DIGITAL TWIN

SEMINAR REPORT

Submitted to the APJ Abdul Kalam Technological University in partial

fulfilment of the requirements for the award of the Degree of

Bachelor of Technology

In

MECHANICAL ENGINEERING

By,

FAHEEM M M

(Reg no: MEC17ME014)

DEPARTMENT OF MECHANICAL ENGINEERING

MALABAR COLLEGE OF ENGINEERING AND

TECHNOLOGY
DESHMANGALAM, PALLUR (P.O)

THRISSUR, KERALA-679532

JULY, 2021

i
MALABAR COLLEGE OF ENGINEERING AND TECHNOLOGY
DEPARTMENT OF MECHANICAL ENGINEERING

DESHAMANGALAM, PALLUR (P.O), THRISSUR, KERALA-679532

CERTIFICATE
This is to certify that this is a bonafied report on the seminar titled

DIGITAL TWIN
Done by,

AZWAN BIN ASHRAF

FAHEEM MM

(Reg no: MEC17ME014)

during the year 2020-2021 in partial fulfilment of the requirements for the award of
the degree, BACHELOR of TECHNOLOGY in MECHANICAL ENGINEERING
under A.P.J Abdul Kalam Technological University.

Seminar coordinator Head of the Department

SATHIL P T ANEESH A
Asst. Professor, Asst. Professor,
Dept. of Mechanical Engineering Dept. of Mechanical Engineering

ii
 ACKNOWLEDGEMENT

I would like to express my deepest gratitude to Dr. P. Babu, Principal, Malabar College
of Engineering and Technology, Pallur for forecasting an excellent academic climate in
the college and for this support and encouragement throughout the course period.

I am very much grateful to Mr. Aneesh A, Assistant Professor and Head of Department
of Mechanical Engineering, Malabar College of Engineering and Technology, Pallur,
for encouragement and inspiration for execution of the seminar.

I wish to thank Mr. Sathil P T, Assistant Professor and seminar coordinator of

Department of Mechanical Engineering, Malabar College of Engineering and
Technology, Pallur whose advice, support, stimulating suggestions and constant
encouragement proved decisive in shaping up of this seminar.

I would like to take this opportunity to thank my friends who spent their valuable time
and shared their knowledge for helping me to complete the seminar with the best
possible result

Finally, I thank my parents for their inspiration and ever encouraging moral support,
which enabled me to pursue my studies.

FAHEEM M

iii
 ABSTRACT

A digital twin is a digital representation of a physical object, process or service. The

concept originated earlier the first practical definition of digital twin originated from
NASA in an attempt to improve physical model simulation of spacecraft in 2010.
Digital twins are the result of continual improvement in the creation of product design
and engineering activities. Product drawings and engineering specifications progressed
from handmade drafting to computer aided drafting/computer aided design to model-
based systems engineering.

A digital twin can be a digital replica of an object in the physical world, such as a jet
engine or wind farms, or even larger items such as buildings or even whole cities. As
well as physical assets, the digital twin technology can be used to replicate processes in
order to collect data to predict how they will perform. A digital twin is, in essence, a
computer program that uses real world data to create simulations that can predict how
a product or process will perform. These programs can integrate the internet of things
(Industry 4.0), artificial intelligence and software analytics to enhance the output. With
the advancement of machine learning and factors such as big data, these virtual models
have become a staple in modern engineering to drive innovation and improve
performance. The concept of digital twins is not exactly new – it was first presented by
Dr Michael Grieves in 2002, and, prior to that, NASA had been using complex
simulations of spacecraft for decades. But thanks to the explosion of the internet of
things (IoT), and the subsequent lowering costs of associated technologies, digital twins
are now more accessible than ever.

iv
 CONTENTS

CONTENTS Page No.

List of figures vi

Abbreviations vii

1. Introduction 1

1.1 Importance of digital twin 1

1.2 Essential components of digital twin 2

2. Literature survey 3

3. Digital twin misconceptions 4

4. Working 6

4.1 Steps to implement digital twin model 7

5. Creating a digital twin 8

6. Digital twin maturity model 11

7. Underlying technologies 12

8. Advantages 16

9. Disadvantages 17

10. Applications 19

11. Conclusion 21

12. References 22

v
 LIST OF FIGURES

No. Title Page No.

