Prediction of soil corrosivity index : a Bayesian belief network approach Demissie, Gizachew; Tesfamariam, Solomon; Sadiq, Rehan
Soil and their inherent properties play a very significant role in aggravating the corrosion process of metallic pipes as they are buried underground. The most common causes of corrosion are lower resistivity of soil; lower and higher pH; presence of sulfate-reducing bacteria, chlorides, sulfate and sulfides; difference in soil composition; and differential aeration of soil around the laid water pipes. The interaction of these variables are highly complex and challenging to predict the degree of corrosion due to the soil environment. In this paper, a Bayesian belief network (BBN) approach is proposed to address the inter-dependency of soil parameters and their effect on the corrosivity of soil. The proposed approach uses a combination of in situ collected data and expert knowledge of soil parameters to model the inter-dependency between soil parameters and predict the SCI using an updating capability of the BBN. The model was developed and trained using soil parameters data collected by the city of Calgary in combination with expert knowledge. The performance of the developed soil corrosivity index-Bayesian belief network (SCI-BBN) model was evaluated by the BBN model sensitivity analysis. In order to demonstrate the developed approach, the SCI-BBN model output was converted into five indexes, which are very high to very low, so that the decision makers clearly understand their system’s situation. Finally, the linguistic soil corrosivity indices of each pipes were mapped using a geographic information system (GIS) platform in order to indicate its spatial representations.
Item Citations and Data
Attribution-NonCommercial-NoDerivs 2.5 Canada