Conference PaperPDF Available

Intelligent Design and Operation of Ship Energy Systems combining Big Data and AI

Authors:

Abstract and Figures

Digitalization and automation have been transforming the shipping industries. INTENS is an industry-wide joint effort dedicated to advancing and promoting the digital transformation in Finnish marine industries and beyond, with special focus on ship energy systems. By combining Big Data and Artificial Intelligence, it is able to holistically integrate ship energy systems at the component, system, ship and fleet levels, aiming to achieve intelligent and optimal design and operation of ship energy systems throughout their life cycles. Consequently, it can potentially change and disrupt the ways how the marine industries operate currently and pave the way to the future shipping.
Content may be subject to copyright.
497
Intelligent Design and Operation of Ship Energy Systems
combining Big Data and AI
Zou Guangrong, VTT Technical Research Centre of Finland, Espoo/Finland, guangrong.zou@vtt.fi
Abstract
Digitalization and automation have been transforming the shipping industries. INTENS is an industry-
wide joint effort dedicated to advancing and promoting the digital transformation in Finnish marine
industries and beyond, with special focus on ship energy systems. By combining Big Data and Artificial
Intelligence, it is able to holistically integrate ship energy systems at the component, system, ship and
fleet levels, aiming to achieve intelligent and optimal design and operation of ship energy systems
throughout their life cycles. Consequently, it can potentially change and disrupt the ways how the
marine industries operate currently and pave the way to the future shipping.
1. Introduction
As a global effort into greenhouse gas emissions reduction, the introduction of International Maritime
Organization’s (IMO) energy efficiency measures (EEDI - Energy Efficiency Design Index, EEOI -
Energy Efficiency Operational Indicator, SEEMP - Ship Energy Efficiency Management Plan, and ECA
- Emission Control Areas) has stimulated the development and adoption of novel energy technologies,
practices and innovations throughout ships’ design, building and operation phases. However, despite
the great efforts, if business goes as usual, a 50-250% increase in maritime CO2 emissions from
international maritime transport is projected by 2050 due to the expected future economic growth and
transport demand increase, according to IMO (2014). As the most recent action, IMO and its member
states have adopted an initial strategy that envisages reducing the total annual GHG emissions from
international shipping by at least 50% by 2050 compared to 2008.
Meanwhile, digitalization and automation have been transforming the shipping industries. Novel
technologies and innovations are continuously gaining momentum in the marine domain and speeding
up the mega-transition at a rapid pace. Major digital transformation trends, such as Artificial
Intelligence (AI), Big Data, Digital Twin, Internet of Things (IoT) and Cloud/Edge Computing, are
already shaping the future of shipping. In the foreseeable future, the shipping industries will be radically
different from what they are now, which poses both challenges and opportunities to the global marine
cluster.
Owning the knowledge of cutting-edge digital technologies and expertise in the marine domain, Finland
has all the necessary ingredients to pioneer the digital transformation of the marine sector globally.
Profoundly, a group of industry-leading marine companies (such as Wärtsilä (2017), ABB (2017) and
Rolls Royce (2017)) are the global forerunners of marine industry digitalization. The project INTENS
(Integrated Energy Solutions to Smart and Green Shipping) aims to integrate Big Data, AI, Digital Twin
and Cloud Computing into the whole ship lifecycles and to strengthen the position of the Finnish marine
industries. The consortium, consisting of nineteen partners from Finnish marine industries and research
institutions, dedicates ten networked RDI projects (nine industrial projects and one public project) to
advancing the digital transformation in Finnish marine industries and beyond, with special focus on
ship energy systems, and to deepening the scientific and practical knowledge of smart and green
shipping.
2. Research, Development and Innovation (RDI) Methodology
Novel technologies and innovative solutions have been widely applied to ship designing, building,
retrofitting and operating processes, which, however, rarely resulted in expected energy efficiency
increases and emissions reduction, especially under dynamic operating conditions and uncertainties.