1 Digital twin 2

2 Digital shadow, digital model and digital twin 4

3 Creating a digital twin 9

4 IoT 12

vi
 ABBREVIATIONS

DT Digital twin

IP Internet protocol

AI Artificial Intelligence

VR Virtual reality

AR Augmented reality

IoT Internet of Things

vii
 CHAPTER 1

INTRODUCTION

The concept of digital twins is not exactly new – it was first presented by Dr Michael
Grieves in 2002, and, prior to that, NASA had been using complex simulations of
spacecraft for decades. But thanks to the explosion of the internet of things (IoT), and
the subsequent lowering costs of associated technologies, digital twins are now more
accessible than ever.
A digital twin is a virtual representation of a real-life object or device. If you think that
sounds a lot like 3D renderings of computer-aided design (CAD) models, you’d be
right. But where digital twins differ crucially from simple 3D models is that they also
combine the physical elements and the dynamics of how that object or device operates
in the real world. In other words, you can see, almost in real time, precisely how an
object or device responds throughout its lifecycle. Just as an asset drifts in response to
factors like the weather, the ambient temperature, operator idiosyncrasies, and so forth,
so too does its digital twin.
Digital twins do this by combining data collected from sensors on the device, with
knowledge related to the design, build, operation and servicing of the physical twin.
Already, just from this data, you have a rich, highly detailed picture of the asset.
Intelligence, in the form of analytics, physics, and machine learning, is then built on top
of the data, acting as the “brain” of the digital twin, and making things like predictive
modelling, optimization and early warning systems possible.

1.1 IMPORTANCE OF DIGITAL TWIN TECHNOLOGY

Digital twins are powerful technologies to drive innovation and performance. It is the
most important product for technicians with the most advanced monitoring, analytical,
and predictive capabilities at their fingertips. Its estimated that by 2018 companies who
invest in digital twin technology will see a 30 percent improvement in cycle time of
critical processes. Over the next five years, billions of things will be represented by
digital twins. These representations of the physical world will lead to new
collaborations and opportunities among physical world product experts and data
1
 scientists whose jobs are to understand what data tell us about operations. Digital twin
technology help companies improve the customer experience by better understanding
customer needs, develop enhancements to existing products, operations, and services,
and can even help drive the innovation of new business.

1.2 ESSENTIAL COMPONENTS OF A DIGITAL TWIN

Analytics at every step: A digital twin deals with a staggering amount of data, and its
effectiveness is reliant on whether this data is:
• real-time,
• operational,
• high-quality, and
• predictive-orientated in its nature.

Open and federated data: The data has to be accessible from several sources, and be
pulled together into a federated model, rather than being centralized in proprietary
systems.

Applied industry context: Applying industry context is essential to getting maximum

value out of a digital twin. In fact, it is possible to have two different digital twins for
the same product that is being used in two different industries, because of how the
industry context is applied to the twin.

2
 CHAPTER 2

LITERATURE SURVEY

Since Dr. Grieves presented the concept, and NASA gave the first specific
definition, large number of literatures regarding digital twin have been published,
including six reviews. Holler et al. analyzed 38 articles. The review results provided an
overview of established concepts, classified the existing body of literature, provided a
lifecycle perspective on applications, and suggested directions for further research.
Negri et al. conducted a comprehensive literature review to answer two questions: ‘How
does scientific literature define the digital twin?’ and ‘What role does it play in Industry
4.0?’. The review presented three possible uses of digital twin: analyzing health
conditions to plan maintenance activities, managing the whole lifecycle of the physical
object, and improving decision-making through engineering and numerical analysis.
Krit- Zinger et al. reviewed digital twin in manufacturing from a categorical
perspective. To clarify integration level of digital twin in existing researches, the author
proposed three subcategories of digital twin according to data integration levels. The
classified subcategories were Digital Model, Digital Shadow, and Digital Twin. Tao et
al. reviewed the state-of-the-art of the digital twin researches thoroughly. The authors
focused on the key components, the up-to-date development, and the major applications
of digital twin in industry. They divided the development trend of DT research into
three stages, which is formation stage (2003–2011), incubation stage (2011–2014),
growth stage (2014-now). The paper reviewed the most relevant theories: (1) DT
modeling, simulation, verification, validation, and accreditation (VV&A), (2) data
fusion, (3) interaction and collaboration, and (4) service. Liu et al. compared and
analyzed the DT models in the scientific publications. Digital twin models were retraced
from the initial one to the most up-to-date one to find some principles of DT modeling.
The paper reviewed relevant information on DT models according to the application
purpose, model level, and model representation. For the analysis of Digital Twin
applications, Enders and Hoßbach proposed a classification scheme with six dimensions
to describe the applications identified. The six dimensions include industrial sector,
purpose, physical reference object, completeness, creation time, and connection.

