Digital Twins

Image source : Siemens

Industry 4.0: Technologies
Industry 4.0 comprises a set of latest technologies
which are deployed to deliver the complete
transformation of modern factories into smart
manufacturing factories.
1. The Cloud
2. Sensors And Connected Devices
3. Immersive Technologies (AR/VR/MR)
4. Artificial Intelligence
5. Big Data
6. Digital Twin
7. Cybersecurity
8. Additive Manufacturing and Digital Scanning
Digital Twins : Overview
• Digital version of a physical object
• Dynamic, up to date digital replica of a built asset or environment.
• Data from the original asset is used to build a digital twin.
• Digital twin can help in
• Planning
• Design
• Constructions
• Operations
• Maintenance
Digital Twin
• It is an up-to-date representation of an
actual physical asset in operation.
• It reflects the current asset condition and
includes relevant historical data about the
asset.
• It can be used to evaluate the current
condition of the asset and, more
importantly, predict future behavior, refine
the control, or optimise operation.
• It can model
• A component
• A system of components
• A system of systems
• It can include physics-based approaches or
statistical approaches.
• Example: pumps, engines, power plants,
manufacturing lines, wind turbines and a Image source : Entso-E
fleet of vehicles.
Why Digital Twin?
• It is used in applications like anomaly detection , asset management ,
and fleet management.
• Up to date representation of real operating assets : Optimisation ,
improve efficiencies, automate , evaluate future performance.
• Areas : Automobiles, Aerospace, Wind turbines , Buildings, Cities,
Factories and many more…
• Operations optimisation
• Thousands of what if simulations
• Variables: weather, fleet size, energy costs, performance factors
• To evaluate readiness/necessary adjustments to current system set points.
Digital Twin : Characteristics
• Connectivity
• It enables connection between the physical element and its digital
counterpart.
• The sensors create the connectivity of physical products that obtain,
integrate and communicate data using various integration technologies.
• Homogenization
• Digital twins are both the consequence and enabler of homogenization of
data. It allows the decoupling of information from its physical form.
• Reprogrammable and Smart
• Digital twins automatically enable re-programmability through sensors,
artificial intelligence techniques and predictive analysis.
• Digital traces
• Digital twin technologies leave digital traces. The trails are helpful to
diagnose the source of the problem that occurred in case of machine
malfunctions.
• Modularity
• Modularity is referred to the design and customization of products and
production modules. The addition of modularity to functional models helps
manufacturers gain the ability to tweak machines and models.

Source: LeewayHertz
Digital twins : Attributes

Image Source : DPDHL

Digital Twins : Timeline
Digital Twins : Timeline

Image Source : DPDHL

Digital Twins : 1960’s NASA Pairing technology
• NASA using the concept since 1960’s : Pairing
Technology
• Use : Space programming , to simulate out of reach
environment
• Challenges : Operate, maintain , repair system which
are out of physical proximity
• Pairing technology : Physically duplicated space
systems at ground level
• Apollo 13 : Nasa developed a digital twin to assess and
simulate conditions on board apollo 13.
• Result : Apollo 13 faced with disaster >>> Mirrored
system at earth >>> Engineers attempted to ways how
to rescue the mission.
• Current Technology : Digital Twins
• To predict the useful life of space vehicles
• Roadmaps
• Next-generation vehicles and aircraft
• Mission success prediction

Source : Siemens blog

Digital Twins : Industry 4.0
Equipment Virtual
Virtual Product Quality Process Predictive
health commissioning
Testing Management Validation Maintenance
monitoring factory
Product
Testing of product Monitoring and To run a factory
customisation Continuous health
under simulated modelling of every Equipment health virtually before
affect on monitoring of
conditions before part of production monitoring ever building or
production device
manufacturing process layout
process

Improvement of
Timely recognition Reducing the need
design in early
Quality issues of potential for real world
stages and cost
anomalies/failures adjustments
saving

Identification of
better production
process and choice
of materials
 Digital Twins – Applications areas
Operation and
Engineering Production Marketing and sales
Service
• Link virtual models • Predictive methods • Shopfloor • Increase customer
with real physical • Condition management interaction process
objects Monitoring • Performance • Data and content
• Reduce engineering • Plant maintenance review management
costs and strategies • Supply chain • Detect and develop
• Run what if • Maximise utilisation management new business
scenarios • Detect quality trend • Fleet optimisation models
• Reflect customer defects sooner • Improve • Customer validation
usage in digital twin infrastructure
• Create feedback
loop over lifecycle

Source: Mastering Digital Twins

 Digital Twins : How we can make one ?

