IEEE Robotics & Automation Magazine - September 2023 - 8

infrastructure for not only overall system
design, allowing configuration of
systems and verification of operational
performance, but also for focusing more
on providing early-warning, lifecycle
service support, and system behavior
prediction. Maritime digital twin models
should be constructed prior to or in
parallel with the actual building of a vessel,
enabling virtual manufacturing and
commissioning and integration testing
and analysis in the earliest stage. During
the operational phase, the digital twin
becomes a system for integration, processing,
and analysis of operational data.
Ideally, the digital twin will provide decision
support and predictions for a ship
owner, subsystem manufacturers, and
safety training/improvement for crew
and operators. It will enable the use of model-/data-based
simulation in combination with sensor measurements from
the real vessel, without the need for physical inspections. The
digital twin tracks information on all the parameters to define
how each individual module and submodule behaves over
its entire useful life, including the initial design and further
refinement, manufacturing-related deviations, modifications,
uncertainties, and updates as well as sensor data from onboard
systems, maintenance history, and all available historical and
fleet data obtained using data mining. All the research outcomes
will be further used for ships that are either autono "
ADVANCED
MARINE
SYSTEMS SHOULD BE
ABLE TO DECIDE AMONG
DIFFERENT ACTIONS,
ADAPT TO DYNAMIC
ENVIRONMENTS, AND
EXECUTE HIGH-LEVEL TASK
SPECIFICATIONS WITHOUT
EXPLICITLY BEING
PROGRAMMED.
„
mous or remote controlled for safety and
reliability enhancement [5].
Using digital twins for marine engineering
could bring the following advantages:
■ Reduce development time and enhance
production efficiency: digital twins
provide an integrated view of the vessel's
various physical and behavioral
aspects during all stages and allow
optimization of all functional performance
requirements throughout the
entire development cycle.
■ Improve operational flexibility and
reduce cost: digital twins create more
predictable, faster starts for flexible
objectives, execute day-ahead and longterm
planning for improved operations,
and reuse the subsystem's models, data,
and operational sources.
■ Enhance the lifecycle value chain and improve the system
performance and health conditions: digital twins allow
data exchange among different subsystems, modules, and
proprietary applications; ensure remote access systems
availability, and utilize early warnings for short-time technical
support.
■ Improve quality and efficiency of maritime product and
operation approval and certification processes: digital
twins combine simulation models and sensor data on an
open platform and facilitate the design and verification of
cyberphysical systems.
FMUs
Optimization
Design
Suppliers
FIGURE 1. The digital twin of Gunnerus ship. FMU: Functional Mock-Up Unit.
8 IEEE ROBOTICS & AUTOMATION MAGAZINE SEPTEMBER 2023
Manufacturing
Cosimulation
Operation
Machine
Learning
Maintenance and
Service
Customers
IEEE Robotics & Automation Magazine - September 2023

Table of Contents for the Digital Edition of IEEE Robotics & Automation Magazine - September 2023
