Machine Learning

Turbofan Engine Degradation Prediction Using Machine Learning

The Turbofan Engine Degradation Prediction Using Machine Learning system is a comprehensive machine learning solution that predicts Remaining Useful Life (RUL) of turbofan engines using the NASA CMAPSS FD004 dataset. This project is ideal for B.Tech, MCA, CSE, and engineering students as their final year project. It implements Lasso and Ridge Regression with feature engineering, achieving 94.71% R² accuracy and 18.45 RMSE.

The system utilizes the NASA CMAPSS FD004 dataset containing simulated sensor measurements from 21 sensors across 249 engines under various operational conditions. It provides a user-friendly web interface for data upload, exploratory data analysis, model training, and real-time RUL prediction, enabling proactive maintenance scheduling and optimized fleet operations.

• Multi-Model RUL Prediction
• Ridge Regression (R²: 0.9471)
• Lasso Regression (R²: 0.9295)
• Feature Engineering (rolling stats, interactions)
• 5-Fold Cross-Validation
• Interactive Visualizations
• Real-time RUL Predictions
• Model Performance Comparison
• Feature Importance Analysis
• Flask Web Application