Digital twin

Seminar Report
on
DIGITAL TWIN
submitted by
SREELAKSHMI A.P. (12160096)
In partial fulﬁlment of the requirements for the award of degree of Bachelor of Technology
in Computer Science and Engineering.
DIVISION OF COMPUTER SCIENCE AND ENGINEERING
SCHOOL OF ENGINEERING
COCHIN UNIVERSITY OF SCIENCE AND TECHNOLOGY
APRIL 2019

DIVISION OF COMPUTER SCIENCE AND ENGINEERING
SCHOOL OF ENGINEERING
COCHIN UNIVERSITY OF SCIENCE AND TECHNOLOGY
CERTIFICATE
Certified that this is a bonafide record of the Seminar report titled
DIGITAL TWIN
done by
Sreelakshmi A.P. (12160096)
of VIII Semester, Computer Science and Engineering in the year 2019 in partial fulfillment
of the requirements for the award of degree of Bachelor of Technology in Computer Science
and Engineering of Cochin University of Science and Technology.
Dr.Latha R Nair
Head of Division
Ms.Preetha S.
Project Coordinator
Ms.Sheena S.
Seminar Guide

ACKNOWLEDGEMENT
I take this opportunity to thank the supreme being, the source of all
knowledge whose blessings are our guiding light in any venture we take up.
I am in short of words to express my gratitude to Ms Sheena S., my semi-
nar guide who guided and helped constantly with his inputs and suggestions
without which I couldnt have successfully completed this seminar. I am also
highly indebted to Dr. Sudheep Elayidom and Ms Preetha S, my staﬀ advi-
sors for their constant supervision and support in completing this seminar.I
express my immense pleasure and thanks to all the teachers and staﬀ of the
Department of Computer Science and Engineering, CUSAT for their cooper-
ation and support. A bouquet of gratitude to Dr.Latha R Nair, Head of the
Division of Computer Science and Engineering for all kinds of encouragement
extended.
i

DECLARATION
I hereby declare that this seminar report is the record of authentic work
carried out during the academic year 2018 - 2019 and has not been submitted
to any other University or Institute towards the award of any degree.
ii

ABSTRACT
Digital twin refers to a digital replica of physical assets (physical twin),
processes, people, places, systems and devices that can be used for various
purposes. The digital representation provides both the elements and the dy-
namics of how an Internet of things device operates and lives throughout its
life cycle. Definitions of digital twin technology used in prior research em-
phasize two important characteristics. Firstly, each definition emphasizes the
connection between the physical model and the corresponding virtual model.
Secondly, this connection is established by generating real time data using
sensors.
Digital twins integrate artificial intelligence, machine learning and software
analytics with spatial network graphs to create living digital simulation mod-
els that update and change as their physical counterparts change. A digital
twin continuously learns and updates itself from multiple sources to repre-
sent its near real-time status, working condition or position. This learning
system, learns from itself, using sensor data that conveys various aspects of
its operating condition; from human experts, such as engineers with deep and
relevant industry domain knowledge; from other similar machines; from other
similar fleets of machines; and from the larger systems and environment in
which it may be a part of. A digital twin also integrates historical data from
past machine usage to factor into its digital model.
In various industrial sectors, twins are being used to optimize the operation
and maintenance of physical assets, systems and manufacturing processes.
They are a formative technology for the Industrial Internet of things, where
physical objects can live and interact with other machines and people virtu-
ally. In the context of the Internet of things, they are also referred as ”cyber
objects”, or ”digital avatars”. The digital twin is also a component of the
Cyber-physical system concept.
The technology of a digital twin creates several opportunities for new play-
ers that want to tap into this emerging market. Since the technology can
iii

be brought into a more operational framework, not only the incumbents can
exploit the opportunities that arise. In the following part we discuss two
start-ups that try to exploit the opportunities that emerge around this new
technology.
iv

Contents
1 INTRODUCTION 1
2 DIGITAL TWIN 3
2.1 The Orgin of Digital Twin . . . . . . . . . . . . . . . . . . . . 3
2.2 What is Digital Twin? . . . . . . . . . . . . . . . . . . . . . . 5
2.3 Why Digital Twins are so important? . . . . . . . . . . . . . . 5
2.4 Formal Deﬁnition and its Types . . . . . . . . . . . . . . . . . 6
2.4.1 Digital Twin Prototype (DTP) . . . . . . . . . . . . . 7
2.4.2 Digital Twin Instance (DTI) . . . . . . . . . . . . . . . 7
2.4.3 Digital Twin Aggregate (DTA) . . . . . . . . . . . . . 7
2.4.4 Digital Twin Environment (DTE) . . . . . . . . . . . . 8
3 Working of Digital Twin 9
3.1 Making Digital Twins A Reality . . . . . . . . . . . . . . . . . 10
3.2 GE Digital Twin . . . . . . . . . . . . . . . . . . . . . . . . . 13
3.2.1 Asset Performance Management (APM) . . . . . . . . 14
3.2.2 Operations Optimization . . . . . . . . . . . . . . . . . 14
3.2.3 Business Optimization . . . . . . . . . . . . . . . . . . 14
3.2.4 Advanced Controls/Edge Computing . . . . . . . . . . 14
3.2.5 Cyber . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
3.2.6 Digital Twin Application Suite . . . . . . . . . . . . . 15
4 Characteristics of Digital Twin 16
5 Applications of Digital Twin 18
5.1 Examples . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
6 Advantages and Issues 22
v

