REPORT ON

INTERNSHIP ON INDUSTRY 4.0

from 15/02/2022 to 13/03/2022

INDUSTRY 4.0
 We’re in the midst of a significant transformation
regarding the way we produce products thanks to the
digitization of manufacturing. This transition is so compelling
that it is being called Industry 4.0 to represent the fourth
revolution that has occurred in manufacturing. From the first
industrial revolution (mechanization through water and
steam power) to the mass production and assembly lines
using electricity in the second, the fourth industrial
revolution will take what was started in the third with the
adoption of computers and automation and enhance it with
smart and autonomous systems fueled by data and machine
learning.
This manufacturing revolution will increase productivity,
shift economics, foster industrial growth, and modify the
profile of the workforce—ultimately changing the
competitiveness of companies and regions.
As the adoption of Industry 4.0 is increasing day by day
across various industries, the scope for the skill sets will be
enormous for the driving technologies of Industry 4.0
The technologies of Industry 4.0 include Integrated
System, IOT, Data Management, Cloud Computing, Cyber
security, Artificial Intelligence, Additive Manufacturing,
Augmented Reality.

Technologies of Industry 4.0

About the Company
 Gustovalley Technovations is automation-based
company working towards the goal of Digital transformation.
Gusto Learn is the initiative of Gustovalley technovations
which focuses on offering Industry training to the students.
The Students will good exposed to the latest
technologies and will have the opportunity to work on
Solutions for the Realtime problems.
Our course is designed in such a way that each students
will get complete hands on experience and will have deeper
understanding of concepts by working on projects and
assignments to solve real-time problems.

Student’s Responsibility
I, LOGESHWARAN M in the course of the Internship has
been provided training all the concepts of Technologies
involved in Industry 4.0. During the Internship period, I have
assigned for the Project on Titanic Survival. I have
successfully completed the project under the mentorship of
Ejaz Ahmed from Gustovalley Technovations.
This report is prepared as requirement for the internship
of BE program of Electronics and Communication
Engineering, R.M.K. Engineering College.
Week 1: Embedded System & IOT
Embedded systems are part and parcel of every
modern electronic component. These are low power
consumption units that are used to run specific tasks for
example remote controls, washing machines, microwave
ovens, RFID tags , sensors, actuators and thermostats used in
various applications, networking hardware such as switches,
routers, modems, mobile phones, PDAs, etc.
Usually embedded devices are a part of a larger device
where they perform specific task of the device. For example
embedded systems are used as networked thermostats in
Heating, Ventilation and Air Conditioning (HVAC) systems, in
Home Automation embedded systems are used as wired or
wireless networking to automate and control lights, security,
audio/visual systems, sense climate change, monitoring, etc.
Embedded systems will also be at the cornerstone for
the deployment of many Internet of Things (IoT) solutions,
especially within certain industry verticals and Industrial
Internet of Things (IIoT) applications.
Major players in embedded system hardware and
software developments are aiming to bring these
transformations into their products to take advantage of
growing IoT market. The areas that are going to transform
are Real Time Operating Systems (RTOS) and microprocessors
and microcontrollers, followed by memory footprints and
networking, open source communities and developers.
 In the first week we learned about the basics of
Embedded system and IOT by understanding one of the most
commonly used Microcontroller for Prototyping in Industry,
Node MCU ESP8266 and also Arduino UNO.
We have also learned how to get start with the Micro
Controller by understanding the Architecture, pinout and
documentation of the Micro controller. This has given
confidence that we can easily to any new Microcontroller
used in Industry by looking at its architecture.

Architecture of ESP8266 and Arduino UNO

ESP8266 Pinout Diagram

Arduino UNO Architecture

THINKERCAD SIMULATION
 We had a real-time working experience with simulation
platform. We worked on all components and had an Hands
on experience working on assignments.
We have also used Arduino IDE platform for Compilation
and uploading of code to controller
We also learned ADC and PWM concepts by working on
application-based assignments.
 In IOT front we learned Communication model and
various communication protocols

OSI LAYERS
The Open Systems Interconnection
model (OSI model) is a conceptual model that
characterizes and standardizes the
communication functions of
a telecommunication or computing system
without regard to its underlying internal structure
and technology. Its goal is the interoperability of
diverse communication systems with
standard communication protocols. The model
partitions a communication system
into abstraction layers.
We also learned the basics of IP address, MAC address, IP
Address classes, Subnet masking.

