Developing an AI-powered Platform that Automates Train Condition Monitoring, Cleanliness Assessment, and Predictive Maintenance

EYYA aims to revolutionise train condition monitoring and in-depot fault monitoring through an AI-driven platform that enhances efficiency, sustainability and safety in the rail industry. An innovative, scalable solution will be developed that transforms traditional monitoring and flagging of issues into a data-driven, real-time process with predictive rather than reactive capability, empowering operators to optimise maintenance schedules and improve fleet performance. The project focuses on developing advanced AI and IoT solutions to automate train condition reporting (cleanliness and damage) and depot fault reporting (signals and points) and provide predictive maintenance recommendations. Using cutting-edge technologies in computer vision and data analytics, EYYA will create a fully integrated cloud-based platform. Key objectives include: Developing AI algorithms to detect issues (damage, cleanliness, faults). Implementing scalable data pipelines for real-time processing of train images. Delivering actionable insights via intuitive dashboards tailored for Train Operating Companies and maintenance firms. This project is innovative in its integration of AI, IoT, and data insights to address rail industry challenges. Unlike traditional manual inspections, EYYA's platform offers predictive maintenance recommendations leading to enhanced operational efficiency, cost savings and improved sustainability. This approach bridges a significant gap in the rail industry, also enabling EYYA to scale into adjacent markets.

People

	Name	Telephone	Email	Office
	Dr Weifeng Chen Reader (Principal investigator) T: +44 (0)1895 265302 E: weifeng.chen@brunel.ac.uk	+44 (0)1895 265302	weifeng.chen@brunel.ac.uk	Eastern Gateway 202q