7 CONCLUSION 27
8 References 28
vi

List of Figures
2.1 conceptual ideal for PLM . . . . . . . . . . . . . . . . . . . . . 3
2.2 Digital Twin Types . . . . . . . . . . . . . . . . . . . . . . . . 6
3.1 working of digital twin . . . . . . . . . . . . . . . . . . . . . . 10
3.2 A subject interacting with the holographic representation of
his digital twin. . . . . . . . . . . . . . . . . . . . . . . . . . . 11
3.3 GE Digital Twin . . . . . . . . . . . . . . . . . . . . . . . . . 13
3.4 Predix Platform . . . . . . . . . . . . . . . . . . . . . . . . . . 15
4.1 Communication/interaction between digital and real twins. . . 17
6.1 Expected Digital Twins market growth according to a study
published in June 2018. Reaching 15B$ in 2023.. . . . . . . . . 23
vii

Chapter 1
INTRODUCTION
A digital twin is a digital replica of a living or non-living physical en-
tity. By bridging the physical and the virtual world, data is transmitted
seamlessly allowing the virtual entity to exist simultaneously with the phys-
ical entity. Digital twin refers to a digital replica of physical assets (physical
twin), processes, people, places, systems and devices that can be used for
various purposes. The digital representation provides both the elements and
the dynamics of how an Internet of things device operates and lives through-
out its life cycle.
Digital Twin integrate internet of things, artiﬁcial intelligence, machine learn-
ing and software analytics with spatial network graphs to create living digi-
tal simulation models that update and change as their physical counterparts
change. A digital twin continuously learns and updates itself from multiple
sources to represent its near real-time status, working condition or position.
This learning system learns from itself, using sensor data that conveys vari-
ous aspects of its operating condition; from human experts, such as engineers
with deep and relevant industry domain knowledge; from other similar ma-
chines; from other similar ﬂeets of machines; and from the larger systems
and environment in which it may be a part of. A digital twin also integrates
historical data from past machine usage to factor into its digital model.
In various industrial sectors, twins are being used to optimize the operation
and maintenance of physical assets, systems and manufacturing processes.
They are a formative technology for the Industrial Internet of things, where
physical objects can live and interact with other machines and people vir-
tually. In the context of the Internet of things, they are also referred as
”cyberobjects”, or ”digital avatars”. The digital twin is also a component of
1

DIGITAL TWIN
the Cyber-physical system concept.
As a digital representation, a digital twin provides both the elements and the
dynamics of how an Industrial Internet of Things device operates throughout
its life cycle. Using this technology, an organization can increase predictabil-
ity and lower risks. The Digital Twin is an up-to-date and accurate copy
of the physical objects properties and states, including their position, shape,
status and motion.
Today enterprises can monitor and control systems digitally. This happens
by connecting to digital twins. Organizations are able to accumulate infor-
mation about the operation of the physical system it is connected to. Thus
Digital Twins are a formative technology, where physical objects live and
interact with other machines and people virtually.
A digital twin learns and updates itself from multiple sources. This system
uses sensor data that conveys various aspects of its operating condition ;
from human experts, from other machines ; from the surrounding environ-
ment; from the historical data from past machine usage, and so on.
An example of digital twins is the use of 3D modeling to create digital com-
panions for the physical objects in order to view the status of the actual
object. For example, when sensors collect data from a connected device, the
sensor data can be used to update a twin copy or a device shadow of the
devices state in real time. As a new concept, digital twins are still not widely
used, but a number of companies have introduced them in order to ﬁnd the
root cause of issues and improve productivity by better understanding and
predicting the performance of their machines.
These digital replicas help to ﬁnd new revenue streams, and change the way
businesses operate, as this technology provides unprecedented knowledge and
deeper insights.
This concept is rapidly becoming a business imperative, covering the entire
lifecycle of an asset or process and forming the foundation for connected
products and services.
Division of Computer Science and Engineering, SOE, CUSAT 2

Chapter 2
DIGITAL TWIN
2.1 The Orgin of Digital Twin
The concept of the Digital Twin dates back to a University of Michigan
presentation to industry in 2002 for the formation of a Product Lifecycle
Management (PLM) center.
Figure 2.1: conceptual ideal for PLM
The presentation slide, as shown in Figure 2.1 and originated by Dr. Grieves,
was simply called Conceptual Ideal for PLM. However, it did have all the el-
ements of the Digital Twin: real space, virtual space, the link for data ﬂow
from real space to virtual space, the link for information ﬂow from virtual
space to real space and virtual sub-spaces.
The premise driving the model was that each system consisted of two sys-
tems, the physical system that has always existed and a new virtual system
that contained all of the information about the physical system. This meant
that there was a mirroring or twinning of systems between what existed in
3

