Research Fellow in Predictive Analytics

The Position

This will involve experimental design, software development and data science, carrying out research and development of models to predict and diagnose asset health condition. Candidates will be expected to have expertise and track record in all of the areas listed below. Please do apply even if you only meet some of the criteria:

• Condition monitoring and asset management of engineering systems, and subsystems, particularly rotating machines.
• Data Science – handling and processing large data sets (experience across multiple domains welcome).
• Research in Artificial Intelligence – including predictive modelling, pattern analysis and recognition.
• Demonstration of AI algorithms implementation

To be considered for the role, you will be educated to a minimum of PhD level in an appropriate discipline, or have significant relevant experience in addition to a relevant degree. You will have an ability to plan and organise research programmes, to ensure successful completion, including the ability to supervise and delegate work. You will have some experience of teaching at undergraduate and/or postgraduate levels, an ability to work within a team environment, to lead teams and excellent interpersonal and communication skills.

The Project

The researcher will work on will be to join a team to develop and deploy intelligent decision support software for enhanced operation and predictive maintenance of pumps and rotating assets within the UK’s submarine capability. The project has three main aims:

• Completion of a detailed review and assessment of the data and experience associated with existing rotating plant equipment, including current approaches to maintenance (run to failure, time-based, and predictive), existing models and processes used to inform current asset health, data captured (both online through condition monitoring, as well as operational parameters, and offline during routine inspection and maintenance activities), platforms or technologies employed to manage and analyse the data. This will provide the baseline data sets and analytics approaches currently employed
• Development of a proof-of-concept tool, which will provide a single point of access for historic data and records, analyses tools and a RAG-type indicator showing the current estimate of each rotating asset’s condition.
• Development of a suite of demonstration analytics, accessible through the visualisation tool, and providing support for typical through life asset management activities. This will include:
  • Population-based predictive analytics. Typically used for smaller value, non-critical pumps to support time-based maintenance strategies.
  • Operations-based population predictive analytics. An extension of population-based analytics, but including the impact of operational environment and duty cycle into the analysis.
  • Predictive models of performance degradation.
  • Operational anomaly detection and normal behaviour benchmarking.

Department of Electronic and Electrical Engineering (EEE)

The position will be hosted in the Department of Electronic and Electrical Engineering is internationally recognised for its research excellence, industrial engagement and first-class teaching programmes. Further information on the Department can be found at www.strath.ac.uk/engineering/electronicelectricalengineering. The successful candidate will join the Intelligent Systems Team in the Advanced Electrical Systems group in the Institute for Energy and Environment in the Department. While the primary focus will be the delivery of the project successful candidates will join a vibrant team delivering a wider range of projects across a range of industry partners, with opportunities for career development through and potentially beyond the fix-term of the post.

Security Clearance

Possession and maintenance of security clearance (SC) is an essential requirement for this post. Further details can be found here: www.gov.uk/government/publications/united-kingdom-security-vetting-clearance-levels/sc-guidance-pack-for-applicants