ANTI-SLIP: A study on using Network Rail's and train borne information to anticipate and mitigate the impact of slippery rail

ANTI-SLIP: A study on using Network Rail's and train borne information to anticipate and mitigate the impact of slippery rail

Liverpool John Moores University

With support from Network Rail and Merseyrail


SUMMARY

This project aims to construct a framework of integrating and analysing multi-source real-time data – from track-side data streams and train-based datasets - to deepen our understanding of low adhesion and provide better decision support for mitigating its effect. The involves developing higher resolution automated warnings for drivers, and techniques to help validate the effectiveness of current mitigation strategies and suggest optimal solutions.


AN INTERVIEW WITH THE PROJECT LEAD


Dr Trung Thanh Nguyen, Liverpool John Moores University (LJMU)

How would you describe your project in one Tweet (i.e. 280 characters)? 
"This project will construct a framework of integrating and analysing multi-source of data, including track-side, train-side and weather data, to deepen our understanding towards low adhesion and provide better decision support for mitigating its impact on performance."

What are the benefits for industry, within in the context of the wider forecasting adhesion landscape?  
"This project will potentially help enhance the current adhesion reporting/warning procedure and provide more insights into adhesion, helping managers to have more targeted intelligence about where and why performance-related adhesion occurs. It will also help validate the effectiveness and efficiency of mitigation strategies. Finally, this project will provide optimal suggestions on certain adhesion mitigations to assist managers with effective decision making. Ultimately, the proposed solutions will benefit passengers with safer and more reliable service."

What are you hoping to achieve with this project? 
"We will design data analytic techniques that can automatically warn trains and drivers of potential adhesion-related effects that could impact performance  on individual sections of tracks with high resolution. We will also develop techniques that help validate the effectiveness of some current mitigation strategies and suggest optimal solutions and recommendations of how the current mitigations can be improved, e.g. providing optimal treatment plans or improving braking practice. This project will initially focus on a case study relating to the Northern line of Merseyrail."

Team members
Job title and organisation
Interests
Dr Trung Thanh Nguyen
Reader
Co-director of the LOOM institute
Liverpool John Moores University
  • Optimisation
  • Data analytics
  • Machine learning
  • Rail transportation
Igor Deplano
Research Fellow
Liverpool John Moores University
  • Optimisation
  • Data analytics
  • Machine learning
  • Rail transportation
Dr. Ran Wang
Research Fellow
Liverpool John Moores University
  • Optimisation
  • Rail transportation
Dr Qian Zhang
Senior Lecturer
Liverpool John Moores University
  • Data-driven modelling
  • Multi-objective optimisation
  • Robotics and control
Ala Al-Kafri
Liverpool John Moores University
  • Data analytics
  • Rail transportation




Reports and Research in Brief

More
Liverpool John Moores University
share