NVIDIA enables real-time railway analysis for Hitachi Rail

The company has adopted the NVIDIA IGX platform, an enterprise-level solution designed for industrial applications. NVIDIA IGX offers high-bandwidth sensor processing, advanced AI computing, and robust security features. It has been incorporated into Hitachi Rail’s new HMAX platform to enable real-time processing of sensor and camera data.

By eliminating delays between data collection and analysis, the HMAX platform allows Hitachi Rail’s clients to detect issues such as track defects, monitor the wear and tear of overhead power lines, and evaluate the condition of trains and signalling equipment more efficiently.

According to Hitachi Rail, conducting proactive maintenance is about seven times less expensive than dealing with emergency repairs caused by unexpected infrastructure failures. Its current AI-driven monitoring systems have already contributed to up to a 20% reduction in service delays and a 15% decrease in maintenance costs. Moreover, energy consumption has been reduced by up to 40% through optimised fuel use at depots. Hitachi Rail aims to further these savings with the implementation of real-time analysis powered by NVIDIA IGX and the NVIDIA Holoscan platform.

Koji Agatsuma, Executive Director and Chief Technology Officer for Rail Vehicles at Hitachi Rail, stated: “Using previous digital monitoring systems, it would take a few days to process the data and discover issues that need attention. If we can instead conduct real-time prediction using NVIDIA technology, that enables us to avoid service disruptions and significantly improve safety, reliability and operating costs.”

Real-time AI driving innovation

Hitachi Rail has leveraged NVIDIA IGX and the NVIDIA AI Enterprise software platform to expand its suite of HMAX applications, currently processing data from 8,000 railcars across 2,000 trains. NVIDIA AI Enterprise offers a range of tools, pretrained models, and frameworks to expedite the development of AI applications designed to enhance fleet and infrastructure monitoring.

The enhanced applications, soon to be available through the HMAX platform, will enable Hitachi Rail’s global customers to manage vast quantities of sensor data collected from trains. This data can come from existing systems or be imported from third-party software used by customers.

In the UK, for instance, each Hitachi Rail train is equipped with sensors capable of transmitting nearly 50,000 data points as frequently as every fifth of a second. AI infrastructure designed to handle this data flow can provide operators with timely alerts when maintenance is required on a component. These insights are also accessible through a chatbot interface, allowing operators to easily identify patterns and improve maintenance schedules.

Agatsuma emphasised the importance of timely identification, adding: “If a potential issue isn’t identified and fixed promptly, it can result in a service disruption that causes significant economic loss for our customers and impacts the passengers who rely on these transit lines. NVIDIA AI infrastructure has enabled us to get immediate alerts on thousands of miles of railway for the first time, which we anticipate will reduce delays and disruptions to passenger travel.”

Expanding benefits beyond rail monitoring

Hitachi Rail’s use of AI extends beyond the trains themselves. By equipping trains with cameras, the company can monitor overhead power lines for signs of wear or damage, preventing disruptive breakdowns. Previously, analysing one day’s worth of video data collected from trains could take up to ten days. With NVIDIA-accelerated sensor processing, data is processed in real time at the Edge, ensuring only the most critical information is sent to control centres for further action.