Broken rail detection – Rail health monitoring

Location: West Perth, WA

Duration: 5 months

Proposed start date:  TBD

Keywords: Software Engineering, Algorithm Development, C++, Python, Machine Learning

Please note: Due to funding requirements, students must have Australian Citizenship or Permanent Residency to apply. Any applicants not meeting this requirement will be ineligible for this project.

This internship is exclusive to PhD students at the University of Western Australia as this project is from an existing relationship with University of Western Australia. Any applicants not meeting this requirement will automatically be deemed ineligible for this project.

Project Background

Broken rails present a serious safety risk to rail operators in both freight and commuter networks as a key contributor to derailments. MRX Technologies has developed a unique and innovative train mounted measurement system that monitors rail continuously to provide near real time indication of potential rail breaks. This technology uses an array of magnetic field sensors to analyse the interaction of a magnet (mounted to the sensor head) and the rail steel. The sensors are robustly and reliably capable of observing discontinuities in the rail.

MRX’s Broken Rail Detection (BRD) technology is currently being trialled on some rail networks. The system alerts train control and track maintenance personnel with the precise location of a detected break to prevent further rail traffic over the break and allow immediate rectification works to commence.

BRD technology supplements existing methods of broken rail and rail defect detection. Most rail networks depend on track circuit technologies to facilitate signalling of rail traffic, a by-product of this is real time monitoring for rail breaks. With the advent of communication-based signalling systems, track circuit infrastructure is no longer required, and the passive detection of broken rails no longer exists. Even where track circuits are providing broken rail detection, the coverage is not complete and track circuits inherently depend on complete separation to break the circuit. BRD does not face the same limitations, with the technology able to monitor every metre of rail and detect rail that is not completely broken.

MRX has identified a significant opportunity to develop BRD technology further, utilising the existing hardware to detect and monitor smaller rail defects through the use of sophisticated software processing algorithms. If successful, this will add functionality to the system to allow BRD to pre-empt rail breaks and drive corrective actions.

Research to be Conducted

Objectives:

1.  Enhance existing BRD technology through the use of sophisticated software processing algorithms;

2. Develop prototype algorithms (direct and machine learning-based) to detect and classify small surface defects in rail steel and welds;

3. Undertake trending analysis to track the characteristics of welds or defects and look for degradation before notifying maintenance personnel to tack action.

Skills Required

MRX are looking for a PhD student who meets some of the skills below:

  • C++ and/or Python programming
  • Machine Learning
  • Software Engineering
  • Ability to work in a multidisciplinary team
  • Strong communication skills

Additional Details

The intern will receive $3,000 per month of the internship, usually in the form of stipend payments.

It is expected that the intern will primarily undertake this research project during regular business hours, spending at least 80% of their time on-site with the industry partner.  The intern will be expected to maintain contact with their academic mentor throughout the internship either through face-to-face or phone meetings as appropriate.

The intern and their academic mentor will have the opportunity to negotiate the project’s scope, milestones and timeline during the project planning stage.

Applications Close

 29 August 2018

Reference

INT – 0492

FOR ANY ENQUIRIES ABOUT THIS INTERNSHIP

03 8344 1785
contact@aprintern.org.au