09-10-2020
Evolution of the industry
Industry 4.0
Shashanka RH (120881)
9986192247
shashanka.rh@gmail.com
What is Industry 4.0? Why know about Industry 4.0?
• …….. current trend of automation and data exchange in manufacturing
technologies, including cyber-physical systems, the Internet of things, cloud
computing and cognitive computing and creating the smart factory………
• …….. a vision that evolved from an initiative to make the German
manufacturing industry more competitive (‘Industrie 4.0’) to a globally
adopted term………
• …….. characterized by, among others,
• even more automation than in the third industrial revolution,
• the bridging of the physical and digital world through cyber-physical systems,
enabled by Industrial IoT,
• a shift from a central industrial control system to one where smart products define
the production steps,
• closed-loop data models and control systems and
• personalization/customization of products.
09-10-2020
What are Cyber-Physical
Six principles of Industry 4.0 Systems?
• A network of interacting elements
with physical input and output
devices.
• Tied to concepts of robotics and
sensor networks.
• Ongoing advances in science and
engineering improve the link
between computational and physical
elements by means of intelligent
mechanisms, increasing the
adaptability, autonomy, efficiency,
functionality, reliability, safety, and
usability of cyber-physical systems.
Definition of IoT
• A dynamic global network infrastructure with self-configuring
capabilities based on standard and interoperable communication
protocols where physical and virtual "things" have identities, physical
attributes, and virtual personalities and use intelligent interfaces, and
are seamlessly integrated into the information network, often
communicate data associated with users and their environments.
09-10-2020
Characteristics of IoT Physical Design of IoT
• Dynamic & Self-Adapting • The "Things" in IoT usually refers to IoT devices which have unique
• Self-Configuring identities and can perform remote sensing, actuating and monitoring
capabilities.
• Interoperable Communication Protocols
• IoT devices can:
• Unique Identity • Exchange data with other connected devices and applications (directly or
• Integrated into Information Network indirectly), or
• Collect data from other devices and process the data locally or
• Send the data to centralized servers or cloud-based application back-ends for
processing the data, or
• Perform some tasks locally and other tasks within the IoT infrastructure,
based on temporal and space constraints
Communication Protocols
Generic block diagram of an IoT Device
An IoT device may consist of several interfaces for
connections to other devices, both wired and
wireless.
• I/O interfaces for sensors
• Interfaces for Internet
connectivity
• Memory and storage
interfaces
• Audio/video interfaces.
09-10-2020
Logical Design of IoT Request-Response communication model
• Request-Response is a communication model
• Logical design of an IoT system in which the client sends requests to the
refers to an abstract representation server and the server responds to the
of the entities and processes requests.
without going into the low-level • When the server receives a request, it
specifics of the implementation. decides how to respond, fetches the data,
• An IoT system comprises of a retrieves resource representations, prepares
number of functional blocks that the response, and then sends the response to
provide the system the capabilities the client.
for identification, sensing,
actuation, communication, and
management.
Publish-Subscribe communication model Push-Pull communication model
• Publish-Subscribe is a communication model that • Push-Pull is a communication model
involves publishers, brokers and consumers. in which the data producers push
• Publishers are the source of data. Publishers send the the data to queues and the
data to the topics which are managed by the broker. consumers pull the data from the
Publishers are not aware of the consumers.
queues. Producers do not need to
• Consumers subscribe to the topics which are be aware of the consumers.
managed by the broker.
• When the broker receives data for a topic from the • Queues help in decoupling the
publisher, it sends the data to all the subscribed messaging between the producers
consumers. and consumers.
• Queues also act as a buffer which
helps in situations when there is a
mismatch between the rate at
which the producers push data and
the rate rate at which the
consumers pull data.
09-10-2020
Exclusive Pair communication model IoT Levels & Deployment Templates
• Exclusive Pair is a bidirectional, fully duplex
communication model that uses a persistent • An IoT system comprises of the following components:
connection between the client and Server. • Device: An IoT device allows identification, remote sensing, actuating and
remote monitoring capabilities. You learned about various examples of IoT
• Once the connection is setup it remains open devices in section
until the client sends a request to close the • Resource: Resources are software components on the IoT device for
connection. accessing, processing, and storing sensor information, or controlling actuators
connected to the device. Resources also include the software components
• Client and server can send messages to each that enable network access for the device.
other after connection setup. • Controller Service: Controller service is a native service that runs on the
device and interacts with the web services. Controller service sends data from
the device to the web service and receives commands from the application
(via web services) for controlling the device.
