Transforming data into knowledge: augmenting digital twins

Trappett, James (2024). Transforming data into knowledge: augmenting digital twins. University of Birmingham. M.Phil.

Trappett2024MPhil.pdf
Text - Accepted Version
Restricted to Repository staff only
Available under License All rights reserved.
Download (7MB)

Abstract

The United Kingdom water network has significant engineering challenges due to its age, condition, water scarcity, increasing demand and the need to fit within a regulatory framework. Additionally, water companies are looking to better understand the sector challenges (e.g., supply integrity, security, criticality of aging infrastructure, etc.) to meet economic expectations whilst satisfying stakeholders and customers.

Digitally transforming water infrastructure is vital for sustainability as water companies face increasing pressures to remain competitive. This work focuses on using digital twin models to predict the performance of water treatment processes. Empowering water companies to control the risks and uncertainties associated with their operations. The main motivation for this work is to provide tools which water companies can use to improve the efficiency of their processes. Water companies will be able to control the day-to-day management of their treatment processes more easily, reducing the operational risks associated with their businesses.

A systematic framework is presented for the development of a digital twin that can predict water quality parameters, using historical data to train, test and validate the selected model. In practice, the real-world operating conditions can be constantly evaluated to detect perturbations. This approach can provide valuable guidance for water treatment operations, providing a tool to achieve better day-to-day performance management.

Type of Work:

Thesis (Masters by Research > M.Phil.)

Award Type:

Masters by Research > M.Phil.

Supervisor(s):