Graduation Semester and Year




Document Type


Degree Name

Doctor of Philosophy in Civil Engineering


Civil Engineering

First Advisor

Mohammad Najafi


The water distribution system in the United States consists of 2.2 million miles of pipelines with water main breaks that the American Society of Civil Engineers (ASCE) 2021 Report Card estimated results in six billion gallons of drinking water lost daily. Detecting the state of pipeline deterioration should always be a top priority in the water pipeline industry This dissertation statistically evaluates data from more than 70,000 electromagnetic inspections that have been performed since the installation of these pipes in 1971. The scope of this dissertation is related to performance and degradation of prestressed concrete cylinder pipe (PCCP) which is used in large diameter water transmission to predict remaining useful life (RUL) using different modeling technologies such as the artificial neural network and decision tree. The objective of this research is to prepare a model to predict the RUL of PCCP. The results showed that the artificial neural network (ANN) method is the most accurate method for calculating the (RUL) with a 97.9% accuracy value compared with K-nearest neighbor and decision tree models with values of 83% and 97 % respectively. Broken wires and internal water pressure were found to be the most important parameters to calculate the RUL of PCCP for the two diameters 72” and 90” considered. This research should serve as a guideline for future research designed to investigate additional diameters.


Remaining useful life, Artificial neural network, Condition assessment, Prestressed concrete cylinder pipe


Civil and Environmental Engineering | Civil Engineering | Engineering


Degree granted by The University of Texas at Arlington