Meanwhile, modern ships are generating huge amount of data all the time during the operation. Given
498
the recent advancement of ICT technologies and data analytics, how to utilize and enrich the data
collected from ships has been a normal routine for all people working in the marine cluster.
Thanks to its great potential and expected advantages, the Digital Twin concept has started gaining
momentum and become more and more imperative to the business when the IoT starts emerging, and
will continue playing a central role in industries’ digital transformation. Industrial leaders, such as GE
(2017) and IBM (2017), have been introducing Digital Twin in their businesses. Specifically, DNV GL
(2017) has been promoting Digital Twin in marine industries as part of their digital asset ecosystem.
Done properly, Digital Twin can bring IoT, Big Data, AI, VR/AR (virtual reality/augmented reality),
Cloud/Edge Computing and dynamic simulation and optimization to one central place and communicate
interactively with physical counterparts, which can potentially transform the industries and the whole
society. However, there are still some challenges and questions to answer before digitally-twinned
industries become real. To name a few:
How can we build digital twins of components, devices and systems with tools and technologies
at hand? Who will build the different digital twins?
At which level do we need to develop different Digital Twins? Always at very detailed level?
How can we integrate different digital twins to act as a seamless function, which is especially
critical for shipping?
How can we curate the huge amount of data for specific purpose? Is it all about data?
How can we figure out the (known and unknown) unknowns from the knowns?
In INTENS, we adopt the Digital Twin concept as the main RDI methodology to study, develop and
implement Digital Twins into the marine cluster, and to address the scientific and practical challenges
hindering the wider utilization of the concept in the industries. Instead of identical twins of physical
systems, we would rather build schematic twins with necessary details for desired purpose and focus
more on developing the capacities of Digital Twin for
perceiving, related to effectual Big Data handling and understanding of the systems and
environment,
learning, related to effective machine learning and data enrichment,
thinking, related to reasoning and efficient optimization with cloud/edge computing, and
acting, related to design, operation, maintenance, prognostics and diagnostics.
Fig.1: An illustrative diagram of the RDI methodology
499
As shown in Fig.1, the schematic twins (virtual models) of the case energy systems (including fleets,
ships, systems and components) connect and run in parallel with their physical counterparts online or
offline. Combined with AI and Big Data technologies, they learn and update themselves based on the
available information, which includes multi-source data, generated by themselves or collected from the
case systems or other sources (e.g. similar systems, environments, …) in real time or in the past, and
knowledge accumulated through the earlier experience during the long history of shipping. Thus, the
roles of models have been redefined as
information collector and carrier to collect and carry the information throughout their lifecycles,
information enabler and transformer to enrich and transform the information to benefit the
system design and operation, and
information generator as large amount of information is generated when virtually running the
models in parallel with their physical counterparts identically or for various scenario analyses.
Digital Twins are primarily built based on their physical counterparts. However, advanced digital design
methods are commonly used in all engineering domains nowadays. The future twins will be digital by
design before even having the physical counterparts. Different from identical twins that represent all
the details of the physical counterparts, the schematic twins contain only necessary details and can be
efficiently utilized for various purposes. There are three common approaches to build virtual models,
namely physics-based (white-box) approach, data-driven (black-box) approach or the hybrid of two
(grey-box approach). Physics-based first-principle models contain more details but need more prior
information, which in theory needs to be identical to the physical systems. The data-driven models are
built solely based on the data available but need large amount of high quality data to train before
reaching an acceptable level of accuracy. The hybrid models are especially useful to represent the
systems with only partially available information. In practice, the selection of the modelling approaches
depends on the requirement of specific tasks and the available information.
