K-Line Initiates Utilizing AI For Future With Maritime Autonomous Surface Ships

Kawasaki Kisen Kaisha, Ltd. (“K” Line) and Kawasaki Heavy Industries, Ltd. (KHI) announced that they have concluded a co-development contract for “AI (Artificial Intelligence)-based Marine Machinery Operation Support System” (hereinafter referred to as “the System”) that is expected to be part of the core technology to achieve autonomous vessel operation in the future. The System will have such functions as failure prediction/ diagnostics, CBM (Condition-Based Maintenance), and optimum operation support, based on the data analytics of marine machinery operation data using AI.

In view of safer operations at sea, improvement of the working environment for seafarers, and higher pressure for industrial competitiveness, the expectations for autonomous operations for ships are increasingly growing these days.

Through this co-development project, they aim to complete the System by combining “K” Line’s extensive data on vessel operation and marine machinery operation collected from Kawasaki-Integrated Marine Solutions (Note 5) and its years of experiences in operation and maintenance of onboard machinery, and KHI’s technology and expertise in building ships and propulsion plants, and by having AI learn these data and knowledge.

The System manages not only a specific piece of equipment but marine machinery onboard as a whole, including the main engine and power generator. In developing the System, we will first target those vessels with diesel propulsion plants, and then those with various types of propulsion systems such as steam turbines and electronic propulsion systems in the next phase.

The System will be beneficial for crew onboard as well as ship management personnel on land, providing useful information on failure predictions and failure diagnostics. This not only enables users to prevent major engine troubles from occurring but also assists in planning effective maintenance schedules and advises optimum engine operation based on the condition of plants, ultimately improving fuel consumption and contributing to greenhouse gas reduction.

Preferred Networks, Inc. (Note 6)  known for their cutting-edge technologies on deep-learning and machine-learning, is joining us in developing the “Marine AI,” the core of the System that executes failure prediction and operation condition diagnostics.

The Marine AI will be implemented both onboard and in the cloud system. The one onboard learns the vessel’s operation data and uses them to diagnose on a real-time basis. The one in the cloud system periodically collects the data accumulated on each vessel, and centrally uses them for further learning, allowing itself to become smarter and offer failure prediction and diagnostics as well as optimum operation support for any type of vessel.

A proof-of-concept has been established for the core technology of the Marine AI for failure prediction and diagnostics. With abundant data collected from various ships via Kawasaki-Integrated Marine Solutions, as well as such data obtained from the latest sensors that were not available before, “K” Line and KHI will further proceed on developing the Marine AI that is versatile enough to be applied for any types of vessels.

Both “K” Line and KHI are innovators, fully utilizing their expertise in maritime transport and shipbuilding, collaborating with entities from other industries with their special knowledge and technologies to accelerate system development so that they will achieve autonomous vessel operation for the future. “K” Line and KHI will contribute to accomplishing safer operations at sea, improved working environment for seafarers, and higher competitiveness in the marine industry.

As a part of an initiative to expedite the implementation of autonomous ships, Kawasaki Kisen Kaisha, Ltd. (“K” LINE) has entered into a joint R&D agreement with Japan Radio Co., Ltd.(JRC) and YDK Technologies Co., Ltd. (YDK) to develop an integrated navigation support system that utilizes artificial intelligence (AI) and other cutting-edge technologies for assisting manoeuvring in making safety manoeuvring decisions. This joint R&D project aims to develop a system that will prevent serious maritime accidents such as ship collisions and groundings and that will lead to autonomous ship operations by combining “K” Line’s manoeuvring knowledge and experience in safe ship operation over many years, JRC marine equipment’s knowledge and advanced radio technology developed, and YDK’s steering and propulsion control technology.

This system is expected to meet Degree 1(*1) of the International Maritime Organization (IMO) standard for development stages of autonomous ships and is an initiative to follow the global trend of the development of autonomous ships and further expedite the project.

An overview of this initiative and the joint R&D structure is shown below. The aim is to develop a comprehensive system that will further improve the safety of ship operations by utilizing the knowledge and technologies of the three partners in each process from situation awareness by the seafarer to maneuvering control of the ship, combined with the most advanced technologies provided by Groke Technologies(*2), Fujitsu Limited(*3), and Forum8 Co.(*4).

【Overview of Initiative and Joint R&D Structure】

Starting from April 2023, demonstration at sea will be conducted on various ship types and routes, both domestic and international, with the aim of full-scale commercial implementation in the future. “K” Line, JRC, and YDK will continue to develop the system to further improve the safety of ship operations by providing more advanced support and reducing the burden on seafarers and to assist in implementing autonomous ships.

This R&D is a part of our efforts to develop a crew support system for navigation and engine part. The aim is to prevent serious marine accidents under congested water such as collision and grounding by providing safety information to navigators and supporting their decision-making through this Integrated Navigation Support System that utilizes advanced technology. We will continue to accelerate development to improve safety, transportation quality and environmental performance that includes the basic technologies required for future autonomous ships in view of cooperation with various partners.

This R&D is a part of our efforts to develop a crew support system for navigation and engine part. The aim is to prevent serious marine accidents under congested water such as collision and grounding by providing safety information to navigators and supporting their decision-making through this Integrated Navigation Support System that utilizes advanced technology. We will continue to accelerate development to improve safety, transportation quality and environmental performance that includes the basic technologies required for future autonomous ships in view of cooperation with various partners.

*1: IMO’s Development Level for Automated Ships (Degree 1)
Degree 1 is defined as a state where part of the ship’s operation is automated, but the crew is still on board. This requires that human operators be ready and able to take control if any unforeseen circumstances arise.

*2: Groke Technologies
Groke Technologies was established in 2019 by founders from the Rolls-Royce Ship Intelligence Team, the pioneers in the development of autonomous navigation technology today, with the investment backing from Mitsubishi Corporation. They are a provider of intelligent navigation solutions with extensive background in autonomous maritime systems. Groke Technologies has extensive expertise in maritime sensor fusion, machine vision and artificial intelligence solutions.

*3: Fujitsu Limited
Since 2018, Fujitsu Limited has been conducting joint performance testing with the Maritime and Port Authority of Singapore to verify the effectiveness of Fujitsu’s AI-based ship collision risk prediction technology in actual sea conditions. Starting from 2019, performance tests of this technology have also been conducted at the Tokyo Bay Maritime Traffic Center, Japan Coast Guard.

*4: Forum8 Co., Ltd.
Forum8’s CG-based VR simulation technology has already been used in a wide range of fields such as civil engineering and transportation, and recently, Forum8 has also been working on CG-based simulations of ships and marine traffic and has the technology to properly simulate the environment surrounding an operating ship.

Notes
*5. Kawasaki-Integrated Marine Solutions is an ICT system for vessels that allows ship operation management, condition monitoring, performance analysis, and others from management office on land, using ship-land communication network.

*6. Preferred Networks, Inc. was founded in March 2014, and has been making progressive advancement to achieve the application of machine learning and deep learning to industry in collaboration with leading companies of many different fields, including transportation system, manufacturing industries, and bio-healthcare since then. As part of the areas of machine learning/ deep learning application, Preferred Networks has been employing their cutting-edge technology for failure prediction of industrial equipment based on anomaly detection using time-series data and operation optimization of factory plants.

Reference: kline.co.jp