Monitoring a complex structure, such as the wing of an aircraft, for damage using sensors is known as Structural Health Monitoring (SHM). SHM can extend the overall lifetime of a structure whilst reducing its maintenance costs, but its use raises questions such as:
How should we position sensors across a structure to monitor for damage effectively? [1] For example, how should we position sensors across the wing of an aircraft to measure the stress accurately at a set of critical points?
How can we minimize the number of sensors used in the structure? Each additional sensor we use may weaken the structure, so generally we wish to reduce the number of sensors used.
What are the most suitable algorithms for analysing the data coming from the sensors? A wide range of algorithms are today used for analysing sensor data [2]. For best results, we should tailor the choice of algorithm to the SHM problem at hand.
The aim of this interdisciplinary PhD project is to use state-of-the-art methods from artificial intelligence, such as transfer learning and Bayesian optimization, to solve real, practical problems in the structural health monitoring of advanced composite materials. Working with partners from the Northern Ireland Advanced Composites and Engineering (NIACE) centre in Belfast, this project has the potential to have impact in a range of sectors including aerospace, automotive, space and construction.
The objectives of the research are:
This interdisciplinary project brings together expertise in machine learning, optimization and sensors [3,4] from the School of Computing, and in composite materials [5] from the Engineering Composites Research Centre. With scope to publish in both computer science and engineering journals, and opportunities to attend technical presentations at NIACE, the PhD student will develop skills relevant to a career in both data science and materials science.
[1] Sun et al. (2015) Optimal sensor placement in structural health monitoring using discrete optimization, Smart Mater. Struct. 24 125034.
[2] Farrar and Worden (2012) Structural Health Monitoring: A Machine Learning Perspective, Wiley.
[3] Hawe et al. (2008) A scalarizing one-stage algorithm for efficient multi-objective optimization, IEEE Trans. Magnetics, 44 (6) 1094-1097.
[4] Liu et al. (2016) Optimizing the configuration of a heterogeneous architecture of sensors for activity recognition, using the extended belief rule-based inference methodology. Microprocessors and Microsystems, 52 381-390.
[5] McIlhagger et al. (2014) Repair of damaged aerospace composite structures, in Polymer Composites in the Aerospace Industry.
Applicants should hold, or expect to obtain, a First or Upper Second Class Honours Degree in a subject relevant to the proposed area of study.
We may also consider applications from those who hold equivalent qualifications, for example, a Lower Second Class Honours Degree plus a Master’s Degree with Distinction.
In exceptional circumstances, the University may consider a portfolio of evidence from applicants who have appropriate professional experience which is equivalent to the learning outcomes of an Honours degree in lieu of academic qualifications.
If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.
The University offers the following levels of support:
The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £19,000 (tbc) per annum for three years (subject to satisfactory academic performance).
This scholarship also comes with £900 per annum for three years as a research training support grant (RTSG) allocation to help support the PhD researcher.
Due consideration should be given to financing your studies. Further information on cost of living
Submission deadline
Monday 30 April 2018
12:00AM
Interview Date
May 2018
Preferred student start date
Mid September 2018
Telephone
Contact by phone
Email
Contact by email