DIGITAL TWIN
real space to what existed in virtual space and vice versa.
The PLM or Product Lifecycle Management in the title meant that this
was not a static representation, but that the two systems would be linked
throughout the entire lifecycle of the system. The virtual and real systems
would be connected as the system went through the four phases of creation,
production (manufacture), operation (sustainment/support), and disposal.
This conceptual model was used in the first executive PLM courses at the
University of Michigan in early 2002, where it was referred to as the Mirrored
Spaces Model. It was referenced that way in a 2005 journal article (Grieves
2005). In the seminal PLM book, Product Lifecycle Management: Driving
the Next Generation of Lean Thinking, the conceptual model was referred to
as the Information Mirroring Model (Grieves 2006).
The concept was greatly expanded in Virtually Perfect: Driving Innovative
and Lean Products through Product Lifecycle Management (Grieves 2011),
where the concept was still referred to as the Information Mirroring Model.
However, it is here that the term, Digital Twin, was attached to this con-
cept by reference to the co-authors way of describing this model. Given the
descriptiveness of the phrase, Digital Twin, we have used this term for the
conceptual model from that point on. The Digital Twin has been adopted
as a conceptual basis in the astronautics and aerospace area in recent years.
NASA has used it in their technology roadmaps (Piascik, Vickers et al. 2010)
and proposals for sustainable space exploration (Caruso, Dumbacher et al.
2010). The concept has been proposed for next generation fighter aircraft and
NASA vehicles (Tuegel, Ingraffea et al. 2011, Glaessgen and Stargel 2012)1,
along with a description of the challenges (Tuegel, Ingraffea et al. 2011) and
implementation of as-builts (Cerrone, Hochhalter et al. 2014).

DIGITAL TWIN
2.2 What is Digital Twin?
Digital Twins are basically virtual copies of physical assets, including all
their modeled characteristics and behaviors in time. This may also include
the effects of aging as well as effects of usage over time. The digital twin
gets life from data generated by sensors (IoT) within the physical object and
delivered to data objects relating to the 3D model of the physical asset.
Digital Twins can depict full 3D models of automotive body assembly cells.
Such models can simulate, validate and optimize robotic operations before
they were executed on the shop floor. This can enable customers to virtual
commissioning almost to perfection. Digital Twins can be used to create
comprehensive computerized model of the product enabling almost 100% of
virtual validation and testing of the product under design.
Digital twins consist of three components: a data model, a set of analytics
or algorithms, and knowledge.
Data model:-A hierarchy of systems, sub-assemblies, and components that
describe the structure of the digital twin and its characteristics.
Analytics:-Predict, describe, and prescribe the behavior (current and future)
of an asset or process via both physics and AI/ML models.
Knowledge base:-Data sources that feed analytics, subject matter expertise,
historical data, and industry best practices.
2.3 Why Digital Twins are so important?
1. Digital Twins eliminate the need of prototyping, reduces the amount of
time and cost needed for development (almost by 50%), improves product
quality and enables faster reiteration in response to customer feedback.
2. The ultimate vision of Digital Twins is to create, test and build an equip-
ment in a virtual environment so that it helps us take a decision whether
to manufacture an equipment physically, in case it does not perform to

DIGITAL TWIN
our requirements.
3. Digital Twins can develop and introduce new products much faster than
ever.
4. Billions of things will be represented by Digital Twins in near future.
These proxies of physical world will lead to a new collaboration oppor-
tunities among physical world product experts and the data scientists.
5. Digital Twin eliminate guesswork from determining the best course of
action to service the critical physical assets, from engines to power tur-
bines. Moving forward, easy access to this unique combination of deep
knowledge and intelligence about the asset paves the road to optimization
and business transformation.
2.4 Formal Deﬁnition and its Types
The Digital Twin (DT) is a set of virtual information constructs that fully
describes a potential or actual physical manufactured product from the micro
atomic level to the macro geometrical level. At its optimum, any information
that could be obtained from inspecting a physical manufactured product can
be obtained from its Digital Twin.
Figure 2.2: Digital Twin Types
Digital Twins are of two types: Digital Twin Prototype (DTP) and Digital
Twin Instance (DTI). DTs are operated on in a Digital Twin Environment
(DTE)

