Downer steps towards predictive train maintenance

Downer has rolled out its new data analytics platform, TrainDNA, the first step towards predictive maintenance.

The platform uses complex analytics and machine learning. It will capture data from trains and perform assessments to predict the remaining life of its components.

The solution will enable Downer to make decisions based on data to improve efficiencies in fleet maintenance.

Rollingstock Services Executive General Manager Tim Young said TrainDNA marks a turning point in asset management at Downer.

“This is a data analytics platform on steroids. Analysing such volumes of data will allow our team to establish trends in relative real time, enabling us to proactively predict failures and calculate the remaining life of an asset more effectively.”

A major advantage of the platform for customers is that the assessments take place while the train is in service and will not interrupt the operation.

Worker safety will be enhanced with TrainDNA because it has the potential to remove high risk inspections.

TrainDNA is currently deployed on Sydney’s fleet of Waratah trains and will be rolled out across other trains Downer maintains over the next year.

“These enhancements in Downer’s asset management capability will boost our ability to better predict failure rates and reduce unscheduled downtimes of the train fleet, resulting in enriched outcomes for our customers and our business,” Mr. Young says.

Development of TrainDNA took 18 months using in house expertise and a strategic partnership with Deakin University.

The platform was built on the Downer developed Neuroverse platform and was based on the Microsoft Azure software stack.

Related Stories



Interesting? Share this article