Latest news with #CommandControl&Simulation
The Star
2 days ago
- Science
- The Star
China is working on an ultra-fast torpedo powered by AI for submarine warfare
In the recent Chinese blockbuster Operation Leviathan , an American nuclear submarine uses hi-tech acoustic holograms to bamboozle Chinese torpedoes and their human operators. Months after the film hit cinema screens, military researchers in China revealed they were working on an artificial intelligence system designed to cut through exactly this type of underwater deception. In a peer-reviewed paper published in Chinese-language journal Command Control & Simulation in April, the team from the PLA Navy Armament Department and China State Shipbuilding Corporation said their system had unprecedented accuracy for torpedoes travelling at high speeds. Tested against data from classified high-speed torpedo ranges, the technology achieved an average 92.2 per cent success rate in distinguishing real submarines from decoys even during tense exchanges, according to the paper. That is a leap from the legacy systems that often miss the target. Future submarine warfare hinges on deceiving torpedoes using illusions. Hi-tech decoys – as dramatised in Operation Leviathan – are used to replicate a vessel's acoustic signature, generate a false bubble trail to make it look like it is making an emergency turn, or deploy in coordinated swarms to project ghost targets across sonar screens. These tactics are particularly effective against what is known as ultra-fast supercavitating torpedoes – weapons that generate cavitation, or vapour bubbles, around their hulls to reduce drag. The resulting roar drowns out genuine target echoes while distorting acoustic fingerprints, according to the Chinese researchers. 'Current target recognition methods for China's underwater high-speed vehicles prove inadequate in environments saturated with advanced countermeasures, necessitating urgent development of novel approaches for feature extraction and target identification,' said the team led by senior engineers Wu Yajun and Liu Liwen. 'Only those underwater high-speed systems equipped with long-range detection capabilities and high target recognition rates can deliver sufficient operational effectiveness,' they added. The solution they proposed came from an unorthodox combination of physics and machine learning. Facing scarce real-world combat data, the team began by simulating decoy profiles using hydrodynamic models of bubble collapse patterns and turbulence. To do that they used raw data collected from the PLA Navy's high-speed torpedo test range. These simulations were then added to a 'generative adversarial network' – a duelling pair of AI systems. One of them, the generator, refined decoy signatures by studying submarine physics and acoustic principles. Its opponent, the discriminator, trained to detect flaws in these forgeries using seven layers of sonic pattern analysis. After many rounds of training, the system had created a huge collection of artificial decoy profiles. The AI uses a specialised neural network architecture inspired by image recognition, according to the paper. Sonar signals go through a process where they are normalised for amplitude, filtered through correlation receivers to suppress noise, and finally rendered as spectral 'thumbnails' using a mathematical tool known as a Fourier transform. These sonic snapshots then pass through convolutional layers in the neural network that are tuned to detect anomalies in frequency modulation. Pooling operations then average out distortions like bubble interference. The team said that when confronted with the most sophisticated type of decoys, detection rates went from 61.3 per cent to more than 80 per cent. It comes amid a global race to develop 'smart' torpedoes. Russia's VA-111 Shkval torpedo and its US counterparts under development all rely on supercavitation at present, and they struggle with target discrimination at extreme speeds. 'With continuous advancements in modern underwater acoustics, electronic technologies and artificial intelligence, today's underwater battlespace often contains multiple simultaneous threats within a single operational area – including decoys, electro-acoustic countermeasure systems, electronic jammers and diverse weapon systems,' the paper said. In such intense underwater environments where multiple targets or decoys can appear simultaneously, these systems must be able to instantly distinguish authentic targets from false ones to avoid mission failure or a wasted trajectory and to prioritise the highest-threat targets, according to the team. 'Critically, given the autonomous nature of underwater high-speed vehicles, all decisions must be made without real-time external communication support, substantially increasing algorithmic complexity and computational demands,' the team said. 'The deep-learning recognition model proposed in this study, combined with the generative adversarial networks' small-sample identification solution, enables effective underwater target discrimination. This lays the technical groundwork for field deployment,' they added. – South China Morning Post
Yahoo
23-02-2025
- Politics
- Yahoo
A Chinese wargame hints it can blind a cutting-edge US missile. That may be a mind game.
