Improved Element-Level Bridge Inspection Criteria for Better Bridge Management and Preservation

Bridge inspection data is an essential step in the bridge asset management operation and the bridge management system. As such, a reliability-based, holistic framework was proposed to effectively collect reliable data and perform data fusion and information fusion of sensory data used for element-level inspection and conditional assessment. A comprehensive literature review was conducted to better understand the current state of the research of and practice in the bridge element inspection. To overcome the limitations of the visual inspection used in the routine bridge inspections, an unmanned aerial vehicle (UAV) was used to supplement the traditional visual inspection data by providing high quality, real-time, reliable data. Moreover, effective data fusion and information process methods were proposed to enhance the features extraction for sensor data for in-depth/special/damage inspections. This study explored the new data fusion methods based on three representative feature extraction techniques, while the kernel function-based support vector machine (SVM) was used to facilitate pattern recognition and improve identification. The effectiveness of these methods was verified even in conditions with high levels of noise interference. In addition, this study attempted to unveil and reduce the structural uncertainty experienced in in-depth/special/damage inspection. The deep Bayesian belief network (DBBN) was herein used to extract statistical representation from vast amount of structural data, for probabilistically determining structural condition and health state for decision making.

• Record URL:
  https://www.ugpti.org/resources/reports/details.php?id=986
• Supplemental Notes:
  • This document was sponsored by the U.S. Department of Transportation, University Transportation Centers Program.
• Corporate Authors:

  North Dakota State University, Fargo

  Department of Civil and Environmental Engineering
  Fargo, ND  United States  58105

  Mountain-Plains Consortium

  North Dakota State University
  Fargo, ND  United States  58108

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Authors:
  • Lin, Zhibin
  • Pan, Hong
  • Wang, Xingyu
  • Li, Mingli
• Publication Date: 2019-12

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; Maps; Photos; References; Tables;
• Pagination: 105p

Subject/Index Terms

• TRT Terms: Bridge management systems; Bridge members; Condition surveys; Data collection; Data fusion; Drones; Inspection; Literature reviews; Maintenance management; Sensors; Structural health monitoring
• Subject Areas: Bridges and other structures; Data and Information Technology; Highways; Maintenance and Preservation;

Filing Info

• Accession Number: 01741574
• Record Type: Publication
• Report/Paper Numbers: MPC-19-403
• Contract Numbers: MPC-504
• Files: UTC, TRIS, ATRI, USDOT
• Created Date: May 31 2020 5:55PM