Downer uses Microsoft Azure to improve train safety in Sydney

Downer uses Microsoft Azure to improve train safety in Sydney

Downer Group, an Australia-based firm that designs and constructs infrastructure, has chosen the Microsoft Azure cloud to help it monitor the performance of trains in New South Wales and reduce maintenance downtime. 

The New South Wales Government recently ordered many Waratah Series 2 trains to provide Sydney’s citizens with a greater number of safer and more comfortable and accessible trains. According to a recent Microsoft news story, Downer took the opportunity to leverage the 30,000 signals that each train sends to Downer every 10 minutes via more than 300 internet of things (IoT) sensors and almost 90 cameras in a Sydney station. 

“We’re using those sensors to tell us about the health of the train – it’s almost like having a blood pressure reading,” said Mike Ayling, general manager of Digital Technology and Innovation at Downer. 

Downer is now turning this data into actionable insights with the help of Microsoft Azure. Its TrainDNA solution has been deployed to capture and store all Downer’s IoT data, and use data analytics, artificial intelligence (AI) and machine learning to transform it into insights to help engineers make better-informed decisions. These insights save money and reduce maintenance and downtime, while also improving the safety of its vehicles. 

“What these new systems and some of the Microsoft technology enables us to do is use that data and analyse that data, far quicker and far faster than we’ve ever been able to do before,” said Ayling. “This is where some of the AI comes in. Turning that data into an insight, into something that we can do something with, to say “this is happening, we need to make a correction to our maintenance programme, or we need to do something different.” Those insights, that’s really the gold dust.”

The firm is also considering the use of Microsoft’s mixed reality technology, Microsoft HoloLens, to further train maintenance.

Number of views (4875)/Comments (-)

Comments are only visible to subscribers.