TCP Protocol
• Transmission Control Protocol (TCP)
• One-to-one and connection-oriented reliable protocol
• Used in the accurate transmission of large amount of
data
• Connection-oriented
• Stream Data Transfer
• Reliable
• Flow-Control
• Full-Duplex
• Slower compared to UDP because of additional error
checking being performed
• Suited for critical data transfer applications
TCP (Transmission Control Protocol) is a standard that
defines how to establish and maintain a network
conversation through which application programs can
exchange data. TCP works with the Internet Protocol (IP),
which defines how computers send packets of data to each
other.
 Introduction to Blynk application for IOT
Using Blynk app we made a IOT mobile App for
controlling ESP8266. This library is compatible with all
architectures so you should be able to use it on all the
Arduino boards.
The Blynk Server will act as a Cloud for our IOT device
and with the device we controlled various home appliances.
 We created an IoT application using Blynk app to control
various appliances and also to dashboard to monitor devices
remotely. This working has given us confidence to use this
learning in Industry for controlling and monitoring of the
machines.
 Week2: Development of Server for Monitoring and
controlling IOT Devices
After having been exposed Controlling IOT devices using
3rd Party Blynk application. In 2nd Week we have been trained
on Setting up hosting server to not only connect our IOT
devices but also to develop a webpage as an interface to
control and monitor the IOT device.
Initially we have been trained on HTML, CSS program to
understand the components of Webpage and we also hosted
our Webpage in a server. After having basic knowledge on
Webpage, we were trained to handle SQL database and PHP
interface to capture the status of the Microcontroller.
During this we have developed two API links, one link to
update data in the server and 2nd link to read the status of
the controller from the Server.
After creation of the API links we developed a webapp
to control our IOT devices.
You can access the Web App through the below
Code:
<!DOCTYPE html>
<html>
<body>
<img src="photo-1588666309990-d68f08e3d4a6.jpg" alt="Flowers in Chania"
width="460" height="345">

</body>
</html>
 <p>Name: LOGESHWARAN M</p>
<p>Department: Electronics and Communication Engineering</p>
<p>College Name: R.M.K. Engineering college </p>
<h4 style="color:Tomato;">ABOUT ME</h4>
<p>I am LOGESHWARAN M</p>
<p>I have keen interest in electronics</p>
<p>I use a creative approach to problem solve.</p>
<p>I am always coming up with innovative ideas.</p>
<p>I am always energetic and eager to learn new skills.</p>
<p>I am able to handle multiple tasks on a daily basis</p>
<iframe width="560" height="315"
src="https://www.youtube.com/embed/3LpBQ8FZSuk"
frameborder="0" allow="accelerometer; autoplay; encrypted-media; gyroscope;
picture-in-picture"
allowfullscreen></iframe>
<p><a href="https://gustovalley.in/">GUSTOVALLEY</a></p>
</body>
</html>
Web APP

IOT System
 Week 3: Python – Data Science, Machine Learning and
Image Processing
In the third week we have got introduced to one of the
most widely accepting language, Python. Earlier we started
with basics of Python. We have used Jupyter notebook
platform for compiling and running our code. In Python
basics we learned Operations, Datatypes, Decision making,
Looping, Functions and Classes.
We then used Data processing libraries Numpy and
Pandas for numerical array operations. We understand the
Data processing techniques by working on the datasets.
 We then learned the concepts of Exploratory Data
Analysis (EDA) and applied the learnings of Data Pre
processing from Numpy and Pandas library to our IOT water
consumption data set and visualized our dataset using
Matplotlib and Seaborn library. From the visualization of our
dataset we have found several insights and identified the
principal components for our Machine learning process
 Our Data Visualization

Identifying the Principal Component

 Machine Learning techniques
We have then jumped to Machine learning
techniques using Python. We have been learned about the
types of machine learning techniques. There we went deeper
in to Linear Regression techniques starting from the principle,
working and algorithm.
We then learned working on Scikitlearn Library for
developing a prediction model to predict the water
consumption based on temperature and Humidity data.
After pre-processing and visualization of our data.
We divided our data set in to Training data (70%) and testing
data(30%) and using Scikitlearn Library we developed a
Machine learning model using the training data and
calculated the coefficient and the intercept.
After development of the model we then compared
the result from the Training model and actual data by
feeding the test data set in to the model.
We found that our model is 97% accurate by
considering the Root Mean Squared Error.
 Computer vision using Python
Computer vision is a field of artificial intelligence that
trains computers to interpret and understand the visual
world. Using digital images from cameras and videos and
deep learning models, machines can accurately identify and
classify objects — and then react to what they “see.”
Open CV is the open source library for Python for Image
processing. We have learned the various image processing
concept and practiced the Same in Jupyter notebook.
We have learned the concepts of image manipulation,
Object detection and Face detection concepts.
We have developed an Python app to calculate
manhours in the company based on the video feed.
 Week 4: Dashboard for IOT APP
This week we have taught how to develop an Android
app using MIT app inventor where we will build app using the
drag drop concept. Through this module we developed an
Mobile App which will connect to our Database and the
Database being connected to our IOT devices. The Mobile
app can able to read the status of the IOT device and also can
able to control the IOT device by updating the value in
Database.

We have also developed the Augmented Reality mobile

app using unity game engine which will display the Realtime
dashboard in the virtual world.
 The AR app is connected to our database and will display
the Real time Temperature, Humidity and Water level in the
Virtual space.
This has opened the scope of various application in
Industry to monitor the various parameters of machines and
alert the maintenance team with ease.
 Project
Titanic Survival
Introduction
The RMS Titanic was a British passenger liner that sank
in the North Atlantic Ocean in the early morning hours of 15
April 1912, after it collided with an iceberg during its maiden
voyage from Southampton to New York City. There were an
estimated 2,224 passengers and crew aboard the ship, and
more than 1,500 died, making it one of the deadliest
commercial peacetime maritime disasters in modern history.
The RMS Titanic was the largest ship afloat at the time it
entered service and was the second of three Olympic-class
Ocean liners operated by the White Star Line. The Titanic was
built by the Harland and Wolff shipyard in Belfast. Thomas
Andrews, her architect, died in the disaster.
In this project, we will analyse the Titanic data set and
make two predictions. One prediction to see which
passengers on board the ship would survive and then
another prediction to see if we would’ve survived.

