VISVESVARAYA TECHNOLOGICAL UNIVERSITY

“Jnana Sangama” Belagavi -590018, Karnataka.

MINI PROJECT WORK REPORT

ON
IMPLEMENTATION OF UNDERGROUND MINING ROBOT
USING MACHINE LEARNING
Submitted in the partial fulfillment of the requirement for the award of degree

BACHELOR OF ENGINEERING
IN
ELECTRONICS AND COMMUNICATION ENGINEERING

Submitted by:
BHARGAVI B N (1EW20EC010)
MUKTHA M K (1EW20EC037)
SAGARI P GOWDA (1EW20EC050)
SOUJANYA CHETHANA (1EW20EC058)

UNDER THE GUIDANCE OF Mrs. Manasa S Assistant Professor Dept. of ECE, EWIT

EAST WEST INSTITUTE OF TECHNOLOGY

DEPARTMENT OF ELECTRONICS AND COMMUNICATION
ENGINEERING BENGALURU-560091

2023-2024
EAST WEST INSTIUTE OF TECHNOLOGY
No.63, Off Magadi Road, Vishwaneedam Post, Bangaluru-560091
Department of Electronics and Communication Engineering
 CERTIFICATE

This is to certify that the mini project work report entitled “Implementation of Underground
mining robot using machine learning” is a bonafide work carried out by BHARGAVI B N
(1EW20EC010), MUKTHA M K (1EW20EC037), SAGARI P GOWDA (1EW20EC050),
SOUJANYA CHETHANA (1EW20EC058) in partial fulfillment for the award of degree of
Bachelor of Engineering in Electronics and Communication of Visvesvaraya Technological
University, Belagavi during the year 2023-2024. This project work reporthas been approved as it
satisfies the academic requirement in respect of project work prescribed for Bachelor of
Engineering Degree.

……………………............................. ……………………………………
…………………………………………….. ………………

Signature of Guide Signature of HOD Signature of Principal

Mrs. Manasa S Dr. S G Hiremath Dr.K Channakeshavalu
Assistant Professor. H.O.D., Dept of ECE Principal,
Dept of ECE, EWIT, Bengaluru EWIT, Bengaluru
EWIT, Bengaluru
External Viva

Name of the Examiners Signature with Date

1.

2.
 ACKNOWLEDGEMENT

Any achievement, be it scholastic or otherwise does not depend solely on the individual efforts
but on the guidance, encouragement and cooperation of intellectuals, elders and friends. A
number of personalities, in their own capacities have helped us in carrying out this project
work.
We would like to take this opportunity to thank them all.

With proud gratitude we thank God almighty for all the blessings showered on us and for
being able to complete the project work successfully.

First and foremost, we would like to thank Dr. K Channakeshavalu, Principal, EWIT,
Bengaluru, for his moral support towards completing our project work.

We would like to thank, Dr. S G Hiremath, Professor and Head of Department of ECE,
EWIT, Bengaluru, for his valuable suggestions and expert advice.

We deeply express our sincere gratitude to our guide Mrs. Manasa S, Assistant Professor,
Department of ECE, EWIT, Bengaluru for her valuable guidance throughout the project work
and guiding us to organize the report in a systematic manner.

We extend our thanks to the Mini Project coordinators Mr.Kotresh H M, Associate Professor,
Mrs. Manasa S, Assistant Professor, for their constant support, guidance and encouragement
for project work.

We thank our Parents, and all the faculty members of Department of Electronics and
Communication Engineering for their constant support and encouragement.

Last, but not the least, we would like to thank our peers and friends who provided us with
valuable support and suggestions.
BHARGAVI B N (1EW20EC010)

MUKTHA M K (1EW20EC037)

SAGARI P GOWDA (1EW20EC050)

SOUJANYA CHETHANA (1EW20EC058)

iii
 DECLARATION

We BHARGAVI B N (1EW20EC010), MUKTHA M K (1EW20EC037), SAGARI P GOWDA

(1EW20EC050) and SOUJANYA CHETHANA (1EC20EC058), students of 6th semester
Bachelor of Engineering in the Department of Electronics & Communication Engineering of East
West Institute of Technology, Bengalore-560091, hereby declare that the project entitled
“IMPLEMENTATION OF UNDERGROUND MINING ROBOT USING MACHINE
LEARNING” has been carried out by us under the supervision of Internal Guide Prof Manasa S ,
Assistant Professor, Department of Electronics & Communication Engineering, EWIT, Bangalore
submitted in the fulfillment of the course requirement for the award of the degree of Bachelor of
Engineering in Electronics & Communication Engineering of Visvesvaraya Technological
University during the academic year 2023-2024.

PLACE: BANGALORE

DATE:

NAME USN SIGNATURE

BHARGAVI B N 1EW20EC010 MUKTHA M K 1EW20EC037

SAGARI P GOWDA 1EW20EC050 SOUJANYA CHETHANA
1EW20EC058

iv
 ABSTRACT
Underground mining operations pose significant safety risks, making early detection of hazards and
real-time monitoring of worker health crucial. This abstract presents a novel Undermining Detection
Robot (UDR) designed to enhance safety in underground mining environments. The UDR employs
Arduino microcontrollers to interface with a suite of sensors, including metal sensors, fire sensors,
gas sensors, ultrasonic sensors, and moisture sensors. These sensors provide real-time data on
potential hazards such as gas leaks, fires, and unstable underground conditions. Additionally, the
robot incorporates a water pump to address moisture related issues that may arise in mining
operations. The UDR is equipped with an ESP32 CAM module, stream video from the mining site.
This feature enhances remote monitoring and situational awareness for mine operators. The data
collected from these sensors and the ESP32 CAM are transmitted to the cloud-based IoT platform,
ThingSpeak, for real-time data analysis and visualization. The UDR also integrates sensors for
monitoring personnel health parameters, including heartbeat, temperature, and Spo2 levels. This
functionality ensures that workers' well-being is constantly monitored, and any anomalies or
emergencies are promptly detected. The final layer of innovation in this system is the application of
machine learning using Python. The collected data is analyzed using machine learning algorithms to
predict potential safety hazards or health related issues. These predictions are then used to trigger
immediate responses or alert personnel to take appropriate actions.