DIGITAL TWIN
Digital Twin Prototype (DTP)
This type of Digital Twin describes the prototypical physical artifact. It
contains the informational sets necessary to describe and produce a physical
version that duplicates or twins the virtual version. These informational sets
include, but are not limited to, Requirements, Fully annotated 3D model, Bill
of Materials (with material speciﬁcations), Bill of Processes, Bill of Services,
and Bill of Disposal.
Digital Twin Instance (DTI)
This type of Digital Twin describes a speciﬁc corresponding physical prod-
uct that an individual Digital Twin remains linked to throughout the life
of that physical product. Depending on the use cases required for it, this
type of Digital Twin may contain, but again is not limited to, the following
information sets: A fully annotated 3D model with General Dimensioning
and Tolerances (GDT) that describes the geometry of the physical instance
and its components, a Bill of Materials that lists current components and
all past components, a Bill of Process that lists the operations that were
performed in creating this physical instance, along with the results of any
measurements and tests on the instance, a Service Record that describes
past services performed and components replaced, and Operational States
captured from actual sensor data, current, past actual, and future predicted.
Digital Twin Aggregate (DTA)
This type of Digital Twin is the aggregation of all the DTIs. Unlike the DTI,
the DTA may not be an independent data structure. It may be a computing
construct that has access to all DTIs and queries them either ad-hoc or
proactively. On an ad hoc basis, the computing construct might ask, What is
the Mean Time Between Failure (MTBF) of component X. Proactively, the
DTA might continually examine sensor readings and correlate those sensor
readings with failures to enable prognostics.

DIGITAL TWIN
Digital Twin Environment (DTE)
This is an integrated, multi-domain physics application space for operating
on Digital Twins for a variety of purposes. These purposes would include:
Predictive
The Digital Twin would be used for predicting future behavior and perfor-
mance of the physical product. At the Prototype stage, the prediction would
be of the behavior of the designed product with components that vary be-
tween its high and low tolerances in order to ascertain that the as-designed
product met the proposed requirements. In the Instance stage, the predic-
tion would be a speciﬁc instance of a speciﬁc physical product that incorpo-
rated actual components and component history. The predictive performance
would be based from current point in the product’s lifecycle at its current
state and move forward. Multiple instances of the product could be aggre-
gated to provide a range of possible future states
Interrogative
This would apply to DTIs as the realization of the DTA. Digital Twin In-
stances could be interrogated for the current and past histories. Irrespective
of where their physical counterpart resided in the world, individual instances
could be interrogated for their current system state: fuel amount, throttle
settings, geographical location, structure stress, or any other characteristic
that was instrumented. Multiple instances of products would provide data
that would be correlated for predicting future states. For example, correlating
component sensor readings with subsequent failures of that component would
result in an alert of possible component failure being generated when that
sensor pattern was reported. The aggregate of actual failures could provide
Bayesian probabilities for predictive uses.

Chapter 3
Working of Digital Twin
Digital Twins, the virtual counterparts of the physical assets are cre-
ated as digitalized duplicates of machines/ equipment or physical sites using
sensors. These digital assets can be created even before an asset is built phys-
ically. To create a digital twin of any physical asset, the engineers collect and
synthesize data from various sources including physical data, manufacturing
data, operational data and insights from analytics software. All this informa-
tion along with AI algorithms is integrated into a physics-based virtual model
and by applying Analytics into these models we get the relevant insights re-
garding the physical asset. The consistent ﬂow of data helps in getting the
best possible analysis and insights regarding the asset which helps in opti-
mizing the business outcome. Thus the digital twin will act as a live model
of the physical equipment. In general, virtual models are used to monitor,
analyze and improve their physical prototypes. Figuratively, their functions
can be divided into three stages:
To See :- at this stage, sensors and devices collect data to picture the situa-
tion.
To Think :- at this stage, the smart software analyzes collected data and, if
there are any issues, ﬁnds several possible solutions to each one.
To Do :- at this stage, intelligent algorithms choose the most appropriate so-
lution and implement them to address the problems. The technology allows
people to see the inner problems of physical objects without getting inside
due to computer visualization, and solve them with no risks for peoples health
and life.
9

DIGITAL TWIN
Figure 3.1: working of digital twin
Cybernated replicas of machines or physical sites using sensors are the vir-
tual equivalents i.e- Digital Twins of the physical assets which are created
in this form. These Digital assets come with an advantage i.e- even before
an asset is built physically, these digital assets can be developed. Data is
assembled and amalgamated from various origins including physical data,
manufacturing data, operational data and insights from analytics software,
by the engineers for creating a digital twin of any physical asset.
Analytics are applied to these models, which helps us in obtaining an ap-
plicable judgment related to the physical asset and all the data besides the
AI Algorithms is fused into a physics-based virtual model. The homogenous
drifting of data assists in achieving the apt inspection, which aids in the
growth of the business outcome. Digital twin can be synonymized as a live
model of the concrete machine.
3.1 Making Digital Twins A Reality
Realizing such digital twins will necessitate the support of several key tech-
nologies.

DIGITAL TWIN
Augmented, virtual, and mixed reality
Digital twins could be generated with 3D technologies and displayed as a
hologram or using AR/VR/MR devices (for example, Microsoft HoloLens),
as depicted in Figure 3.2. For instance, if a person is at work and his daughter
gets sick at home, he can use sensors installed in his oﬃce to generate his
real-time digital twin and appear in front of his daughter as a hologram to
comfort her. Hence, people in diﬀerent locations could interact as if they
were in the same space.
Figure 3.2: A subject interacting with the holographic representation of his digital twin.
Haptics
Digital twins can enhance communications by integrating haptic properties.
For example, if Alex shakes hands with Lisas digital twin, the digital twin
could provide appropriate haptic feedback to Lisa.
Robotics
Humanoid as well as soft robotics technologies could be leveraged to let digital
twins physically act on behalf of their real twin.

