Rail (real) safety issues: predictive maintenance for Singapore railway

Abstract

This Final Year Project (FYP) aims to evaluate the possibility of performing fault prediction in Singapore’s rail network from available data. The quest to predict railway faults in Singapore is still underway, spearheaded by the Rail Enterprise Asset Management System (REAMS) project jointly led by SIEMENS and ST Engineering Consortium formed in 2018.

This project’s main purpose is to identify useful indicators in existing data that can be used as performance indicators for predictive maintenance. The focus is on the observable trends in the Automatic Train Supervision (ATS) and Corrective Maintenance Data (CMD) records, with findings supported by the F&D Daily Report, Workorder (WO), and Fault & Delay (F&D) data.

This report covers the analytic approaches taken and their results to evaluate the possibility of performing predictive maintenance in Singapore’s rail network. It also briefly covers existing shortcomings of the available datasets. As no predictive maintenance has been implemented in Singapore’s rail network, the commencement and submission of this project is done in the hope that the identified shortcomings may be overcome, and featured potential performance indicators can be built upon to establish a foundation for predictive maintenance in Singapore’s rail network.