EL

Industry 4.0:
Cyber-Physical Systems and Next-Generation Sensors

PT Dr. Sudip Misra

Professor
Department of Computer Science and Engineering
Indian Institute of Technology Kharagpur
Email: [email protected]
Website: http://cse.iitkgp.ac.in/~smisra/
Research Lab: cse.iitkgp.ac.in/~smisra/swan/

Industry 4.0 and Industrial Internet of Things 1

What are Cyber-Physical Systems?

EL
 “Cyber-Physical Systems or ‘smart’ systems are co-engineered
interacting networks of physical and computational
components. These systems will provide the foundation of our
critical infrastructure, form the basis of emerging and future

PT
smart services, and improve our quality of life in many areas.”
-- NIST, Engineering Laboratory

Industry 4.0 and Industrial Internet of Things 2

What are Cyber-Physical Systems? (Contd.)

EL
 Generalization of “embedded” systems
 Possess compute, communicate and control capabilities
 Interaction with the physical world through sensors and actuators.

 Examples:





PT
Medical instruments
Transportation vehicles
Defense systems
Robotic equipment
Process monitoring and factory automation systems
Source: Lee, IEEE ISORC, 2008

Industry 4.0 and Industrial Internet of Things 3

 EL
Sensing Actuation

PT Source: Ali et al., Sen. J., 2015

4
Industry 4.0 and Industrial Internet of Things
Differences with Embedded Systems

EL
Embedded Systems CPS
Devices having information processing Complete system having physical
systems embedded into them components and software
Typically confined to a single device Networked set of embedded systems

PT
Limited resources for performing limited
Not resource constrained
number of tasks
Main issues are real-time response and
Main issues are timing and concurrency
reliability

Source: Lee, IEEE ISORC, 2008

Industry 4.0 and Industrial Internet of Things 5

Features of Cyber-Physical Systems

EL
 Reactive Computation:
 Interact with environment in an ongoing manner
 Sequence of observed inputs and outputs
 Concurrency:

PT
 Multiple processes running concurrently
 Processes exchange information to achieve desired result
 Synchronous or asynchronous modes of operation
Source: R. Alur, Principles of Cyber-Physical Systems, The MIT Press

Industry 4.0 and Industrial Internet of Things 6

Features of Cyber-Physical Systems (Contd.)

EL
 Feedback Control of the Physical World:
 Equipped with control systems with feedback loop
 Sensors sense environment and Actuators influence it
 Hybrid control systems for complex tasks

PT
 Real-Time Computation:
 Time sensitive operations such as coordination, resource-allocation
 Safety-Critical Applications:
 Precise modelling and validation prior to development
Source: R. Alur, Principles of Cyber-Physical Systems, The MIT Press

Industry 4.0 and Industrial Internet of Things 7

Applications of CPS: Healthcare

EL
 Highly accurate medical devices and systems
 Image-guided surgery and therapy
 Control of fluid flow for medicinal purposes and biological analysis
 Intelligent operating theatres and hospitals

PT
 Engineered systems based on cognition and neuroscience
(e.g., brain-machine interfaces, therapeutic and
entertainment robotics, orthotics and exoskeletons, and
prosthetics)
Source: Baheti and Gill, Cyber Physical Systems, Tech. Rep., IOCT, 2011

Industry 4.0 and Industrial Internet of Things 8

Applications of CPS: Transportation

EL
 Infrastructure-based transportation CPS
 Real-time monitoring of traffic infrastructure (traffic signals, cameras,
etc.) and traffic control
 Vehicle-Infrastructure-coordinated transportation CPS

PT
 Transit signal priority, queue warning (for e.g., ambulances)
 Vehicle-based transportation CPS
 Proximity detection for safety
 Vehicle health monitoring
Source: Baheti and Gill, Cyber Physical Systems, Tech. Rep., IOCT, 2011

Industry 4.0 and Industrial Internet of Things 9

Applications of CPS: Smart Grid

EL
 Smart meters
 Demand management with distributed generation
 Automated distribution with intelligent substations
 Wide-area control of Smart grids

PT
 Phasor measurement units (PMUs)
 Data aggregation units (DAUs)

Source: Rajkumar et al., DAC, 2010

Industry 4.0 and Industrial Internet of Things 10

Applications of CPS: Industry

EL
 Manufacturing systems and logistics integrated with
communication abilities, sensors and actuators
 Smart control
 Optimal resource utilization

PT
 Smart diagnostics and maintenance
 Flexibility of development of systems
 End products customized specific to needs of customers
Source: Rajkumar et al., DAC, 2010

Industry 4.0 and Industrial Internet of Things 11

CPS Architecture for Industry 4.0

EL
 Designing CPS-based manufacturing systems for Industry 4.0
 “5C architecture” comprising of 5-levels
 Connection
 Conversion



Cyber

PT
Cognition
Configuration
Source: Lee et al., Manufacturing Letters, 2015

Industry 4.0 and Industrial Internet of Things 12

CPS Architecture for IIoT: Connection

EL
 Smart connections to ensure accurate data is obtained from
the IIoT devices
 Two factors to be considered:
 Obtaining seamless and tether-free data

PT
 Selection of sensors with proper specifications

Source: Lee et al., Manufacturing Letters, 2015

Industry 4.0 and Industrial Internet of Things 13

CPS Architecture for IIoT: Conversion

EL
 Conversion of machine data to meaningful information
 Data analysis tools and methodologies to be developed for
 Prognostics and health monitoring of machine components
 Multi-dimensional data-correlation

PT
 Machines become self-aware

Source: Lee et al., Manufacturing Letters, 2015

Industry 4.0 and Industrial Internet of Things 14

CPS Architecture for IIoT: Cyber

EL
 Central information hub
 Gathers system information from fleet of machines
 Obtaining precise status information of individual machines
 Rating of performance of individual machines among fleet

PT
 Predicting future behavior of machines based on historical data
 Utilize clustering for data mining
 Machines achieve self-comparison ability

Source: Lee et al., Manufacturing Letters, 2015

Industry 4.0 and Industrial Internet of Things 15

CPS Architecture for IIoT: Cognition

EL
 Proper presentation of information to users for generating
thorough knowledge of the system
 Collaborative diagnostics
 Decision making for:

PT
 Prioritization
 Optimization processes

Source: Lee et al., Manufacturing Letters, 2015

Industry 4.0 and Industrial Internet of Things 16

CPS Architecture for IIoT: Configuration

EL
 Supervisory control to determine actions to be taken by the
machines:
 Self-configuration for resilience
 Self-adjustment for variations

PT
 Self-optimization for disturbances
 Machines become self-adaptive

Source: Lee et al., Manufacturing Letters, 2015

Industry 4.0 and Industrial Internet of Things 17

Challenges for CPS Development

EL
 Safety, security and robustness
 Hybrid control systems
 Computational and real-time embedded system abstractions

PT
 Sensor and mobile networks
 Architecture and modelling
 Verification, validation and certification
 Education and training
Source: Sha et al., IEEE SUTC, 2008

Industry 4.0 and Industrial Internet of Things 18

 EL
Next-Generation Sensors

PT
Industry 4.0 and Industrial Internet of Things 19
Need for Next-Generation Sensors

EL
 Interoperability of networks, transducers and control systems
of different manufacturers
 Compatibility of sensors with multiple sensor actuator bus
standards, reducing wiring cost and complexity

PT
 Interconnection of analog transducers with digital networks
 Increasing usage of existing networks instead of proposing
new standards
Source: Gervais-Ducouret, IEEE SAS, 2011

Industry 4.0 and Industrial Internet of Things 20

What are Next-Generation Sensors?

