022, 12(6): 843.

[2] Fan Jiansheng, Liu Yufei. Research on the Current Status of In-Service Bridge Inspection and Health Monitoring Technology and a Spatio-Temporal Fusion Diagnosis System [J]. Municipal Engineering Technology, 2022, 40(08): 1-11+40.

[3] Li Qi. A Brief Discussion on the Application of Machine Learning in Bridge Engineering [J]. Construction Machinery, 2019, (09): 54-57.

[4] Wang Kai, Chen Yun, Tang Jianlin. Application of BP neural networks in performance detection of large-span cable-stayed bridges [J]. Journal of Zhejiang University of Technology, 2023, 51(02).

[5] Sun Bin, Zhang Bo, Yu Xianghua, et al. Research on Bridge Condition Prediction Based on Deep Learning [J]. China Transportation Informatisation, 2024, (S1): 568-571.