Joint research undertaken by Fujitsu Laboratories and Tokyo University of Marine Science and Technology has resulted in the development of new technology that analyses ship-related big data to estimate fuel efficiency, speed and other performance in actual sea conditions with a low error margin.
The new technology facilitates an accurate estimation of ship performance in actual sea conditions, with reduced errors, making use of Fujitsu Laboratories’ patented high-dimensional statistical analysis technology, Human Centric AI Zinrai, which is used to estimate the performance of ships that are at sea.
It uses a large volume of measurement data gathered during the ship’s voyage, including sensor data of meteorological and hydrographic conditions, such as wind, waves, and ocean currents, ship engine log data, and data about the speed and position of the ship.
The company noted that the technology is said to assist mariners in gathering information on the effects of meteorological and hydrographic conditions on a ship’s fuel performance in order to plan the duration of their route in terms of fuel efficiency to avoid wind and waves.
Further, this will benefit ship operators by providing them with extended information on the complicated interactions of the wind, waves, and ocean currents with ship conditions, reducing errors.
Originally, meteorological factors could not be analysed by existing ship performance estimation technologies, which rely on experiments with model ships in tanks of water, or on physics model simulations.
The new technology automatically groups the high-dimensional ship data by similar meteorological and hydrographic conditions, and then machine estimations are carried out on each group individually.
Fujitsu Laboratories applied the result of this research to Tokyo University of Marine Science and Technology’s weather routing simulator for evaluation, and verified it for a Pacific Ocean shipping route from Tokyo to Los Angeles. Taking an optimal route based on the ship’s performance can reduce ship fuel consumption by 5%, subsequently lowering both fuel costs and carbon dioxide emissions.
Image: Contrast of analysis between the existing physics model and the newly developed technology. Photo: courtesy of FUJITSU.