3
 CHAPTER 3

DIGITAL TWIN MISCONCEPTIONS

1) Digital Model

A digital model is described as a digital version of a pre-existing or planned physical

object, to correctly define a digital model there is to be no automatic data exchange
between the physical model and digital model. Examples of a digital model could be
but not limited to plans for buildings, product designs and development. The important
defining feature is there is no form of automatic data exchange between the physical
system and digital model. This means once the digital model is created a change made
to the physical object has no impact on the digital model either way. Figure. illustrates
a Digital Model.

2) Digital Shadow

A digital shadow is a digital representation of an object that has a one-way flow between
the physical and digital object. A change in the state of the physical object leads to a
change in the digital object and not vice versus. Figure illustrates a Digital Shadow.

3) Digital Twin

If the data flows between an existing physical object and a digital object, and they are
fully integrated in both directions, this constituted the reference “Digital Twin”. A
change made to the physical object automatically leads to a change in the digital object
4
and vice versa. Figure illustrates a Digital Twin.

These three definitions help to identify the common misconceptions seen in the
literature. However, there are several misconceptions seen but they are not limited to
just these specific examples. Amongst the misconceptions is the misconception Digital
Twins have to be an exact 3D model of a physical thing. On the other hand, some
individuals that think a Digital Twin is just a 3D model.

5
 CHAPTER 4

HOW DOES DIGITAL TWIN WORK?

Digital Twin is a complex system that produces tremendous amount of data. All
of this data from devices is descriptive in nature. That is, the data tells you what
happened and when it happened. Using data analytics, you can exploit this data to be
predictive and tell you when something will happen like a failure, for instance. In
contrast, digital twin which is basically a virtual representation of the process, product
or system will allow you to improve them to avoid a failure. Digital Twin technology
integrate AI, software analytics and machine learning data to create a digital simulation
models that update and change as their physical counterparts’ change. This near real-
time update and continuous learning from multiple sources represent the status,
working condition or position of the physical asset. Digital twin contains sensors that
collect data to represent real time data of the physical asset. The sensor data is collected,
analyzed and used in predictive analytics by the digital twin to optimize the product's
performance via a maintenance regime. Digital twin technology offers an interface that
makes organizations familiar to past and present operation, and helps them to make
predictions of the future. Various data sources contribute to the digital twins learning
curve. This model learns from the historical data from past machine usage, processes,
or system usage, from humans with relevant domain knowledge, from other sources.

4.1 STEPS TO IMPLEMENT DIGITAL TWIN MODEL

While it may seem easy to list out the steps to implement digital twins, it
requires a lot of practical realities to make this possible. Businesses must check on the
existing infrastructure, policies, organizational wide attitude, budget, and other
mandatory requirements. There are four practical steps to get started with digital twin
implementation
• Integrate smart components into new or existing products.
• Connect the products/services to a central (cloud-based) location with
streaming, big data, in-memory, and analytic capabilities to capture sensor data and
enrich it with business and contextual data.
• Constantly analyze the data to identify areas for improvements, new products

6
or even new business models.
• Use digital insights to create new services that transform the company.

7
 CHAPTER 5

CREATING A DIGITAL TWIN

The creation of digital twin involves the following steps:

1. Create: The create step encompasses outfitting the physical process with myriad
sensors that measure critical inputs from the physical process and its surroundings. The
measurements by the sensors can be broadly classified into two categories:

• operational measurements pertaining to the physical performance criteria of the

productive asset (including multiple works in progress), such as tensile strength,
displacement, torque, and color uniformity;

• environmental or external data affecting the operations of a physical asset, such as

ambient temperature, barometric pressure, and moisture level.