Keywords: UDR, sensors, ESP32CAM, Thingspeak, ESP32, Arduino meg

v
 TABLE OF CONTENTS

TITLE

ACKNOWLEDGEMENT PAGE NO

DECLARATION
iii
ABSTRACT
iv
TABLE OF CONTENT
v
LIST OF FIGURES
vi-viii ix-
CHAPTER 1: INTRODUCTION x

1.1 PROBLEM STATEMENT 1-3

1.2 OBJECTIVES 2

1.3 MOTIVATION 2

CHAPTER-2: LITERATURE SURVEY 3

CHAPTER-3: METHODOLOGY 4-5

3.1 BLOCK DIAGRAM OF UDR ROBOT 6-8

3.2 BLOCK DIAGRAM OF HEALTH BAND 6-7

CHAPTER-4: COMPONENTS REQUIREMENT 8

4.1 HARDWARE COMPONENTS REQUIREMENT 9-25

4.1.1 ARDUINO MEGA 9-23

4.1.2 DC MOTOR 9-10

 4.1.3 LCD DISPLAY
11-12
4.1.4 SENSORS
12-17
4.1.5 ESP32 CAM
17
4.1.6 RELAY
17-18
4.1.7 WATER PUMP
19
4.1.8 BLUETOOTH
20
4.1.9 H-BRIDGE
21
4.1.10 GSM MODULE
21-22
4.1.11 BATTERY
23
4.2 SOFTWARE COMPONENTS REQUIREMENT
24-25
4.2.1 ARDUINO IDE
24
4.2.2 EMBEDDED C
24
4.2.3 PYTHON
24
4.2.4 ANACONDA NAVIGATOR
24

4.2.5 ZIGBEE
24
4.2.6 TELEGRAM BOTS
25
CHAPTER-5: ADVANTAGES AND APPLICATIONS

5.1 ADVANTAGES 26

5.2 APPLICATIONS 26
 27-33

CHAPTER-6: RESULT 34-35

34
CHAPTER-7: CONCLUSION AND FUTURESCOPE 35
7.1 CONCLUSION
7.2 FUTURESCOPE

REFERENCES
 LISTS OF FIGURES

Title Page no
3.1 BLOCK DIAGRAM OF UDR 6

3.2 BLOCK DIAGRAM OF HEALTH BAND 8

4.1 ARDUINO MEGA 9
4.2 DC MOTOR 10
4.3 LCD DISPLAY 11
4. LCD PINOUT 11
4.5 FIRE SENSORS 12
4.6 SMOKE SENSOR 12
4.7 ULTRASONIC SENSOR 13
4.8 METAL SENSOR 13
4.9 HEART BEAT SENSOR 13
4.10 TEMPERATURE SENSOR 13
4.11 SPO2 13
4.12 MOISTURE SENSOR 13
4.13 ESP32 CAM 16
4.14 ESP32 CAM PINOUT 16
4.15 RELAY 17
4.16 RELAY PINOUT 18
4.17 WATER PUMP 19

4.18 BLUETOOTH 19

4.19 BLUETOOTH PINOUT 20

4.20 H-BRIDGE 21
4.21 GSM MODULE 22

4.22 BATTERY 23
4.23 TELEGRAM BOTFATHER 25
27
6.1 PROTOTYPE OF UDR
28
6.2 OBSTACLE DETECTION BY UDR
6.3 METAL DETECTED BY UDR 28

6.4 MOISTURE DETECTED BY UDR 29

6.5 GAS DETECTED BY UDR 29

6.6 FIRE DETECTED BY UDR 29

6.7 PROTOTYPE OF HEALTH BAND 30

6.8 OUTPUT OBTAINED ON IOT PLATFORM AND 31

 MACHINE LEARNING 32

6.9 OUTPUT OBTAINED ON ESP32 CAM

x
 Implementation of underground mining robot using machine learning 2023-24

CHAPTER 1

INTRODUCTION

The mining industry is crucial for the global economy, providing essential resources for
various sectors. However, it is also one of the most hazardous industries, with underground
mining operations posing significant safety challenges. To mitigate these risks and enhance
safety standards, innovative technologies are being developed to monitor and detect potential
hazards in real-time. This introduction presents an advanced solution, the "Undermining
Detection Robot," which leverages a range of cutting-edge technologies, including Arduino
microcontrollers, a diverse set of sensors (metal, fire, gas, ultrasonic, moisture), a water pump,
ESP32 CAM module, and real-time monitoring of personnel's health parameters like heartbeat,
temperature, Spo2 levels. The system is further enhanced through the integration of an IoT
platform ThingSpeak , and the application of machine learning using Python. Mining
operations are often carried out in harsh and unforgiving environments, with numerous safety
concerns. Underground mines are particularly prone to hazards such as gas leaks, fires,
collapsing structures, and unstable conditions. Detecting these hazards in a timely manner is
essential to prevent accidents and protect the lives of the miners. The Undermining Detection
Robot is designed to tackle these challenges comprehensively. It is equipped with a range of
sensors, including metal sensors to identify potential obstructions or dangerous metallic
objects, fire sensors to detect fires, gas sensors to monitor gas levels, humidity sensors to
measure environmental moisture, and moisture sensors to address potential water-related
issues. The integration of these sensors provides real-time data on the underground conditions,
enabling quick responses to potential threats. In addition to environmental monitoring, the
robot also considers the well-being of personnel working in these hazardous environments. It
incorporates sensors for monitoring health parameters like heartbeat, temperature, and Spo2
levels. This not only ensures the safety of miners but also facilitates immediate responses in
case of health emergencies. The Undermining Detection Robot is not just a data collection
tool; it also embraces IoT technology through the ESP32 CAM module. This module allows
the robot to capture images and stream video from the mining site, enabling remote monitoring
and enhanced situational awareness for mine operators. The collected data, both from
environmental sensors and the ESP32 CAM, is transmitted to the cloud-based IoT platform,
ThingSpeak,for real-time data analysis and visualization. Furthermore, the system integrates
machine learning using Python. This advanced technology processes the data collected from

Dept of ECE, EWIT Page|1

 Implementation of underground mining robot using machine learning 2023-24
the sensors, applies predictive algorithms, and learns from historical data to identify potential
safety hazards or health-related issues. These predictions are invaluable in ensuring that timely
responses and appropriate actions are taken, thereby reducing accidents and improving overall
safety standards in underground mining operations. In summary, the Undermining Detection
Robot represents a significant leap forward in mining safety technology. By combining
multiple sensors, IoT capabilities, and machine learning, this innovative system offers a
proactive approach to hazard detection and worker health monitoring. Its potential to
revolutionize safety standards in underground mining operations is promising, as it aims to
reduce accidents and enhance the well-being of miners, ultimately making mining operations
safer and more efficient.

