Skip navigation

An evolutionary polynomial regression (EPR) model for prediction of H2S induced corrosion in concrete sewer pipes

An evolutionary polynomial regression (EPR) model for prediction of H2S induced corrosion in concrete sewer pipes

Romanova, Anna, Faramarzi, Asaad, Mahmoodian, Mojtaba and Alani, Morteza (2014) An evolutionary polynomial regression (EPR) model for prediction of H2S induced corrosion in concrete sewer pipes. In: 11th International Conference on Hydroinformatics, 17-22 Aug 2014, New York, NY, USA.

[img]
Preview
PDF (Author Accepted Manuscript)
11519_Romanova_An_evolutionary_polynomail_regression_(conf._paper)_2014.pdf - Accepted Version
Available under License Creative Commons Attribution.

Download (376kB)

Abstract

The sulphuric acid is a known growing threat to concrete sewer pipes. Acid production is dictated by rapid urbanisation, increased use of hot water and discharge of toxic metals and sulphate containing detergents into the wastewater. Concrete sewer pipe corrosion due to sulphuric attack is known to be the main contributory factor of pipe degradation. Very little tools are available to accurately predict the corrosion rate and most importantly the remaining safe life of the asset. This paper proposes a new robust model to predict the sewer pipe corrosion rate due to sulphuric acid. The model makes use of a powerful Evolutionary Polynomial Regression method that provides a new methodology of hybrid data-mining. The results obtained by the model which was validated in the field indicates that the proposed hybrid methodology can accurately predict the corrosion rate in concrete sewer pipe’s given that the pipe installation conditions as well as in-pipe sewage conditions are known.

Item Type: Conference or Conference Paper (Paper)
Uncontrolled Keywords: EPR, Corrosion, Sewer pipes, Sulphuric acid
Faculty / School / Research Centre / Research Group: Faculty of Engineering & Science > School of Engineering (ENG)
Related URLs:
Last Modified: 14 Dec 2016 13:17
URI: http://gala.gre.ac.uk/id/eprint/11519

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics