Aircraft Engine Predictive Maintenance using Machine Learning

Overview

This project focuses on predictive maintenance for aircraft engines using Machine Learning.
The main objective is to predict the Remaining Useful Life (RUL) of an aircraft engine based on sensor data, helping to anticipate maintenance needs before a potential failure occurs.

Predictive maintenance is an important approach in the aeronautical field because it improves safety, reduces unexpected breakdowns, and optimizes maintenance planning.

Project Objective

The goal of this project is to develop a machine learning solution capable of estimating the remaining useful life of an aircraft engine using the FD001 turbofan engine dataset.

The system uses historical engine data and a trained machine learning model to support maintenance decision-making.

Main Features

• Aircraft engine Remaining Useful Life prediction
• Machine learning model trained on turbofan engine data
• Data processing using FD001 dataset
• Python-based application interface
• Prediction system for maintenance decision support
• Organized project structure for GitHub presentation

Dataset

This project uses the FD001 turbofan engine dataset, commonly used for predictive maintenance and Remaining Useful Life prediction tasks.

The dataset contains engine sensor measurements collected over multiple operational cycles.
These values are used to analyze engine degradation and estimate how many cycles remain before failure.

Technologies Used

• Python
• Pandas
• NumPy
• Scikit-learn
• Machine Learning
• Predictive Maintenance
• RUL Prediction
• Python GUI / Application Interface

Project Structure

aircraft-engine-predictive-maintenance/
│
├── app1.py
├── modele_aerophm.pkl
├── requirements.txt
├── RUL_FD001.csv
├── test_FD001.csv
├── unnamed.jpg
└── README.md

Files Description

File	Description
app1.py	Main Python application file used to run the prediction interface
modele_aerophm.pkl	Trained machine learning model used for RUL prediction
requirements.txt	List of required Python libraries
RUL_FD001.csv	File containing Remaining Useful Life values
test_FD001.csv	Test dataset used for prediction
unnamed.jpg	Image or visual asset used in the project interface
README.md	Project documentation

How to Run the Project

1. Clone the repository

git clone https://github.com/anas-iazza/aircraft-engine-predictive-maintenance.git

2. Open the project folder

cd aircraft-engine-predictive-maintenance

3. Install the required libraries

pip install -r requirements.txt

4. Run the application

python app1.py

Expected Result

After running the application, the user can test the predictive maintenance system and obtain an estimated Remaining Useful Life value for an aircraft engine.

This result can help identify whether an engine is in a normal operating condition or approaching a critical maintenance phase.

Importance of the Project

This project demonstrates how machine learning can be applied in the aeronautical field to improve aircraft maintenance strategies.
Instead of relying only on fixed maintenance schedules, predictive maintenance allows engineers to make decisions based on data and engine condition.

Skills Demonstrated

• Data analysis
• Machine learning model usage
• Predictive maintenance concepts
• Python programming
• Aeronautical engineering application
• Model deployment in a simple application interface
• Project organization for GitHub

Future Improvements

• Improve model accuracy using advanced algorithms
• Add more visualizations for sensor data
• Create a more professional graphical interface
• Add training and evaluation scripts
• Include performance metrics such as MAE and RMSE
• Deploy the application as a web dashboard

Author

Anas Iazza
Aeronautical Engineering and Space Technologies Student

License

This project is developed for academic and learning purposes.