China’s mind-boggling ‘claims – New AI system can design hypersonic weapons by itself without human intervention
China’s mind-boggling ‘claims – New AI system can design hypersonic weapons by itself without human intervention

China’s mind-boggling ‘claims – New AI system can design hypersonic weapons by itself without human intervention

Although the United States remains a leader in the field of anti-submarine warfare and artificial intelligence, China’s efforts to exploit “quality data” for military use have brought Beijing far ahead of the Pentagon, said a former U.S. Navy admiral.

A new paper published in a journal run by China’s aerospace industry claims that Beijing has made significant progress in building an AI (artificial intelligence) system that can design new hypersonic weapons independently.

“It was frustrating for all of us who worked with large Excel spreadsheets, deciding which programs we should promote and which ones we should slow down,” he said. Admiral Bill Moran (retired), a former U.S. Naval Operations Deputy Chief of Staff while speaking at a Navy League webinar on artificial intelligence in November 2021.

On March 16, a team of researchers led by Professor Le Jialing of the China Aerodynamics Research and Development Center in Mianyang, Sichuan, announced their fund in Journal of Propulsion Technology.

Le has been an adviser to the Chinese military on hypersonic weapon technology for more than three decades, according to publicly available information.

As hypersonic research in China advances to Mach 8 – eight times the speed of sound – and beyond, the amount of experimental data to be processed and analyzed has also increased significantly, researchers say.

In such a situation, the human brain can no longer keep up with the high pace of hypersonic technology development according to Le and his team.

Countries around the world are racing to achieve hypersonic flight capability, and a significant part of this race is simulation experiments that almost create extreme hypersonic flight conditions in ‘wind tunnels’.

File image: China’s Hypersonic Wind unnel

How AI systems identify ‘shock waves’

When a missile or air object approaches speeds that exceed the sound, it experiences something called a ‘shock wave’, which is basically a disturbance in the air around the vehicle that can cause extremely violent pressure changes over its surface.

So researchers use wind tunnels to basically blow wind at high speeds over their vehicle design to see if their design can work desirably under such conditions.

China hypersonic aircraft
Picture of what is believed to be a Chinese hypersonic plane. (CCTV screenshot)

Now, there are different types of shock waves that can have different impacts on the vehicle, and it is crucial to clearly identify these shock wave types in order to design hypersonic vehicles.

Each wind tunnel experiment can produce around tens of thousands and thousands of simulated images of atmospheric disturbances around the vehicle, and these images must be studied manually by experienced scientists, often pixel by pixel, to identify what disturbance is a shock wave or what type of shock wave it is.

An image of a hypersonic wind tunnel test contains a large amount of turbulence, and it can take human experts “an enormous amount of time and energy to feel the critical shock wave structures pixel by pixel,” Le and colleagues told the newspaper.

Li’s team claims to have built an artificial intelligence machine that could identify most shock waves that occur in wind tunnel tests without even being instructed in what to look for.

Normally, the AI ​​systems are to be taught by humans in a typical training session, which would involve the researchers carefully outlining a shock wave by labeling it with information so that the AI ​​can then proceed to identify themselves.

The AI ​​will start making mistakes so it needs to be corrected repeatedly and this is how it learns to identify a particular shock wave correctly. However, Li claims that his AI system did not need any training at all!

The researchers used a technique called ‘unattended segmentation’ based on a mathematical theory of graphics that can form a relationship between seemingly unrelated objects.

The machine would sense what it thought was a shock wave by examining the location, brightness, and color of each pixel. The AI ​​would use these initial results as training material to continuously improve its performance in shock wave recognition until it could detect the shock wave patterns.

DF-17
China’s DF-17 hypersonic missiles. (Image: China Military Online)

Perfect match

According to the researchers, the shock waves identified by their AI corresponded 85 percent to those marked by human experts.

Moreover, the overall accuracy of the AI ​​system was almost 4 times higher than traditional computer software, and it was based on a cheap, 3-year-old graphics card that took about 9 seconds to process an image.

If true, such a remarkable feat could give China an advantage, not only in designing hypersonic vehicles, but also in military applications such as autonomous target detection and recognition of their weapons based on deep learning and deep neural networks.

“Our future cruise missiles will have a very high level of artificial intelligence and autonomy,” such that commanders will be able to “control them in real time or use a fire-and-forget mode or even add more tasks for in-flight missiles, ”a senior Chinese missile designer said in 2016.

Last year, PLA missile scientists from Rocket Force Engineering University said that the accuracy of hypersonic weapons could be improved by more than 10 times if complete control of the machine is given.

They had released a paper describing how AI can write the weapon’s software “on the fly” while moving at hyper-speed through a unique flight control algorithm.

Leave a Reply

Your email address will not be published.