Postgraduate research project

Advanced Drivetrain Monitoring through use of Machine Learning and Optical Fibre Speckle Patterns (GE Aerospace)

Funding
Competition funded View fees and funding
Type of degree
Doctor of Philosophy
Entry requirements
2:1 View full entry requirements
Faculty graduate school
Faculty of Engineering and Physical Sciences
Closing date

About the project

Embark on a ground-breaking Ph.D. journey poised to revolutionize the field of large aerial drone condition monitoring.

 

Through harnessing the power of Machine Learning (ML), Artificial Intelligence (AI), and advanced optical sensing technologies the vision of our team is to usher in a new era of precision and efficiency for aviation.

According to the FAA's projections, by 2030, large drones (with payloads exceeding 90 kg) are expected to outnumber traditional aircraft by a ratio of 3 to 1. Despite this promising trajectory, the primary challenge lies in ensuring safety due to the constraints of limited ground crew.

This PhD considers development of optical speckle patterns analysed by machine learning, to interpret strains and temperature changes along the length of an optical fibre. Strategically integrated into an airframe this would enable real-time condition monitoring in a package that streamlines Size, Weight, Power (SWAP) metrics, considered essential for aviation.

With a focus on elevating sampling frequency of current technology from 10Hz to over 10kHz and developing more innovative AI algorithms, this collaborative project, in partnership with GE Aerospace, aims to reshape the landscape of optical sensing technology for rotorcraft drivetrain monitoring.

Join us at the forefront of innovation and contribute to the future of high-performance condition monitoring.