School of Engineering - Artificial Intelligence based multi-objective optimisation for energy management in dynamic flexible manufacturing systems

The School of Engineering of the University of Glasgow is seeking a highly motivated graduate to undertake an exciting 3.5-year PhD project entitled ‘Artificial Intelligence based multi-objective optimisation for energy management in dynamic flexible manufacturing systems’ within the Division of Systems Power and Energy.
Manufacturing enterprises have faced the challenge of increasing energy prices and emission-reduction requirements. So far, however, the potential of reducing energy consumption at the system-level has been largely ignored. At this level, operational research methods can be employed as an effective energy-saving approach. Such methods have been adopted for flexible job shops in manufacturing industry. In the future, the requirement on manufacturing system flexibility within the system will be increased to realise mass customisation and personalisation. On-line decision making and optimisation techniques to accommodate these uncertainties and to maintain robustness of the flexible manufacturing system is becoming increasingly important within the background of industry 4.0.
The main goal of this project is to address the multi-objective dynamic flexible job shop scheduling problem for reducing energy consumption and its related costs. Composite dispatching rules which include electricity consumption as an objective to minimise when jobs arrive at the flexible production system at randomly distributed times will be developed. A dispatching rule is a rule that prioritises all the jobs that are waiting for processing on a machine, which is widely used in the manufacturing system for decision support, especially for an on-line environment. The prioritisation scheme may take into account the job’s attributes, the machines’ attributes as well as time. Compared to exact algorithms and meta-heuristics, dispatching rules are easy to implement and fast to calculate, which can be used to schedule jobs in real time. Existing dynamic scheduling algorithms will be extended to address the uncertainties within the manufacturing system as a benchmark.
Artificial intelligence techniques such as genetic programming will be used to construct the composite dispatching rules. Meta-heuristics based optimisation approaches will be developed, which include electricity consumption as an objective to minimise when uncertainties such as machine breakdown occur in the production system at randomly distributed times. In conjunction, reinforcement learning will be used to identify the patterns of uncertainties and the electricity consumption of assets in the manufacturing systems, especially for on-line realisations.
Candidates should possess at least a 2:1 in their undergraduate degree in Engineering, Operations Management, Computer Science, Applied Mathematics or a related subject.
A relevant Master’s degree and / or experience in one or more of the following will be an advantage:
Meta-heuristics, Artificial Intelligence, Engineering Optimisation;
Software skills, such as Java or Python programming.

Application for this scholarship is made by using the online system at the following link for admission as a postgraduate research student to the admission team in the Recruitment and International Office:
http://www.gla.ac.uk/research/opportunities/howtoapplyforaresearchdegree/
It should be noted that this application is to gain admission to our PGR programme with the decision on this being based on your academic achievements, and an offer of admission may be sent out before a decision on this Scholarship is made. Candidates applying for this Scholarship will have their applications further vetted as to acceptability to this Scholarship and will most likely have an interview/discussion with the supervisor before any decision is made.