Conditioning monitoring of train system from sub-systems to predictive fault detection
This Final Year Project (FYP) aims to explore the possibility of carrying out predictive analysis to predict potential train faults for Singapore Mass Rapid Transport (MRT) from the available data provided. The primary objective of this project is to determine valuable indicators within the av...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/167558 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Summary: | This Final Year Project (FYP) aims to explore the possibility of carrying out predictive analysis
to predict potential train faults for Singapore Mass Rapid Transport (MRT) from the available
data provided. The primary objective of this project is to determine valuable indicators within
the available data that can be utilized as performance metrics for the purpose of predictive
analysis on MRT trains in Singapore.
This report discusses the different analytical methods employed and their outcomes in
assessing the feasibility of implementing predictive maintenance in Singapore's railway system
through conditional monitoring, which is monitoring the various subsystem of a train system.
Additionally, the report also briefly addresses the limitations of the current datasets and
collection methodologies. Since there is no existing predictive maintenance system in
Singapore's railway system, the initiation and submission of this project aim to overcome the
identified shortcomings and use the promising performance indicators identified to establish a
framework for predictive maintenance in Singapore's railway system.
Through the analysis of the dataset a positive trend is observed relating the correlation of the
increasing occurrence of “departure” indicator to a fault occurring of the component under the
subsystem of “Passenger Information System”. However, as discussed later in the report, there
are challenges faced in using the dataset to achieve predictive analysis. |
---|