Using Artificial Intelligence to Estimate Vessel Speed and Fuel Consumption at Sea
- Accurately Estimating Vessel Performance within 1.5%, Aiming to Reduce Environmental Impact -
November 08, 2017
TOKYO-Mitsui O.S.K. Lines, Ltd. (MOL; President & CEO: Junichiro Ikeda) today announced that it teamed up with Fujitsu Laboratories Ltd. (CEO: Shigeru Sasaki, Headquarters: Kawasaki-shi, Kanagawa Prefecture), and Tokyo University of Marine Science and Technology (President: Toshio Takeuchi, Main Campus: Koto-ku, Tokyo) to verify the accuracy of technology to estimate vessel performance at sea by applying Fujitsu's artificial intelligence (AI) technology, "FUJITSU Human Centric AI Zinrai."
This project is a part of MOL's initiative to assess the effectiveness of AI technology, and aims to reduce fuel consumption and vessels' environmental impact by verifying the accuracy of the technology, using Fujitsu's AI Technology to estimate vessel performance at sea.
[ Outline of Accuracy Verification Test ]
MOL provided actual voyage data collected from MOL fleet in operation to Fujitsu Laboratories, which, along with Tokyo University of Marine Science and Technology, verified the data by using their jointly developed machine learning method.
Detail of actual voyage data provided by MOL
Items: About 30 in all, such as speed, fuel consumption, main engine rpm, wind direction, wind speed, etc.
Period: October 12, 2015 – December 13, 2015
- Learned the correlation of each item of operation data using Fujitsu's unique AI technology and high-dimensional statistics analysis technology, and established the technology that estimates vessel performance.
- Estimated the ship speed from the data other than the speed and verified the comparison between that estimated value and actual operation data, in case to assess allowance of speed. This same assessment was also applied to fuel consumption.
Example of estimated vessel speed compared to main engine rpm and wind speed
by using high-dimensional statistical analysis
(Graphic provided by Fujitsu Laboratories Ltd.)
Results of verification
- Could estimate vessel speed with about a 1.4% allowance, and fuel consumption with an allowance of about 0.8%, based on the above-mentioned method.
- The following graphs show time-series results of actual measured values of vessel speed and estimated values. Verification confirmed that actual measured values and estimated values are almost the same.
Example of test results (estimate of vessel speed)
(The figure is provided by Fujitsu Laboratories Ltd.)
This project, as a part of the "ISHIN NEXT - MOL SMART SHIP PROJECT –"(Note), assesses the effectiveness of AI technology and aims to enhance operating safety and reduce environmental impact through reduction of fuel consumption.
MOL aims to become the corporate group that customers think of first when they choose a logistics business partner, by drawing upon AI and ICT technologies to enhance its services.
|(Note)||MOL's technology development project.
For details, please refer to the press release of November 24, 2016:
"MOL Launches "ISHIN NEXT - MOL SMART SHIP PROJECT –"