Predictive Maintenance for Turbofan Engines
An AI-powered predictive maintenance tool built with Streamlit to estimate the Remaining Useful Life (RUL) of turbofan engines using NASA’s degradation dataset. Deployed on Azure for real-time industrial insights.
Technologies Used
Overview This personal project implements a predictive maintenance system for turbofan engines using machine learning. Built as an interactive Streamlit web application and deployed on Azure App Service, the platform forecasts Remaining Useful Life (RUL) using NASA’s Turbofan Engine Degradation Simulation dataset.
Key Features
Predicts Remaining Useful Life (RUL) of individual engine units
Allows real-time sensor input to simulate engine behavior
Dynamic sensor trend visualizations for selected engines
User-friendly dashboard for intuitive interaction
End-to-end implementation: data preprocessing, model training, and deployment
System Design & Flow
Data Pipeline: Raw sensor data is cleaned and engineered for feature extraction
Model Training: Regression models are trained on historical engine run-to-failure data
Web Interface: Interactive frontend built with Streamlit allows user exploration
Deployment: Application hosted on Azure App Service for global access
Use Case & Impact This project enables engineers and maintenance teams to anticipate engine degradation and schedule proactive maintenance. By minimizing unplanned downtimes and maximizing component lifespan, the system improves operational efficiency and cost-effectiveness in industries like aviation, manufacturing, and energy.