1. BACHELOR OF TECHNOLOGY
IN
COMPUTER SCIENCE AND ENGINEERING
A
MAJOR PROJECT
ON
E-PILOTS: A SYSTEM TO PREDICT HARD LANDING DURING THE APPROACH PHASE
OF COMMERCIAL FLIGHTS
PRESENTED BY:
RITURAJ UPADHYAY- 19E41A05L0
UPPALA SAGAR- 19E41A05L7
MD ABDULLAH ALIAS NAZIM- 19E41A05L9
SYED NAWAZ- 19E41A05K9
MD MUSHRAF UDDIN- 19E41A05L3
Under the Guidance of
CH.ARUNA REDDY
BATCH – 11 ( CSE – C )
ACADEMIC BATCH: 2019-2023
2. TABLE OF CONTENTS
1. Introduction
2. Abstract
3. Problem Statement
4. Objective
5. Existing System &Drawbacks of Existing System
6. Proposed System &Advantages of Proposed
System
7. System Requirements
8. System Architecture
9. UML Diagrams
10. Implementation
11. Sample Code
12. Testing (Output)
13. Future Scope
14. Conclusion
3. INTRODUCTION
• Between 2008 and 2017, almost 49% of the deadly accidents involving commercial jets happened when they
were landing this percentage has stayed the same for many years.
• Boeing, a company that makes planes, said that only 3% of landings in commercial flights were not done
properly Surprisingly, 97% of these bad landings continued instead of trying again.
• Many of these accidents are caused by planes going off the runway. Not landing properly, hard landing on the
runway, and other things can lead to this.
• However, if pilots decided to try landing again more often, it could reduce the number of accidents in the
aviation industry.
4. ABSTRACT
• This project aims to develop a system called E-Pilots that uses machine learning algorithms to predict hard landings during
the approach phase of commercial flights.
• The system will analyze flight data to precede hard landings.
• The goal is to provide pilots with real-time warnings and guidance to prevent accidents and improve safety.
• The research methodology includes the collection and analysis of flight data, the development and testing of machine
learning algorithms, and the integration of the E-Pilots system with existing flight systems.
• The findings of this project are expected to contribute to the improvement of aviation safety and reduce the occurrence of
hard landings. The implications of this research may also extend to other areas of aviation safety and flight automation.
5. PROBLEM STATEMENT
• The objective is to develop an E-PILOTS (Enhanced Predictive Integrated Landing Optimization
and Tracking System) that utilizes advanced technology and data analysis techniques to predict the
probability of a hard landing during the approach phase of commercial flights.
• The system should aim to assist pilots in making informed decisions and taking corrective actions
to prevent hard landings.
6. OBJECTIVES
• Develop a system that uses machine learning algorithms to predict hard landings during the
approach phase of commercial flights.
• Collect and analyze flight data to identify patterns that precede hard landings. Integrate the E-Pilots
system with existing flight systems to provide pilots with real-time warnings and guidance to
prevent hard landings.
• Evaluate the performance of the E-Pilots system in detecting and preventing hard landings using a
dataset of historical flight data. Compare the performance of the E-Pilots system with existing hard
landing prediction systems and assess its potential for improving aviation safety.
7. EXISTING SYSTEM & DISADVANTAGES
• One existing system for hard landing prediction during the approach phase of commercial flights is the
SmartLand system developed by Honeywell Aerospace.
• The SmartLand system uses multiple sensors on the aircraft to provide pilots with real-time information about
the aircraft's position, velocity, and trajectory during the approach phase.
• The system then uses algorithms to analyze this data and detect any signs of a hard landing, such as excessive
descent rate, high vertical acceleration, or touchdown beyond the designated touchdown zone.