EL
 “Smart Sensors” –
 Integration of sensors and actuators with a processor and a
communication module.
 Defined in IEEE 1451 Standard as:

PT
“Sensors with small memory and standardized physical connection to enable
the communication with processor and data network”
 Functionalities - Self calibration, Communication, Computation, Multi-
sensing, Cost improvement
Source: Spencer Jr et al., J. STC, 2004

Industry 4.0 and Industrial Internet of Things 21

What are Next-Generation Sensors? (Contd.)

EL
 Limitations of Smart Sensors –
 Pre-defined embedded functions, customization not possible
 Narrow application spectrum
 Sensor data aggregation not possible


PT
External processor for sensor calibration
Basic communication protocols
 To overcome these, next generation sensors–
“Intelligent Sensors” Source: Gervais-Ducouret, IEEE SAS, 2011

Industry 4.0 and Industrial Internet of Things 22

What are Next-Generation Sensors? (Contd.)

EL
 “Intelligent Sensors” –
 Capable of processing sensed data and performing pre-defined
functions by processing data
 Capable of customizing embedded algorithms on the fly

PT
 Capable of managing and controlling external sensors/devices
 Comprises of a sensor, a microcontroller, a memory unit comprising of
flash, RAM and ROM, and a platform for running sensor applications

Source: Gervais-Ducouret, IEEE SAS, 2011

Industry 4.0 and Industrial Internet of Things 23

What are Next-Generation Sensors? (Contd.)

EL
 Advantages of Intelligent Sensors –
 Reduce data communication
 Reduced power consumption
 Application-specific customization of sensor nodes




PT
Continuous calibrating and monitoring of the sensors
Adaptive sampling rate and sleep-wake cycles
Shorter software development time
Improved compatibility of sensors
Source: Gervais-Ducouret, IEEE SAS, 2011

Industry 4.0 and Industrial Internet of Things 24

What are Next-Generation Sensors? (Contd.)

EL
Application Digital Embedd Signal
Sensor/ Smart
-ed Condition ADC
Processor Interface
features -ing
MEMS Sensor

RAM

PT
Application Digital ROM Sensor/ Intelligent
ADC
Processor Interface Microcontroller MEMS Sensor
Flash

External Sensor External Sensor External Sensor

Source: Gervais-Ducouret, IEEE SAS, 2011

Industry 4.0 and Industrial Internet of Things 25

Next-Generation Sensors: Applications

EL
 Automatic assembly in factories
 Smart fabric and intelligent textiles
 Advanced driving assistance systems

PT
 Fault detection and forecast using machine intelligence
 Non-invasive biomedical analysis
 Chemical composition analysis
 Resource lifecycle management Source: Gervais-Ducouret, IEEE SAS, 2011

Industry 4.0 and Industrial Internet of Things 26

Next Generation Sensors: Design Challenges

EL
 Hardware Issues –
 Limited power
 High response time
 Synchronization


PT
Limited bandwidth
Security issues
 Software Issues –
 Software partitioning with applications processor
Source: Gervais-Ducouret, IEEE SAS, 2011

Industry 4.0 and Industrial Internet of Things 27

References - I

EL
[1] Transportation Cyber-Physical Systems. Ed. Lipika Deka, Mashrur Chowdhury, Elsevier, 1st Edition, ISBN:
9780128142950
[2] N. Jazdi, "Cyber physical systems in the context of Industry 4.0," IEEE International Conference on
Automation, Quality and Testing, Robotics, Cluj-Napoca, 2014, pp. 1-4.
[3] Hiro Yamasaki, What are the intelligent sensors, Editor(s): Hiro Yamasaki, Handbook of Sensors and
Actuators, Elsevier Science B.V., Volume 3, 1996, Pages 1-17, ISSN 1386-2766, ISBN 9780444895158

PT
[4] S. Gervais-Ducouret, "Next smart sensors generation," IEEE Sensors Applications Symposium, San Antonio,
TX, 2011, pp. 193-196.
[5] Spencer Jr, B. F., Manuel E. Ruiz‐Sandoval, and Narito Kurata. "Smart sensing technology: opportunities and
challenges." Structural Control and Health Monitoring 11.4 (2004): 349-368.
[6] Alur, Rajeev. Principles of cyber-physical systems. MIT Press, 2015.
[7] Baheti, Radhakisan, and Helen Gill. "Cyber-physical systems." The impact of control technology 12.1 (2011):
161-166.

Industry 4.0 and Industrial Internet of Things 28

References - II

EL
[8] Lee, Jay, Behrad Bagheri, and Hung-An Kao. "A cyber-physical systems architecture for industry 4.0-based
manufacturing systems." Manufacturing Letters 3 (2015): 18-23.
[9] Edward A. Lee, Cyber-Physical Systems - Are Computing Foundations Adequate?, NSF Workshop On Cyber-
Physical Systems: Research Motivation, Techniques and Roadmap, October 2006, Austin, TX
[10] E. A. Lee, "Cyber Physical Systems: Design Challenges," 2008 11th IEEE International Symposium on Object
and Component-Oriented Real-Time Distributed Computing (ISORC), Orlando, FL, 2008, pp. 363-369.

PT
[11] Colombo, Armando & Karnouskos, Stamatis & Bangemann, Thomas. (2014). Towards the Next Generation
of Industrial Cyber-Physical Systems. Industrial Cloud-Based Cyber-Physical Systems: The IMC-AESOP Approach.
[12] R. Rajkumar, I. Lee, L. Sha and J. Stankovic, "Cyber-physical systems: The next computing revolution,"
Design Automation Conference, Anaheim, CA, 2010, pp. 731-736.

Industry 4.0 and Industrial Internet of Things 29

 EL
PT
Industry 4.0
Introduction
and Industrial
to Internet
Internet
of of
Things
Things 30
 EL
Industry 4.0:
Collaboration Platform and Product Lifecycle Management

PT Dr. Sudip Misra

Professor
Department of Computer Science and Engineering
Indian Institute of Technology Kharagpur
Email: [email protected]
Website: http://cse.iitkgp.ac.in/~smisra/
Research Lab: cse.iitkgp.ac.in/~smisra/swan/

Industry 4.0 and Industrial Internet of Things

1
What is Collaboration platform?

EL
 Category of business software which combines organizational
networking capacities to operations.
 It includes knowledge management into business operation to
encourage renovation.

