Project Title: Predictive Maintenance of Turbofan Engines Using NASA C-MAPSS Dataset
Overview:
This project applies machine learning to predict the Remaining Useful Life (RUL) of aircraft turbofan engines using NASA's C-MAPSS FD001 dataset, which contains 21 sensor readings across 100 engines.
Key Steps:
Cleaned and preprocessed 20,631 rows of sensor data
Removed 7 non-informative constant sensors, reducing features by 33%
Identified 3 degradation patterns across retained sensors
Built a Linear Regression baseline model
Results:
Test RMSE = 31.95 cycles ✅ (matches published benchmark of ~31)
R² Score = 0.41 on test set
AI Tools Used:
Claude AI (Anthropic) was used for pattern analysis, feature interpretation, and documentation.