• DISADVANTAGES ARE: Limited Data Analysis, Insufficient Integration, High Maintenance Costs
8. PROPOSED SYSTEM & ADVANTAGES
• The system would use machine learning algorithms, such as Naive Bayes, Logistic Regression, SVM, Decision Tree,
SGD Classifier to analyze the flight data and identify patterns that precede hard landings. These patterns might include
changes in altitude, airspeed, or rate of descent. Once the system detects these patterns, it would provide real-time
warnings and guidance to pilots to prevent hard landings
• ADVANTAGES ARE: Enhanced safety, Accurate Predictions, Cost Savings, Continuous Improvement
9. SYSTEM REQUIREMENT
HARDWARE REQUIREMENTS SOFTWARE REQUIREMENTS
Processor : Pentium –IV
RAM : 4 GB (min)
Hard Disk : 20 GB
Key Board : Standard Windows Keyboard
Mouse : Two or Three Button Mouse
Monitor : SVGA
Operating system : Windows 7 Ultimate.
Coding Language : Python.
Front-End : Python.
Back-End : Django-ORM
Designing : Html, css, javascript.
Data Base : MySQL (WAMP Server).
13. IMPLEMENTATION :-
Step:1 Requirements Analysis:
Review and refine the project requirements gathered during the system analysis phase.
Ensure that the scope, objectives, and functional requirements are well-defined and understood.
Step:2 Technology Selection:
Determine the technologies and frameworks to be used for developing the system.
This may include programming languages Python , machine learning libraries scikit-learn or TensorFlow, web development
frameworks Django , and database management systems (such as MySQL).
Step:3 Data Collection and Preparation:
Gather the required data for training the prediction model.
This may involve obtaining historical flight data, weather data, aircraft specifications, and runway information.
Cleanse, preprocess, and normalize the data to ensure its quality and compatibility with the selected machine learning
algorithms.
14. Step:4: Model Training:
Choose the appropriate classification algorithm, such as decision trees or SGD classifiers, and train the prediction model
using the collected and preprocessed data.
Tune the model parameters, validate its performance using appropriate evaluation metrics, and optimize its accuracy and
generalization capabilities.
Step:5 System Development:
Develop the system components, including data input interfaces, prediction modules, data storage mechanisms, and user
interfaces.
Implement the necessary algorithms and functionalities to ensure seamless data flow, real-time prediction capabilities, and
user-friendly interactions.
Step:6: Integration and Testing:
Integrate the developed system components, ensuring smooth communication and data exchange between different
modules.
Conduct thorough testing to validate the system's functionalities, performance, and accuracy. Perform unit testing,
integration testing, and system testing to identify and resolve any bugs or issues.
24. FUTURE SCOPE :
future scopes aim to enhance the system's capabilities, improve flight safety, and provide more
comprehensive support to pilots, air traffic controllers, and other stakeholders involved in the landing phase
of commercial flights.
25. CONCLUSION:
The project "E-Pilots: A System to Predict Hard Landing During the Approach Phase of Commercial Flights" aims to
enhance flight safety by predicting the likelihood of hard landings. The system utilizes machine learning algorithms, such
as decision trees and SGD classifiers, to analyze historical flight data and generate predictions. By providing early
warnings and proactive measures, the system can assist pilots and air traffic controllers in mitigating the risk of hard
landings. The implementation of this project requires data collection, model training, system development, integration,
and testing. The future scope includes refining the prediction models, integrating real-time data sources, facilitating
collaborative decision-making, and expanding the system's capabilities. Overall, this project contributes to improving
flight safety and reducing the occurrence of hard landings during commercial flights
26. REFERENCE :
[1] Boeing Commercial Airplanes. Statistical summary of commercial jet airplane accidents–worldwide operations|
1959–2017. Aviation Saf., Seattle,WA, USA, 2018.
[2] European Aviation Safety Agency. Developing standardised fdm-based indicators. Technical report, European
Aviation Safety Agency, 2016.
[3] Federal Aviation Administration. Advisory circular ac no: 91-79a mitigating the risks of a runway overrun upon
landing. Technical report, Federal Aviation Administration, 2016.
[4] Michael Coker and Lead Safety Pilot. Why and when to perform a goaround maneuver. Boeing Edge, 2014:5–
11, 2014.
[5] Tzvetomir Blajev andWCurtis. Go-around decision making and execution project: Final report to flight safety
foundation. Flight Safety Foundation, March, 2017.