DIGITAL TWIN
5G and Tactile Internet
The emergence of the 5G and Tactile Internet, which aims to providing ultra-
low-delay and ultra-high-reliable communications, has enabled a paradigm
shift from conventional content-oriented to control-oriented communication,
particularly for human-in-theloop applications that are highly delay sensitive
and require a tight integration of communication and control mechanisms.
Digital twins would provide an always-active twin feedback loop that im-
proves the service quality of the physical systems.
Cloud computing
Oﬄoading computation and control to cloud computing infrastructures would
make digital twins more scalable and ensure that they are available to assist
their real twin anywhere, anytime.
Wearables
Wearable technology is attracting many users. The considerable amount of
physiological data gathered daily by these devices could be used by digital
twins to more eﬃciently support their real twin.
IoT
Contextual data could be fed from users to their digital twin through the IoT,
and feedback could be sent to the environment, enabling users to interact
more smoothly with their surroundings as well as remote locations.
AI
IoT data is processed using algorithms that are continuously improved with
updated user data. Using such time-series data, a users digital twin could
suggest actions to control or avoid potentially harmful situations.

DIGITAL TWIN
3.2 GE Digital Twin
GE has created the most advanced and functional Digital Twin that inte-
grates analytic models for components of the power plant that measure asset
health, wear and performance with customer defined KPIs and business ob-
jectives. The Digital Twin runs on an industrial platform, Predix, designed
to ingest massive volumes of machine sensor data, to manage and execute
analytic models, to run a high speed business rules engine and to manage in-
dustrial data at scale. Further, this environment is integrated with business
applications designed to allow plant executives, plant managers and workers
to interact with the Digital Twin in real time. Business applications, shown
Figure 3.3: GE Digital Twin
in the figure above, tied to the Digital Twin provide the window of interac-
tion to take action on insights, to manage the power plant and generation
fleet functions to a greater level of control and to be able to react to changing
market, fuel price and weather conditions in rapid fashion. These business
applications are designed to increase asset performance, enhance operations,
and improve energy trading decisions to create additional revenue and cost
reduction opportunities. The applications fall into the following categories:

DIGITAL TWIN
Asset Performance Management (APM)
Transform data into actionable intelligence by combining robust analytics
with domain expertise. Create a single source of data for all power generation
or renewables assets across a fleet, utilizing predictive analytics to identify
issues before they occur, reducing downtime and extending asset life while
still balancing maintenance costs with operational risk.
Operations Optimization
Deliver enterprise data visibility across power plant and fleet-wide footprints,
providing a holistic understanding of the operational decisions that can ex-
pand capabilities and lower production costs. Empower operators and plant
managers with KPI driven insights to raise overall productivity.
Business Optimization
Reduce financial risk and maximize the real potential of the power fleet to-
ward greater profitability with intelligent forecasting for smarter business
decisions.
Advanced Controls/Edge Computing
Control power plant operations with advanced technologies. Analytics based
solutions manage grid stability, fuel variability, emissions, compliance and
other challenges to reduce costs and maximize revenue.
Cyber
An advanced defense system designed to assess system gaps, detect vulner-
abilities, and protect critical infrastructure and controls in compliance with
cyber security regulations.

DIGITAL TWIN
Digital Twin Application Suite
A set of applications interfacing with Digital Twin analytic models and ap-
plication capabilities of Asset Performance Management, Operations Opti-
mization, Business Optimization and Advanced Controls to bring insights
and actions together for business beneﬁts.
Figure 3.4: Predix Platform
The Predix Platform provider help you build digital twins using sensor net-
work (IoT). You can also create Digital Twin Apps using Predix. Predix
is a proven industrial environment, on which the Digital Twin and business
applications run. Cloud (public or private) based capabilities are closely in-
tegrated with an on-premise Predix Machine and Edge Analytics Control
System, responsible for collecting, formatting and sending machine data and
for executing machine level analytics where real-time responses are required
on site. Predix is speciﬁcally designed for massive data ingestion, housing
and executing analytic models, managing time-series machine data and high
speed application execution. The environment, from Supervisory Control
and Data Acquisition (SCADA) systems through Predix Machine to cloud
and back is a highly secured environment, locked down with the same cyber
technology GE has installed in industrial operations globally.