PT
 Collaboration platform helps employees to share information
and solve business problems.

Source: Techtarget.com: Collaboration-platform

Industry 4.0 and Industrial Internet of Things

2
What is Collaboration platform? (Contd.)

EL
 There are some perspectives to build collaboration platforms.
 A social layer is combined with provision of business utilizations.
 New products are implanted with collaboration tools.
 There are some common attributes in business collaboration
platforms.

PT
 Easily accessible and easy to use.
 They require some familiar functions which help team collaboration.
 Example: ProWork Flow
 Web-based project management designed for Managers
 Collaborate to improve project delivery Source: Techtarget.com: Collaboration-platform

Industry 4.0 and Industrial Internet of Things

3
Collaboration Productivity in Industry 4.0

EL
 Collaboration Productivity
 There are four key parts, which enable collaboration productivity:
 IT Proliferation
 Single Source of Truth

PT
 Industrialization
 Coordination

Source: Collaboration Mechanisms to increase Productivity in the Context of Industries 4.0

Industry 4.0 and Industrial Internet of Things

4
Collaboration Productivity in Industry 4.0
(Contd.)

EL
 IT Proliferation
 It shows the huge impact of computers on economic growth and their
impact on increased capital stock’s shares.
 Industries are required to consider and promote global information

PT
technology and computing power.
 Storage capacity and high speed computing are increasing day by day.

Source: Collaboration Mechanisms to increase Productivity in the Context of Industries 4.0

Industry 4.0 and Industrial Internet of Things

5
Collaboration Productivity in Industry 4.0
(Contd.)

EL
 Single Source of Truth
 It is a kind of practice of formatting information models to store every
data element exactly once.
 SSoT must employ the right software for decision making.

PT
 SSoT is needed to be realized across the whole product lifecycle, so
that even a single change in product associated information is visible.

Source: Collaboration Mechanisms to increase Productivity in the Context of Industries 4.0

Industry 4.0 and Industrial Internet of Things

6
Collaboration Productivity in Industry 4.0
(Contd.)

EL
 Industrialization
 It is the bridge between the virtual world and the physical
environment.
 Physical environment is linked with the virtual world using CPS,

PT
which fix computers and sensors into an application platform.
 It requires intuitive and self-effective elements.
 For dynamic objectives in technology and industrial area, it
adapts the system behaviour like smart factories.
Source: Collaboration Mechanisms to increase Productivity in the Context of Industries 4.0

Industry 4.0 and Industrial Internet of Things

7
Collaboration Productivity in Industry 4.0
(Contd.)

EL
 Coordination
 Stronger coordination between multiple industry agents is required in
Industry 4.0 for enabling collaboration productivity.
 It can be initiated in two steps:

PT
 First, establish a network which communicates with overall target.
 Second, provide authority to decision-makers in a decentralized system.
 This network is maintained by encouraging the exchange of the
employees or by using smart devices.
Source: Collaboration Mechanisms to increase Productivity in the Context of Industries 4.0

Industry 4.0 and Industrial Internet of Things

8
Product Lifecycle Management (PLM)

EL
 It is a type of business activity to manage the lifecycle of a
product.
 PLM works as a management system for a company’s
products.

PT
 PLM handles a product completely, from single part of the
product to entire portfolio of that product.
 Example: Computational Intelligence System (CIS)
Source: Product Lifecycle Management: Stark

Industry 4.0 and Industrial Internet of Things

9
Product Lifecycle Management (PLM) (contd.)

EL
 The main goal of PLM is:
 To maximise product revenues.
 To decrease product-associated costs.
 To increase product’s value.

PT Source: Product Lifecycle Management: Stark

Industry 4.0 and Industrial Internet of Things

10
P, L and M in PLM

EL
 The P of PLM
 P means product in PLM.
 The product has an essential role in industry.
 The product is origin of company earnings.

PT
 There are no services without product.
 An industry leads in industry sector because of its products.
 Product has different type of shapes and sizes.

Source: Product Lifecycle Management: Stark

Industry 4.0 and Industrial Internet of Things

11
 P, L and M in PLM (Contd.)

EL
 The L of PLM 1.
Visualize
 L stands for lifecycle.
2.
 Product lifecycle has five phases. Explain
3.

PT
Perceive
5.
Dispose/
Retire
4. Use/
Support

Source: Product Lifecycle Management, Stark J

Industry 4.0 and Industrial Internet of Things

12
The P, L and M in PLM (Contd.)

EL
 Visualization: People have an idea regarding the product.
 Explanation: This idea is transformed into a representation.
 Perceiveness: By the end of the phase, the product is in its final
form.

PT
 Use/Support: The customer starts to use the product in
use/support phase.
 Retire: Company retires a product when it is not useful.
Source: Product Lifecycle Management: Stark

Industry 4.0 and Industrial Internet of Things

13
P, L and M in PLM (Contd.)

EL
 The M in PLM
 M means management in PLM.
 Product management has:
 Coordination and institution of product-related devices.

PT
 Fix objectives, capability of decision taking and result control.
 To ensure that a product works well, it is managed across its lifecycle
and management guarantees that the product will earn the profit for
the company.

Source: Product Lifecycle Management: Stark

Industry 4.0 and Industrial Internet of Things

14
PLM for Industry 4.0

EL
 The efficiency and effectiveness of PLM has an important role
in today’s enterprise operation systems.
 This efficiency and effectiveness of PLM improves market
share and market size with increasing revenue.

PT
 PLM system manages product’s portfolio. It also manages the
services from the initial concept to the final disposal.

Source: Product Lifecycle Management: Stark

Industry 4.0 and Industrial Internet of Things

15
Business Objectives of PLM for Industry 4.0

EL
 Financial Performance
 Increase market revenue, reduce development cost, etc.
 Time Reduction
 Reduce project time overrun, decrease profitable time(in less time more
profit) , etc.

PT
 Improve Quality
 Decrease defect rate in manufacturing , increase customer satisfaction
rate, etc.
 Business Improvement
 Decrease the delay time in new product release, ensure 100%
configuration conformity, etc. Source: Product Lifecycle Management: Stark

Industry 4.0 and Industrial Internet of Things

16
 Scope of PLM
Objectives and Metrics

EL
 There are nine Organization and Management

components in PLM Activities

to handle a product People

across its lifecycle. Product Data

PT
Product Data Management System

PLM Applications

Equipment and Facilities

Techniques and Methods

Source: Product Lifecycle Management, Stark J

Industry 4.0 and Industrial Internet of Things

17
Scope of PLM (Contd.)

EL
 Objectives and Metrics
 The objective of the company for PLM is to improve quality and
business, reduce the time, improve financial performance.
 Key Performance Indicators (KPIs), which are known as metrics set
targets for the company.