In a rare move, China publicized a wargame in which US ships sank a top Chinese warship. In that simulation, the Chinese ship succeeded in temporarily blinding the incoming US missiles. The Chinese wargame is highly irregular and smacks of disinformation, naval experts said. In a recent Chinese wargame, US missiles sank one of China's most powerful warships. So why does China appear to be happy about that result? The answer may be that China is signaling that it knows the secrets of America's prime ship-killing missile. Or — as some Western analysts suggest — China could be trying to undermine America's confidence in its own weapons. The wargame was disclosed to the public in early January by the South China Morning Post, citing a November paper in the Chinese journal Command Control & Simulation. The game, run by the North China Institute of Computing Technology, involved a Chinese carrier battle group sailing in the South China Sea near the Pratas island, which are controlled by Taiwan but claimed by China. For reasons unspecified, the Chinese task force was attacked by a US carrier strike group, which targeted a Type 055 destroyer escorting the Chinese carrier. The new Type 055 — a 13,000-ton destroyer that the Pentagon classifies as a cruiser — is a formidable vessel armed with 112 launchers capable of firing anti-ship, anti-aircraft and land-attack cruise missiles. "The US military suddenly began a large-scale attack on the Chinese fleet, with one wave of 10 AGM-158C Long Range Anti-Ship Missiles (LRASMs) launched simultaneously from different platforms," according to the Morning Post. The Lockheed Martin-built LRASM is a stealthy, subsonic cruise missile with an estimated range of at least 200 miles. Equipped with multiple guidance systems, LRASM features GPS as well as onboard radar and thermal sensors to home in on the target if satellite-based GPS is jammed. In the Chinese simulation, the US destroyers launched LRASM, which initially rose to high altitude and then descended to skim close to the sea to try to delay their detection by radar, the Morning Post said. "When they were about 10 kilometers [6.2 miles] away from the target, their radars malfunctioned one after another due to electronic warfare interference from the [People's Liberation Army], and they were unable to receive GPS positioning signals." "At this point, the missiles switched to thermal imaging cameras to continue flying and, at a very close distance from the target, they suddenly rose up, confirmed the specific attack location, and then plunged to an extremely low altitude, successfully hitting the Chinese destroyer." Chinese researchers claimed to have gleaned details of the LRASM from open-source intelligence and "long-term accumulation. Yet even the Morning Post — owned by e-commerce giant Alibaba, which has close ties to the Chinese government — admitted that it couldn't use public information to verify the accuracy of the missile's depiction in the game. That China would include the new LRASM in its wargames is no surprise: the missile, with an estimated range of at least 200 miles, would be key to any American attempt to defend Taiwan from Chinese invasion. What did surprise Western analysts was that China felt it had enough knowledge of LRASM, such as its guidance systems, to model them in a game. Also notable was that the Chinese government must have given its permission for Chinese media and defense journals to publish the results of a wargame that typically has been classified. When nations learn the secrets of enemy weapons, through espionage or other means, they are wary about tipping off the enemy. British naval experts offer another potential explanation: China is playing mind games with America. "Although framed as a 'humble brag' with the loss of a PLAN [People's Liberation Army Navy] destroyer, the article clearly advertised a certain Chinese confidence in the inevitable arms race in which China and the US, as technological world leaders, are engaged," said Edward Black and Sidharth Kaushal in an essay for the Royal United Services Institute, a British think tank. Black and Kaushal point to several glaring aspects of the Chinese wargame. For example, the simulation assumes that the Chinese destroyer successfully jammed the LRASM's passive radar, which homes in on electronic signals from enemy ships rather than emitting its own waves that return as an active radar does. In fact, China has been developing methods to jam passive radar, such as feeding it false signals. "The PLA's claimed success here would, if true, have ramifications both for the survivability of missiles with a low radar cross-section (which the PLA is implicitly claiming the ability to track) and for US naval efforts at emissions control and the use of passive detection," the RUSI researchers note. In addition, the game portrays LRASM's GPS being jammed, which suggests Chinese confidence that it can defeat anti-jam features on American GPS. The British experts — and Chinese social media — also point out a curious omission: the Type 055 destroyer only used electronic warfare to stop the LRASMs, even though the ship is well-armed with HHQ-9 and HHQ-10 anti-aircraft missiles as well as a short-range air defense cannon. Yet the destroyer must have detected the LRASMs to jam their passive radar, and radar tracking would allow the crew to fire these interceptors to knock out the incoming missiles. Since each LRASM has a 1,000-pound warhead that can devastate a warship, it's highly unusual to rely on electronic warfare alone and at such close range (only 6 miles) to down an incoming salvo of missiles. Even in the presence of jamming, LRASM could still lock onto the ship's thermal exhaust via infrared guidance. A warship is also unlikely to rely only on electronic warfare against missiles that close: if jamming fails, there's no time to launch missile interceptors and hardly enough for a gun to track and fire at multiple incoming missiles. Black and Kaushal raise a truly Machiavellian possibility for why China is publicizing the wargame: Disinformation to undermine American confidence in LRASM. Precise details of the LRASM's performance, such as its maximum range, are classified. If China is modeling the LRASM in their wargames, then perhaps Beijing has managed to steal the missile's secrets? Not likely, conclude the British analysts. "If the PLA [People's Liberation Army] was truly confident in its success in accessing sensitive data, it would have strong incentives to keep this private to achieve surprise in a conflict rather than alerting the US to the compromise of critical systems," Black and Kaushal said. Michael Peck is a defense writer whose work has appeared in Forbes, Defense News, Foreign Policy magazine, and other publications. He holds an MA in political science from Rutgers Univ. Follow him on Twitter and LinkedIn. Read the original article on Business Insider
