Anglia Ruskin University ARU Featured PhD Programmes
European Molecular Biology Laboratory (Heidelberg) Featured PhD Programmes

Machine Learning Predictive Maintenance for Sustainable Urban Drainage. Engineering PhD Studentship


College of Engineering, Mathematics and Physical Sciences

, Prof Damien Batstone , Monday, May 24, 2021 Competition Funded PhD Project (Students Worldwide)

About the Project

Join a world-leading, cross-continental research team

The University of Exeter and the University of Queensland are seeking exceptional students to join a world-leading, cross-continental research team tackling major challenges facing the world’s population in global sustainability and wellbeing as part of the QUEX Institute. The joint PhD programme provides a fantastic opportunity for the most talented doctoral students to work closely with world-class research groups and benefit from the combined expertise and facilities offered at the two institutions, with a lead supervisor within each university. This prestigious programme provides full tuition fees, stipend, travel funds and research training support grants to the successful applicants. The studentship provides funding for up to 42 months (3.5 years).

Eight generous, fully-funded studentships are available for the best applicants, four offered by the University of Exeter and four by the University of Queensland. This select group will spend at least one year at each University and will graduate with a joint degree from the University of Exeter and the University of Queensland.

Project Description

Background

Typically, wastewater treatment equipment is serviced on a periodic or reactive basis. Consequently, Water and Sewerage Companies (WaSCs) often over maintain or undermaintain process equipment, resulting in unnecessary expenditure and possible periods of non-compliance in their discharge consents, to the detriment of the consumer and the natural environment.

Project Methodology

We plan to develop techniques of predictive maintenance based on Data-Driven Machine Learning, in which extensive historical data donated to the project by Hydro International will be used to train Machine Learning algorithms such as Artificial Neural Networks to identify wastewater treatment equipment in danger of failure. In particular, predictive maintenance can use Machine Learning in 4 distinct ways:

Regression models can be trained to predict Remaining Useful Lifetime (RUL)

Classification models can be developed to predict failure within a given time window

Models can be trained to flag anomalous behaviour in the asset set (Anomaly Detection)

Survival Models predict how failure probability will evolve over time

We will develop novel approaches to asset management using these techniques; essentially developing data-based digital twin models of the asset set capable of estimating equipment condition and failure risks, taking into account regional and seasonal variations. We envisage the various stages of the project as follows:

Year 1 (Exeter): In the first year the student will research methods of predictive maintenance applied in other areas and get up to speed with Data Science techniques for Regression, Classification and Anomaly detection. S/he will catalog the different equipment in the data set and study operation and failure modes; this will involve extensive interaction with Hydro International in the UK and possibly US sites. S/he will start to develop Classification models for failure prediction, examining methods such as Support Vector Machines and Naive Bayes methods; S/he will also research methods of feature extraction and selection to fully understand the dataset available.

Output: Classification model for failure prediction; conference paper in Water World Congress/IWA conference/CCWI.

Year 2 (Exeter): In the 2nd year the student will continue with this work and write a paper on Classification Models for predictive maintenance for water systems.S/he will also develop predictive models based on the other methodologies, particularly RUL regression models and anomaly detection models, and compare the different approaches.

Output: Journal paper in Water Research/Comp. in Chem Eng., toolkit for predictive maintenance based on data-driven machine learning methodologies

Year 3 (Queensland): The student will work in Australia for their 3rd year and will apply the models developed in the first 2 years to distinct data sets from Urban Utilities which represent significantly different environmental conditions pertaining to that region. This will demonstrate the adaptability of these techniques to a wider range of conditions. S/he will also interact with WaSCs in Australia, leveraging links from the Advanced Water Management Centre. The student will also commence the process of writing their thesis, work which will continue on their return to Exeter.

Output: Journal paper on comparative methodologies, 2nd conference publication, thesis.

Find out more about the PhD studentships www.exeter.ac.uk/quex/phds

Successful applicants will have a strong academic background and track record to undertake research projects based in one of the three themes of: Healthy Living, Global Environmental Futures and Digital Worlds and Disruptive Technologies.

The closing date for applications is midnight on 24 May 2021 (BST), with interviews taking place week commencing 12 July 2021. The start date is expected to be 10 January 2022.

Please note that of the eight Exeter led projects advertised, we expect that up to four studentships will be awarded to Exeter based students.


Funding Notes

The QUEX Institute studentships are available for January 2022 entry. This prestigious programme provides full tuition fees, stipend of £15,609 p.a, travel funds of up to £15,000, and RTSG of £10,715 over the life of the studentship. The studentship funding is provided for up to 42 months (3.5 years)

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here

The information you submit to University of Exeter will only be used by them or their data partners to deal with your enquiry, according to their privacy notice. For more information on how we use and store your data, please read our privacy statement.

* required field

Your enquiry has been emailed successfully



Search Suggestions

Search Suggestions

Based on your current searches we recommend the following search filters.



FindAPhD. Copyright 2005-2021
All rights reserved.