1.1 PROBLEM STATEMENT

The underground mining industry plays a crucial role in resource extraction but presents
significant challenges including safety Hazards, inefficiencies and limitation in human
accessibility. To address these issues there is need for development of worker safety, real time
monitoring and data collections, autonomous navigation and adaptation to dynamic
underground condition thereby improving overall coverage of mining activities.

1.2 OBJECTIVES
• Develop a robust system for the real-time detection and monitoring of potential
underground hazards, including gas leaks, fires, metal obstructions, and environmental
conditions.
• Utilize a range of sensors, including gas sensors, fire sensors, metal sensors, ultrasonic
sensors, and moisture sensors, to comprehensively monitor the underground
environment.
• Establish an IoT connection with the ThingSpeak platform to transmit sensor data for
real-time analysis and visualization, enabling mine operators to make informed
decisions promptly.

• Implement machine learning algorithms using Python to process sensor data and
predict potential safety hazards or health-related issues, increasing the system's
predictive accuracy over time.

Dept of ECE, EWIT Page|2

 Implementation of underground mining robot using machine learning 2023-24
1.3 MOTIVATION
• To replace humans with robots in dangerous jobs, enhance efficiency and ultimately
optimize mining operations.

• By implementing wearable devices with sensors can monitor miner’s health.

Dept of ECE, EWIT Page|3

 Implementation of underground mining robot using machine learning 2023-24

CHAPTER 2

LITERATURE SURVEY
2.1 Internet of things based coal mine safety monitoring system by T.Thilagavathi ,Dr.L.
Arockiam in 2023 (IJARCCE)
The safety of miners in the mining environment is a major challenge. A miner's health and life
are exposed to many critical issues. Underground mining requires continuous monitoring of
every parameter like methane gas, high temperature, fire accidents monitored. Disasters in
coal mines are due to the complexity of the mining environment and the various tasks carried
out in coal mines. So, it is very important to monitor the working environment of coal mines.
Coal mine monitoring systems are wired network systems that play an important role in the
safe production of coal mines. Due to the continuous expansion and deepening of the
exploitation areas of coal mines, many paths are turning into blind areas, which have a lot of
hidden dangers. To overcome this problem, advanced mechanisms have been proposed in a
coal mine safety monitoring system that can improve the monitoring level of production safety
and reduce accidents in coal mines.

2.2 Calibration of a multi-sensor wheeled robot for the 3-D mapping of underground
mining tunnels by P. Trybala a, J. Szrek b, F. Remondino c , J. Wodecki a, R. Zimroz a in
2022 (ISPRS)
Mobile robotic systems show great potential for automation and a vast selection of tasks in
everyday life and industrial facilities. The most important fields of application are related to
limiting human exposure to harmful conditions and greatly increasing work safety, among
other cost-driven factors. One of these field is the mining industry. While in surface mining
automation of several tasks is already being done e.g., using drones, in GNSS-denied
underground environments using such innovation at a market-ready level is significantly more
challenging, also due to the difficulties of spatial data acquisition needed, e.g., for navigation.
This paper presents a system calibration procedure (6D pose estimation) of a multi-sensor
mobile robot developed for inspecting underground mining tunnels.

Dept of ECE, EWIT Page|4

 Implementation of underground mining robot using machine learning 2023-24

2.3. Design of An Underground mine safety using embedded and IOT and thingspeak by
N Madhuram,V Viyashini,M Arun kumar in 2021(IJAS)

Underground workers of coal mines are prone to several hazardous conditions during their
work. These may lead to serious injuries and at times loss of life. These incidents have direct
and indirect effects on employees and employers. Accidents in underground mines can often
have disastrous consequences. Risk assessment depends on efficiency of hazard identification
and hence an innovative approach is required that focuses on these safety issues and the
improvement in productivity and cost reduction in underground mines. This study presents a
design that can effectively detect underwater using different sensors.

2.4 IOT based smart mine safety system using Arduino by S.Sujitha Dr.J.B.Shajili Loret;
Mrs.D.Merlin Gethsy in 2020 (IJCSMC)

The mining safety system ensures the hazard free working environment. The main purpose of
the project is to reduce the mining accident and improve the working conditions. IoT based
mine safety system has various sensors for several purpose and the Arduino Uno is used for
better reliability. All the sensors are together considered as a unit and this system is placed in
the mining industry. The various parameters such as temperature and humidity value, light
intensity level, poisonous gas level in the air and trace of flame are observed from the working
area by the sensors. These sensors values are sent to the Arduino for further process and if the
values exceed the threshold level an alert message is sent to the mining control room.

2.5 Autonomous Robots and the internet of things in underground mining by Helmut
Mischo, Franziska Günther in 2018

The mining robot, Julius was developed in a previous project and is used as a prototype. The
wheeled vehicle has a robotic arm with a 3-finger-gripper, different laser scanners, cameras,
wireless router and lighting systems. The robot can be operated via teleoperation or partially
autonomously. Determining the first scenarios for applications of robots and IoT underground
is a step towards a fully automated mine. In the project ARIDuA, some of these possible
application scenarios were partially developed and successfully tested in a deep mine. The
next steps are further development of the technologies and connecting the robot with the IoT
infrastructure underground.

