Application of Artificial Neural Networks (ANN) in modelling water filtration technologies

PhD

Application of Artificial Neural Networks (ANN) in modelling water filtration technologies

Outline

Stormwater filtration technologies play a significant role in improving water quality and making treated water available for several non-potable uses. However, during treatment processes, contaminants such as suspended solids lead to clogging of vegetated and non-vegetated filters, especially those with high infiltration rates. There are several parameters that affect clogging of filters, and a major challenge is to understand the parameter interdependencies, correlations and their individual effects. A robust methodology is, thus, required to accurately predict clogging for diverse operational conditions in different catchment conditions. Such models would further help with predictive maintenance and asset management and hence contribute and uptake of these technologies. This project employs the use of Artificial Neural Networks (ANN) to model and predict clogging performance of filters under different operational conditions. Comparative analysis with other predictive modelling approaches shall also be undertaken to guide development of information systems that can guide data collection in these decentralised systems.

Supervisory Team

Principal Supervisor: Dr Harpreet Kandra

Co-supervisors:

Dr Tanveer Choudhury

A/Prof Andrew Barton