skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: New Measure to Understand and Compare Bridge Conditions Based on Inspections Time-Series Data
The C+ score for US bridges on the 2017 infrastructure report card underscores the need for improved data-driven methods to understand bridge performance. There is a lot of interest and prior work in using inspection records to determine bridge health scores. However, aggregating, cleaning, and analyzing bridge inspection records from all states and all past years is a challenging task, limiting the access and reproducibility of findings. This research introduces a new score computed using inspection records from the National Bridge Inventory (NBI) data set. Differences between the time series of condition ratings for a bridge and a time series of average national condition ratings by age are used to develop a health score for that bridge. This baseline difference score complements NBI condition ratings in further understanding a bridge’s performance over time. Moreover, the role of bridge attributes and environmental factors can be analyzed using the score. Such analysis shows that bridge material type has the highest association with the baseline difference score, followed by snowfall and maintenance. This research also makes a methodological contribution by outlining a data-driven approach to repeatable and scalable analysis of the NBI data set.  more » « less
Award ID(s):
1762034
PAR ID:
10278169
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
Journal of infrastructure systems
ISSN:
1076-0342
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. (, ProQuest Dissertation and Theses)
    null (Ed.)
    US Bridges scored a C+ on the 2017 infrastructure report card. There is a need for substantial improvement in bridge conditions as many of them are structurally deficient and can become unsafe in the near future. The nation's most recent bridge rehabilitation estimate is $123 billion. Many state's department of transportation (DOT) have limited resources, leaving them with difficult decisions about where to invest and allocate limited resources. To make cost-effective decisions, these bridge stakeholders need clean data and studies to estimate the future bridge conditions. This will give them data-driven, accurate life-cycle models for bridges and improved inspections intervals. Previous researchers have identified factors that may cause bridge deterioration. Unfortunately, these researchers limit their data to specific regions and bridge types. This severely limits their result's general applicability. In this thesis, we approach bridge health-related decision making challenges using a novel data science perspective. This bridge health deterioration study provides new insights into making bridge rehabilitation and reconstruction decisions. In this research, we use all US inspection record data regulated by the Federal Highway Agency that is available in the National Bridge Inventory (NBI) database and precipitation data from the Center for Disease Control and Prevention (CDC). Our specific contributions are 1) providing a reference big data pipeline implementation for bridge health-related datasets; 2) demonstrating the feasibility of data science to study bridge deterioration; 3) developing repeatable methods for sharing large datasets with reproducible analysis driven by data science and making them available to other researchers. Further, our curated datasets and platforms are used to analyze the statistical significance of bridge deterioration factors as identified by the literature and subject matter experts at the Nebraska State DOT. From our results, we found that bridge material type has the highest association in comparison to other factors such as average daily traffic, average daily truck traffic, structure length, maintainer, region, and precipitation. This research used all NBI inspection records and precipitation rates from all US counties. 
    more » « less
  2. ; ; ; ; ; ; ; (, Sensors)
    The Federal Highway Administration (FHWA) mandates biannual bridge inspections to assess the condition of all bridges in the United States. These inspections are recorded in the National Bridge Inventory (NBI) and the respective state’s databases to manage, study, and analyze the data. As FHWA specifications become more complex, inspections require more training and field time. Recently, element-level inspections were added, assigning a condition state to each minor element in the bridge. To address this new requirement, a machine-aided bridge inspection method was developed using artificial intelligence (AI) to assist inspectors. The proposed method focuses on the condition state assessment of cracking in reinforced concrete bridge deck elements. The deep learning-based workflow integrated with image classification and semantic segmentation methods is utilized to extract information from images and evaluate the condition state of cracks according to FHWA specifications. The new workflow uses a deep neural network to extract information required by the bridge inspection manual, enabling the determination of the condition state of cracks in the deck. The results of experimentation demonstrate the effectiveness of this workflow for this application. The method also balances the costs and risks associated with increasing levels of AI involvement, enabling inspectors to better manage their resources. This AI-based method can be implemented by asset owners, such as Departments of Transportation, to better serve communities. 
    more » « less
  3. ; ; ; (, Structural Health Monitoring)
    null (Ed.)
    Bridge inspection is an important step in preserving and rehabilitating transportation infrastructure for extending their service lives. The advancement of mobile robotic technology allows the rapid collection of a large amount of inspection video data. However, the data are mainly the images of complex scenes, wherein a bridge of various structural elements mix with a cluttered background. Assisting bridge inspectors in extracting structural elements of bridges from the big complex video data, and sorting them out by classes, will prepare inspectors for the element-wise inspection to determine the condition of bridges. This article is motivated to develop an assistive intelligence model for segmenting multiclass bridge elements from the inspection videos captured by an aerial inspection platform. With a small initial training dataset labeled by inspectors, a Mask Region-based Convolutional Neural Network pre-trained on a large public dataset was transferred to the new task of multiclass bridge element segmentation. Besides, the temporal coherence analysis attempts to recover false negatives and identify the weakness that the neural network can learn to improve. Furthermore, a semi-supervised self-training method was developed to engage experienced inspectors in refining the network iteratively. Quantitative and qualitative results from evaluating the developed deep neural network demonstrate that the proposed method can utilize a small amount of time and guidance from experienced inspectors (3.58 h for labeling 66 images) to build the network of excellent performance (91.8% precision, 93.6% recall, and 92.7% f1-score). Importantly, the article illustrates an approach to leveraging the domain knowledge and experiences of bridge professionals into computational intelligence models to efficiently adapt the models to varied bridges in the National Bridge Inventory. 
    more » « less
  4. ; ; ; ; (, Transportation Research Record: Journal of the Transportation Research Board)
    Airports facilitate the fastest mode of transportation and connect local communities and businesses with national and international destinations. The American Society of Civil Engineers (ASCE) 2021 infrastructure report card rated the aviation infrastructure category with a D+. This highlights the need for frequent monitoring and performing timely preservation techniques to ensure the optimal performance of the asset. The Texas Department of Transportation (TxDOT) periodically inspects the regional airports in Texas through visual surveys and estimates the pavement condition index (PCI) for each airport on a network scale. These ratings are used to assess the need for rehabilitation in a timely manner. In this study, an attempt was made to use an unmanned aerial vehicle (UAV) mounted with an optical camera to inspect and evaluate the condition of various airport assets. Several observations were outlined to conduct a safe inspection of airport assets using UAVs. A comparison of PCI values, grouped into three categories, obtained from traditional and aerial inspections was made to understand the feasibility of using this new technology for airport asset management. It was observed that both inspections classified most of the airport assets similarly. The traditional inspection was observed to be quicker as it requires inspection of only sampled units, however, UAV data processing takes a relatively long time to offer a comprehensive digital footprint and immersive visualization experience of the whole airport assets. Overall, UAVs are identified to have a great potential as a data collection tool supplementary to the current traditional practices. 
    more » « less
  5. ; ; ; (, Structures Congress Conference 2019)
    Real-time fatigue health monitoring has the potential to serve as a valuable complement to structural health monitoring (SHM) for bridge inspections. SHM is an objective supplement to visual bridge inspections with a minimum interval between bridge inspections at 24 months. SHM can provide quantitative and objective data on a bridge’s fatigue condition for fracture-critical components, of which fatigue is a criterion. Current methods of continuous structural health monitoring for condition assessment are performed by collecting measured bridge response subjected to operational traffic from an array of sensors installed on fracture-critical members of a bridge. The measured responses are used to determine the remaining fatigue life of the bridge—the minimum time before repair. The large amount of data involved in this process complicates the design of a system that will automate the data collection process at a bridge, analyze that data, and display information about bridge health to researchers and engineers. Variations in bridge designs and condition assessment algorithms also necessitate that such a system be modular and adaptable to allow for expansion to additional structures. A new system has been developed that separates bridge SHM from the data storage and communication system. This architecture creates a reliable interface for sending data from one or more bridges to a cloud server where it can be processed using modular algorithms that can be adapted for different use cases. The cloud-based web service and data repository makes bridge structural health data available to researchers at all steps of the process. This system provides significant advantages over previous platforms for structural health monitoring and condition assessment, most notably in the areas of modularity, extensibility, and reliability. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email