PT
 Organisation and Management
 Resource management and company’s effectiveness are crucial for
PLM.
 Plans must organize in such a way such that all resources are managed
to fulfil the desired objectives.
Source: Product Lifecycle Management: Stark

Industry 4.0 and Industrial Internet of Things

18
Scope of PLM (Contd.)

EL
 Activities
 There are many product associated activities such as idea
management, program management, new product development.
 People

PT
 Many people are involved to progress and maintain a product. E.g.-
Business analyst, cost accountant etc.
 Product Data
 It is a major asset throughout the product lifecycle.
 Product will face problem, if we provide false product data.
Source: Product Lifecycle Management: Stark

Industry 4.0 and Industrial Internet of Things

19
Scope of PLM (Contd.)

EL
 Product Data Management System
 It manages all the generated product data and it is used for product
lifecycle.
 It provides correct information at the right time.
 PLM Applications

PT
 To get desired performance levels, these applications are responsible
for enabling the people to take decisions.
 These applications support the people to build and maintain the
products.
Source: Product Lifecycle Management: Stark

Industry 4.0 and Industrial Internet of Things

20
Scope of PLM (Contd.)

EL
 Equipment and Facilities
 Product lifecycle use equipment and facilities in every phase.
 They are required to produce, maintain and service the product.
 Cost and quality of the product are effected by them.
 Techniques and Methods

PT
 To refine production across the lifecycle by means of product progress
time, product cost etc. many methods and techniques are proposed:
 ABC (Activity Based Costing)
 Concurrent Engineering
 DFS (Design For Sustainability)
 LCA (Life Cycle Assessment) Source: Product Lifecycle Management: Stark

Industry 4.0 and Industrial Internet of Things

21
Challenges in PLM for Industry 4.0

EL
 Business Drivers
 There are new business challenges for PLM in Industry 4.0.
 Challenges
 Product lifecycle is short.

PT
 Outsourcing is increasing.
 Products' structure is complex.
 Increase in speed, increase in demand and quality of product are the
other challenges to drive a business.
Source: Product Lifecycle Management: Stark

Industry 4.0 and Industrial Internet of Things

22
Challenges in PLM for Industry 4.0 (Contd.)

EL
 Industrial Requirement
 To design products virtually, geographically dispersed design teams
and supply chain partners are required to collaborate.
 A new perspective must be generated to hold net-centric technology.

PT
This perspective will be able to free the inherent value in today’s
enlarged business model.
 Perform project management, exchange and maintain product
information is a challenge in industry.
Source: Product Lifecycle Management: Stark

Industry 4.0 and Industrial Internet of Things

23
The Ten Step Approach: PLM solution in
Industry4.0

EL
 It is based on working experience of companies in Industry
sector.
 This approach has ten steps.

PT
Practice of
Education of PLM Concept PLM Roadmap
Data Gathering management in
PLM Generation Generation
PLM

Management Executive
Development Rate of Interest Executive
Report Decision
Strategy Calculation Presentation
Preparation Support

Source: Product Lifecycle Management: Stark

Industry 4.0 and Industrial Internet of Things

24
References

EL
[1] Stark J.(2015).Product Lifecycle Management(Volume 1).Springer.
[2] Schuh G., Potente T., Wesch-Potente C., Weber A., & Prote J,” Collaboration Mechanisms to increase
Productivity in the Context of Industrie 4.0” Elsevier, Procedia CIRP 19 ,pp.51 – 56,2014.
[3] Kagermann, H., Wahlster, W., Helbig J. “ Recommendations for implementing the strategic initiative Industrie
4.0”. Acatech. pp. 13-78,2013.
[4]Menon K., Gupta P. J., & Karkkainen H.” Role of Industrial Internet Platforms in the Management of Product

PT
Lifecycle Related Information and Knowledge”.IFIP,pp.549-558,2016.
[5]Ming X., Yan J., Lu W & Ma D.,” Technology Solutions for Collaborative Product Lifecycle Management – Status
Review and Future Trend”.Concurrent Engineering, vol. 13, no. 4,pp.311-319,2005.
[6]https://searchcontentmanagement.techtarget.com/definition/collaboration-platform.

Industry 4.0 and Industrial Internet of Things

25
 EL
PT
Industry 4.0 and Industrial Internet of Things 26
 EL
Industry 4.0:
Augmented Reality and Virtual Reality

PT Dr. Sudip Misra

Professor
Department of Computer Science and Engineering
Indian Institute of Technology Kharagpur
Email: [email protected]
Website: http://cse.iitkgp.ac.in/~smisra/
Research Lab: cse.iitkgp.ac.in/~smisra/swan/

Industry 4.0 and Industrial Internet of Things 1

 Augmented Reality and Virtual Reality in IIoT

EL
 From the technological perspective, Augmented Reality (AR) and
Virtual Reality (VR) are used in several contexts and sectors in
Industry 4.0.
 AR and VR plays important role in the primary stages where optimization
and productivity are important in manufacturing industry.

PT
 The efficiency of warehouses are improved using various AR applications.
 AR and VR also plays an important role in safety training, thereby the
potential safety hazards can be easily located.

“Manufacturing”, Reality technologies

Industry 4.0 and Industrial Internet of Things 2

Augmented Reality and Virtual Reality in IIoT
(contd.)

EL
 Use cases:
 Machining and production
 Education and collaboration
 Assembly

PT
 Safety and security
 Digital prototyping
 Factory planning
 Maintenance and inspection
“Virtual-reality-vr-augmented-reality-ar-trends”, I-scoop

Industry 4.0 and Industrial Internet of Things 3

 Augmented Reality (AR)

EL
 Augmented Reality is
 an enhanced version of reality
 direct/indirect views of physical world environments are “augmented”
with computer-generated superimposed images

PT
 adds digital elements into their actual environment
 amplifies the present perception of reality.

“Augmented Reality”, Reality technologies

“ Augmented Reality”, Techtarget

Industry 4.0 and Industrial Internet of Things 4

Key Features of AR

EL
 The key features of AR are:
 It lies in the middle of the mixed reality spectrum.
 It provides multiple sensor modalities – visual, auditory, and haptic.

PT
 It utilizes the existing environment and overlays new information on top
of it.

