Railway rolling stock fleet data analytics towards reliability and performance prediction

In this PhD research project, the student will be expected to conduct a comprehensive investigation into the rolling stock fleet in-service, risks, reliability, and operational performance to understand the reasons for the apparent differences in fleet reliability and performance data. A good technical understanding of the mechanical and electrical design configuration of rolling (passenger and freight services) is desirable in this project. Student will also be expected to explore and conduct investigation of the academic literature specifically within the mechanical, statistical, risk, performance, and reliability domain to determine the state-of-the-art dynamic statistical and other modelling methods using the concept of AI and machine learning approach towards anomaly detection, predictive, prescriptive analytics, and maintenance optimisation.

Finally, conduct multiple criteria decision analysis (MCDA) incorporating AI and Machine Learning techniques and use the ANN concept, time series modeling approach linked to dashboard systems.