Dept of ECE, EWIT Page|5

 Implementation of underground mining robot using machine learning 2023-24
CHAPTER 3
METHODOLOGY

The "Undermining Detection Robot," which leverages a range of cutting-edge technologies,

including Arduino microcontrollers, a diverse set of sensors (metal, fire, gas, humidity,
moisture), a water pump, ESP32 CAM module, and real-time monitoring of personnel's health
parameters like heartbeat, temperature, Spo2 levels. The system is further enhanced through the
integration of an IoT platform, ThingSpeak, and the application of machine learning using
Python. Mining operations are often carried out in harsh and unforgiving environments, with
numerous safety concerns. When the power supply is provided the system, it energizes the
components. With the help of DC motor, the movement of robot can be navigated through
bluetooth. The live streaming can be done from mining sites using ESP32CAM module. The
sensors are interfaced with Arduino mega such as metal sensor, ultrasonic sensor and moisture
when these sensors are actively senses the parameters then buzzer turn ON and corresponding
LED glows. The fire sensor detect fire it is extinguished using water pump by relay and exhaust
fan is switched ON when hazardous gas has been detected. The health band consists of ESP32
module interfaced with temperature, heartbeat and Spo2 sensors. The health band mainly
provides the information on health parameter of workers. The output data of these parameters
are uploaded to cloud and then displayed on thinkspeak. Finally, through Zigbee the
informationgets transferred to UDR. Thus, the UDR will analyses the Spo2 level, temperature
and heartbeatof the miners and gives a preventionary measures on serious condition the
immediate messages/calls are sent to workstation.
3.1 BLOCK DIAGRAM OF UDR

Dept of ECE, EWIT Page|6

 Implementation of underground mining robot using machine learning 2023-24

Fig.: 3.1 Block diagram of UDR

Dept of ECE, EWIT Page|7

 Implementation of underground mining robot using machine learning 2023-24

3.1.1 SYSTEM APPROACH

3.1.1.1 System Design and Configuration: Define the overall architecture of the
Undermining Detection Robot. Select suitable hardware components, including Arduino
microcontrollers, metal sensors, fire sensors, gas sensors, humidity sensors, moisture sensors,
a water pump, and the ESP32 CAM module. Design the physical structure and mobility
system of the robot to navigate the underground environment. Identify suitable sensors for
monitoring health parameters, such as heartbeat, temperature, and Spo2 levels.

3.1.1.2 Sensor Integration and Calibration: Integrate and calibrate the various sensors into
the robot's hardware. Ensure that each sensor provides accurate and reliable data, accounting
for any potential interferences or variations in the underground environment.

3.1.1.3 Remote Monitoring and Live Streaming: Integrate the ESP32 CAM module stream
Video from the underground mining site. Develop a user-friendly interface for mine operators
to access the live feed remotely.

BLOCK DIAGRAM OF HEALTH BAND

cloud THING
TEMPERATUR SPEAK

HEART BEAT
ESP32 ZIGBEE

SPO2 ANACONDA
NAVIGATOR

Fig 3.2 Block diagram of health band

Dept of ECE, EWIT Page|8

 Implementation of underground mining robot using machine learning 2023-24

CHAPTER 4

4
HARDWARE AND SOFTWARE REQUIREMENTS
4.1 HARDWARE COMPONENTS REQUIREMENT
4.1.1 Arduino Mega2560: The Arduino Mega is a microcontroller board based on the
ATmega1280 (datasheet). It has 54 digital input/output pins (of which 14 can be used as
PWM outputs), 16 analog inputs, 4 UARTs (hardware serialports), a 16 MHz crystal
oscillator,a USB connection, a power jack, an ICSP header, and a reset button. It contains
everything needed to support the microcontroller; simply connect it to a computer with a USB
cable or power it with a AC-to-DC adapter or battery to get started.
The Arduino Mega2560 can be powered via the USB connection or with an external power
supply. The power source is selected automatically. External (non-USB) power can come
either from an AC-to-DC adapter (wall-wart) or battery. The adapter can be connected by
plugginga 2.1mm center-positive plug into the board's power jack. Leads from a battery can
be insertedin the Gnd and Vin pin headers of the POWER connector.

Voltage and Current Specifications

• Operating voltage: 5 V
• Input Voltage 7-12 V (recommended)
• Input Voltage 6-20 V (limit for this board)
• DC Current per input/output pin: 20mA
• DC Current for 3.3 V pin: 50mA

Memory Specifications
• Flash Memory: 256 KB
• SRAM: 8 KB
• EEPROM: 4 KB

Dimension and weight

• Length of board: 101.52 mm
• Width of board: 53.3 mm
• Weight: 37 g

Dept of ECE, EWIT Page|9

 Implementation of underground mining robot using machine learning 2023-24

Fig 4.1 Arduino Mega2560

4.1.2 DC Motor: A DC motor is an electrical motor that uses direct current (DC) to produce
mechanical force. The most common types rely on magnetic forces produced by currents in
the coils. Nearly all types of DC motors have some internal mechanism, either
electromechanical or electronic, to periodically change the direction of current in part of the
motor. It is used for motion of robot.

Fig 4.2 DC Motor

Here we use two DC motors for the movement of rover. A DC motor is any of a class of
rotary electrical machines that converts direct current electrical energy into mechanical
energy.The most common types relyon the forces produced bymagnetic fields. Nearlyall types
of DCmotors have some internal mechanism, either electromechanical or electronic, to
periodically change the direction of current flow in part of the motor. DC motors were the
first form of motor widely used, as they could be powered from existing direct-current
lighting power distribution systems. A DC motor's speed can be controlled over a wide range,
using either a variable supply voltage or by changing the strength of current in its field
windings. Small DC motors are used in tools, toys, and appliances.

Dept of ECE, EWIT P a g e | 10

 Implementation of underground mining robot using machine learning 2023-24

4.1.3 LCD Display: The Liquid-Crystal library allows you to control LCD displays that are
compatible with the Hitachi HD44780 driver. There are many of them out there, and you can
usually tell them by the 16-pin interface. Frequently, an 8051 program must interact with the
outside world using input and output devices that communicate directly with a human being.
One of the most common devices attached to an 8051 is an LCD display. Some of the most
common LCDs connected to the 8051 are 16x2 and 20x2 displays. This means 16 characters
per line by 2 lines and 20 characters per line by 2 lines, respectively

Fig 4.3 LCD Display

The 44780 standard requires 3 control lines as well as either 4 or 8 I/O lines for the data bus.
The user may select whether the LCD is to operate with a 4-bit data bus or an 8-bit data bus.
If a 4-bit data bus is used the LCD will require a total of 7 data lines (3 control lines plus the
4 lines for the data bus). If an 8-bit data bus is used the LCD will require a total of 11 data
lines (3 control lines plus the 8 lines for the data bus).

Fig 4.4 LCD Pinout

The three control lines are referred to as EN, RS, and RW.

Dept of ECE, EWIT P a g e | 11

 Implementation of underground mining robot using machine learning 2023-24

The EN line is called "Enable." This control line is used to tell the LCD that you are sending
it data. To send data to the LCD, your program should make sure this line is low (0) and then
set the other two control lines and/or put data on the data bus. When the other lines are
completely ready, bring EN high (1) and wait for the minimum amount of time required by
the LCD datasheet (this varies from LCD to LCD), and end by bringing it low (0) again.

The RS line is the "Register Select" line. When RS is low (0), the data is to be treated as a
command or special instruction (such as clear screen, position cursor, etc.). When RS is high
(1), the data being sent is text data which should be displayed on the screen. For example, to
display the letter "T" on the screen you would set RS high.

The RW line is the "Read/Write" control line. When RW is low (0), the information on the
data bus is being written to the LCD. When RW is high (1), the program is effectively
querying (or reading) the LCD. Only one instruction ("Get LCD status") is a read command.
All others are writing commands--so RW will almost always be low. Finally, the data bus
consists of 4 or 8 lines (depending on the mode of operation selected by the user). In the case
of an 8-bit data bus, the lines are referred to as DB0, DB1, DB2, DB3, DB4, DB5, DB6, and
DB7.

4.1.4 Sensors: A sensor is a device that produces an output signal for the purpose of sensing
physical phenomenon. A sensor is a device, module, machine, or subsystem that detects events
or changes in its environment and sends the information to other electronics, frequently a
computer processor.

Fig 4.5 Fire sensor Fig 4.6 Smoke sensor

Dept of ECE, EWIT P a g e | 12

 Implementation of underground mining robot using machine learning 2023-24
Fig 4.7 Ultrasonic sensor Fig 4.8 Metal sensor

Fig 4.9 Heart beat sensor Fig 4.10 Temperature sensor

Fig 4.11 SPO2 Fig 4.12 Moisture sensor

4.1.4.1 Fire sensor: Is a device that detects the presence of fire in an environment. Its primary
function is to provide an early warning of a potential fire hazard, allowing for prompt action
to be taken to mitigate the risk and protect lives and property. Fire sensors can be found in
residential, commercial, and industrial buildings, as well as in vehicles and various other
settings where fire detection is crucial for safety.

4.1.4.2 Smoke sensor: A smoke sensor, also known as a smoke detector or smoke alarm, is a
type of sensor that is specifically designed to detect the presence of smoke particles in the air.
Smoke sensors are essential components of fire detection systems and are commonly used in

Dept of ECE, EWIT P a g e | 13

 Implementation of underground mining robot using machine learning 2023-24

residential, commercial, and industrial buildings to provide early warning of potential fire
hazards. When smoke is detected, the sensor triggers an alarm, alerting occupants to the
presence of smoke and allowing them to take appropriate action, such as evacuating the
premises or extinguishing the fire. Smoke sensors are available in various types, including
ionization, photoelectric, and dual-sensor models, each with its own method of detecting
smoke particles.

4.1.4.3 Ultrasonic sensor: An ultrasonic sensor is a type of sensor that uses sound waves
with frequencies higher than the audible range of humans (typically above 20 kHz) to detect
the presence or distance of objects. These sensors typically consist of a transmitter and a
receiver. The transmitter emits ultrasonic waves, which bounce off objects in their path and
are then detected by the receiver. By measuring the time it takes for the ultrasonic waves to
travel to the object and back, the sensor can calculate the distance to the object. Ultrasonic
sensors are commonly used in various applications, including distance measurement, object
detection, and proximity sensing in robotics, automotive systems, industrial automation, and
more.

4.1.4.4 Metal sensor: A metal sensor, also known as a metal detector, is a device that is
designed to detect the presence of metal objects in its vicinity. Metal detectors typically
consist of a coil of wire through which an electric current is passed, creating a magnetic field.

4.1.4.5 Heart beat sensor: A heart rate sensor, also known as a heart rate monitor or pulse
sensor, is a device that measures a person's heart rate in real-time. It typically works by
detecting the electrical signals produced by the heart as it beats or by sensing the pulse of
blood flow through blood vessels. Heart rate sensors are commonly used in fitness trackers,
smartwatches, medical devices, and sports equipment to monitor heart rate during exercise,
track overall cardiovascular health, and provide feedback to users in real-time.
4.1.4.6 Temperature sensor: A temperature sensor is a device that measures the temperature
of its surroundings and converts it into a corresponding electrical signal or output. These
sensors are widely used in various applications to monitor and control temperature levels in
environments, equipment, and processes. Temperature sensors are used in a wide range of
industries and applications, including HVAC systems, automotive engines, medical devices,
industrial processes, and environmental monitoring, among others. They play a crucial role in
ensuring safe and efficient operation by providing accurate temperature measurements and
enabling temperature control systems to maintain desired setpoint.

Dept of ECE, EWIT P a g e | 14

 Implementation of underground mining robot using machine learning 2023-24

4.1.4.7 SPO2: An SPO2 sensor, also known as a pulse oximeter sensor, is a medical device
used to measure the oxygen saturation level in a person's blood. SpO2 stands for peripheral
capillary oxygen saturation. The sensor typically consists of a small clip or probe that is
attached to a person's finger, earlobe, or other suitable body part. The amount of light
absorbed by the oxygenated and deoxygenated hemoglobin in the blood is then measured by a
photodetector in the sensor. SpO2 sensors are commonly used in medical settings such as
hospitals, clinics, and emergency departments to monitor patients' oxygen levels, especially
those with respiratory conditions, during surgery, or in critical care situations. They are also
used in home healthcare settings for continuous monitoring of patients with chronic
respiratory conditions.

