Hitachi Rail, a global transportation company that powers rail systems in more than 50 countries, is integrating NVIDIA AI technology to reduce maintenance costs for rail operators, reduce train downtime, and improve transit reliability for passengers.
The company is adopting NVIDIA IGX — an enterprise-grade, industrial-grade platform that delivers high-bandwidth sensor processing, powerful AI computing, functional safety capabilities, and enterprise security — on its new HMAX platform for processing sensor and camera data in real time.
By eliminating the delay between data collection and analysis, the HMAX platform will enable Hitachi Rail customers to more quickly detect rail tracks in need of repair, monitor degradation of overhead power lines, and assess the condition of trains and signaling equipment.
Hitachi Rail estimates that proactive maintenance costs around 7 times less than emergency repairs carried out when infrastructure fails unexpectedly. Its existing AI monitoring systems are already reducing service delays by up to 20% and train maintenance costs by up to 15%, and are reducing energy consumption by lowering fuel costs at train stations by up to 40%.
With real-time analysis using NVIDIA IGX and NVIDIA Holoscan platform for sensor processing, the company aims to further increase these savings.
“With previous digital control systems, it took a few days to process data and uncover issues that needed attention,” said Koji Agatsuma, CEO and CTO of rail vehicles at Hitachi Rail. “If we can instead make real-time predictions using NVIDIA technology, it will allow us to avoid service disruptions and significantly improve safety, reliability and operating costs.”
NVIDIA IGX powers the artificial intelligence engine in real time
Building on its existing collection of HMAX applications, currently running on data from 8,000 rail cars on 2,000 trains, Hitachi Rail has used NVIDIA IGX and NVIDIA AI for Business Software platform for building new accelerated AI applications that help operators monitor fleets and rail infrastructure. NVIDIA AI Enterprise offers tools, pre-trained models, and application frameworks to streamline the development and deployment of production-grade AI applications.
These applications, which will soon be available through the HMAX platform, can be used by the company's international customer base to process vast amounts of data transmitted from onboard sensors, taken from existing systems or imported from third-party software already in use by the customer.
In the UK, for example, each Hitachi Rail train has sensors reporting nearly 50,000 data points at a frequency of up to one-fifth of a second. AI infrastructure that keeps pace with this data stream can send timely alerts to train operators when a component on a train or rail line needs maintenance. AI insights can also be accessed through a chatbot interface, helping operators easily identify trends and opportunities to optimize maintenance schedules and more.
“If a potential issue is not identified and addressed quickly, it can lead to a service disruption that causes significant economic loss for our customers and impacts the passengers who rely on these transit lines,” Agatsuma said. “NVIDIA’s AI infrastructure has enabled us to receive immediate alerts on thousands of miles of rail track for the first time, which we anticipate will reduce delays and disruptions to passenger travel.”
Long-term driving benefits
The opportunities go beyond monitoring trains and tracks.
By installing cameras on top of trains, Hitachi Rail can monitor overhead power lines to identify failing electrical cables and help prevent disruptive faults. Traditionally, it takes up to 10 days to process a day’s worth of video data collected by the train. With NVIDIA-accelerated sensor processing, data can be processed in real time at the edge, sending only the relevant information to operational control centers for analysis and action.
Learn more about the NVIDIA IGX platform.
Main image courtesy of Hitachi Rail.
