An Evolutionary Polynomial Regression (EPR) model for prediction of H2S induced corrosion in concrete sewer pipes

Romanova, Anna, Faramarzi, Asaad, Mahmoodian, Mojtaba and Alani, Amir (2014) An Evolutionary Polynomial Regression (EPR) model for prediction of H2S induced corrosion in concrete sewer pipes. In: 11th International Conference on Hydroinformatics (HIC 2014), 17-21 Aug 2014, New York, USA.

[thumbnail of An Evolutionary Polynomial Regression (EPR) Model For Prediction.pdf]
Preview
PDF
An Evolutionary Polynomial Regression (EPR) Model For Prediction.pdf - Accepted Version

Download (452kB) | Preview

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 Workshop Item (Paper)
Keywords: EPR, corrosion, sewer pipes, sulphuric acid
Subjects: Construction and engineering > Built environment
Construction and engineering > Civil and structural engineering
Construction and engineering
Depositing User: Fabio Tosti
Date Deposited: 26 May 2016 11:07
Last Modified: 28 Aug 2021 07:20
URI: https://repository.uwl.ac.uk/id/eprint/2154

Downloads

Downloads per month over past year

Actions (login required)

View Item View Item

Menu