1.

INTRODUCTION

1.1 Industrial IoT:

The industrial Internet of Things (IIoT) connects your people, products, and processes to
power digital transformation. Using industrial IoT platforms, companies connect,
monitor, analyze, and act on data in new ways. With NI’s technology providing
unmatched capabilities in measurement, control, ruggedness, and connectivity, along with
our expert ecosystem, we can realize the benefits of the Industrial Internet of Things
(IIoT). The world economy will greatly change in the next decade as new Internet-
enabled applications are rolled out. Some of these applications are likely to be disruptive
and innovative as well as have a large economic impact. This will affect many industries
and sectors, as already seen in consumer sectors like hotels (Airbnb) and taxis (Uber).
This trend is also noticeable in the industry, for example, Germany’s Industry 4.0
initiative. Within Industry 4.0 or the Industrial IoT (IIoT), the focus is on integration and
better use of existing technologies. In this sense, industry, machines, products, and people
are all digitally connected. Manufacturers are mass producing bespoke products in
quantities of one. Intelligent software in the cloud connects enterprise IT systems with the
operational world, machines, devices, and sensors to control and optimize production
flow.

Fig: 1.1

1
1.2 Machine learning:
Machine learning is an application of artificial intelligence (AI) that provides systems the
ability to automatically learn and improve from experience without being explicitly
programmed. Machine learning focuses on the development of computer programs that
can access data and use it learn for themselves. The process of learning begins with
observations or data, such as examples, direct experience, or instruction, in order to look
for patterns in data and make better decisions in the future based on the examples that we
provide. The primary aim is to allow the computers learn automatically without human
intervention

Methods of Machine Learning:

• Supervised Learning

• Unsupervised Learning

Supervised Learning:

Supervised learning refers to the generalization of the relationship (function) between the
input data and their corresponding outputs (labels). The relationship (function) is learned
through a training set of examples, each of which is a pair of an input data and a desired
output. During the training, the error between the actual and the desired outputs is
frequently fed back into the system for tuning the system parameters according to certain
learning rule. After the training, the performance of the learned relationship (function)
should be evaluated on a test set (of examples) that is separate from the training set.

Unsupervised Learning:

Unsupervised learning refers to the problems of revealing hidden structure in unlabeled

data. Since the data are unlabeled, there is no error signal fed back to the learner in the
algorithm. This distinguishes unsupervised learning from supervised learning.

2
 2. ORGANISATION PROFILE

VI Solutions is an automation Company and a pioneer in providing Systems, Solutions

and Products for a wide range of industries and applications. Headquartered in Bangalore,
India, VI Solutions was founded by a pool of live wire professionals having several years
of combined technical and corporate expertise in providing high quality, cost-effective
and complete end-to-end solutions to its valued customers. All our team members are
highly qualified in their respective fields and have years of industrial experience behind
them.
 VI Solutions is specialized in the design and realization of turnkey machines and tools.
As an engineering company, we are known for our expertise in automated assembly lines,
process automation, data acquisition and visual inspection. VI Solutions is one of the
leading companies in building Advanced Communication Systems, Real Time Embedded
Systems and other Industrial Automation services for applications in Department of
Defense, Aerospace and Educational Institutions.
VI Solutions was started with the aim of always staying at the cutting-edge of automation
technology and thereby providing the most appropriate technology for every automation
application. VI Solutions is focused on becoming a leader in the development of test and
measurement and industrial automation software and systems. We are proud of the
current products and services we offer and we look forward to contribute to future
innovations in virtual instrumentation and automation technology.
VISION OF THE ORGANISATION
 "Engineering Manpower to provide global solutions".

ADRESS: #2/3, 8th 'A' Cross, M. T. Street, Vasanthnagar, Bengaluru - 560052, INDIA

CONTACT NUMBER: +91-80-40948484

3
 3. CHAPTER
3.1 Industrial Internet of Things in Graphical System Design:

Remote Monitoring & Control – Mobile Device:

The evolution of the web and mobile devices has changed how we interact with our
surroundings. Remote monitoring and control of LabVIEW-based systems from a mobile
platform is an increasingly important aspect to a flexible and efficient system. Data
Dashboard for LabVIEW is a mobile application that enables the creation of custom user
interfaces that can monitor and control LabVIEW applications remotely. This tutorial
describes some of the more advanced capabilities of Data Dashboard and assumes some
familiarity with the product.