“Augmented Reality”, Reality technologies

“ Augmented Reality”, Techtarget

Industry 4.0 and Industrial Internet of Things 5

Chronological order of Augmented Reality

EL
Battlefield Google glass
Augmented Reality
System (BARS)
First functioning AR
Coined the term Google
Published heads system
Augmented US Naval (2013)
up display for
teaching real- Reality research
Louis laboratory
world flight skills
Idea of Electronic Rosenberg (1999)

PT
display/ spectacles Thamos Caudell (1992)
Gavan Lintern (Boeing
(University of Researcher,
L. Frank Baum Illinois, 1980) 1990)
(author, 1901)

“Augmented Reality”, Wikipedia

Industry 4.0 and Industrial Internet of Things 6

Applications of Augmented Reality

EL
Tourism Entertai
nment

Retail Industrial
design

PT Medical

Educati
on
Flight
Training

Military

“Augmented Reality”, Wikipedia

Industry 4.0 and Industrial Internet of Things 7

Applications of Augmented Reality (contd.)

EL
Key components of
AR Eyeglasses
devices:
Head-up
display  Sensors and
Cameras
 Projection Screen

PTMedical
Applications
 Processing unit
 Reflection

“Ar glasses”, Uploadvr

“Medical Research”, Pehub

Industry 4.0 and Industrial Internet of Things 8

Types of Augmented Reality

EL
Marker-Based Augmented Reality

Markerless Augmented Reality

PT
Projection Based Augmented Reality

Superimposition Based Augmented Reality

“Augmented Reality”, Reality technologies

Industry 4.0 and Industrial Internet of Things 9

Types of Augmented Reality (contd.)

EL
 Marker-based augmented reality gives an outcome when the
reader is sensed by the camera and visual marker.
 camera: differentiates between a marker and a real object.
 marker: recognizes simple, distinct patterns and can be easily processed.

PT
 Markerless augmented reality is commonly utilized for mapping
directions. The location is provided based on the GPS, digital
compass, or accelerometer, which is attached to the device.
“Augmented Reality”, Reality technologies

Industry 4.0 and Industrial Internet of Things 10

Types of Augmented Reality (contd.)

EL
 Projection-based augmented reality gives an outcome by
projecting light onto real world surfaces.
 It allows human interaction by sending light.

PT
 It differentiates between the expected projection and altered
projection.

“Augmented Reality”, Reality Technologies

Industry 4.0 and Industrial Internet of Things 11

Types of Augmented Reality (contd.)

EL
 Superimposition-based augmented reality partially or fully
substitutes the original view of the object with the augmented
view.

PT
 Object recognition plays an important role
 Application cannot replace the original view with the augmented one.

“Augmented Reality”, Reality technologies

Industry 4.0 and Industrial Internet of Things 12

How do Augmented Reality works ?

EL
Sensors gather Processing
Camera scan to Projector Mirrors assist
real world devices
collect data projects into an the reflection
interaction, processes to

PT
from interactive according to
communicate provide users’
surrounding environment user’s eye
them the experience

“Augmented Reality”, Reality technologies

Industry 4.0 and Industrial Internet of Things 13

 Virtual Reality (VR)

EL
 Virtual Reality is
 a mixture of interactive hardware and software based artificial
environment
 a realistic three-dimensional image is created

PT
 presented to the user, in such a way so that they interacts with the real
or physical world.

“Augmented Reality”, Reality technologies

Industry 4.0 and Industrial Internet of Things 14

 Key Features of VR

EL
 The key features of VR are:
 It creates and enhances an imaginary reality.
 It gives the perception of being physically present in a non-physical world.
 It incorporates auditory and visual sensory feedback.

PT
 It allows users to get naturally absorbed into the virtual environment.

“Augmented Reality”, Reality technologies

Industry 4.0 and Industrial Internet of Things 15

Chronological order of Virtual Reality

EL
Large Expanse,
Extra Google’s first-ever
Perspective (LEEP) “resident artist”
optical system
Produced navigable
virtual worlds Michael
Coined the term Naimark
Virtual Reality Eric
Howlett (2015)
Sword of David EM
Damocles (1979)

PT
Experience Jaron Lanier (First artist,
Theatre 1977 - 1984)
Ivan (American
Sutherland Philosopher
Morton Heilig (MIT Computer and
(film-maker, Scientist, 1968 Scientist,
1962) God father of VR 1987)
displays)

“Virtual Reality”, Wikipedia

Industry 4.0 and Industrial Internet of Things 16

Applications of Virtual Reality

EL
Real estate Entertai
agents nment

Robotics Astronauts

PT Health and
Safety

Educati
on
3-D
artists

Mass
surveillance

“Virtual Reality”, Wikipedia

Industry 4.0 and Industrial Internet of Things 17

Applications of Virtual Reality (contd.)

EL
Key components of
headsets:
 Sensors –
Magnetometer,
Military Accelerometer, and

PT
VR Headset
Applications Gyroscope
 Lenses
 Display screens
 Processing unit
“Glasses”, Uploadvr
“Sony-hmz”, Polygon

Industry 4.0 and Industrial Internet of Things 18

Types of Virtual Reality

EL
Non-immersive Simulations

Semi-immersive Simulations

PT
Fully-immersive Simulations

“Virtual Reality”, Reality Technologies

Industry 4.0 and Industrial Internet of Things 19

Types of Virtual Reality (contd.)

EL
 Non-immersive simulations utilizes only a subset of the user’s
senses.
 User enters into the virtual environment through a portal or window
 Users allows a peripheral awareness of the reality outside the virtual

PT
reality simulations.

“Augmented Reality”, Reality Technologies

Industry 4.0 and Industrial Internet of Things 20

Types of Virtual Reality (contd.)

EL
 Semi-immersive simulations provides a partial or fully
immersive experience of the user’s senses. The simulations
are :
 powered by high performance graphical computing system, and

PT
 coupled with a large screen projector.

“Virtual Reality”, Wikipedia

Industry 4.0 and Industrial Internet of Things 21

Types of Virtual Reality (contd.)

EL
 Fully-immersive simulations provides realistic experience to
the users. The simulations
 delivers a wide field of view, and

PT
 uses head-mounted displays and motion detecting devices to
simulate user’s experiences.

“Virtual Reality”, Reality Technologies

Industry 4.0 and Industrial Internet of Things 22

How do Virtual Reality works ?

EL
Processing units takes
Sensors estimate the Lenses focus and the input information Display screen
user’s motion and reshape the image for from user, process displays the user view

PT
direction in space each eye them, and creates through the lenses.
sensations for user.

“Virtual Reality”, Reality Technologies

Industry 4.0 and Industrial Internet of Things 23

Similarities of AR and VR

EL
PT “Virtual Reality”, Reality Technologies

Industry 4.0 and Industrial Internet of Things 24

Comparison of AR and VR

EL
Augmented Reality Virtual Reality
• It adds digital elements to the • Immersive application, which
actual environment. affects the experience of user.

PT
• It delivers virtual elements as an
encrust of the real world.
• It offers a digital recreation of a
real life setting.

