Zhang, Qianyun
(2022)
Multi-sensor Data Interpretation and Fusion Frameworks for Bridge Deck Condition Assessment.
Doctoral Dissertation, University of Pittsburgh.
(Unpublished)
Abstract
Economic and effective management of aging bridges is a challenging task for the state departments of transportation and government agencies. Reliable condition evaluation of bridges plays a key role in any decision-making for their repair and maintenance. This study presents new multi-sensor data interpretation and fusion methodologies for improving current bridge inspection strategies based on vision-based and non-destructive evaluation (NDE) inspection techniques. Unmanned aerial vehicle (UAV) techniques and deep learning processing methods are integrated to automate the detection and quantification of bridge surface and subsurface defects using high-definition and infrared thermography images. Advanced data fusion methods based on discrete wavelet transforms and improved Dempster-Shafer evidence combination theory are developed to create a multi-resource NDE data fusion framework for bridge deck condition assessment. The proposed methodologies focus on addressing the principal challenges associated with studying the service life of bridge decks, which are related to: (a) the long-time scales (which requires accelerated aging), (b) the diverse outputs related to bridge deck conditions (in terms of data collected through UAV, NDE, and visual inspection), and (c) advanced data interpretation and fusion framework for automated detection and quantification of bridge deck surface and subsurface defects. By leveraging the access to the unique dataset generated by the Bridge Evaluation and Accelerated Structural Testing (BEAST) facility, this dissertation identifies the potential synergies among bridge degradation, remaining service life, and the results taken from the multimodal sensing technologies (i.e., UAV and NDE techniques). The feasibility of the proposed methodologies in detecting bridge defects is further discussed via correlating the information captured during the accelerated bridge testing with a representative bridge in the state of Pennsylvania.
Share
| Citation/Export: |
|
| Social Networking: |
|
Details
| Item Type: |
University of Pittsburgh ETD
|
| Status: |
Unpublished |
| Creators/Authors: |
|
| ETD Committee: |
|
| Date: |
6 September 2022 |
| Date Type: |
Publication |
| Defense Date: |
1 June 2022 |
| Approval Date: |
6 September 2022 |
| Submission Date: |
23 June 2022 |
| Access Restriction: |
2 year -- Restrict access to University of Pittsburgh for a period of 2 years. |
| Number of Pages: |
161 |
| Institution: |
University of Pittsburgh |
| Schools and Programs: |
Swanson School of Engineering > Civil and Environmental Engineering |
| Degree: |
PhD - Doctor of Philosophy |
| Thesis Type: |
Doctoral Dissertation |
| Refereed: |
Yes |
| Uncontrolled Keywords: |
Bridge inspection; Machine learning; Data fusion; Nondestructive Evaluation; Computer vision; UAV; |
| Date Deposited: |
06 Sep 2022 16:07 |
| Last Modified: |
06 Sep 2024 05:15 |
| URI: |
http://d-scholarship.pitt.edu/id/eprint/43215 |
Metrics
Monthly Views for the past 3 years
Plum Analytics
Actions (login required)
 |
View Item |
![[feed]](/images/feed-icon-32x32.png){kind=icon}