Fig.2: A multi-layer platform for design, operation and maintenance of ship energy systems
Fig.2 gives a brief overview of how we develop and utilize the virtual models to identify proper
scenarios, novel solutions and innovations for design, operation and maintenance of ship energy
systems throughout their lifecycles. The core of the conceptual framework is the three-layer platform
500
built on top of an information (knowledge and data) base. The knowledge base includes various ship
energy technologies, energy systems and their dynamic and/or data-driven models and libraries; the
database includes measurement data, collected via ship onboard energy management systems (EMS)
and on-site or lab experiments, and simulation data generated in the earlier work. The system-level ship
energy flow simulation platform provides a multi-domain dynamic simulation environment where ship
energy systems are modelled based on first principles and simulated under real operating conditions.
Fig.3 shows one example of how to evaluate ship energy saving scenarios using the system-level
dynamic energy flow simulation, where a combined shaft generator and waste heat recovery (WHR)
system is implemented and optimized for optimal energy efficiency improvement of one case container
ship. Zou et al. (2014) Big Data-centric operations, such as data handling, data-driven modelling and
data analytics, are carried out on the AI-enabled information enrichment platform; and the ship energy
system optimization platform is the multi-objective optimization layer that holistically generates and
optimizes the design (new-build or retrofit), operation and maintenance scenarios of the energy systems
in question. The virtual models can be connected to the corresponding energy systems on board or via
satellite remotely, running in parallel as the schematic digital twins with the physical counterparts, in
real time or offline, for exploring novel energy solutions and innovations, for business-critical decision-
making, and for energy system condition monitoring, diagnosis and “measuring” critical sports via
simulation, called equipment-free soft sensors.
Fig.3: A top-level diagram of the energy flow simulator with implemented energy saving scenarios
3. Multi-Level Framework
Building modern ships, especially large cruise ships, is of a collaborative nature due to their complexity
and the involvement of large number of suppliers. However, in the current modus operandi, the same
or similar operations still involve plenty of operation silos (ship design, build, operation, ship
maintenance, supply, logistics, etc.). The limited collaborations and interactions between different silos
result in the lack of systematic consideration and hence unnecessary inefficiency and waste of energy
and resources, especially during the design and operation phases of ships. This becomes even more
critical when the scale and the complexity of ship energy systems and shipping network increase. On
the other hand, digital transformation will only gain full speed after a critical mass of players is involved.
In this paper, we propose a network-based multi-level collaboration framework, aiming to enable and
encourage the industry-wide cooperation, information exchange and enrichment within the consortium
during the project period and to the whole cluster afterwards. As shown in Fig.4, ship energy systems
can be represented at multiple levels, with higher levels specifying the topology of the networks or ship
energy plants and lower levels including more components with more detailed dynamic representation.
It is not limited to four levels, however. For instance, on top of the fleet level, the framework can be
expanded to the global shipping network level and even further extended to land-based energy and
501
logistics networks related to shipping. Different companies are grouped to corresponding levels
according to their main businesses. The INTENS consortium covers the whole value chain of the marine
cluster, vertically across all the component, system, ship, and fleet levels, which offers ideal
opportunities to research and demonstrate how to enable industry-wide collaboration and information
sharing. Done properly, this could benefit different players in the domain and ensure the developed
solutions and innovations can be feasible and applicable to the whole cluster later on.
Fig.4: Illustration of the multi-level collaboration framework
Fig.4 shows the foundation of the multi-level collaboration framework is the aforementioned multi-
layer conceptual energy system platform, which runs as an information fusion reactor to generate added
value, optimized solutions and innovations for the involved partners from the information they shared.
Specifically, each partner can design and optimize their products in a true marine environment and
evaluate system performances with operating profiles from real operating conditions, not just with
single “design points”. Furthermore, the partners work together to offer a better-integrated product
portfolio to their customers. The advanced platform and its vast information base provide the
collaboration framework with some unique features:
Scalability The energy systems of ships of different types, scales and complexities, can be
systematically represented at one or more levels, with necessary details for specific purpose. At
each level, the systems are shown as a network, and all levels together form an overall network.
Flexibility The energy systems can be modelled using physics-based, data-driven or hybrid
approaches at one or more levels depending on requirements and information available. During
the optimization process, different concepts or scenarios of design, operation and maintenance
can be formed and evaluated at each level or across all the levels of the overall network.