“Virtual Reality”, Reality Technologies

Industry 4.0 and Industrial Internet of Things 25

 References

EL
[1] http://www.realitytechnologies.com/virtual-reality
[2] http://www.realitytechnologies.com/augmented-reality
[3] https://en.wikipedia.org/wiki/Augmented_reality
[4] https://en.wikipedia.org/wiki/Virtual_reality
[5] https://computer.howstuffworks.com/augmented-reality.htm
[6] https://www.theguardian.com/technology/augmented-reality
[7] Ma, D., Gausemeier, J., Fan, X., Grafe, Virtual Reality & Augmented Reality in Industry, Springer, 2011.

PT
Industry 4.0 and Industrial Internet of Things 26
 EL
PT
Industry 4.0 and Industrial Internet of Things 27
 EL
Industry 4.0:
Artificial Intelligence

PT Dr. Sudip Misra

Professor
Department of Computer Science and Engineering
Indian Institute of Technology Kharagpur
Email: [email protected]
Website: http://cse.iitkgp.ac.in/~smisra/
Research Lab: cse.iitkgp.ac.in/~smisra/swan/

Industry 4.0 and Industrial Internet of Things

1
 What is Artificial Intelligence (AI)?

EL
“AI is a branch of computer science that deals with the study and the creation
of computer systems that exhibit some form of intelligence.”
- Patterson

“AI is the study of mental faculties through the use of computational models.”

PT - Eugene Charniak and Drew McDermott

Source: Artificial Intelligence by David L. Poole, Alan K. Macworth, Artificial Intelligence by Rajiv Chopra

Industry 4.0 and Industrial Internet of Things

2
 What is Artificial Intelligence (AI)? (Contd..)

EL
Artificial + Intelligence = Artificial Intelligence

Manmade Thinking power Creation of manmade

thinking power

PT
In simple way, Artificial Intelligence is a creation of software having
intuitive decision making ability.

Source: Artificial Intelligence by David L. Poole, Alan K. Macworth, Artificial Intelligence by Rajiv Chopra

Industry 4.0 and Industrial Internet of Things 3

 History of AI

EL
AI based hardware
Dartmouth First Expert
Start of DOD’s sells $425 million
conference System AI system
Lisp advanced research PROLOG to companies
beats human
language project language
Birth of AI chess master
developed revealed

PT
1950 1956 1958 1963 1970 1972 1986 1990

The first use of phrase Artificial Intelligence was proposed by John McCarthy
in 1956 in the article A Proposal for Dartmouth Summer Research Project on
Artificial Intelligence
Source: Artificial Intelligence by David L. Poole, Alan K. Macworth, Artificial Intelligence by Rajiv Chopra

Industry 4.0 and Industrial Internet of Things

4
 Difference between program with and without AI

EL
A computer program without AI uses large database and uses
algorithmic search method whereas computer program with AI

PT
uses large knowledge base and heuristic search method

Source: Artificial Intelligence by Rajiv Chopra

Industry 4.0 and Industrial Internet of Things

5
 AI Techniques

EL
Knowledge is the information that can be used to perform a particular
task

Knowledge

PT
Procedural or Declarative or Heuristic
Operational Relational knowledge
knowledge knowledge

Source: Artificial Intelligence by David L. Poole, Alan K. Macworth, Artificial Intelligence by Rajiv Chopra

Industry 4.0 and Industrial Internet of Things

6
 Scopes of AI

EL
Artificial Intelligence

Games Expert
System

PT
NLP Vision & Speech
processing

Theorem Robotics
Proving
Source: Artificial Intelligence by Rajiv Chopra

Industry 4.0 and Industrial Internet of Things

7
 AI vs Machine learning vs Deep learning

EL
Artificial Intelligence

Machine Learning

PT Deep
Learning

Source: Artificial Intelligence by David L. Poole, Alan K. Macworth, Artificial Intelligence by Rajiv Chopra

Industry 4.0 and Industrial Internet of Things 16

 Machine learning

EL
Machine learning is a part of Artificial Intelligence which empower
machines to make decisions based on their experience rather than
being explicitly programmed.

PT
Source: Artificial Intelligence by David L. Poole, Alan K. Macworth, Artificial Intelligence by Rajiv Chopra

Industry 4.0 and Industrial Internet of Things

9
 Deep learning

EL
Deep learning is a subset of machine learning which can learn
automatically by finding the features of the object by own.

PT
Source: Artificial Intelligence by David L. Poole, Alan K. Macworth, Artificial Intelligence by Rajiv Chopra

Industry 4.0 and Industrial Internet of Things

10
Role of AI in Industry 4.0

EL
 Industry 4.0: Human-machine interaction, CPS, cloud
computing, cognitive computing, IoT/IIoT, etc – in
Manufacturing
 Smart Factory: Virtualized instances of physical objects in a

PT
factory interacting with one another.
 Role of AI: Machine safety, efficient product lifecycle, efficient
manufacturing processes, etc.

Industry 4.0 and Industrial Internet of Things

11
 AI in IIoT

EL
 Use of AI helps machines and equipment to
communicate and relay information with one Finance Retail
another
 Examples: Computer Vision, Robotics,
NLP, ML, DL, RL, etc.
 With the help of AI industries are capable of

PT
Healthcare Agriculture
taking the advantage of large amount
generated data by machines
 Example: Prediction of yield, quality of
yield etc in Manufacturing
Source: The Significance of AI and Machine Learning in IIoT, Inc42

Industry 4.0 and Industrial Internet of Things

12
 Challenges of AI in IIOT

EL
Connecting Understanding
devices data

PT Training AI
Making it
actionable

Source: Four Artificial Intelligence challenges in facing the Industrial IoT, Clearblade

Industry 4.0 and Industrial Internet of Things

13
 Advantages of AI in IIoT

EL
The usefulness of AI in industrial scale are,

Increase Improve Augment Boost

Save costs security resources

PT
efficiency performance

Source: The Significance of AI and Machine Learning in IIoT, Inc42

Industry 4.0 and Industrial Internet of Things

14
 Significance of AI in Agriculture industry

EL
 CropIn’s smart farm solution
Crop and Supply  Intello lab using AI based solution for
Precision
soil
agriculture
chain crop health monitoring
monitoring efficiency
 Microsoft India AI based sowing app

PT  Gobasco AI based Agri supply chain

Source: Artificial Intelligence in Indian Agriculture – An Industry and Startup Overview

Industry 4.0 and Industrial Internet of Things

15
 Significance of AI in Education industry

EL
 Smart learning systems by
Providing Carnegie Learning
Improve Making
immersive
student interesting
technology
retention study
into

PT
rate program
classroom
 Querium Corporation AI
based education system

Source: AI in Education: 3 Industry Defining Trends in 2018

Industry 4.0 and Industrial Internet of Things

16
 Significance of AI in Manufacturing factories

EL
Maintain
Improve in
Detection of product supply
machines
machinery by predicting
power