IoT Levels & Deployment Templates IoT Level-1
• A level-1 IoT system has a single
• Database: Database can be either local or in the cloud and stores the data
generated by the IoT device. node/device that performs sensing
• Web Service: Web services serve as a link between the IoT device, and/or actuation, stores data, performs
application, database and analysis components. Web service can be either analysis and hosts the application
implemented using HTTP and REST principles (REST service) or using
WebSocket protocol (WebSocket service).
• Analysis Component: The Analysis Component is responsible for • Level-1 IoT systems are suitable for
analyzing the IoT data and generate results in a form which are easy for the modeling lowcost and low-complexity
user to understand. solutions where the data involved is not
• Application: IoT applications provide an interface that the users can use to big and the analysis requirements are not
control and monitor various aspects of the IoT system. Applications also allow computationally intensive.
users to view the system status and view the processed data.
09-10-2020
IoT Design Methodology - Steps Example Case
Implementation of IoT for Home Automation
09-10-2020
Step:1 - Purpose & Requirements
• Applying this to our example of a smart home automation system, the purpose and
requirements for the system may be described as follows:
• Purpose : A home automation system that allows controlling of the lights in a home
remotely using a web application.
• Behavior : The home automation system should have auto and manual modes. In
auto mode, the system measures the light level in the room and switches on the light
when it gets dark. In manual mode, the system provides the option of manually and
remotely switching on/off the light.
• System Management Requirement : The system should provide remote monitoring
and control functions.
• Data Analysis Requirement : The system should perform local analysis of the data.
• Application Deployment Requirement : The application should be deployed locally on
the device, but should be accessible remotely.
• Security Requirement : The system should have basic user authentication capability.
09-10-2020
09-10-2020
Introduction to Internet of Things
Sensors and actuators
• The Internet of Things (IoT) describes the network of physical
objects—“things”—that are embedded with sensors, software, and
other technologies for the purpose of connecting and exchanging
data with other devices and systems over the internet.
09-10-2020
Communication technology
Sensors and actuators
Wireless sensor networks
Typical IoT Architecture
09-10-2020
……………………..so now we have our data, WHAT NEXT?
What is Data Analytics? Data for Analytics
Analytics is the use of: DATA
data, - collected facts and figures
information technology, DATABASE
statistical analysis, - collection of computer files containing data
quantitative methods, and
INFORMATION
mathematical or computer-based models
- comes from analyzing data
to help managers gain improved insight about their business
operations and make better, fact-based decisions.
Business Analytics (BI) is a subset of Data Analytics
09-10-2020
Data for Business Analytics Decision Models
Metrics are used to quantify performance. Model:
Measures are numerical values of metrics. An abstraction or representation of a real system, idea, or object
Discrete metrics involve counting Captures the most important features
- on time or not on time Can be a written or verbal description, a visual display, a
- number or proportion of on time deliveries mathematical formula, or a spreadsheet representation
Continuous metrics are measured on a continuum
- delivery time
- package weight
- purchase price
Decision Models Decision Models
A decision model is a model used to understand, analyze, or facilitate
decision making.
Types of model input
- data
- uncontrollable variables
- decision variables (controllable)
09-10-2020
Types of data analytics
Types of Analytics
Decision Models Descriptive Analytics
• Descriptive analytics, such as reporting/OLAP, dashboards, and
Descriptive Decision Models data visualization, have been widely used for some time.
• They are the core of traditional BI.
Simply tell “what is” and describe relationships
Do not tell managers what to do
What has occurred?
Descriptive analytics, such as data visualization, is
important in helping users interpret the output from
predictive and predictive analytics.
09-10-2020
Decision Models
Diagnostic Analysis
What are the causes the trigger a particular
response?
Give a relationship in the form of :
Y = f(x1, x2, x3, ……); where Y is the response and x1,
x2, x3, …. Are the causes
Predictive Analytics
Decision Models • Algorithms for predictive analytics, such as regression analysis, machine
learning, and neural networks, have also been around for some time.