Modelling Reuse
• Identification of • Communication
digital twin scope • Infrastructure for
• Creating digital twin • Reuse information
• Identification of aggregation of data
& modelling
basic requirements and information
for digital twin • Connecting to data
• Analysis
points & existing
information system Enrichment
Initiation
and utilisation
Data sources for DT
• Embedded Sensors
• In smart equipment
• Wireless sensor networks
• Temperature, Humidity, Lighting, Occupancy
• Digitised building lifecycle data and systems
• BIM Data
• Smart HVAC systems
• Digitised Pneumatic thermostats
• Smart Plugs
• Integration with other cloud services and Data providers
DT Terminology
• Device Knowledge
• Intimate knowledge of that device
• AI can help detect patterns in data, but it cant tell whether these patterns are
practically meaningful
• Device Data
• To predict when a device needs maintenance, the real time data feedback is
needed from the device
• Physics based device modelling
• Life of the device
• AI/Data Analytics
• Prediction of execution, performance and failure
 Digital thread and Digital Twins

Source | CW

• Flow of information about a product

• Digital thread refers to the communication framework that allows a connected data flow and
integrated view of the asset’s data throughout its lifecycle across traditionally siloed
functional perspectives.
• To inform decision makers all through life cycle by providing capability to integrate, access
and transform data into actionable information
Digital Thread and Digital Twins

The digital thread is the bridge between the real-world part or process and its digital twin.

Image credit: altexsoft

Digital Twins : Real Time usage examples
• Industrial Sectors
• Energy
• Production
• Health wellness
• Aerospace
• Smart city
• Telecommunication
• GE wind farm Digital twin
• Maserati Production Plant digital twin
 Example: A Predictive Maintenance [MATLAB]
• Well sites [Oil] at different locations
• Multiple pumps to extract oil and gas
from the ground
• Digital twin : Real asset in operation
• In this case
• Component of a system : Valve of a
pump
• System, the pump itself
• System od systems, well site with
multiple pumps

Source : Matlab
There are three well sites at different
locations with multiple pumps running at
each of the well sites.

Source : Matlab
Digital twin model
• An up-to-date representation of the
pump by building a model that gets
updated with the incoming data
from the pump
• Data transmitted from sensors and
current operating conditions
• Digital twin model then represents
the current state of the pump.
• Sensor measurements & operating
conditions of pump >>> model >>>
current state of the pump

Source : Matlab
Source : MATLAB YouTube channel
https://www.youtube.com/watch?v=RmVWKLbLq2Y ,
Source : MATLAB YouTube channel
https://www.youtube.com/watch?v=RmVWKLbLq2Y
 Advantages of digital twin model of pump
• Expensive parts
Equipment • Seals & Plungers
Downtime
Reduction • Prevention of failures in advance
• Reduce downtime

• Identify faults
Inventory
• Repairing/Replacement of parts
Management
• Better inventory management

• Proper fleet management

Fleet • Different working conditions at different sites
Management • Working conditions and their affects on the
pumps efficiency

• Simulations of future scenarios

What-If
• Comparison between various parameters
Simulations Well site has different average temperature
• Operational Planning
operating conditions.
Source : MATLAB YouTube channel
https://www.youtube.com/watch?v=RmVWKLbLq2Y ,
Digital twins : Based on Product, Process
Component System/Unit Process
Asset twins
twins twins Twins
Collection of assets
Digital twin of a that together
Digital twin of an
component of an Highest level twin perform a system or
entire asset
asset network wide
function

Typically a major sub

Can be collection of Provides a view into Provides visibility
component that has
and informed by set of activities or across a collection of
significant impact on
component twin operations equipment
performance of asset

