From defect recognition to maintenance decision-making: A review of intelligent bridge inspection technologies and their digital evolution
Bridge defect inspection is evolving from isolated surface recognition toward an integrated paradigm that combines multisource sensing, spatial localization, and maintenance-oriented decision support. Although substantial progress has been achieved in UAV- and robot-based inspection platforms, deep-learning-driven defect recognition, multimodal data fusion, digital twins, and knowledge-graph-enabled bridge management, current studies still face several persistent limitations, including fragmented datasets, insufficient cross-scene generalization, weak coupling between inspection outputs and structural performance assessment, and incomplete knowledge closed loops for operation and maintenance. To address these issues, this review provides a systematic synthesis of intelligent bridge defect inspection from four interconnected perspectives: sensing platforms, recognition algorithms, fusion and localization, and decision support. This review is expected to provide a useful reference for intelligent lifecycle management of bridge infrastructure.
Authors
- Pan Guo (ORCID: https://orcid.org/0000-0002-7782-0352)
- Yao Mengcheng
- Qingxin Meng (ORCID: https://orcid.org/0000-0003-0680-7000)
- Yuanxun Zheng
- Qianxiang Zhang
- Yaohui Zhang
- Jiahao Wang (ORCID: https://orcid.org/0009-0006-6159-545X)
Institutions
- Zhengzhou University (CN)
- China Railway Group (China) (CN)
Publication Details
- Journal
- Advances in Structural Engineering
- Published
- 2026-11-17
- DOI
- https://doi.org/10.1177/13694332261507475
- Primary Topic
- Infrastructure Maintenance and Monitoring
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China