A domestically developed autonomous fire suppression system from South Korea, designed to detect and extinguish oil fires on naval vessels, has undergone successful testing aboard an operational ship for the first time, according to the Korea Institute of Machinery and Materials (KIMM).
Led by senior researcher Hyuk Lee from the AX Convergence Research Center’s Virtual Engineering Platform Research Division, the research team created a system that relies on AI to assess fire authenticity, activating only when a genuine fire is detected.
Go deeper with GlobalData
Discover B2B Marketing That Performs
Combine business intelligence and editorial excellence to reach engaged professionals across 36 leading media platforms.
Upon confirmation, it directly targets the source of the fire, providing precise suppression without the need for human guidance.
Conventional shipboard firefighting systems discharge extinguishing agents across wide areas when alarms are triggered. This often causes unnecessary damage or fails to accurately address fires during false alarms.
In contrast, the newly developed technology uses an AI-driven approach. It combines precision detection and reinforcement learning algorithms to adapt to factors such as ship movement and sea conditions, thereby improving both accuracy and efficiency in emergency response.
The system’s key components include fire detection sensors, directional fire monitors, and an analysis and control unit powered by AI-based algorithms for determining fire authenticity and location.
US Tariffs are shifting - will you react or anticipate?
Don’t let policy changes catch you off guard. Stay proactive with real-time data and expert analysis.
By GlobalDataKIMM reported that tests demonstrated over 98% accuracy in fire detection, while the foam discharge was effective at a range of around 24 metres (m).
The equipment remained functional even when subjected to sea states of level 3 or higher, said KIMM.
Before onboard deployment, researchers conducted extensive validation at a large-scale land-based simulation facility, measuring 25m×5m×5m.
This environment replicated actual ship compartment conditions, including specific lighting and colour schemes.
Within this setting, researchers simulated both real oil fires, such as those caused by equipment or aircraft leaks, and scenarios that could be mistaken for fires, including welding activities and operating electric heaters.
The AI system underwent pre-training and accuracy testing across these varied situations to ensure reliable discrimination between genuine and false alarms.
Performance verification included suppressing both open-area oil fires using trays up to 4.5m2 in size and shielded oil fires replicating situations on aircraft carriers, with helicopter-sized shields set 50 centimetres (cm) above trays measuring 3m².
These tests demonstrated the system’s capability to address all probable types of oil fires aboard naval vessels.
Following land-based simulations, the research team moved to real-ship trials on the LST-II class amphibious assault ship, ROKS Ilchulbong.
The system successfully discharged extinguishing water onto a fire source situated 18m away under live sea conditions with waves reaching 1m in height.
For this, a reinforcement learning algorithm recalculated aiming angles in real time by analysing six-degree-of-freedom acceleration data reflecting ship motion.
Hyuk Lee said: “This newly developed initial suppression firefighting system for shipboard oil fires is the world’s first technology to complete step-by-step verification from land-based simulation facilities to actual shipboard environments. It can autonomously respond to the most dangerous oil fires on ships in both open and shielded conditions, marking a groundbreaking turning point for crew safety and preserving the ship’s combat effectiveness.”