The measurements can be transformed into secured digital messages using encoders
and then transmitted to the digital twin. The signals from the sensors may be augmented
with process- based information from systems such as the manufacturing execution
systems, enterprise resource planning systems, CAD models, and supply chains
systems. This would provide the digital twin with a wide range of continually updating
data to be used as input for its analysis.

2. Communicate: The communicate step helps the seamless, real-time, bidirectional

integration/connectivity between the physical process and the digital platform.
Network communication is one of the radical changes that have enabled the digital
twin; it comprises three primary components: Industry 4.0 and the digital twin

• Edge processing: The edge interface connects sensors and process historians,
processes signals and data from them near the source, and passes data along to the
platform.

• Communication interfaces: Communication interfaces help transfer information

from the sensor function to the integration function.
8
• Edge security: New sensor and communication capabilities have created new
security issues, which are still developing. The most common security approaches are
to use firewalls, application keys, encryption, and device certificates. The need for new
solutions to safely enable digital twins will likely become more pressing as more and
more assets become IP enabled.

3. Aggregate: The aggregate step can support data ingestion into a data repository,
processed and prepared for analytics. The data aggregation and processing may be done
either on the premises or in the cloud. The technology domains that power data
aggregation and processing have evolved tremendously over the last few years in ways
that allow designers to create massively scalable architectures with greater agility and
at a fraction of the cost in the past.

4. Analyze: In the analyze step, data is analyzed and visualized. Data scientists and
analysts can utilize advanced analytics platforms and technologies to develop iterative
models that generate insights and recommendations and guide decision making.

9
5. Insight: In the insight step, insights from the analytics are presented through
dashboards with visualizations, highlighting unacceptable differences in the
performance of the digital twin model and the physical world analogue in one or more
dimensions, indicating areas that potentially need investigation and change.

6. Act: The act step is where actionable insights from the previous steps can be fed
back to the physical asset and digital process to achieve the impact of the digital twin.
Insights pass through decoders and are then fed into the actuators on the asset process,
which are responsible for movement or control mechanisms, or are updated in back-
end systems that control supply chains and ordering behavior—all subject to human
intervention. This interaction completes the closed loop connection between the
physical world and the digital twin.

The digital twin application is usually written in the primary system language of the
enterprise, which uses the above steps to model the physical asset and processes. In
addition, throughout the process, standards and security measures may be applied for
purposes of data management and connectivity

10
 CHAPTER 6

DIGITAL TWIN MATURITY MODEL

The maturity model for digital twins depends on the level of information that’s
known about a physical asset and its environment. This model shows that the digital
model improve over time as more derivative information is accumulated. The
recorded data and its storage intimates about the asset’s current state and condition
the level of Digital Twin maturity model include:

a) Partial
•At this level, the digital twin typically contains a limited number of data sources
such as pressure, temperature and device state.
•The twin is useful to capture a key metric or state from a low power or resource-
constrained asset, such as a connected light bulb that simply reports its current
power state.
•This level is also seen in proof-of-connectivity development, as it enables quick
development of device-to-platform functionality.
•This level contains enough data sources to create derivative data for further
analysis. For example, if pressure is down but temperature is up, and linear
regression identifies a correlation, a corresponding inference about the health of the
asset can be made.

b) Clone
•This form of a digital twin contains all meaningful and measurable data sources
from an asset.
•This level is applicable when a connected asset is not power or data constrained.
•This level is useful in prototyping and data characterization phases of IoT
development.

c) Augmented
•The augmented digital twin enhances the data from the connected asset with
derivative data, correlated data from federated sources, and/or intelligence data
from analytics and algorithms.
11
 CHAPTER 7

UNDERLYING TECHNOLOGIES

The technologies which enable digital twin technology are given below

7.1 Internet of Things (IoT)

The Internet of Things is the term given to devices connected to the internet. It is
about giving so-called “things” a sense of intelligence and the ability to collect
information on their environment. The idea that all devices that are interconnected
gives the developer the ability to track and monitor everything we do, thus leading
to a smarter world. The number of IoT devices recorded year on year shows the
considerable growth of this technology

7.2 Data Analytics

The term data analytics stems from the field of “Data Science”, a multidisciplinary
subject that covers a range of concepts, with an emphasis on collecting and
presenting data for analysis to gain greater insight. To perform data analysis, the
need for raw data is paramount. There are several actions needed to turn this data
into usable information, ready for use in algorithms and statistical analysis. These
being the requirements, collection, processing and cleaning. The requirements set
out the necessary needs of the data and how it is used, ensuring that specific