Chapter 4
Characteristics of Digital Twin
Unique identiﬁer
Digital twins would each have a unique identiﬁer in order to communicate
with their twin. Sensors and actuators. Real twins could be equipped with
sensors so that digital twins could replicate their sensessight, hearing, taste,
smell, and touchusing the appropriate actuators, depending on application
needs.
AI
Digital twins should be equipped with a controller embedded with ontologies,
machine learning, and deep learning techniques in order to make fast and
intelligent decisions on behalf of their real twin.
Communication
Digital twins should be able to interact in near real time with the environ-
ment, real twins, and/or other digital twins as Figure 1 shows. Communica-
tion, including the sense of touch (haptics), must occur within 1 ms and thus
must follow 5G and Tactile Internet standards.
16

DIGITAL TWIN
Figure 4.1: Communication/interaction between digital and real twins.
Representation
Digital twins could have a virtual representation as a 3D avatar, hologram,
or even a humanoid social robot but it could also be software components
without a tangible representation, depending on the application.
Trust
For digital twins to handle sensitive tasks such as managing ﬁnancial trans-
actions or a stock portfolio for their real twin, or interacting on the real twins
behalf in meetings, real twins must be able to trust their digital twin.
Privacy and security
twins should be able to protect the identity and privacy of their real twin.
This would require the use of advanced cryptography algorithms and biomet-
rics techniques(ECG-biometrics, haptic biometrics, and so on) as well as the
resolution of regulatory and political issues.

Chapter 5
Applications of Digital Twin
Digital Twin concept is the next big thing in most of the business sectors,
which helps in accurately predicting the current state and future of physi-
cal assets by analyzing their digital counter parts. By implementing Digital
Twins, organizations can gain better insights on product performance, im-
prove customer service and make better operational and strategic decisions
based on these insights. We have started seeing the major applications of
Digital Twins in the following sectors.
Manufacturing
Digital Twin is poised to change the current face of manufacturing sector.
Digital Twins have a signiﬁcant impact on the way products are designed
manufactured and maintained. It makes manufacturing more eﬃcient and
optimized while reducing the throughput times.
Automobile
Digital Twins can be used in the automobile sector for creating the virtual
model of a connected vehicle. It captures the behavioral and operational data
of the vehicle and helps in analyzing the overall vehicle performance as well
as the connected features. It also helps in delivering a truly personalized/
customized service for the customers.
18

DIGITAL TWIN
Retail
Appealing customer experience is key in the retail sector. Digital twin imple-
mentation can play a key role in augmenting the retail customer experience
by creating virtual twins for customers and modeling fashions for them on it.
Digital Twins also helps in better instore planning, security implementation
and energy management in an optimized manner.
Healthcare
Digital Twins along with data from IoT can play a key role in the health care
sector from cost savings to patient monitoring, preventative maintenance and
providing personalized health care.
Smart Cities
The smart city planning and implementation with Digital Twins and IoT data
helps enhancing economic development, efficient management of resources,
reduction of ecological foot print and increase the overall quality of a citizens
life. The digital twin model can help city planners and policymakers in the
smart city planning by gaining the insights from various sensor networks and
intelligent systems. The data from the digital twins help them in arriving at
informed decisions regarding the future as well.
Industrial IoT
Industrial firms with digital twin implementation can now monitor, track
and control industrial systems digitally. Apart from the operational data,
the digital twins capture environmental data such as location, configuration,
financial models etc. which helps in predicting the future operations and
anomalies
Other digital twin applications range from e-learning to financial management
to virtual tours to shopping to online social interactions. For many such ap-
plications, digital twins must be highly personalizable in order to effectively

DIGITAL TWIN
interact on behalf of their real twin with other people or digital represen-
tations. For example, media such as photos, videos, and sound recordings
enable us to hold onto the past much better than our memories allow and to
recall people who have touched us throughout our life. Digital twins might
make it possible to also restore the smell, touch, and hugs of deceased loved
ones. In addition, digital twins would continuously absorb information about
their real twin, training their neural networks using the latters actions and
decisions. Digital twins would continue to exist after their real twin passes
away, enabling loved ones to continue to communicate with deceased persons.
In this way, digital twins would extend humans presence beyond their biolog-
ical limitations. Another application is dating. The popularity of dating sites
is increasing, but information on these sites is not always accurate, in part
because users must manually input subjective information about their per-
sonality. Some people do not know themselves well, while others enter false
information. Digital twins could help provide more accurate descriptions of
their real twin on such sites at diﬀerent privacy levels. They could also be
used to simulate a real-life hookup todetermine if it is a good match.
5.1 Examples
An example of how digital twins are used to optimize machines is with the
maintenance of power generation equipment such as power generation tur-
bines, jet engines and locomotives. In Enterprise Architecture, architects
create EA blueprints as digital twin for the organization.
Another example of digital twins is the use of 3D modeling to create digital
companions for the physical objects. It can be used to view the status of the
actual physical object, which provides a way to project physical objects into
the digital world. For example, when sensors collect data from a connected
device, the sensor data can be used to update a ”digital twin” copy of the
device’s state in real time. The term ”device shadow” is also used for the
concept of a digital twin. The digital twin is meant to be an up-to-date and
accurate copy of the physical object’s properties and states, including shape,
position, gesture, status and motion.
A digital twin also can be used for monitoring, diagnostics and prognostics