Interactivity The energy systems have to be taken into consideration as an integrated one and
the interactions between different subsystems are key to the systems’ performances. Huge data
502
communication not only happens at each level, but more importantly, across the different levels,
which is one of the key features of the framework.
4. Application Cases
As an industry-wide collaborative consortium, INTENS aims to develop and implement various novel
solutions and innovations in 15 practical application cases. Specifically, corresponding to the multi-
level collaborative framework, the application cases are grouped into fleet, ship, system and component
levels, respectively, although we do need to extend most of the cases across more than one level in
practice. As listed in Table I, the RDI activities of all the application cases are further highlighted,
especially with respect to the Digital Twin advancing efforts.
Table I: List of application cases and their RDI activities
Case group
RDI highlight
Fleet level
- Big Data driven collaborative voyage
optimization
- Advanced IoT utilization
- Learning-aided ship operation and forecasting
- Nature-inspired regional fleet operation
optimization
- System-level data mining
Ship level
- Lifecycle excellence through simulation
- Cloud-based dynamic system optimization
- Optimization as a service
- Optimal battery hybridization and integration
- Poly generation concepts
- Robust automation
- Learning-based ship operation optimization
- Schematic Serenade twin
- Waste heat recovery
System level
- Simulation-enabled system integration
- Adaptive system parameter learning
- Engine and battery system integration
- Hybrid engine system twins
- Waste to electricity
- ORC system twins
- Waste to energy
- WHR system twins
Component level
- Emissions reduction
- Data-enriched fault diagnostics
- Engine twins
- Data-driven design optimization
- Heat exchanger twins
- Adaptive emissions reductions
- Catalyst twins
- Simulation-based optimization
- AI-enabled condition monitoring
- Filter twins
5. Conclusions
As industry-wide collaborative effort, the INTENS projects aims to accelerate the digital transformation
and to leap Digital Twin closer to reality in the marine industries, which could potentially change and
disrupt the ways how the marine industries operate currently and pave the way to the future shipping.
503
By implementing Digital Twin into the marine industries, significant scientific breakthroughs,
innovations and solutions are expected. Using the proposed multi-level collaborative framework, we
can enable efficient technology transfer and intensive technical cooperation. The enhanced collabora-
tion will largely benefit the marine industries and beyond, help the digital transformation of marine
businesses, improve ship energy efficiency and help to achieve ambitious goal of GHG emissions
reduction globally.
Acknowledgement
The work presented in the paper is supported by the INTENS research project, jointly funded by
Business Finland’s Arctic Seas program and the INTENS consortium (Wärtsilä Finland Oy, NAPA Oy,
Meyer Turku Oy, Dinex Ecocat Oy, Deltamarin Oy, Vahterus Oy, Protacon Technologies Oy, Parker
Hannifin Oy, JTK Power Oy, 3D Studio Blomberg Ab, Jeppo Biogas Ab, Visorc Oy, Tallink Silja Oy,
NLC Ferry Ab Oy, Aalto University, Lappeenranta University of Technology, University of Vaasa,
Åbo Akademi University and VTT Technical Research Centre of Finland Ltd), which are gratefully
acknowledged.
