A vessel collision risk reduction solution tested at one of the world’s busiest ports

1. Challenges:

   • Busy ports create potential for vessel collisions that can cost lives and impact the environment.
   • Detecting these risks is largely left to the judgement of the operator in the current operational model, and this creates the problem of human error occurrence, such as failure to detect risk or delay in detecting it. It is often too slow for operators to take evasive action.
   • Vessel operations and interactions are becoming more complex, leading to more risk.

2. Results:

   • Fujitsu developed an artificial intelligence-driven system to proactively identify future risks.
   • The solution provides up to 15 minutes’ warning, letting operators act fast to avoid collisions.
   • The solution removes the risk of near misses being overlooked, through the meticulously accurate detection of risk for vessel collision
   • The solution, by assisting in the avoidance of collisions, will save lives, reduce the risk of ships and their cargo being lost, and avoid environmental damage.

The Fujitsu Human Centric AI Zinrai solution uses artificial intelligence to identify the risk of vessel collisions in one of the world’s busiest ports. It delivers warnings in plenty of time for ships’ crews or traffic control officers  to take evasive action, avoiding potentially-catastrophic collisions.

Tested in the Singapore Straits at one of the world’s busiest ports, the solution was found to flag potential risks 10 minutes before a near-miss, giving approximately five minutes’ lead time for human operators to execute the necessary actions.

Dynamic risk hotspot detection technology could detect risks up to 15 minutes in advance, giving staff even more time to react and prevent incidents.

Watch our video to see how AI can accurately identify risk of vessel collisions in busy ports

The risks and ramifications of vessel collisions

When ships collide, the ramifications can be enormous. As well as injury and loss of life, the cost of the damage to the ships and their cargo can be massive.

Traditionally, ships have avoided colliding through the use of human lookouts. Vessel traffic services (VTS) systems can augment anti-collision efforts by detecting potential collisions and notifying ships when vessels get too close to each other.

As vessel operations and interactions become more complex, the ability to detect and predict vessel movements in advance, especially in high density vessel traffic areas like Singapore, is key to managing and reducing collision risks.

A proactive approach  that accurately identifies risks could save lives and money.

A solution tested at one of the world’s busiest ports

The Singapore Strait links one of the largest ports to the rest of the world and more than 200 vessels pass through daily, carrying 80 per cent of the oil transported to Northeast Asia and one third of the world’s traded goods.

At any given moment there are about 1,000 vessels in the Singapore port, with a ship arriving to or leaving Singapore once every 2-3 minutes. However, the geography of the Singapore Strait makes it a natural chokepoint, creating increased risk of vessel collisions. In the traffic lanes, there are more than 2,000 conflicts per month, while the average number of collisions is close to two each year.^[1]

This made the Singapore Strait the ideal testing ground for an innovative ship collision risk prediction technology that uses artificial intelligence (AI) to predict collisions and near-misses, letting ships’ crews take evasive action in time to avert disaster.

• [1]
  Jinxian Weng, Shanghai Maritime University & Xiaobo Qu, Chalmers University of Technology: Vessel Collision Frequency Estimation in the Singapore Strait, Journal of Navigation, April 2012.