DIGITAL TWIN
to optimize asset performance and utilization. In this field, sensory data can
be combined with historical data, human expertise and fleet and simulation
learning to improve the outcome of prognostics. Therefore, complex prog-
nostics and intelligent maintenance system platforms can use digital twins
in finding the root cause of issues and improve productivity. Digital twins
of autonomous vehicles and their sensor suite embedded in a traffic and en-
vironment simulation have also been proposed as a means to overcome the
significant development, testing and validation challenges for the automotive
application, in particular when the related algorithms are based on artificial
intelligence approaches that require extensive training data and validation
data sets. Digital twins should be thought of in the context of the fourth
paradigm of science. The four paradigms are: 1. Empirical 2. Theoretical
3. Computational (e.g. Finite Element Analysis) 4. Big Data It is therefore
useful to think of Digital Twin as a Big Data driven simulation. Further
examples of industry applications: Aircraft engines Wind turbines Large
structures e.g. offshore platforms, offshore vessels etc. HVAC control sys-
tems Locomotives Buildings Utilities (Electric, Gas, Water, Waste Water
Networks)

Chapter 6
Advantages and Issues
Digital twins can represent objects and entities as varied as a turbine, a robot,
a whole ship, a cow, a human being or a city, and everything else in between.
More recently they have started to be used to represent intangible entities
like services, processes and knowledge.
Digital twins are already used in design, planning, manufacturing, operation,
simulation and forecasting. They are also used in agriculture, transportation,
health care and entertainment. Applications will continue to grow through
the next decade, hence it is not surprising that they named among the ten
most strategic emerging concepts for the coming years by Gartner, or that
MPL Systems expects 25% of asset-intensive companies to be using them by
2020 and supporting technology spending of $10.96 billion in 2022.
When considering digital twins, the key word is represents. Basically, a dig-
ital twin mimics in bits an objects atoms and their structural/functional
relations. It does not necessarily represent all of them (something conceptu-
ally impossible, as you cannot represent a single atomic electron cloud with
unlimited precision), but what matters is that the representation is accurate
enough to support the goals that have been identiﬁed and that are being pur-
sued. For example, if you want to check the proper working of an engine you
need to represent all aspects that are functional to that goal (e.g., you may
disregard the color used to paint parts of that engine). However, if you are
mirroring a car then the color of the paint is important because retouching
a car after an accident requires knowing the original paint color.
22

DIGITAL TWIN
Figure 6.1: Expected Digital Twins market growth according to a study published in June 2018. Reaching
15B$ in 2023..
Note that a digital twin can also, and usually it does, contain more data than
its real counterpart. As an example, an engines digital twin is likely to con-
tain the list of suppliers of the various components of the engine as well as the
identity of the robots and workers that assembled it. A digital twin is also a
historical repository of its counterpart. Thus, in the case of an engine, it may
include extensive data on maintenance events and operations, for example,
the minute-to-minute monitoring of airplane engine data including rotation
speed, oil usage, pressure, temperature, and so forth.
All these data sets can be used for real-time analyses and simulation. They
can also be used collectively to identify patterns and meanings. Take the
example of General Electric (GE), which creates a digital twin for each of
the turbines they produce. Once these turbines are assembled on a windmill
to generate electricity or deployed on an aircraft to generate thrust, the tur-
bines report operation status back to GE in quasi real time. This information
is then compared with data generated by each unique digital twin for con-
sistency. Any deviation activates an application to analyse the discrepancy
and take action if needed, such as ordering the turbine ﬂying on the plane
to reduce power and decreasing the rotation speed to safeguard the integrity
of the engine. Of course, this aﬀects the other digital twin engine on the
aircraftin this case making sure that balancing measures are implemented by
increasing the thrust of the other engine and repositioning the wings moving

DIGITAL TWIN
parts to maintain equilibrium. At the same time, the applications will look
for an emerging pattern related to the situation (present and past) of other
digital twins and will store data on any mismatches.
There are similar scenarios with our own digital twins. For instance, I have
a bunch of data on Facebook that identifies my friends, information on my
travel logged on Instagram, and a Twitter account that shows my reactions to
events. Additionally, I have sensors on my body (a smartphone) that tracks
my daily activity and provides further data. More data may come from my
health records, if I am willing to share them, and in the future I could even
have the data from my sequenced genome. Applications can continuously
analyse my digital twin and detect emerging patterns that may require at-
tention. This is particularly true in the health care domain, where Bill Ruh,
CEO of GE Digital, in a recent presentation stated, I believe we will end up
with health care being the ultimate digital twin.
Similar to a digital twin of an object like a turbine, my digital twin is more
than a representation of myself within a specific domain of interest. It con-
tains the copy of my past, very possibly keeping memories of something I
forgot long ago. There is a need, therefore, to distinguish between the instan-
taneous digital twin, which represents me at a specific moment in a specific
context, and my global digital twin that remembers what I had for dinner a
year ago and what pill I took to ease my digestion.
A digital twin can be used to monitor its real twin and to simulate the effect
of some actions (e.g., increasing the rotation speed of a turbine or changing
a persons diet). It can be used to derive relevant information from other
digital twins, such as detecting a malfunction that could affect other turbines
or determining the side effects of a particular remedy. Statistical information
and pattern data can be used to monitor changes in a particular activity, for
example, turbines on a specific assembly line showing a power decrease in
certain conditions or several persons taking two different kind of pills being
subjected to undesirable side effects.
Digital twins can also become impersonators, where they can act out in cy-
berspace the part of the object in the real space. Hence, they can be used
when designing a new object to study the interactions that may happen, as

