Shengfei Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Shengfei Zhang has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Pinghe Ni
State Key Laboratory of Bridge Engineering Safety and Resilience, Beijing University of Technology, Beijing, China
4 shared publications Qiang Han
4 shared publicationsJianian Wen
3 shared publicationsXiuli Du
3 shared publications- Jinlong Fu
Queen Mary University of London
2 shared publications Guoquan Wang
Department of Earth and Atmospheric Sciences, University of Houston, Houston, USA
1 shared publication
Latest Publications
- 1 September 2026
- Published by Elsevier in Mechanical Systems and Signal Processing
- Vol. 259
Physics-guided Siamese tracker for robust vision-based structural displacement monitoring under visibility degradation
- 1 September 2026
- Published by Elsevier in Mechanical Systems and Signal Processing
- Vol. 259
Physics-guided Siamese tracker for robust vision-based structural displacement monitoring under visibility degradation
- 24 June 2026
- Published by Elsevier in Structures
- Vol. 90
A hybrid enhanced snake optimizer–SQP framework for robust structural damage identification via model updating
- 24 June 2026
- Published by Elsevier in Structures
- Vol. 90
A hybrid enhanced snake optimizer–SQP framework for robust structural damage identification via model updating
- 27 April 2026
- Published by Elsevier in Measurement
- Vol. 279
A vision-based substructure approach for Bayesian model updating using displacement measurements
- 27 April 2026
- Published by Elsevier in Measurement
- Vol. 279
A vision-based substructure approach for Bayesian model updating using displacement measurements
- 30 October 2025
- Published by Elsevier in Engineering Structures
- Vol. 346
Vision-based identification method of earthquake ground motions
- 30 October 2025
- Published by Elsevier in Engineering Structures
- Vol. 346
Vision-based identification method of earthquake ground motions
- 9 June 2024
- Published by Springer Nature in Journal of Civil Structural Health Monitoring
- Vol. 14 (8) , 1819-1837
Robust and versatile vision-based dynamic displacement monitoring of natural feature targets in large-scale structures
- 9 June 2024
- Published by Springer Nature in Journal of Civil Structural Health Monitoring
- Vol. 14 (8) , 1819-1837
Robust and versatile vision-based dynamic displacement monitoring of natural feature targets in large-scale structures
- 30 March 2024
- Published by Elsevier in Mechanical Systems and Signal Processing
- Vol. 214
Intelligent identification of moving forces based on visual perception
- 30 March 2024
- Published by Elsevier in Mechanical Systems and Signal Processing
- Vol. 214
Intelligent identification of moving forces based on visual perception
- 12 February 2024
- Published by SAGE Publications in Structural Health Monitoring
- Vol. 23 (6) , 3525-3544
Non-contact impact load identification based on intelligent visual sensing technology
Accurate identification of impact loads is vital for structural assessment and design. Traditional methods rely on complex equipment, such as accelerometers or strain gauge, which can be expensive and prone to failure. This study introduces a non-contact intelligent identification approach incorporating visual sensing technology, providing a convenient means to identify impact loads. Numerical simulations explore the differences in identifying impact forces through acceleration and displacement responses, particularly by considering such variables as measurement noise and number of measurement points. A meticulously designed experiment verified the feasibility of the proposed method for measuring the displacement and velocity of rapidly moving targets, and evaluated its performance in terms of accuracy. A series of impact loading experiments were conducted on a simply supported girder bridge model to validate the effectiveness of the proposed impact force identification method. Results indicate strong agreement between displacement response measurements and percentile meters. The proposed non-contact method accurately identifies single or continuous impact loads, with a minimum peak relative error of 0.2%. This study represents a pioneering application of intelligent visual sensing technology in the field of impact load identification. Moreover, the current research introduces a novel approach to address the challenges faced by conventional methods in identifying impact loads. Future research can leverage the groundwork laid by this study to further optimize and expand the proposed method, enhancing its capabilities and fully harnessing its potential to offer advanced solutions in structural health monitoring.
- 12 February 2024
- Published by SAGE Publications in Structural Health Monitoring
- Vol. 23 (6) , 3525-3544
Non-contact impact load identification based on intelligent visual sensing technology
Accurate identification of impact loads is vital for structural assessment and design. Traditional methods rely on complex equipment, such as accelerometers or strain gauge, which can be expensive and prone to failure. This study introduces a non-contact intelligent identification approach incorporating visual sensing technology, providing a convenient means to identify impact loads. Numerical simulations explore the differences in identifying impact forces through acceleration and displacement responses, particularly by considering such variables as measurement noise and number of measurement points. A meticulously designed experiment verified the feasibility of the proposed method for measuring the displacement and velocity of rapidly moving targets, and evaluated its performance in terms of accuracy. A series of impact loading experiments were conducted on a simply supported girder bridge model to validate the effectiveness of the proposed impact force identification method. Results indicate strong agreement between displacement response measurements and percentile meters. The proposed non-contact method accurately identifies single or continuous impact loads, with a minimum peak relative error of 0.2%. This study represents a pioneering application of intelligent visual sensing technology in the field of impact load identification. Moreover, the current research introduces a novel approach to address the challenges faced by conventional methods in identifying impact loads. Future research can leverage the groundwork laid by this study to further optimize and expand the proposed method, enhancing its capabilities and fully harnessing its potential to offer advanced solutions in structural health monitoring.