Provide visibility at Engine/Pump , MRI Combines all Entire manufacturing

an equipment level Machine production units process

Focuses on the
Rotor/bulb
process itself
 Digital Twins : Manufacturing

Conceptual framework of digital twin in manufacturing

Warke, V.; Kumar, S.; Bongale, A.; Kotecha, K. Sustainable Development of Smart Manufacturing Driven by the Digital Twin
Framework: A Statistical Analysis. Sustainability 2021, 13, 10139. https://doi.org/10.3390/su131810139
Digital twin use cases : Aerospace Sector
• GE90 Engine
• Aircraft engine
blade
• Eroding of blade
material over
time
• Degrade rate
prediction

Source : GE
Digital twin use cases : Aerospace Sector

Source : AIAA
 Digital twin use cases : Aerospace Sector
• Types of Maintenance
• Reactive
• Do maintenance once there’s a problem
Example: replace car battery when it has a
problem
• Problem: unexpected failures can be
expensive and potentially dangerous
• Preventive
• Do maintenance at a regular rate
• Example: change car’s oil every 5,000 miles
• Problem: unnecessary maintenance can be
wasteful; may not eliminate all failures
• Predictive
• Forecast when problems will arise
• Example: certain GM car models forecast
problems with the battery, fuel pump, and
starter motor
• Problem: difficult to make accurate forecasts
for complex equipment

Source : Mathworks
 Digital Twins : Power Plant
• Digital Power
Plant by GE
• Critical
component
models
• Fuel costs
• Electricity Price
• Cost saving &
Perfomance

Source : GE
 Digital Twins: Transportation
• GE Locomotive
• Digital Twin :
Trip Optimiser
• Train Engine
• Load
• Time
• Weather
conditions
• Fuel saving
• Decrease in
emissions

Source : GE
Digital twin use cases : Automotive Sector
• Activities that can be simulated
• Crash Tests
• Real time car experience – feedback to their digital twins
• Data analysis : Advanced warning related to repairmen and maintenance
• Modelling of airbag system
• Vehicle Maintenance
• Health monitoring of all parts
• Performance of engine under different conditions
• Customer experience
• Virtual experience of car at home
• Reduction of maintenance cost
• Personalisation
• Tesla creates a digital simulation of every one of its cars, using data collected from
sensors on the vehicles and uploaded to the cloud.
 Digital Twins : Logistics
• Optimise
Warehouse Space
• Shipment
• Transportation
Management
• Better freight
handling at Ports
• Better Inventory
Management
• Roadblock with
alerts

Source : DDPHL
 Digital twin use cases : Smart cities
• A digital replica – a virtual city
• The Shanghai Urban Operations and
Management Center has built a digital twin
of the city of 26 million inhabitants, which
models 100,000 elements from refuse
disposal and collection facilities to e-bike
charging infrastructure, road traffic, and the
size and location of apartment buildings.
• uses data from satellites and drones to
construct the living model
• It can also be used to simulate the effects of
natural disasters such as flooding to aid
with response planning.

Source : The B1M ; Youtube

Digital twin software
• Digital twins are becoming more widely adopted across many
industries.
• To create digital twins, these industries use specific software that
allows them to run the complex monitoring required.
• Some of the most popular digital twin software include:
• Azure digital twin
• IBM Digital Twin Exchange
• AWS IoT TwinMaker
 Challenges in Implementing a Digital Twin
Education  Cost
• Fast advancements in technology : Adaptability • Requirement of costly sensor,
problem software's and latest technology
• Implementation • High volume of data, data
Accurate representation storage problem and its handling
• Perfect replication of physical system : Intricate cost
and complex process  Intellectual property
• Time consuming
protection
Data quality  Digital security
• Accurate data: Crucial part
• Cyber attacks : A major problem
• Noise: Environmental factors and operational
conditions
• Extra steps required: Data pre processing , and
filtration
• Increase in computational time

Warke, V.; Kumar, S.; Bongale, A.; Kotecha, K. Sustainable Development of Smart Manufacturing Driven by the Digital Twin Framework: A
Statistical Analysis. Sustainability 2021, 13, 10139. https://doi.org/10.3390/su131810139