DIGITAL TWIN
well as to solicit a digital twin to learn from those interactions, and then to
transfer what has been learnt to the physical object. This may be particu-
larly useful in robotics where the digital twin of a robot can be solicited by
other digital twins, including ones representing a specific situation, and can
try different approaches to find the most effective one. This experience (or
knowledge) can then be shared with/downloaded to the real robot, providing
it with an experience that it could not have had in the real space, perhaps
because the situation could not be replicated at will or because the real ex-
perience might damage the robot.
There are many situations that are easier and cheaper to replicate in cy-
berspace with no likelihood of collateral damage and many examples of ap-
plications getting smarter by challenging themselves and learning from the
experience. In the future, digital twins may become an essential component
in the evolution of machines and the growing symbiosis between humans and
machines.
Over the next decade, many objects will be created with their own digital
twin and will live in symbiosis with them. In various situations, as Ive de-
scribed, robot intelligence will emerge through interactions with a digital twin
in cyberspace, and over time the evolution and continuous learning of robots
and other objects will undoubtedly be fostered by digital twins.
As with any new technology, digital twins are prompting ethical, legal and
societal questions. Imagine a company with hundreds of human and robot
workers, each one with a digital twin! Suppose a robot breaks down and
needs to be replacedwouldnt it be normal to associate the new robot to the
previous robot digital twin so that it immediately inherits the previous robots
experience? Of course, no discussion about that.
Now consider a human worker who decides to retire, or just change jobs.
What about her digital twin? Will it remain the property of the company
and as such be used by the company to train a new worker? What might
happen when it becomes feasible to replace a worker with a robot? Can the
company associate the human digital twin to the robot, hence transferring
the experience previously accumulated by the human worker to the robot?
Is it possible in the future that companies will hire humans just for creating

DIGITAL TWIN
a digital twin that along with a robot will make them redundant?
As a robot digital twin learns by interacting with a human digital twin, is
it likely to become smarter and smarter, accelerating the process of human
displacement in factories and, more generally, in the labour market? These
are just a few of the questions that are popping up as we walk the unexplored
trails heading towards a future that probably is just around the corner.

Chapter 7
CONCLUSION
Realizing the full potential of digital twins will require a convergence of
the above-mentioned technologies. In particular, more research is needed to
improve traditional data collection and processing methods and to implement
the communication interface between real and physical twins. In addition,
digital twin applications need to be accurate to earn users conﬁdence and
trust, and be robust enough to allow users to live their normal lives. The
system must have security mechanisms to guarantee users privacy and protect
their personal data, and be able to detect failures and missing data.
Foreseeing the emergence of diﬀerent realizations of a digital twin, it would
also be imperative to standardize technologies to interoperate in the long
term. Moreover, to facilitate collaboration worldwide, digital twins must
incorporate mechanisms to accommodate a diversity of cultures.There are
also legal issues that must be resolved, such as how much responsibility digital
twins should be entrusted with to act on behalf of individuals, and what entity
is liable for any harmful actions attributed to a digital twin.
27

Chapter 8
References
1. Abdulmotaleb EISaddik, Digital Twins: The Convergence of
Multimedia Technologies, IEEE Multimedia 25(2):87-92April 2018
2. Dr. Michael Grieves and John Vickers Digital Twin: Mitigating
Unpredictable, Undesirable Emergent Behavior in Complex Systems
(Excerpt) white paper
3. K. Bruynseels, F. Santoni di Sio, and J. van den Hoven, Digital Twins
in Health Care: Ethical Implications of an Emerging Engineering
Paradigm, Frontiers in Genetics, 13 February 2018
4. S. Boschert, R. Rosen, ”Digital twin-the simulation aspect”,
Mechatronic Futures: Challenges and Solutions for Mechatronic
Systems and Their Designers, pp. 59-74, 2016.
5. Shoumen Palit Austin Datta, ”Datta, Emergence of Digital Twins”,
Journal of Innovation Management, 2017
6. Neda Mohammadi, John E. Taylor, ”Smart city digital twins”, IEEE
Symposium Series on Computational Intelligence (SSCI) 2017
7. Qinglin Qi, Fei Tao, ”Digital Twin and Big Data Towards Smart
Manufacturing and Industry 4.0: 360 Degree Comparison” IEEE
28

DIGITAL TWIN
Access, vol. 6, 15 January 2018 pp. 3585-3593.
8. M. Grieves, Digital Twin: Manufacturing Excellence through Virtual
Factory Replication, white paper, 2014
9. K.M. Alam and A. El Saddik, C2PS: A Digital Twin Architecture
Reference Model for the Cloud-Based Cyber-Physical Systems, IEEE
Access, vol. 5, 2017, pp. 20502062.

Digital twin

More Related Content

What's hot

Similar to Digital twin

Recently uploaded

Digital twin