4.1.4.8 Moisture sensor: A moisture sensor, also known as a humidity sensor or hygrometer,
is a device that measures the moisture content or relative humidity of its surroundings. These
sensors are commonly used in various applications to monitor and control humidity levels in
environments, materials, and processes. Moisture sensors are used in a wide range of
industries and applications, including agriculture,building automation, HVAC systems, food
processing, pharmaceuticals, and environmental monitoring. They play a crucial role in
maintaining optimal moisture levels to ensure product quality, prevent damage, and promote
human comfort and safety.

4.1.5 ESP32 Cam: ESP32-CAM is a low-cost ESP32-based development board with onboard
camera, small in size. The board integrates WiFi, traditional Bluetooth and low power BLE,
with 2 high- performance 32-bit LX6 CPUs. Here are some potential ways one might
undermine the functionality of an ESP camera:
Exploiting Firmware Vulnerabilities: Like any software, the firmware running on the ESP
microcontroller may have vulnerabilities that could be exploited to gain unauthorized access
or control over the device. This could involve techniques such as buffer overflow attacks,
code injection, or exploiting weak authentication mechanisms.

Network Attacks: If the ESP camera streams data over a network connection, it could be
vulnerable to network-based attacks. For example, an attacker might intercept or manipulate
the data being transmitted, launch denial-of-service attacks to disrupt communication, or
attempt to gain unauthorized access to the device through its network interface.

Dept of ECE, EWIT P a g e | 15

 Implementation of underground mining robot using machine learning 2023-24

Fig 4.13 ESP32 Cam

Fig 4.14 ESP32 Cam Pinout

Features of ESP32 CAM

• Onboard ESP32-S module, supports WiFi + Bluetooth

• OV2640 camera with flash
• Onboard TF card slot, supports up to 4G TF card for data storage
• Supports WiFi video monitoring and WiFi image upload
• Supports multi sleep modes, deep sleep current as low as 6mA
• Control interface is accessible via pin-header, easy to be integrated and embedded into
userproducts
Specifications

• WIFI module: ESP-32S

• Processor: ESP32-D0WD
• Built-in Flash: 32Mbit
• RAM: Internal 512KB + External 4M PSRAM
• Antenna: Onboard PCB antenna

Dept of ECE, EWIT P a g e | 16

 Implementation of underground mining robot using machine learning 2023-24
• WiFi protocol: IEEE 802.11 b/g/n/e/i
• Bluetooth: Bluetooth 4.2 BR/EDR and BLE
• WIFI mode: Station / SoftAP / SoftAP+Station
• Security: WPA/WPA2/WPA2-Enterprise/WPS
• Output image format: JPEG (OV2640 support only), BMP, GRAYSCALE
• Supported TF card: up to 4G
• Peripheral interface: UART/SPI/I2C/PWM
• IO port: 9
• UART baud rate: default 115200bps
• Power supply: 5V
• Operating temperature: -20 ℃ ~ 85 ℃
• Storage environment: -40 ℃ ~ 90 ℃, <90%RH
• Dimensions: 40.5mm x 27mm x 4.5mm

4.1.6 Relay: A relay module is a relay that's been mounted on a board with other
components to provide isolation and protection. Current flowing through the coil of the relay
creates a magnetic field which attracts a lever and changes the switch contacts. The coil
current can be on or off so relays have two switch positions and they are double throw
(changeover) switches.

Fig 4.15 Relay

Specification of relay

• Supply voltage – 3.75V to 6V

• Quiescent current: 2mA
• Current when the relay is active: ~70mA
• Relay maximum contact voltage – 250VAC or 30VDC
• Relay maximum current – 10A

Dept of ECE, EWIT P a g e | 17

 Implementation of underground mining robot using machine learning 2023-24

Fig 4.16 Relay Pinout

First is the screw terminal block. This is the part of the module that is in contact with mains so
a reliable connection is needed. Adding screw terminals makes it easier to connect thick mains
cables, which might be difficult to solder directly. The three connections on the terminal block
are connected to the normally open, normally closed, and common terminals of the relay.The
second is the relay itself, which, in this case, is a blue plastic case. Lots of information can be
gleaned from the markings on the relay itself. The part number of the relay on the bottom says
“05VDC”, which means that the relay coil is activated at 5V minimum – any voltage lower
than this will not be able to reliably close the contacts of the relay. There are also voltage and
current markings, which represent the maximum voltage and current, the relay can switch. For
example, the top left marking says “10A 250VAC”, which means the relay can switch a
maximum load of 10A when connected to a 250V mains circuit. The bottom left rating says
“10A 30VDC”, meaning the relay can switch a maximum current of 10A DC before the
contacts get damaged.

4.1.7 Water Pump: Water pump controlled by an Arduino microcontroller is a type of system
that uses an Arduino to control the operation of a water pump.
A 5V water pump is a type of pump designed to be powered by a 5-volt power supply. These
pumps are commonly used in small-scale projects and applications where low voltage
operation is required.

Dept of ECE, EWIT P a g e | 18

 Implementation of underground mining robot using machine learning 2023-24

Fig 4.17 Water Pump

4.1.8 Bluetooth: The Arduino BT is a microcontroller board originally was based on the
ATmega168, but now is supplied with the 328P (datasheet) and the Bluegiga WT11 Bluetooth.

Fig 4.18 Bluetooth

The HC-05 is a popular module which can add two-way (full-duplex) wireless functionality
this module to communicate between two microcontrollers like Arduino or communicate
with any device with Bluetooth functionality like a Phone or Laptop. There are many android
applications that are already available which makes this process a lot easier. The module
communicates with the help of USART at 9600 baud rate hence it is easy to interface with
any microcontroller that supports USART. We can also configure the default values of the
module by using the command mode. So if you looking for a Wireless module that could
transfer data from your computer or mobile phone to microcontroller or vice versa.

Dept of ECE, EWIT P a g e | 19

 Implementation of underground mining robot using machine learning 2023-24

Fig 4.19 Bluetooth Pinout

Specifications

• Serial Bluetooth module for Arduino and other microcontrollers

• Operating Voltage: 4V to 6V (Typically +5V)
• Operating Current: 30mA
• Range: <100m
• Works with Serial communication (USART) and TTL compatible
• Follows IEEE 802.15.1 standardized protocol
• Uses Frequency-Hopping Spread spectrum (FHSS)
• Can operate in Master, Slave or Master/Slave mode
• Can be easily interfaced with Laptop or Mobile phones with Bluetooth
4.1.9 H-bridge: An H-Bridge circuit contains four switching elements transistors or
MOSFETs, with the motor at the center forming an H-like configuration. By activating two
particular switches at the same time we can change the direction of the current flow, thus
change the rotation direction ofthe motor. H Bridges can be found in many different
applications where there is a desire to have control over the direction current can flow. Some
common examples of this would be controlling the direction an electric motor can turn by
allowing current to flow in one direction and then reversing that direction in the bridge, thus
causing the motor to turn in the opposite direction.

Dept of ECE, EWIT P a g e | 20

 Implementation of underground mining robot using machine learning 2023-24

Fig 4.20 H-bridge

Specification

• Double H bridge Drive Chip: L298N

• Logical voltage: 5V Drive voltage: 5V-35V

• Logical current: 0-36mA Drive current: 2A (MAX single bridge)

• Max power: 25W

• Dimensions: 43 x 43 x 26mm

• Weight: 26g

4.1.10 GSM module: GSM is a mobile communication modem; it stands for global system
for mobile communication (GSM). The idea of GSM was developed at Bell Laboratories in
1970. It is widely used mobile communication system in the world. GSM is an open and
digital cellular technology used for transmitting mobile voice and data services operates at
the 850MHz, 900MHz, 1800MHz and 1900MHz frequency bands.

Dept of ECE, EWIT P a g e | 21

 Implementation of underground mining robot using machine learning 2023-24
Fig 4.21 GSM module

Features

• Improved spectrum efficiency

• International roaming
• Compatibility with integrated services digital network (ISDN)
• Support for new services.
• SIM phonebook management
• Fixed dialing number (FDN)
• Real time clock with alarm management
• High-quality speech
• Uses encryption to make phone calls more secure
• Short message service (SMS)

The security strategies standardized for the GSM system make it the most secure
telecommunications standard currently accessible. Although the confidentiality of a call and
secrecy of the GSM subscriber is just ensured on the radio channel, this is a major step in
achieving end-to- end security.
4.1.11 Battery: A battery is a device consisting of one or more electrochemical cells with
external connections provided to power electrical devices such as flashlights, smartphones,
and electric cars. When a battery is supplying electric power, its positive terminal is the
cathode and its negative terminal is the anode.

The terminal marked negative is the source of electrons that will flow through an external
electric circuit to the positive terminal. When a battery is connected to an external electric
load, a redox reaction converts high-energy reactants to lower-energy products, thin cells used
in smartphones, to large lead acid batteries or lithium-ion batteries in vehicles, and at the
largest extreme, huge battery banks the size of rooms that provide standby or emergency
power for telephone exchanges and computer data centers.

Dept of ECE, EWIT P a g e | 22

 Implementation of underground mining robot using machine learning 2023-24

Fig 4.22 Battery

4.2 SOFTWARE REQUIREMENTS

4.2.1 Arduino IDE: The Arduino IDE (Integrated Development Environment) is a

software platform used to write and upload code to Arduino boards. It provides a user-
friendly interface to write, compile, and upload code, making it easier for beginners and
experienced developers to work with Arduino hardware.

4.2.2 Embedded C: Embedded C refers to a variant of the C programming language

specifically tailored for programming embedded systems, which are small-scale computer
systems typically designed to perform dedicated functions within a larger mechanical or
electrical system. Embedded C accounts for the limitations and requirements of embedded
systems, such as limited memory, specific hardware constraints, and real-time operation,
allowing developers to write efficient code for these devices.

4.2.3 Python: Python is a high-level, general-purpose programming language. Its design

philosophy emphasizes code readability with the use of significant indentation. Python is
dynamically typed and garbage-collected. It supports multiple programming paradigms,
including structured, object-oriented and functional.

4.2.4 Anaconda Navigator: Anaconda Navigator is a graphical user interface (GUI)

included in the Anaconda distribution, which is a package manager, environment manager,
and collection of pre-installed scientific libraries and tools for Python programming.
Navigator simplifies the management of environments, packages, and development
environments for data science and scientific computing by providing a visual interface to
navigate through these resources and launch applications or tools.

Dept of ECE, EWIT P a g e | 23

 Implementation of underground mining robot using machine learning 2023-24

4.2.5 Zigbee: Zigbee is for low-data rate, low-power applications and is an open
standard. This, theoretically, enables the mixing of implementations from different
manufacturers, butin practice, Zigbee products have been extended and customized by
vendors and, thus, plagued by interoperability issues.
4.2.6 Telegram Bots
Bots are third-party applications that run inside Telegram. Users can interact with bots by
sending them messages, commands and inline requests. You control your bots using HTTPS
requests to our Bot API.
At the core, Telegram Bots are special accounts that do not require an additional phone
number to set up. Users can interact with bots in two ways:
Send messages and commands to bots by opening a chat with them or by adding them to
groups. This is useful for chat bots or news bots like the official TechCrunch bot.
Send requests directly from the input field by typing the bot's @username and a query. This
allows sending content from inline bots directly into any chat, group or channel.
Messages, commands and requests sent by users are passed to the software running on your
servers. Our intermediary server handles all encryption and communication with the Telegram
API for you. You communicate with this server via a simple HTTPS-interface that offers a
simplified version of the Telegram API. We call that interface our Bot API.

Dept of ECE, EWIT P a g e | 24

 Implementation of underground mining robot using machine learning 2023-24

Fig 4.23: Telegram Botfather

CHAPTER 5 ADVANTAGES AND APPLICATIONS

5.1 ADVANTAGES:

1. Cost-Effective: Using Arduino Mega as the brain of the robot can be cost-effective
compared to other complex microcontrollers or proprietary systems.
2. Open-Source: Arduino is an open-source platform, providing access to a vast community
of developers and resources. This allows for easy customization and troubleshooting.
3. Versatility: Arduino Mega has numerous digital and analog pins, enabling the connection
of various sensors and actuators, making it suitable for a wide range of applications.
4. Ease of Programming: Arduino IDE offers a user-friendly programming environment,
making it accessible to beginners and experts alike.
5. Modularity: The robot's design can be modular, allowing for easy upgrades and
modifications as per the requirements of different applications.

