Graduation Semester and Year

2020

Language

English

Document Type

Dissertation

Degree Name

Doctor of Philosophy in Civil Engineering

Department

Civil Engineering

First Advisor

Ali Abolmaali

Abstract

In this dissertation, through utilizing various artificial intelligence-based as well as statistical models, an effort has been made to investigate the deterioration of sewer pipes. Once the deterioration rates of sewer pipes are estimated, by assuming failure criteria, as specified in the dissertation, the associated service lives for the sewer pipes can therefore be estimated. However, it should be noted that for different sewer pipes and based upon the availability of suitable data, and due to various failure modes that could transpire in various sewer pipes, the results will thus be subjected to uncertainties and variations. In other words, depending on different sewer pipes, the adequacy and the availability of suitable data, the decision-makers’ priorities and failure criteria, the estimated service lives as well as the associated deterioration curves could be subjected to variation. Selecting a suitable model plays an important role in reducing the amount of uncertainty associated with estimation of service life of sewer pipes. In order to estimate the service lives of sewer pipes, the first step is to estimate the rate of deterioration which affects the condition rating of sewer pipes. Next, by designating a certain threshold or cut-off value, the service life of sewer pipes could thus be estimated as well. Therefore, depending on the type of selected deterioration modeling, the assignment of threshold (cut-off value) needs to be conducted with adequate engineering judgement. Additionally, based upon the criteria of decision-makers, the certain threshold for service life may be subject to further change and improvement. Hence, the suitable modeling approach may differ for various projects and sewer pipes; i.e. a model which yields suitable results for one project may not necessarily yield suitable and reliable results in another project. This stems from the assumptions and uncertainties associated with each of the modeling approaches.

Keywords

Artificial intelligence, Statistical modeling, LightGBM, CatBoost

Disciplines

Civil and Environmental Engineering | Civil Engineering | Engineering

Comments

Degree granted by The University of Texas at Arlington

29377-2.zip (6145 kB)

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.