Shared Variables in Applications with Data Dashboard:

Shared variables interact with the host application through the LabVIEW Shared Variable
Engine (SVE) and the updates are handled through the Publish Subscribe Protocol (NI-
PSP). For Data Dashboard to have access to these variables, they must be deployed to the
SVE through a library project item. Each variable in the library will be deployed and the
SVE will reserve a memory space for it. They will remain in the memory space as part of
the LabVIEW process whether Data Dashboard is interacting with them or not. With
larger data types and data types that can vary in size (strings and arrays) it is important to
remember that mobile devices are very different from a full development system.

Fig: 3.1

4
LabVIEW code:

Fig: 3.2
Data Dashboard:

Fig: 3.3

TCP/IP Communication for Local Network:

Internet Protocol (IP), User Datagram Protocol (UDP), and Transmission Control
Protocol (TCP) are the basic tools for network communication. The name TCP/IP comes
from two of the best-known protocols of the internet protocol suite, the Transmission
Control Protocol and the Internet Protocol. With TCP/IP you can communicate over
single networks or interconnected networks (Internet).

5
TCP/IP Server:

Fig: 3.4

TCP/IP Client:

Fig: 3.5

LabVIEW users can develop custom applications for TCP/IP communication.

The programmer is responsible for developing both the client and the server.

Because anyone can initiate a connection to a server, you might want server access
control. The following block diagram shows how the server uses the remote address
output value of the TCP Listen VI to determine whether a remote client has permission to
access the server.

Cloud Communication:

All cloud computing platforms securely send and receive data, use strong authentication
and authorization methods, and use encryption. The majority also have audit capabilities.
Communication protocols are responsible for the network connectivity to the server.
Protocols like Wi-Fi, Ethernet, cellular, and LoRaWAN are all communication protocols
that provide this level of connectivity. Application protocols sit on top of them to
communicate application-specific messages.

6
Multiple standards handle the communication between devices and the cloud. As
application requirements differ, specific IoT protocols have been developed and therefore
the confusion is understandable. Protocols may even have multiple implementations and
IoT platforms may have proprietary IoT solutions. To provide a universal solution,
devices, applications, and platforms need to be interoperable.

Cloud computing refers to a flexible way of delivering hardware, software, or data

resources via the network on a user’s request. This is opposite to the use of running a
software application on a local computer.

Google Firebase:

The Firebase Realtime Database is a cloud-hosted database. Data is stored as JSON and
synchronized in real-time to every connected client. When you build cross-platform apps
with our iOS, Android, and JavaScript SDKs, all of your clients share one Realtime
Database instance and automatically receive updates with the newest data.

LabVIEW Program:

Fig: 3.6

Google Firebase:

7
Web-based Communication with a LabVIEW Application:

A web client can exchange data with a remote LabVIEW stand-alone application over a
network through LabVIEW Web services. A Web service consists of VIs and other files
running on a server that respond to HTTP requests from clients.

Fig: 3.7
Web services are useful in the following situations:

Users can invoke the Web service VIs with any HTTP-capable web client, including a
standard web browser, to exchange data using a URL and standard HTTP methods such
as POST. For example:

• Uploading new parameters to an application

• Retrieving current state or status

Users can remotely monitor and control embedded applications using custom thin clients.
For example:

• Updating application state

8
 • Starting or stopping a process

You can conduct application-to-application data exchange between numerous HTTP-

capable devices and software from both National Instruments and third parties. For
example:

• Connecting to non-LabVIEW clients

• Implementing security and authentication

3.2 Machine Learning – Graphical System Design

Methods of Machine Learning:
• Supervised Learning
• Unsupervised Learning
Supervised Learning:
Supervised learning refers to the generalization of the relationship (function) between the
input data and their corresponding outputs (labels). The relationship (function) is learned
through a training set of examples, each of which is a pair of an input data and a desired
output. During the training, the error between the actual and the desired outputs is
frequently fed back into the system for tuning the system parameters according to certain
learning rule. After the training, the performance of the learned relationship (function)
should be evaluated on a test set (of examples) that is separate from the training set.

Fig: 3.8
Supervised learning is useful for pattern recognition, function regression, etc. One
example of applications is recognition of handwriting numbers. A supervised classifier
can be trained with a reservoir of handwriting numbers, each with a label (the true
9
numbers it represents). Having been validated on a separate test set, the trained classifier
can be used for fast and accurate recognition of future handwriting numbers.

Unsupervised Learning:

Unsupervised learning refers to the problems of revealing hidden structure in unlabeled

data. Since the data are unlabeled, there is no error signal fed back to the learner in the
algorithm. This distinguishes unsupervised learning from supervised learning.

Fig: 3.9
Clustering is one of the main and important approaches of unsupervised learning.
Clustering means the assignment of class memberships to a set of objects so that similar
objects are assigned into the same class and dissimilar ones are assigned into different
classes. Each class often represents a meaningful pattern in the respective problem.
Clustering is thereby useful for identification of different patterns in data. For example, in
image processing, clustering can be used to divide a digital image into distinct regions for
border detection or object recognition.

B) Prediction:

“Prediction” refers to the output of an algorithm after it has been trained on a historical
dataset and applied to new data when forecasting the likelihood of a particular outcome,
such as whether or not a customer will churn in 30 days. The algorithm will generate
probable values for an unknown variable for each record in the new data, allowing the
model builder to identify what that value will most likely be.

BP Prediction using k-NN Algorithm

10
The k-NN algorithm is used to predict new data based on the trained data set. The health
status of the patients and their BPM data are structured in a database and it is fed to the k-
NN algorithm to train. Once the algorithm is trained if any new BPM data is given to the
trained k-NN algorithm, it then predicts the health status.

Fig: 3.10

k-Nearest Neighbour Algorithm

K-NN algorithm assumes the similarity between the new data and available data and put
the new case into the category that is most similar to the available categories.

Fig: 3.11

k-NN Algorithm Breakdown:

1. Load the known data & its labels (class) 2. Initialize K to choose the number of
neighbour’s

11
2. Load the new data.

3. Calculate the distance between the new data with each known data points.

4. Sort the ordered collection and indices from smallest to largest by the distances.

5. Pick the first K entries from the sorted collection

6. Get the labels of the selected K entries

7. Return the mode of the K label which has the maximum entry.

k-NN Algorithm Implementation in LabVIEW

Fig: 3.12
Health Status Prediction Implementation:

1. Load the csv data set using File IO.

2. Separate data & labels using array functions.
3. Feed BPM data & labels to the k-NN function.
4. Feed new BPM data for which the health status should be predicted
5. Take the predicted label out & display.

12
 Fig:
3.13
C) Optical
Character
Recognition:

Optical character
recognition or
optical character
reader (OCR) is
the electronic or mechanical conversion of images of typed, handwritten or printed text
into machine-encoded text, whether from a scanned document, a photo of a document, a
scene-photo (for example the text on signs and billboards in a landscape photo) or from
subtitle text superimposed on an image.

LabVIEW Implementation:

Step 1: Training – OCR Interface

Fig: 3.14

Step 2: Testing

13
 Fig: 3.15

Step 3: Deployment

Fig: 3.16

Fig: 3.17

14
D. Image Segmentation:

In digital image processing and computer vision, image segmentation is the process of
partitioning a digital image into multiple segments (sets of pixels, also known as image
objects). The goal of segmentation is to simplify and/or change the representation of an
image into something that is more meaningful and easier to analyse.

LabVIEW Implementation:

Fig: 3.18

LabVIEW Front Panel:

15
 Fig: 3.19
(D) Waveform Identification:

Step 1: Data Collection with Extracted Features

Fig: 3.20

Step 2: Training

16
 Fig: 3.21

Fig: 3.22

Step 3: Test & Deployment

Fig: 3.23

Test Data Generator

17
Fig: 3.24

18
 4. ASSESMENTS & CONCLUSION
Assignment 1: Train Berth
Front Panel

Fig: 4.1
Block Diagram

Fig: 4.2

19
Assignment 2: Boolean Counter
Front Panel

Fig: 4.3
Block Diagram

20
Fig: 4.4

21