|Funding for:||UK Students, EU Students, International Students|
|Placed On:||2nd December 2019|
|Closes:||30th April 2020|
Coventry University has been voted ‘Modern University of the Year’ for three straight years (The Times/Sunday Times Good University Guide 2014−2016) and is ranked in the UK’s top 15 overall for the fifth year in a row (Guardian University Guide). We have a global reputation for high quality teaching and research with impact. Almost two-thirds (61%) of our research was judged ‘world leading’ or ‘internationally excellent’ in the Research Excellence Framework (REF) 2014.
Covering the full spectrum of land, rail, air and water-based transport, the Institute for Future Transport and Cities (IFTC) at Coventry University addresses the whole innovation chain from design, materials, advanced manufacturing, systems and supply chain as well as the business environment. Within the IFTC, the Autonomous Vehicles & Artificial Intelligence Laboratory (AVAILab) has been recently established. While open to a wide spectrum of applications, its main motivation is in conducting research that involves mathematical modelling, optimisation, soft and natural computing, self-organisation, swarm robotics and autonomous navigation.
Coventry University is inviting applications from suitably qualified graduates for a fully-funded PhD studentship.
The project is concerned with predictive maintenance in the railways and roads, which is paramount to maintain these critical systems in continuous operation. Maintenance issues include missing fasteners, deformed track geometry, subgrade/ballast instabilities, structural health problems, failures, obstructions, potholes, roadside vegetation, damaged guardrails, etc. Inspections typically involve foot-patrols, trolleys and/or measuring vehicles. These can be accurate at the expense of significant manpower and time. Maintenance is often reactive (too late) or preventive, regularly performed to decrease the probability of failure (too early). Instead, Predictive Maintenance (PdM) is informed by the infrastructure condition rather than its expected lifespan. PdM has been attempted using pattern recognition systems based on test-vehicle data. However, this requires the interruption of the normal traffic.
The use of remotely-controlled monitoring drones to identify maintenance needs has been proposed, with preliminary trials showing that data-acquisition time is drastically reduced. Drone-based inspection does not require stopping the traffic and can work in areas inaccessible to human operators. However, the use of Artificial Intelligence (AI) enabled autonomous drones is yet to be explored.
This project will investigate the railways and roads maintenance current practices and technologies, as well as relevant state-of-the-art autonomous navigation and pattern recognition algorithms. The aim is to identify application-based improvements and to develop a drone-based autonomous intelligent system to detect maintenance needs without disrupting the normal traffic of these transport systems. The project will be carried out within the AVAILab (availab.org) under the supervision of Dr Mauro S. Innocente (msinnocente.com, pureportal.coventry.ac.uk/en/persons/mauro-innocente).
To apply please contact:
Dr. Mauro S. Innocente (Mauro.S.Innocente@coventry.ac.uk).
To apply online, please visit pgrplus.coventry.ac.uk.
All applications require full supporting documentation, a covering letter, plus a 2000-word supporting statement showing how the applicant’s expertise and interests are relevant to the project.
Reason for eligibility restriction
PhD funding award
This is a full studentship, which includes tuition fees and living expenses for a doctoral candidate over 3.5 years.
Stipend rates set by UKRI with an annual projected average increase of 1.25% per year. Stipend for the first year will be £15,009
Start date: September 2020
Duration of study: Full-Time – between three and three and a half years fixed term
Interview dates: Estimated Date: 18/05/2020 (will be confirmed to shortlisted candidates)
Enquiries may be addressed to: Dr. Mauro S. Innocente, Mauro.S.Innocente@coventry.ac.uk
Type / Role: