Bridge Element Weights Based on Data-Driven Model with Artificial Neural Networks
Publication: Structures Congress 2023
ABSTRACT
The proliferation of element level condition data recorded by state departments of transportation on bridges makes it pertinent to consider a more efficient use of these data for an improved bridge and asset management. This paper unravels how individual elements can predict the overall condition of the bridge since the direct relationship between component rating and element health index does not follow a regular pattern. For this study, element data from 20,250 bridges across five different states in the Mid-Atlantic United States were collected from the Federal Highway Administration web portals. The health indices of the bridge elements were computed using four different weight distribution ratios based on the four condition states: good, fair, poor, and severe. The efficiency of each weight distribution method was tested by running an artificial neural network (ANN) and logistic regression model with the health index of the elements as the feature variable and the overall bridge condition as the target variable. The results show that the dataset with 1:0.40:0.25:0 weight distribution ratio gave the highest prediction accuracy of 87% and also for the f1-score. The weight of the bridge elements were also determined from this ANN model.
Get full access to this article
View all available purchase options and get full access to this chapter.
REFERENCES
AASHTO. (2018). Manual for Bridge Evaluation. In: AASHTO Washington, DC.
Ali, G., Elsayegh, A., Assaad, R., El-adaway, I. H., & Abotaleb, I. S. (2019). Artificial neural network model for bridge deterioration and assessment.
Althaqafi, E., & Chou, E. (2022). Developing Bridge Deterioration Models Using an Artificial Neural Network. Infrastructures, 7(8), 101.
Assaad, R., & El-adaway, I. H. (2020). Bridge infrastructure asset management system: Comparative computational machine learning approach for evaluating and predicting deck deterioration conditions. Journal of Infrastructure Systems, 26(3), 04020032.
Chase, S. B., Adu-Gyamfi, Y., Aktan, A., & Minaie, E. (2016). Synthesis of national and international methodologies used for bridge health indices.
FHWA. (2017). National Performance Management Measures; Assessing Pavement Condition for the National Highway Performance Program and Bridge Condition for the National Highway Performance Program. Federal Register, 82(11), 14438–14439.
Inkoom, S., & Sobanjo, J. (2018). Availability function as bridge element’s importance weight in computing overall bridge health index. Structure and Infrastructure Engineering, 14(12), 1598–1610.
Inkoom, S., Sobanjo, J. O., Thompson, P. D., Kerr, R., & Twumasi-Boakye, R. (2017). Bridge health index: Study of element condition states and importance weights. Transportation Research Record, 2612(1), 67–75.
Jiang, X., & Rens, K. L. (2010a). Bridge health index for the city and county of Denver, Colorado. I: Current methodology. Journal of performance of constructed facilities, 24(6), 580–587.
Jiang, X., & Rens, K. L. (2010b). Bridge health index for the city and county of Denver, Colorado. II: Denver bridge health index. Journal of performance of constructed facilities, 24(6), 588–596.
Liu, H., & Zhang, Y. (2020). Bridge condition rating data modeling using deep learning algorithm. Structure and Infrastructure Engineering, 16(10), 1447–1460.
Nguyen, T. T., & Dinh, K. (2019). Prediction of bridge deck condition rating based on artificial neural networks. Journal of Science and Technology in Civil Engineering (STCE)-HUCE, 13(3), 15–25.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., & Dubourg, V. (2011). Scikit-learn: Machine learning in Python. Journal of machine Learning research, 12, 2825–2830.
Yoon, Y., & Hastak, M. (2017). Multitiered prioritizing method using urgency scale for bridge deck rehabilitation. Journal of Infrastructure Systems, 23(4), 04017020.
Information & Authors
Information
Published In
Structures Congress 2023
Pages: 106 - 119
History
Published online: May 1, 2023
ASCE Technical Topics:
- Architectural engineering
- Artificial intelligence and machine learning
- Asset management
- Bridge components
- Bridge engineering
- Bridge management
- Bridges
- Building management
- Business management
- Computer programming
- Computing in civil engineering
- Engineering fundamentals
- Financial management
- Information management
- Maintenance and operation
- Management methods
- Neural networks
- Practice and Profession
- Ratings
- Structural engineering
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.