Machine learning for flow measurement diagnostics and uncertainty analysis

Machine learning for flow measurement diagnostics and uncertainty analysis

Eligibility: UK/EU/International graduates with the required entry requirements

Funding details: Bursary plus tuition fees (UK/EU/International)

Duration: Full-time – between three and three and a half years fixed term

Application deadline: 22nd March 2021

Interview dates: Will be confirmed to shortlisted candidates

Start date: September 2021 

For queries please contact Professor James Brusey.

Introduction

Coventry University is inviting applications from suitably-qualified graduates for a fully funded PhD studentship in the Machine Learning domain within the Centre for Data Science (CDS).

Coventry University has been voted ‘Modern University of the Year’ three times running by The Times/Sunday Times Good University Guide. Ranked in the UK’s top 15 (Guardian University Guide), we have a global reputation for high quality teaching and research with impact. Almost two-thirds (61%) of our research was judged ‘world leading’ or ‘internationally excellent’ in the Research Excellence Framework (REF) 2014.

CDS aims to develop cutting edge pure research in Artificial Intelligence, Data Science and Future Computing, linking fundamental science to real-world applications.

Data Science deals with the analysis and exploitation of large amounts of data (Big Data) drawing together disciplines as diverse as Computer Science, Artificial Intelligence, Statistics and Mathematics. The centre is organised according to three key themes:

  • Machine Learning for Big Data
  • Wireless Sensors and Internet of Things
  • Computational and Statistical Modelling
  • Advanced Computing

About the project

The aim of this PhD is to gain a deep understanding of how to estimate uncertainty in practical measurement systems and particularly in flow measurement based on Coriolis mass flow meters that need to deal with multi-phase (liquid and gas) flows.

The work will build on the applicant’s solid understanding of data science and machine learning and apply this understanding to practical problem of multiphase flow measurement.

A key part of the work will be applying neural networks or related methods to a problem where estimating uncertainty is important and relevant to industry. The results are expected to lead to advances in methods for uncertainty estimation in machine learning.

Multi-phase flow measurement is an important problem for the oil and gas industry, both for current fluids (e.g. oil/water/gas extraction) and for future carbon capture and storage (CCS) in depleted reservoirs (CO2 liquid/gas injection). Multiphase flow measurement errors/uncertainties are high, vary significantly with flow conditions, and have large financial impact (£100Ms) for taxation/carbon net zero accreditation purposes. Improved measurement, combined with diagnostics and uncertainty estimation, supports optimal reservoir management and accounting. Coriolis is an attractive, non-radiation based flow metering technology which has recently been extended to apply to multiphase flow; to do so requires multidimensional corrections to the ‘raw’ Coriolis measurements. Extending measurement models to provide on-line uncertainty estimation supports a current research priority in the UK national measurement strategy.

Funding 

Fully funded single studentship, which includes tuition fees and living expenses for a doctoral candidate over 3.5 years.

Stipend rates will be equivalent to those set by UKRI and will rise annually with a projected average increase of 1.25% per year. Tuition fees are adjusted yearly in line with the rates set by UKRI.

Benefits

The successful candidate will receive comprehensive research training including technical, personal and professional skills.

All researchers at Coventry University (from PhD to Professor) are part of the Doctoral College and Centre for Research Capability and Development, which provides support with high-quality training and career development activities. 

Candidate specification

  • A minimum of a 2:1 first degree in a relevant discipline/subject area with a minimum 60% mark in the project element or equivalent with a minimum 60% overall module average. 
    PLUS 
    the potential to engage in innovative research and to complete the PhD within a 3.5 years
  • a minimum of English language proficiency (IELTS overall minimum score of 7.0 with a minimum of 6.5 in each component)
In addition

The candidate must have some expertise in software development and a basic programming skills test will be requested of all eligible candidates.

How to apply

All applications require full supporting documentation, and a covering letter – plus an up to 2000-word supporting statement is required showing how the applicant’s expertise and interests are relevant to the project.

Apply to Coventry University
Coventry University No.1 Modern University No.1 Modern University in the Midlands
Coventry University awarded TEF GOLD Teaching Excellence Framework
University of the year shortlisted
QS Five Star Rating 2020
Coventry City of Culture 2021