References
ABB (2017), Remote Diagnostics services Predicting by analyzing, ABB Global Service,
http://new.abb.com/docs/librariesprovider91/leaflets-brochures/rds/digital_level3_leaflet_web1.pdf
DNV GL (2017), Software inspired by a broader view a leading provider of digital solutions, DNV
GL, pp.11-15
GE Digital (2016), The rise of Digital Twins, https://www.ge.com/digital/blog/rise-digital-twins
IBM (2017), Digital Twin - IBM Watson Internet of Things, https://www.ibm.com/internet-of-
things/resources/digital-twin
IMO (2014), Third IMO Greenhouse Gas Study 2014, Int. Maritime Org., London, pp.21
ROLLS ROYCE (2017), Rolls-Royce announces investment in Research & Development for Ship
Intelligence, https://www.rolls-royce.com/media/press-releases/yr-2017/08-03-2017-rr-announces-
investment-in-research.aspx
WÄRTSILÄ (2017), Digital transformation, Finland 100 Future of the seas, https://www.wartsila.com/
finland-100/digitalisation
ZOU, G.; KINNUNEN, A.; TERVO, K.; ORIVUORI, J.; VÄNSKÄ, K.; TAMMI, K. (2014), Evaluate
ship energy saving scenarios using multi-domain energy flow simulation, 13th COMPIT Conf.,
Redworth, pp.408-417
ZOU, G. (2017), Ship energy efficiency technologies - now and the future, VTT Technology (306),
pp.120
... Moreover, a single ship or marine vessel can be considered as a system with many interacting levels [36][37][38][39], some of them pertain to control and management issues and some others are directly linked to physical system dynamics [40]. All these levels are mutually interacting and many of them interact also with external factors like logistic chain constraints and the metocean environment. ...
Article
Full-text available
In the complex processes of route planning, voyage monitoring, and post-voyage analysis, a key element is the capability of merging metocean forecast data with the available knowledge of ship responses in the encountered environmental conditions. In this context, a prototype system has been implemented capable of integrating metocean models forecasts with ship specific performance data and models. The work is based on the exploitation of an open source ECDIS-like system originally developed in the e-Navigation framework. The resulting prototype system allows the uploading and visualization of metocean data, the consequent computation of fuel consumption along each analyzed route, and the evaluation of the encountered meteo-marine conditions on each route way point. This allows us to “effectively and deeply dig inside” the various layers of available metocean forecast data regarding atmospheric and marine conditions and evaluating their effects on ship performance indicators. The system could also be used to trigger route optimization algorithms and subsequently evaluate the results. All these functionalities are tailored in order to facilitate the “what-if” analysis in the route selection process performed by deck officers. Many of the added functionalities can be utilized also in a shore-based fleet monitoring and management center. A description is given of the modeling and visualization approaches that have been implemented. Their potentialities are illustrated through the discussion of some examples in Mediterranean navigation.
... In the future, with long distances, traditional trains that used to need at least 25 people to operate may need fewer or completely without direct control if its route is not involved in natural disasters [47]. Fig. 5 The proposed system architecture for the automation of the end-to-end delivery process [48] In a study by Bilal Muhammad and colleagues presented a very practical solution to enhance port operations by the application of robotics and automation technology. In this study, the authors have built an optimal infrastructure structure using the Remotely-Piloted Aircraft System (RPAS), as shown in Figure 5 to improve cargo volume, reliability, and safety. ...
Article
The Industrial Revolution 4.0 is having a substantial impact on countries in many fields such as industry structure, human resource needs, production management systems. Transportation is a high-community industry, so it will also be strongly affected by this industrial revolution. The achievements of Industry 4.0 can reshape the nation's transportation systems. That poses challenges for transportation managers to change the operating model as well as the transport-related policies. Building and developing intelligent transport systems (ITS) is attracting considerable attention, research, and investment to serve the development of transportation systems in the world as well as in Vietnam. Vietnam is gradually building Intelligent Governments, Intelligent Cities, and the Intelligent Transportation system will be an essential part of that development and entering the stage of access to the 4.0 industrial revolution, building a smart city applying 4.0 technology to bring convenience, friendliness, and safety to people in each city. As a step ahead, the Transport industry gradually realizes its dream of developing intelligent transportation in developed cities like Hanoi and Ho Chi Minh City. The paper presents an overview of the impact of Industry 4.0 on key aspects of the transport sector in general and ITS development strategy in Vietnam. On that basis, state-of-the-art technologies-technology 4.0 are proposed to meet the demands of intelligent transportation development. The paper will show that 4.0 technology is the key to the development of ITS in Vietnam.