PT
fault consumer
consumption
demand

Source: The Significance of AI and Machine Learning in IIoT, Inc42

Industry 4.0 and Industrial Internet of Things

17
 Significance of AI in Aerospace industry

EL
 Boeing 787 generates large
amount of data at each flight
Extracting Improve
useful data productivity of where AI is used to extract useful
from every manufacturing
flight process
information

PT
Source: The Significance of AI and Machine Learning in IIoT, Inc42
 Airbus is moving on with “Factory
of Future”, to improve the
productivity of manufacturing
process.
https://inc42.com/resources/the-significance-of-ai-and-machine-learning-in-iiot/

Industry 4.0 and Industrial Internet of Things

18
 Significance of AI in Transportation industry

EL
 Indian railways utilizes AI to secure
Assist to
prevent
Self driving safety of trains
car
accidents

PT
 Tesla first automotive brand to
launch self driving car

Source: The Significance of AI and Machine Learning in IIoT, Inc42

Industry 4.0 and Industrial Internet of Things

19
 References

EL
[1] D. L. Poole, A. K. Macworth (2017). “Artificial Intelligence”. Cambridge University Press
[2] R. Chopra (2012). “Artificial Intelligence”. S. Chand & Company Pvt. Ltd.
[3] E. Kumar (2008). “Artificial Intelligence”. L.K. International Publishing House
[4] The Significance of AI and Machine Learning in IIoT. Inc42
URL: https://inc42.com/resources/the-significance-of-ai-and-machine-learning-in-iiot/
[5] Four Artificial Intelligence challenges in facing the Industrial IoT, Clearblade
URL: https://www.clearblade.com/blog/four-artificial-intelligence-challenges-facing-the-industrial-iot

PT
[6] Artificial Intelligence in Indian Agriculture – An Industry and Startup Overview
URL: https://www.techemergence.com/artificial-intelligence-in-indian-agriculture-an-industry-and-startup-
overview/
[7] AI in Education: 3 Industry Defining Trends in 2018
URL: https://www.technavio.com/blog/ai-education-industry-trends-2018

Industry 4.0 and Industrial Internet of Things

20
 EL
PT
Industry 4.0 and Industrial Internet of Things
21
 EL
Industry 4.0:
Big Data and Advanced Analysis

PT Dr. Sudip Misra

Professor
Department of Computer Science and Engineering
Indian Institute of Technology Kharagpur
Email: [email protected]
Website: http://cse.iitkgp.ac.in/~smisra/
Research Lab: cse.iitkgp.ac.in/~smisra/swan/

Industry 4.0 and Industrial Internet of Things 1

 What is Big Data?

EL
 Big data means
 data which is “too big” to be handled by
 processing tools, and
 conventional databases.

PT
 Big data consists of
 structured and
 non-structured data
such as web blogs, FB chats, images, news, tweets, comments, etc.
Source: cs.kent.edu: Big data

Industry 4.0 and Industrial Internet of Things

 Big Data: Definition

EL
 “Big data will represent the data of which acquisition speed,
data volume or data characterization restricts the capacity of
using conventional associated methods to manage successful
analysis or the data which can be successfully operated with
important horizontal zoom technologies.”

PT
[NIST(National Institute of Standards and Technology)]

Source: cs.kent.edu: Big data

Industry 4.0 and Industrial Internet of Things 3

 Data Types

EL
 Structured data
 Data that can be easily organized.
 It is stored in relational databases.
 It is managed by Structured Query Language (SQL) in databases.


PT
It accounts for only 20% of the total available data today in the world.

Source: Big data analytics : Srinivasa

Industry 4.0 and Industrial Internet of Things

4
Data Types(Contd.)

EL
 Unstructured data
 Data that do not possess any pre-defined model.
 Traditional RDBMSs are unable to process unstructured data.
 Enhances the ability to provide better insight to huge datasets.


PT
It accounts for 80% of the total data available today in the world.

Source: Big data analytics : Srinivasa

Industry 4.0 and Industrial Internet of Things 5

Characteristics of Big Data

EL
Variability

Volume

Veracity Big Data Visualization

Big Data
Variety

PT Velocity

There are mainly 3 Vs in Big Data

Value

Some authors also include another 4 Vs

Source: Big data analytics : Srinivasa

Industry 4.0 and Industrial Internet of Things

6
Characteristics of Big Data (Contd.)

EL
 Volume
 Quantity of created data.
 Sources of data are added continuously.
 Example of volume -

PT
 More than 32TB of pictures will be created each night from the Large
Synoptic Survey Telescope (LSST).
 In every minute, 70 hours of video is uploaded to Youtube.

Source: Big data analytics : Srinivasa

Industry 4.0 and Industrial Internet of Things 7

Characteristics of Big Data (Contd.)

EL
 Velocity
 Speed of generation of data.
 Data processing time is decreasing day by day to provide real-time
services.
 Older processing technologies can not help to handle high velocity of
data.

PT
 Example of velocity –
 140 million tweets per day on average (according to a survey conducted in
2011)
 NYSE(New York Stock Exchange) measures 1TB of exchange data during
every exchanging session.
Source: Big data analytics : Srinivasa

Industry 4.0 and Industrial Internet of Things 8

 Characteristics of Big Data (Contd.)

EL
 Variety
 Category of the data.
 No restriction over the input data formats.
 Mostly data are not structured.

PT
 Example of variety –
 Pure text, images, audio, video, web, GPS data, sensor data, SMS,
documents, PDFs, flash etc.

Source: Big data analytics : Srinivasa

Industry 4.0 and Industrial Internet of Things

9
Characteristics of Big Data (Contd.)

EL
 Variability
 Variability is different from variety.
 Data whose meaning is constantly changing.
 Such data appear as an indecipherable mass without structure.
 Example:

PT
 Language processing, Hashtags, Geo-spatial data, Multimedia, Sensor
events.

Source: Big data analytics : Srinivasa

Industry 4.0 and Industrial Internet of Things

10
 Characteristics of Big Data (Contd.)

EL
 Veracity
 Veracity indicates biasness in the data, unusualness and noise in data.
 It is important in programs which involve automated decision-making.
 It is also important for feeding the data into an unsupervised machine

PT
learning algorithm.
 Veracity deals about the data understandability, not just the
data quality.