12
requirements are outlined, considering the intended use of the data. The second
stage acts on the requirement of collecting the relevant data, identifying physically
where and how the data

will be collected. The collected data will then go through a processing phase in
which it is sorted according to specific requirements. The final phase and arguably
the most important is the cleaning of data. Despite the data being collected and
sorted, it may have significant gaps or erroneous data. This cleaning phase uses the
imputation methods, previously identified as challenges to data analytics. These
methods ensure that no missing data exists

7.3 Statistics
Statistics is the overarching term for the collection, classification, analysis, and
interpretation of data. Briefly relevant in this case for data analysis as statistical
models underpin machine learning algorithms. Statically inference and descriptive
statistics are another way in which data analytics are used to describe observations
in collected data. AI and the following topics below show the growth of advanced
data analytics

7.4 Artificial intelligence

Artificial intelligence (AI) is a wide-ranging branch of computer science concerned
with building smart machines capable of performing tasks that typically require
human intelligence. AI is an interdisciplinary science with multiple approaches, but
advancements in machine learning and deep learning are creating a paradigm shift
in virtually every sector of the tech industry. AI programming focuses on three
cognitive skills: learning, reasoning and self- correction.

7.5 Machine Learning

A subsection of AI, machine learning is the creation of algorithms that can give the
computer the ability to learn and act for the user without being directly programmed
to do so. Machine learning is used to create programmes that use sophisticated
algorithms to collect and analyze data autonomously. For more general analysis,
machine learning can fit into two types of learning:

13
a) Supervised Learning This is the most popular form of machine learning. The
algorithms use large amounts of labelled data to analyze and learn. The algorithm
is tasked with learning and analyzing the labelled data to identify a given task
correctly; image classification is one example. The algorithms learn from training
data and are then given test data to see how well it is accurately predicting what an
image is showing, presented through an accuracy percentage. The user then analyses
these answers and any errors are corrected and re-learned, helping train the model
and increasing the accuracy of a given algorithm

b) Unsupervised Learning Unsupervised learning is another form of machine

learning, it does not require expensively marked-up data where for each input
pattern the desired output has previously been determined: as is required
for supervised learning Unsupervised learning algorithms learn using its own
methods in categorizing and highlighting patterns within data instead of relying on
user feedback. Clustering is one method of categorizing data. Algorithms learn to
cluster unlabeled data sets together, potentially showing hidden patterns that were
not explicitly identifiable

7.6 Deep Learning

Deep learning is another part of the field of data analytics and a subsection of
machine learning. Deep learning algorithms learn unstructured and unlabeled data
using complex neural networks with autonomous input feature extraction as
opposed to manual extraction. These networks utilize machine learning to create
deep learning models that can take longer to train because of the much larger neural
networks, but this allows for greater accuracy. Another type of learning is semi-
supervised learning, defined as having some labelled data, but more data is
unlabeled to see how the algorithms can learn to be more accurate. Many more
algorithms appear throughout the field of data science, but these are the most
common.

7.7 Data Visualization

The final subtopic within data analytics is visualization, defined as a graphical
representation or visualization of data or results. The type of data affects the way it
is visualized. The most common being multidimensional data, which can be

14
presented using graphs and charts, taking multiple variables, for instance, bar or pie
charts. Another data type is geospatial; this involves data collected from the earth
through location data, visualized through distribution maps, cluster maps, and more
commonly, contour maps

7.8 Cloud computing

Simply put, cloud computing is the delivery of computing services—including
servers, storage, databases, networking, software, analytics, and intelligence—over
the Internet (“the cloud”) to offer faster innovation, flexible resources, and
economies of scale. You typically pay only for cloud services you use, helping
lower your operating costs, run your infrastructure more efficiently and scale as
your business needs change

7.9 API and open standards

An open API (often referred to as a public API) is a publicly available application
programming interface that provides developers with programmatic access to a
proprietary software application or web service. APIs are sets of requirements that
govern how one application can communicate and interact with another.