... Recently, much attention has been paid to digital innovations and connectivity on the ships. According to Guangrong (2018) major digital transformation trends, such as Artificial Intelligence (AI), Big Data, Digital Twin, Internet of Thing and Cloud/Edge Computing are shaping the future of shipping. ...
Conference Paper
Full-text available
As data is becoming an increasingly valuable asset for organizations, pressure to improve its governance is increasing. Prior research provides a thorough view on data governance within a single organization. Although data sharing with partner organisations in data platforms provides a means to add data's value, empirical studies addressing data governance in shared data platforms are still few. We propose a literature based preliminary framework for platform data governance with five domains: original data quality; ownership and access; stewardship; platform data quality and value of data usage. We report experiences from a European shipbuilding network, which is seeking ways to share data collected during ship's operations. While the device manufacturers already process sensor data within their device-specific platforms, they are knowledgeable about potential benefits of sharing their data with others in the network. Based on interviews within the shipyard network, we report views along the five platform data governance domains.
Chapter
The purpose of this chapter is to provide an overview of the state-of-the-art and future perspectives of Data Science and Advanced Analytics for Shipping Energy Systems. Specifically, we will start by listing the different static and dynamic data sources and knowledge base available in this particular context. Then we will review the Data Science and Advanced Analytics technologies that can leverage these data to extract and synthesize new additional actionable information, suggestions, and actions. We will then review the current exploitation strategies of these technologies aiming at improving the current Shipping Energy Systems. In conclusion, we will depict our vision on the future perspectives of the application and adoption of Data Science and Advanced Analytics for shaping the next generations of Shipping Energy Systems.
Book
Full-text available
The global marine cluster is in major transition to smart and green shipping. The pressure and need for the decarbonization, digitalization and automation in shipping are high from regulatory, environmental, economic and technological perspectives, which poses challenges and opportunities to the cluster. It is imperative for Finland since the hi-tech and marine industries are two of the mainstay industries for the country. This book is one of the activities to disseminate and showcase the Finnish expertise, practices and on-going efforts towards smart and green shipping, It also acts as the proceedings of the first public seminar of the INTENS project, which is a national collaborative research and innovation action striving to advance and promote the digital transformation and collaboration in the Finnish marine industries and beyond. It features a collection of extended abstracts, concerning simulations, algorithms, technologies and practical applications of major digital transformation methods, including Artificial Intelligence (AI), Big Data, Digital Twins, Industrial Internet of Things (IIoT) and Cloud Computing, specifically to the energy efficiency improvement and emissions reduction of ship energy systems. It highlights the prominent roles of both innovations and collaborations in the digital transformation and decarbonization of global shipping. (full text access: https://doi.org/10.32040/2242-122X.2019.T354)
Remote Diagnostics services -Predicting by analyzing
ABB (2017), Remote Diagnostics services -Predicting by analyzing, ABB Global Service, http://new.abb.com/docs/librariesprovider91/leaflets-brochures/rds/digital_level3_leaflet_web1.pdf
Software inspired by a broader view -a leading provider of digital solutions
  • Dnv Gl
DNV GL (2017), Software inspired by a broader view -a leading provider of digital solutions, DNV GL, pp.11-15
Third IMO Greenhouse Gas Study
IMO (2014), Third IMO Greenhouse Gas Study 2014, Int. Maritime Org., London, pp.21
Rolls-Royce announces investment in Research & Development for Ship Intelligence
  • Rolls Royce
ROLLS ROYCE (2017), Rolls-Royce announces investment in Research & Development for Ship Intelligence, https://www.rolls-royce.com/media/press-releases/yr-2017/08-03-2017-rr-announcesinvestment-in-research.aspx
Digital transformation
WÄRTSILÄ (2017), Digital transformation, Finland 100 Future of the seas, https://www.wartsila.com/ finland-100/digitalisation
Ship energy efficiency technologies-now and the future
ZOU, G. (2017), Ship energy efficiency technologies-now and the future, VTT Technology (306), pp.120