Source: Big data analytics : Srinivasa

Industry 4.0 and Industrial Internet of Things

11
Characteristics of Big Data (Contd.)

EL
 Visualization
 Data can be in form of pictures or in form of a graphical format.
 Visualization provides the power to decision makers to see visually.
 It is helpful to identify new patterns.
 Value

PT
 It means extracting useful business information from scattered data.
 Simple to access and provides quality investigation that empowers
informed decisions.
Source: Big data analytics : Srinivasa

Industry 4.0 and Industrial Internet of Things

12
Data Sources

EL
• Online trading & data analysis
Enterprise data • Production and inventory data
• Sales and other financial data

PT
IoT data
• Industrial data
• Healthcare data
• Agricultural data

Source: The Making of ENCODE: Lessons for Big-Data Projects : Birney

Industry 4.0 and Industrial Internet of Things

13
Data Sources

EL
Biomedical • Data generated from gene sequencing
data • Data from medical clinics

Others

PT • Computational biology
• Astronomy
• Nuclear research

Source: The Making of ENCODE: Lessons for Big-Data Projects : Birney

Industry 4.0 and Industrial Internet of Things

14
 Data Acquisition

EL
 Data collection
 Data sources automatically generate log files or record files to record
activities for further analysis.
 Complex and variety of data collection through mobile devices. E.g. –
geographical location, 2D barcodes, pictures, videos etc.

PT
 Data transmission
 Categorized as – Inter-DCN transmission and Intra-DCN transmission.
 Collect data and transfer to storage system for further processing and
analysis of the data.
Source: The Making of ENCODE: Lessons for Big-Data Projects : Birney

Industry 4.0 and Industrial Internet of Things

15
Data Acquisition (Contd.)

EL
 Data pre-processing
 Pre-processing of data is
Integration
necessary as collected
datasets suffer from noise,
redundancy etc. Clearing

PT
 Pre-processing of relational
data mainly follows- Redundancy Mitigation

Source: The Making of ENCODE: Lessons for Big-Data Projects : Birney

Industry 4.0 and Industrial Internet of Things

16
Data Acquisition (Contd.)

EL
 Integration:
 combine data from various sources and
 delivers the users a constant data view.
 Clearing:

PT
 spot incorrect, insufficient, or uncooperative data, and
 correct or remove such data.
 Redundancy mitigation:
 eliminate data repetition through detection, filter and compression
of data to avoid unnecessary transmission.
Source: The Making of ENCODE: Lessons for Big-Data Projects : Birney

Industry 4.0 and Industrial Internet of Things

17
Data Storage

EL
 File system
 Distributed file systems that store massive data and ensure –
consistency, accessibility, and fault tolerance of data.
 GFS is a distributed file system that supports large-scale file system.

PT
 HDFS(Hadoop Distributed File System) is a notable file systems, derived
from the open source codes of GFS.
 Databases
 Emergence of non-traditional relational databases (NoSQL) in order to
deal with the characteristics that big data possess.
Source: The Making of ENCODE: Lessons for Big-Data Projects : Birney

Industry 4.0 and Industrial Internet of Things

18
 Why Data Analytics?

EL
Sensors are very small in sizes. They can be placed anywhere and
transfer the data over wireless technology, because of this explosion
of data moving to systems from sensors. Some data are irrelevant for
systems. How can one know which data are relevant, this requires

PT
analysis of the data.

Source: Industry 4.0:The Industrial Internet of Things: Gilchrist

Industry 4.0 and Industrial Internet of Things

19
Why Data Analytics?(Contd.)

EL
Appropriate
Product Help to learn
Recommendations About competitors

Customer

PT
Improve
Market Help to join an activity
Effectiveness which expands business

Protect from wrongful

decision
Source: stat.si: Big data tutorial

Industry 4.0 and Industrial Internet of Things

20
 Big Data Analytics

EL
 Big data is different from conventional Data Warehouse (DW)
approaches.
 Big data apps cannot be fit in traditional DW architectures
(e.g. Exadata, Teradata).

PT
 Distributed nothing, mighty parallel performing, scale out
frameworks are convenient for big data apps.

Source: Industry 4.0:The Industrial Internet of Things: Gilchrist

Industry 4.0 and Industrial Internet of Things

21
Big Data Analytics for Industry 4.0

EL
 Industrial Internet require an approach to manage and
process data coming from thousand of sensors for precious
perceptions .
 To manage and handle the huge data in health services and

PT
manufacturing etc. is not new. For example-
 An event is detected by a sensor and sent to the operational recorder.
An operational recorder is a database which stores data. After that this
data is optimized by querying such as, what about this hour’s
production from the norm.
Source: Industry 4.0:The Industrial Internet of Things: Gilchrist

Industry 4.0 and Industrial Internet of Things

22
Big Data Analytics for Industry 4.0 (Contd.)

EL
 IIoT can be recognized as a big benefactor of Big Data.
 It needs new technologies to manage vast data.
 Cloud services are accessible to handle Big Data with no-limit
of storage on demand.

PT
 In IIoT, Hadoop (open source cloud based distributed data
storage) is also available for managing the data.

Source: Industry 4.0:The Industrial Internet of Things: Gilchrist

Industry 4.0 and Industrial Internet of Things

23
Cloud-Based Method for Analytics

EL
 Essential features (according to NIST)
 On-demand self service
 Wide network access
 Method grouping

PT
 Fast flexibility
 Measured service

Source: Industry 4.0:The Industrial Internet of Things: Gilchrist

Industry 4.0 and Industrial Internet of Things

24
Types of Analytics

EL
Prescriptive Analytics
-> Best action?
-> Should we try this?
Predictive Analytics
->What next?

PT ->Pattern?
Descriptive Analytics
->When, where?
->What happened?
Source: Industry 4.0:The Industrial Internet of Things: Gilchrist

25
 References

EL
[1] A. Machanavajjhala and J.P. Reiter, “Big Privacy: Protecting Confidentiality in Big Data,” ACM Crossroads, vol.
19, no. 1, pp. 20-23, 2012.
[2] E. Birney, “The Making of ENCODE: Lessons for Big-Data Projects,” Nature, vol. 489, pp. 49-51, 2012.
[3] J. Bughin, M. Chui, and J. Manyika, Clouds, Big Data, and Smart Assets: Ten Tech-Enabled Business Trends to
Watch. McKinSey Quarterly, 2010.
[4] S. Banerjee and N. Agarwal, “Analyzing Collective Behavior from Blogs Using Swarm Intelligence,”
Knowledge and Information Systems, vol. 33, no. 3, pp. 523-547, Dec. 2012.

PT
[5] Marko Grobelnik (2012).Big-Data Tutorial.Online .URL https://www.stat.si/dokument/8682/BigDataIntro-
MarkoGrobelnik.pdf.
[6] Ruoming Jin.Introduction to Big Data.Online.URL https://www.cs.kent.edu/~jin/BigData/.
[7] S. Aral and D. Walker, “Identifying Influential and Susceptible Members of Social Networks,” Science, vol.
337, pp. 337-341, 2012.
[8] Srinivasa S.,& Bhatnagar, V.(2012), Big data analytics, Springer.
[9] Gilchrist A.(2016).Industry 4.0:The Industrial Internet of Things.Apress.

Industry 4.0 and Industrial Internet of Things

26
 EL
PT
Industry 4.0 and Industrial Internet of Things 27