5.2 APPLICATIONS:

1. Mine Exploration: The undermining robot can be used for exploring mines or caves
where human access is limited or hazardous. Sensors can detect obstacles, gas leaks, or
temperature changes, ensuring safe exploration.
2. Environmental Monitoring: It can be deployed in environments such as forests or oceans
to collect data on temperature, humidity, pollution levels, or wildlife activity using
appropriate sensors.
3. Search and Rescue: In disaster scenarios, the robot can navigate through debris to locate
survivors using sensors like infrared or thermal sensors to detect body heat or heartbeat
4. Infrastructure Inspection: The robot equipped with sensors like cameras and ultrasonic
sensors can inspect infrastructure such as pipelines, bridges, or buildings for defects, leaks,
or structural integrity.

CHAPTER 6

Dept of ECE, EWIT P a g e | 25

 Implementation of underground mining robot using machine learning 2023-24

RESULT
The project employs a machine learning-based undermining robot that includes the increased
operational efficiency, improved safety through autonomous decision-making, and potentially
enhanced resource identification. ML algorithms enable the robot to adapt for varying
conditions, making it a valuable tool for mining applications.

Fig 6.1: Prototype of UDR

Dept of ECE, EWIT P a g e | 26

 Implementation of underground mining robot using machine learning 2023-24

Fig 6.2: Obstacle detected by UDR

• The picture indicates obstacle detection; when an obstacle is found, a red LED lights
up, and the LCD displays corresponding information.

Fig 6.3: Metal detected by UDR

• The picture indicates metal detection; when metal object is detected, a yellow LED
lights up, and the LCD displays corresponding information.

Dept of ECE, EWIT P a g e | 27

 Implementation of underground mining robot using machine learning 2023-24

Fig 6.4: Moisture detected by UDR

• The picture indicates moisture detection; when moisture is detected, a green LED lights up,
and corresponding information is displayed on LCD.

Fig 6.4: Gas detected by UDR

• The picture indicates gas detection; when gas is detected, an exhaust fan turns on and data
displayed on LCD.

Fig 6.4: Fire detected by UDR

• The pitcher indicates fire detection: When fire is detected by robot, relay pump turns on
and flows. Thus resulting output is displayed on LCD

Dept of ECE, EWIT P a g e | 28

 Implementation of underground mining robot using machine learning 2023-24

Fig 6.4: Prototype of Health band

The above fig illustrates the health parameter like SPO2, temperature and heartbeat of miners.

• When SPO2 level gets lower than normal threshold value, Robot will autonomously
change its path and in case of emergency oxygen pumps.
• The data will get collected from sensor(SPO2,temperature,heartbeat) and then displayed
on LCD.

Dept of ECE, EWIT P a g e | 29

 Implementation of underground mining robot using machine learning 2023-24

Fig 6.5: Output obtained on IOT platform and Machine learning

• Graph obtained on IOT platform showing the health parameter of miners.

• Results are uploaded on Machine learning in real time.

Dept of ECE, EWIT P a g e | 30

 Implementation of underground mining robot using machine learning 2023-24

Fig 6.6: Output obtained on ESP32Cam

The above picture shows result of ESP32Cam that have been attached to the Robot for
analysing image inside tunnel.

CHAPTER 7

CONCLUSION AND FUTURE SCOPE

7.1 CONCLUSION

The project mainly aims for the utilization of machine learning in underground mining
robots. It offers significant advancements in efficiency, safety, and productivity. By
leveraging machine learning algorithms, these robots can autonomously navigate complex
intricate underground passages, optimizing their pathfinding abilities to avoid obstacles and
hazards. This technology holds promise for revolutionizing the mining industry by enhancing
worker safety, reducing operational costs, and maximizing resource extraction. The modular

Dept of ECE, EWIT P a g e | 31

 Implementation of underground mining robot using machine learning 2023-24

design of the system allows for easy integration with existing mining infrastructure and the
incorporation of additional sensors or functionalities in the future. This ensures adaptability
to evolving needs and scalability across different mining environments However, further
research and development are necessary to address challenges such as robustness in harsh
environments, data limitations underground, and integration with existing mining
infrastructure. The aggregation of health data collected from multiple sources enables the
generation of valuable insights through data analytics. These insights can be utilized to
optimize work processes, predict potential hazards, and improve overall operational
performance. The provision of health data to workers via the LCD display on their
workstations empowers them to make informed decisions about their health and well-being.
This promotes a culture of self-care and preventive measures among mining personnel.
Overall, the integration of machine learning into underground mining robots represents a
transformative step towards a more sustainable and efficient mining industry.

7.2 FUTURESCOPE

1. Enhanced Autonomy: Continued advancements in machine learning algorithms will

enable underground mining robots to operate with even higher levels of autonomy, reducing
the need for human intervention and supervision.

2. Improved Safety: Machine learning algorithms can continuously analyze data from
various sensors to detect and mitigate safety hazards in real-time, ultimately reducing the
risk of accidents and injuries for human miners.

3. Optimized Resource Extraction: By leveraging machine learning for data analysis,

underground mining robots can optimize their extraction processes, leading to more efficient
utilization of resources and increased productivity.

5. Integration with Emerging Technologies: Integration with emerging technologies such

as Internet of Things (IoT), augmented reality, and digital twins can further enhance the
capabilities of underground mining robots, enabling better decision-making and remote
monitoring.

Dept of ECE, EWIT P a g e | 32

 Implementation of underground mining robot using machine learning 2023-24

6. Environmental Sustainability: Machine learning can help minimize the environmental

impact of mining operations by optimizing resource usage, reducing energy consumption,
and facilitating the adoption of eco-friendly practices.

7. Collaborative Robotics: Future developments may involve the collaboration between

human miners and autonomous underground mining robots, leveraging the strengths of both
to maximize efficiency and safety.

Overall, the future of underground mining robots using machine learning holds immense
potential for revolutionizing the mining industry, driving improvements in safety,
productivity, and sustainability. Continued research and innovation in this field will be
crucial for unlocking these opportunities and addressing the challenges inherent in
underground mining operations.

Dept of ECE, EWIT P a g e | 33