AI reduces human error onboard

Transas has launched its first package of applications built on THESIS, a unified cloud-based platform for managing operations, which utilising the latest in machine learning techniques to help make sure officers and crew take the best operational action.

“Technology shouldn’t be an end in itself – but a tool to achieve an end,” said Transas CEO Frank Coles. “We want to help the industry improve by enabling it to make better decisions and boost competitive advantage, using machine intelligence to augment the human in the loop.”

Algorithms

The Transas A-Suite uses algorithms to detect anomalies in the behaviour of the human operator wherever they are in the operational chain and raise the alarm before the consequences of a course of action or momentary lapse in attention become irreversible.

The first version of the A-Suite package comprising three core modules – Advanced Intelligent Manoeuvring (AIM), Advanced Intelligent Diagnostics (AID), and Advanced Intelligent Routing (AIR).

AIM is a track prediction system and anti-collision support tool designed to improve situational awareness and reduce the probability of officer inattention or poor judgement leading to an incident.

Detecting anomalies

AID is primarily intended to detect anomalies and provide decision support both in real-time or during a more methodical post-voyage analysis. This module detects excessive or unusual manoeuvring patterns, keeping an eye on parameters such as speed and rate of turn, as well as unexpected deviations in fuel consumption.

AIR creates a platform for voyage planning and optimisation based on an extensive set of parameters. The application absorbs real time metocean data, hazards and a vessel’s hydrodynamic performance. It also takes into account the impact of known and anticipated vessel traffic along the route and at bottlenecks.