Postgraduate research opportunities

Machine Learning-Based Control of Pressure Waves in Subsurface Engineering

A theoretical understanding of the movement and interaction of pressure waves (i.e. pulses) along a fluid conduit (e.g. well bore) can be developed by analytical models and laboratory test rigs. Both approaches assume that the fluid and the conduit have largely uniform and known properties.

Number of places

1

Funding

Home fee, Stipend

Opens

20 December 2019

Deadline

27 March 2020

Duration

42 months

Eligibility

Undergraduate First class Hons/Distinction in a relevant discipline.

Project Details

The proposed PhD project will investigate if Machine Learning technologies can be used to rapidly characterise the properties (i.e. responses) of the conduit to create a model that can be used to both predict the behaviour and tailor the input of a mechanical pulse generator to create desired pressure waves.   The knowledge gaps addressed are the interlinked problems of: 1) how should the conduit and fluid response be represented, 2) how should the system be trained and 3) how can results be incorporated in a control system.  These are generic problems that draw on a significant volume of published work and a number of establish software platforms.  The work will be interdisciplinary requiring a candidate to have, or acquire, knowledge of both advanced engineering science (control theory and fluid dynamics) and computer science (ML, ANN etc).   The approach will use bench-top rigs to explore, assess and demonstrate a number of possible approaches before scaling the most promising to a larger lab-based rig and ultimately to a test bore hole. 

The proposed research project sits within the area of mechatronics that seeks to incorporate forms of pattern recognition into the control loop of, so called, cyber-physical systems. Similar approaches are being investigated for control of autonomous vehicles and wind turbines.    Essentially these systems are seeking to enable feedback control systems to responded to sensor data that provides more than single values (eg pressure, speed etc). It is applicable to a wide range of industries, including mineral extraction, waste processing, the water treatment industries.

Funding Details

Fees, stipend and project expenses

Supervisor

Prof. Jonathan Corney (DMEM)

Dr Bill Dempster (MAE)

Number of places

0

Further information

The student would join the University of Strathclyde’s 60-credit postgraduate training programme leading to the Postgraduate Certificate in Researcher Professional Development.

 The student will benefit from interaction with other academics and PhD students within an active research community, as well as being embedded within the SMART Pumps for Subsurface Engineering Project, a joint EPSRC-industry funded multi-institutional partnership, and interacting and engaging with researchers at the School of Geosciences at the University of Edinburgh.

 The PhD student will gain a range of technical, practical and problem solving skills required in the hydraulic industry. With the specific technical expertise, a wide range of career routes is possible, including the service industries (water, electricity, gas), consultancy, government agencies and the design and manufacture. Further academic and research routes will also be possible.