7.10 virtual reality

Virtual reality (VR) is a simulated experience that can be similar to or completely
different from the real world. Applications of virtual reality include entertainment
(e.g., video games), education (e.g., medical or military training) and business (e.g.,
virtual meetings). Other distinct types of VR-style technology include augmented
reality and mixed reality, sometimes referred to as extended reality or XR.

15
 CHAPTER 8

ADVANTAGES

The advantages of digital twins are incredibly far-reaching, and extend throughout
a product’s entire lifecycle, from design, to build, and finally to operation. The main
benefit of digital twin is to provide an integrated outlook of any project to any user
at any point of the product lifetime. This single source of factual truth allows
organizations to foster collaboration across various teams and departments, and
even outside the organization. Digital twin technology can drastically reduce the
product development time and cost by up to 50%. Through lean development
cycles, increased collaboration between external and internal partners and the
suppliers, businesses can effectively change the design, manufacturing, sales, and
maintenance of complex products in multiple industries. With real-time mirroring,
engineers can simulate the behavior of complex system to predict and prevent
mechanical breakdowns
Here are just some of the advantages of digital twins:

1. Improved design: Digital twins allow you to quickly test designs using
simulations, without the need for costly prototypes.

2. Improved build: Digital twins allow you to project how a change in the
manufacturing process might impact things like efficiency, quality and yield.

3. Better early detection and warnings: Digital twins can quickly alert you to
any abnormalities or failures in the asset, allowing you to address before it becomes
a major (and potentially costly) problem.

4. Predictive maintenance: Digital twins not only gives you real-time insight
into how an asset is performing, but it also allows you to model your interventions,
so you can see the full-scale of their impact and minimize downtime losses.

5. Aggregated data: Aggregated data is valuable. As Dimitri Volkmann of GE

16
notes: “If your organization is monitoring multiple systems of the same type of
assets, for instance a fleet of jet engines (each of which has an individual digital
twin), you can start to learn

from all of them as a cohort, find similar patterns or trends, and that analysis can
lead to refining models for higher fidelity in the future.”

6. Post-manufacturing visibility of products: For many products, once they

leave the factory, there is no more insight into how that product is being used by
consumers – until something goes wrong, that is. Digital twins can change that, by
giving manufacturers visibility into their real-world usage, allowing them to further
optimize the product, predict when it might be in need of service, and quickly fix
any problems that do arise.

7. Continuous refinement of design and models through data captured and easily
crossed referenced to design details
•

17
 CHAPTER 9

DISADVANTAGES

The main disadvantage of digital twin technology is that it only works with one type
of measurement. For example, velocity and displacement measurements cannot be
accurately converted to an absolute value. Digital representation requires a different
type of measuring device.
Other limitation of the digital twin method is that it cannot produce a velocity or
displacement measurement at the same time, in the same area. This means that there
may be two or more measurements to be taken, and they will not be converted
correctly into an accurate value.
Other disadvantages include:
• The requirement for complex measuring equipment
• Expensive equipment and software.
• There is also the need to provide a large number of digital measurement
points, and more space for storing measurement results.
• Highly qualified professionals are needed for executing the digital twin
model.
• The success of technology is dependent on internet connectivity.
• The security is at stake.
• The digital twin’s concept is based on 3D CAD models and not on 2D
drawings.
• Digital twin will be required across entire supply chains.
• The challenges involved here include globalization and new manufacturing
techniques. Managing all these design data for digital twin among partners and
suppliers as the physical product evolves will be a challenge.

18
 CHAPTER 10

APPLICATIONS

Digital Twin technology eliminates the guesswork from determining the best course
of action to service critical physical assets. Asset-centric organizations that have
focused on combining traditional operational technologies with IT governed
technologies will now have easy access to this unique blend of deep knowledge and
intelligence about their assets, and pave the road to optimization and business
transformation. The increasing adoption of IoT is ideal for enterprises to leverage
digital twin platforms to boost their services and processes. A new market category
will emerge that will see the outcome-based applications being more versatile.

Improve customer experience:

Customers play a key role in influencing the strategies and decisions in any
business. Enhancing your customer’s experience to retain and explore new customer
base, is the ultimate goal for businesses. By directly creating a digital twin of the
customer facing applications, they can get feedback that boost the services directly
offered to customers.

