|Funding for:||UK Students, EU Students, International Students|
|Funding amount:||See advert text|
|Placed On:||4th August 2022|
|Closes:||18th September 2022|
‘Leaves on the line’ is a perennial problem for railways worldwide. Contaminants (such as from compressed leaf matter) in the critical wheel/rail contact can mean that services are seriously disrupted as trains miss station stops, or in extremis pass signals at danger. The rail industry invests large amounts of time, effort, and money on prediction of the occurrence of these event and cleaning of the railhead. To date, there is no reliable means of detecting where these events occur, how long they last and or how effective the mitigations are. This project will build on a concept developed by the Control System Group that uses in-service rail vehicles as ‘sensors’ to detect what the adhesion conditions are in real-time. Read more here.
The core concept of the work is the use of novel processing methods to interpret changes in the running dynamics of a rail vehicle, and from this to infer the adhesion conditions. The successful candidate will apply data processing, artificial intelligence and machine learning method to a data set that has been recently collected from full scale trials. The candidate would ideally have a familiarity with programming (MATLAB, Python, etc.), data processing methods, and a knowledge of dynamics.
The candidate will be joining the long-established Control System Group in the Wolfson School of Mechanical, Electrical and Manufacturing Engineering. The group has a focus on intractable industrial problems in the control, condition monitoring and mechatronics areas. The group has worked with a wide variety of partners across the transport, energy, and health sectors.
Is the project University funded or self-funded?: University funded
Funding eligibility: Competition funded project (students worldwide)
Who is eligible to apply?: Both UK and International
Full-time/part-time availability: Full-time (3 years)
Closing Date: 18th September 2022
Advert Reference: P2SAM22-22
Type / Role: