AMD powers AI track inspection solution for Japanese bullet train

This AI-driven approach marks a significant departure from the traditional, labour-intensive methods of manual track inspections, delivering enhanced speed, cost-effectiveness, and accuracy in compliance with Japan’s rigorous railway safety standards.

JR Kyushu's bullet trains cover a vast network exceeding 1,455 miles of track, achieving speeds of up to 161mph. With safety as its paramount concern, the company performs meticulous track inspections at regular intervals. To refine the precision and efficiency of these inspections, JR Kyushu has adopted a solution engineered by Tokyo Artisan Intelligence (TAI), powered by AMD. This system employs rapid image processing and sophisticated AI technology to identify and examine issues such as loose bolts and other track anomalies.

Kazuhiro Sakaguchi, Deputy Manager in the Engineering Division, Shinkansen Department at JR Kyushu, expressed his satisfaction with the innovation: “With the new solution from TAI and AMD, we were able to improve the efficiency of conventional track inspection, and we anticipate further improvements in inspection efficiency through future functional enhancements.”

Central to this inspection solution is a vision computing box mounted on a cart, which conducts track inspections at 12mph. This unit incorporates a high-speed camera and the FPGA-based Kria K26 SOM for AI-powered data and image analysis before and after capture. The Kria K26 SOM distinguishes itself as a compact, integrated platform featuring a custom AMD Zynq UltraScale+ MPSoC, DDR memory, non-volatile storage, a security module, and an aluminium thermal heat spreader.

Hiroki Nakahara, Co-Founder, and CEO of TAI highlighted the financial advantages of the AI implementation: “The most important benefit of AI in this case was reduction of cost. Replacing the conventional method of inspecting tracks on foot with carts has led to a dramatic improvement in operational efficiency.”

The AMD Kria SOM's programmability, durability, and embedded intelligence enable it to adapt to the diverse and evolving landscapes, conditions, and demands of JR Kyushu's extensive territory and passenger base. The dynamic natural environment of railway tracks necessitates the capacity for ongoing updates to the Kria SOM, ensuring the longevity and relevance of the technology investment.

Chetan Khona, Senior Director of Industrial, Vision, Healthcare, and Sciences Markets at AMD, commented on the broader implications of this technology: “AMD Kria SOMs are accelerating innovation at the Edge and simplifying solution development through deployment. JR Kyushu is a perfect example of how the endless programmability of Kria SOMs, combined with Edge AI computing, can automate processes and dramatically enhance operational efficiency across a variety of applications, from machine vision to industrial robotics and AI/ML computing.”