AI manages the world's largest high-speed rail network

China applies an AI system that processes large amounts of data in real time, helping to quickly alert high-speed railway maintenance teams .

China is using an artificial intelligence (AI) system in Beijing to operate and maintain the country's high-speed rail network, Interesting Engineering reported on March 12.

High-speed trains parked on the railway, photographed from above. (Photo: ximushushu/iStock)

With a total length of about 45,000km, China has the largest high-speed rail network on the planet.

The AI ​​system processes large amounts of data across China in real time, and can alert maintenance teams when unusual situations occur within 40 minutes with an accuracy rate of up to 95%.

Liu Daoan, a senior engineer at the infrastructure inspection center of the China State Railway Corporation, commented that the system worked effectively. "The system helps on-site operations teams conduct re-inspections and repairs as quickly as possible ," Daoan said in research published in the specialized journal China Railway.

China's high-speed railway is the fastest in the world, with an operating speed of 350km/h and is expected to increase to 400km/h next year. The country plans to continue expanding its rail network until every city with a population over 500,000 people is connected.

With AI, the number of minor track defects on high-speed railways operating in China decreased by 80% in the past year. None of these lines received a deceleration warning due to serious track problems. Research shows that the amplitude of track displacement due to strong winds is also significantly reduced thanks to AI.

America's rail network is facing predictable challenges, with improper maintenance leading to constant safety risks. Over the past 50 years, the average number of train derailments has exceeded 2,800 per year.

More than a decade ago, countries such as Germany and Switzerland first recognized the possibility of applying AI to railway management. Both are trying to use AI to improve their railway networks. However, the networks in these countries are smaller than in China.

To train the AI ​​system, Chinese scientists must collect a huge amount of raw data. They took data from records of ship hull movements, track vibrations, waveform values ​​and meteorological records. Previously, the maintenance center issued warnings once a week. Now, thanks to AI, reports are released daily.