Methodology
In this project, I will go through the whole process of
creating a machine learning model on the famous Titanic
dataset, which is used by many people all over the world. It
provides information on the fate of passengers on the Titanic,
summarized according to economic status (class), sex, age
and survival. For the data visualization, many libraries have
been used to fetch the required data. Some of the used
libraries in this model are: matplotlib, Pandas, NumPy,
seaborn.

Matplotlib
“Matplotlib is a Python 2D plotting library which
produces publication quality figures in a variety of hardcopy
formats and interactive environments across platforms.
Matplotlib can be used in Python scripts, the Python and I
Python shells, the Jupyter notebook, web application servers,
and four graphical user interface toolkits.”

Pandas
Pandas is an open-source python library that is used for
data manipulation and analysis. It provides many functions
and methods to speed up the data analysis process. Pandas is
built on top of the NumPy package; hence it takes a lot of
basic inspiration from it. The two primary data structures are
Series which is 1 dimensional and Data Frame which is 2
dimensional. It is one of the most important and useful tools
in the arsenal of a Data Scientist and a Data Analyst.
NumPy
NumPy is a Python library used for working with arrays.
It also has functions for working in domain of linear algebra,
Fourier transform, and matrices. NumPy was created in 2005
by Travis Oliphant. It is an open-source project and you can
use it freely. NumPy stands for Numerical Python. NumPy
arrays facilitate advanced mathematical and other types of
operations on large numbers of data. Typically, such
operations are executed more efficiently and with less code
than is possible using Python's built-in sequences.

Seaborn
Seaborn is a data visualization library built on top of
matplotlib and closely integrated with pandas’ data
structures in Python. Visualization is the central part of
Seaborn which helps in exploration and understanding of
data. One has to be familiar with NumPy and Matplotlib and
Pandas to learn about Seaborn.
Results & insights
1. Reading the data from the data set

The data is read by using read function, from the data

set.

2. Reading first 5 rows in the data set

pandas “head ()” function is used to display the top 5

rows from our data set. Note – We can provide the no. of
rows that we want to display by providing the count as a
parameter to the “head ()” function.
3. Shape of the data set

To know the dimension of our dataset, we can use

“shape”, which will show the dimensions in (No. of
rows, No. of columns) format.

4. Data pre-processing
Loading the data set

Using “isnull()” and “sum()” functions, we can find that

the no. of null values in a DataFrame for every feature. It’s a
pre- processing step, before analysing the data.

5. Finding the mean of age

 One of the techniques is mean imputation in which the
missing values are replaced with the mean value of the entire
feature column. One can use mean value to replace the
missing values in case the data distribution is symmetric. To
fill the missing data, The mean value of the age is found and
inserted in the missing cells.

6. Number of people survived

According to counter chart, 549 people have been

survived and 342 have been died in this incident.
 7. Total number of people by gender

According to bar chart, 577 are male passengers and

314 are female passengers.

8. Number of people survived by gender

 According to bar chart, 109 male passengers survived
and 468 male passengers are died. 233 female passengers
have been survived and 81 female passengers died.
9. Number of people survived by class

According to counter chart, 136 passengers survived in

first class, 87 passengers survived in second class and 119
passengers survived in third class.

10. Age distribution of passengers

The histogram provides a quick visual representation of

the frequency of different age groups. Age of the passengers
is the example of normal distribution. Most of the passengers
in the ship are of average age. The number of passenger
older and younger than the average age of the passenger is
almost equal. However, age is not a single characteristic.
Therefore, it follows the normal distribution.

11. Number of siblings/spouses abroad

Here “SibSp” variable refers to the number of sibling or

spouse the person was accompanied with. We can see most
of the people came alone.

12. Number of siblings/spouses abroad survived

 According to bar chart, 398 passengers was survived,
who came alone and 210 of the passengers didn’t survive in
the incident.

Conclusion
Python has a powerful and most popular package
‘Pandas’ built on top of NumPy which has the
implementation of many data objects and data operations.
Pandas is one of the most famous data science tools and it’s
definitely a game-changer for cleaning, manipulating, and
analysing data. Thus, the data set of titanic survival is
analysed.
 Conclusion
The learning experience was very satisfactory and the
internship gave us an insight into these latest technologies.
Since the internships was based on practical hands on
experience and not just theoretical concept, it helped us
understand these technologies in a better way.
Overall it was a very knowledgeable experience and we
look forward to gain more insight into these technologies
using the basic knowledge we gained during this internship.
The hands on training has given me confidence and
interest to learn the concepts of Industry 4.0 deeper and I’m
sure that my learnings will me to shape a better carrier.