Performance tuning:
A digital twin helps to determine the optimal set of actions that can help maximize
some of the key performance metrics, and also provide forecasts for long-term
planning. For example, the performance of a scientific device, which is deployed
on a spacecraft, can be tuned from Earth using digital twin as a 3D real-time
visualization.

Digital machine building:

A digital twin is used as a digital copy of the real machine that is created and
developed simultaneously. Data of the real machine is loaded into the digital model
to enable simulation and testing of ideas even before actual manufacturing starts

Healthcare:
A digital twin can help virtualize a hospital system in order to create a safe
19
environment and test the impact of potential changes on system performances. Not
just operations, digital twins can also help improve the quality of health services
delivered to patients. For example, a surgeon can use a digital twin for a digital
visualization of the heart, before operating it.

Smart cities:
A digital twin can be used for capturing the spatial and temporal implications to
optimize urban sustainability. For instance, ‘Virtual Singapore’, a part of the
Singapore government’s Smart Nation Singapore initiative, is the world’s first
digital twin of an existing city-state, providing Singaporeans and effective way to
engage in the digital economy.

Maintenance:
A digital twin is capable of analyzing performance data collected over time and
under different conditions. For example, with a digital twin, a racecar engine can be
visualized to identify the required maintenance, such as a component that is about
to burn out. With a digital twin, your business can integrate the insights generated
in a system, allow visibility into current and future machine states, and trigger
appropriate remedial business workflows.

20
 CHAPTER 11

CONCLUSION

The growth in Digital Twin use has seen a shift in recent years, facilitated by an
increase in the number of published papers and industry leaders investing heavily
in developing Digital Twin technology. It would not be possible without the same
growth in the AI, IoT and IIoT fields, which are becoming key enablers for Digital
Twins. The majority of the Digital Twin research is focused on the manufacturing
field. The number of papers found in manufacturing is noticeably higher compared
to papers discussing Digital Twins for smart cities and healthcare, highlighting gaps
in the research for these areas.

AI is becoming a component within Digital Twins and exploring where these

algorithms can be applied is another avenue of open research. The effects of AI
combined with Digital Twin are topics amongst the publications but on a small
scale. The exciting and inevitable future research will explore scaling up smaller
successful Digital Twin and AI projects. An important finding is the lack of
standardization and misconceptions with definitions for Digital Twins. Addressing
the challenges with standardization ensures future developments are actually Digital
Twins and not wrongly defined concepts.

The digital twin may drive tangible value for companies, create new revenue
streams, and help them answer key strategic questions. With new technology
capabilities, flexibility, agility, and lower cost, companies may be able to start their
journeys to create a digital twin with lower capital investment and shorter time to
value than ever before. A digital twin has many applications across the life cycle of
a product and may answer questions in real time that couldn’t be answered before,
providing kinds of value considered nearly inconceivable just a few years ago.
Perhaps the question is not whether one should get started, but where one should
start to get the biggest value in the shortest amount of time, and how one can stay
ahead of the competition. What will be the first step, and how will you get started?
It can be an overwhelming task to get there, but the journey starts with a single step.

21
 CHAPTER 12

REFERENCES

[1] Emergence of digital twin -Dr Shoumen datta

[2] Industry 4.0 and digital twin paper
[3] "Industrial IoT: Rise of Digital Twin in Manufacturing Sector". Biz4intellia
[4] Marr, Bernard (March 6, 2017). "What Is Digital Twin Technology - And
Why Is It So Important?
[5] Elisa Negri (2017). "A review of the roles of Digital Twin in CPS-
based production systems". Procedia Manufacturing.
[6] Guerra, R.H.; Quiza, R.; Villalonga, A.; Arenas, J.; Castano, F. (2019).
"Digital Twin- Based Optimization for Ultraprecision Motion Systems with
Backlash and Friction". IEEE Access.
[7] "Siemens and General Electric gear up for the internet of things". The
Economist. 3 December 2016
[8] Digital twin service towards smart manufacturing – science direct
[9] "Digital twins – rise of the digital twin in Industrial IoT and Industry 4.0"
[10] An introduction to digital twin development – any logic
[11] ‘Digital Twin: Manufacturing Excellence through Virtual Factory
Replication ‘-seimens
[12] Digital Twin in Industry: State-of-the-Art – IEEE paper
[13] google
[14] Wikipedia

22