Neural Network Approach to Condition Assessment of Highway Culverts: Case Study in Ohio.

Saved in:

Bibliographic Details
Title:	Neural Network Approach to Condition Assessment of Highway Culverts: Case Study in Ohio.
Authors:	Tatari, Omer, Sargand, Shad M.¹, Masada, Teruhisa², Tarawneh, Bashar³
Source:	Journal of Infrastructure Systems. Dec2013, Vol. 19 Issue 4, p409-414. 6p.
Subjects:	Culvert design & construction, Road construction & the environment, Artificial neural networks, Infrastructure (Economics), Civil engineering
Abstract:	Millions of culverts exist in the United States, and they are aging rapidly. Inspection of all the culverts consumes a lot of time and resources. Instead of inspecting each culvert every 5 years, this study presents a more intelligent approach to predict the condition of each culvert. An artificial neural network (ANN) model is built to assess the condition of the culverts based on culvert inventory data. The overall condition-rating predictions are compared with the condition rating based on manual inspection. The results of this study have shown that ANN was able to predict culvert adjusted overall rating with high precision, as the course of action score prediction rate was 100%. Sensitivity analysis of the ANN model is provided to assess the effect of variables. The goal of this study is to show that more intelligent culvert-management systems could be devised by taking advantage of artificial intelligence. [ABSTRACT FROM AUTHOR]
	Copyright of Journal of Infrastructure Systems is the property of American Society of Civil Engineers and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	Millions of culverts exist in the United States, and they are aging rapidly. Inspection of all the culverts consumes a lot of time and resources. Instead of inspecting each culvert every 5 years, this study presents a more intelligent approach to predict the condition of each culvert. An artificial neural network (ANN) model is built to assess the condition of the culverts based on culvert inventory data. The overall condition-rating predictions are compared with the condition rating based on manual inspection. The results of this study have shown that ANN was able to predict culvert adjusted overall rating with high precision, as the course of action score prediction rate was 100%. Sensitivity analysis of the ANN model is provided to assess the effect of variables. The goal of this study is to show that more intelligent culvert-management systems could be devised by taking advantage of artificial intelligence. [ABSTRACT FROM AUTHOR]
ISSN:	10760342
DOI:	10.1061/(ASCE)IS.1943-555X.0000139