• Predictive analytics are often referred to as advanced analytics.
• Predictive Decision Models often incorporate uncertainty to help
managers analyze risk.
• Aim to predict what will happen in the future.
• Uncertainty is imperfect knowledge of what will happen in the future.
• Risk is associated with the consequences of what actually happens.
What will occur?
• Marketing is the target for many predictive analytics applications.
• Descriptive analytics, such as data visualization, is important in helping
users interpret the output from predictive and prescriptive analytics.
09-10-2020
Decision Models
Decision Models
A Linear Demand Prediction Model A Nonlinear Demand Prediction Model
As price increases, demand falls. Assumes price elasticity (constant ratio of % change in
demand to % change in price)
Prescriptive Analytics
Decision Models • Prescriptive analytics are often
referred to as advanced analytics.
• Regression analysis, machine
Prescriptive Decision Models help decision makers identify the best learning, and neural networks
solution. • Often for the allocation of scarce
resources
Optimization - finding values of decision variables that minimize (or
maximize) something such as cost (or profit).
Objective function - the equation that minimizes (or maximizes) the
quantity of interest. What should occur?
Constraints - limitations or restrictions.
Optimal solution - values of the decision variables at the minimum • For example, the use of mathematical programming for revenue management is common for
(or maximum) point. organizations that have “perishable” goods (e.g., rental cars, hotel rooms, airline seats).
09-10-2020
What is Artificial Intelligence Types of Artificial Intelligence
• Artificial Superintelligence: An intellect that is much smarter
than the best human brains in practically every field, including
scientific creativity, general wisdom and social skills.
• Artificial General Intelligence: A machine with the ability to
apply intelligence to any problem, rather than just one
Input: Output: specific problem (human-level intelligence)
Data Artificial Action
Sensors Intelligence Movement
Images Text • Artificial Narrow Intelligence: Machine intelligence that equals
or exceeds human intelligence or efficiency at a specific task
What is Machine Learning
(some) Subsets of Artificial Intelligence
• Type of Artificial Intelligence that provides computers with the ability
to learn without being explicitly programmed
• Various techniques can be used to for it learn make predictions based
Artificial Intelligence on data
Machine Learning
Artifical
Machine Learning is a subset of Machine Learning
Training Data
Artificial Intelligence Algorithm
Deep Training
Deep Learning Deep Learning uses neural
Learning is a subset of networks to simulate human Prediction
Machine Learning like decision making
“Live” Data Trained Model Prediction
09-10-2020
Machine Learning Approaches
• Supervised Learning: Learning with a labelled training
set
• Example: email spam detector with training set of labelled
emails
• Unsupervised Learning: Discovering patterns in
unlabelled data
• Example: cluster similar documents based on the text
content
• Reinforcement Learning: learning based on feedback
or reward
• Example: learn to play chess by winning or losing
What Machine Learning can do No-code platforms
INPUT A RESPONSE B APPLICATION
Picture Are there human faces? (0 or 1) Photo tagging
Loan Application Will they repay the loan? (0 or 1) Loan approvals
Ad plus user information Will user click on ad? (0 or 1) Targeted online ads
Audio clip Transcript of audio clip Speech recognition
English Sentence French Sentence Language translation
Sensor from plane engine, etc Is it about to fail? Preventive maintenance
Car camera and other sensors Position of other cars Self-driving cars
Source: Andrew Ng
09-10-2020
How to convince your boss to think of
Hiccups in implementation
Industry 4.0?
• Lack of unified leadership that makes cross-unit coordination difficult • Making Your Case with Data
within the company.
• Make Use of Case Study
• Data ownership concerns when choosing third-party vendors for hosting
and operationalizing company data. • Showcase the ROI
• Lack of courage to launch the radical digitalization plan. • Ask the Right Questions
• Do you need more information to make a decision and what information do
• Lack of in-house talent to support the development and deployment of you need?
Industry 4.0 initiatives. • Would you be interested in a 6-month trial?
• Difficulties with integrating data from various sources to enable initial • If it helps you surpass your personal targets will you try it?
connectivity.
• Associate the Integration of Industry 4.0 with Achieving Business
• Lack of knowledge about technologies, vendors and IT outsourcing Goals
partners that could help execute the core initiative.
Impact of Industry 4.0
