Graduation Semester and Year
2018
Language
English
Document Type
Dissertation
Degree Name
Doctor of Philosophy in Civil Engineering
Department
Civil Engineering
First Advisor
Mohammad Najafi
Abstract
The U.S. water distribution system contains thousands of miles of pipes with differing materials, sizes, and ages. These pipes experience physical, environmental, structural and operational parameters that cause corrosion and eventually lead to their failures. The Remaining Useful Life (RUL) is the estimated time before a pipe will experience a failure mode specifically a pipe break. Pipe failure means collapse and deterioration of water pipes overtime. Pipe deterioration results in increased break rates, reduced hydraulic capacity, and detrimental impacts on water quality. Therefore, it is crucial to perform accurate models that can forecast deterioration rates along with estimates of remaining useful life of pipelines to implement essential interference plans that can reduce catastrophic failures. This dissertation discusses a computational model that forecasts the RUL of water pipelines using Artificial Neural Network (ANN) and Adaptive Neural Fuzzy Inference System (ANFIS). ANN and ANFIS are developed using Levenberg-Marquardt backpropagation algorithm and mixture of backpropagation and least squares (hybrid method). Those models are trained and tested with acquired field data. The developed models identify the significant parameters that impact on prediction of RUL. It is concluded that, on the average, with approximately 10% of wall thickness loss in existing cast iron, ductile iron, asbestos-cement and steel water pipes analyzed in this dissertation, the reduction of their remaining useful life will be approximately 50%.
Keywords
Remaining useful life, Deterioration, Water pipes failure, Condition assessment
Disciplines
Civil and Environmental Engineering | Civil Engineering | Engineering
License
This work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.
Recommended Citation
Tavakoli, Razieh, "REMAINING USEFUL LIFE PREDICTION OF WATER PIPES USING ARTIFICIAL NEURAL NETWORK AND ADAPTIVE NEURO FUZZY INFERENCE SYSTEM MODELS" (2018). Civil Engineering Dissertations. 309.
https://mavmatrix.uta.edu/civilengineering_dissertations/309
Comments
Degree granted by The University of Texas at Arlington