README.md

---
title: Jet Engine Predictive Maintenance
emoji: ✈️
colorFrom: blue
colorTo: red
sdk: streamlit
sdk_version: 1.31.0
python_version: "3.10"
app_file: app.py
pinned: false
---

# ✈️ Jet Engine Predictive Maintenance System
### B.Tech AI & Data Science - Special Project

This project implements an Industrial AI solution to predict the **Remaining Useful Life (RUL)** of turbofan engines. By analyzing multivariate time-series data from 21 sensors, the system identifies degradation patterns and provides proactive maintenance alerts.

---

## 📌 Project Overview
Traditional maintenance is either **Reactive** (fixing after failure) or **Preventive** (fixing on a schedule). This project uses **Predictive Maintenance**, which uses machine learning to forecast exactly when a part will fail, saving costs and improving safety.

### Key Features:
* **Real-time RUL Prediction:** Forecasts how many flight cycles remain before an engine requires service.
* **Interactive Dashboard:** Built with Streamlit, allowing users to input sensor readings manually.
* **Health Analytics:** Visualizes engine health status through a dynamic Gauge chart (Healthy, Caution, Critical).
* **Machine Learning Backend:** Uses an **XGBoost Regressor** optimized for time-series tabular data.

---

## 🛠️ Technical Stack
* **Language:** Python 3.10
* **Model:** XGBoost (Extreme Gradient Boosting)
* **Web Framework:** Streamlit
* **Libraries:** Pandas, NumPy, Scikit-learn, Joblib, Plotly
* **Deployment:** Hugging Face Spaces

---

## 📁 Repository Structure
| File | Description |
| :--- | :--- |
| `app.py` | The main Streamlit web application. |
| `engine_model.pkl` | The trained AI model (XGBoost). |
| `requirements.txt` | Lists the Python packages needed to run the app. |
| `train_local.py` | (Optional) The script used to train the model locally. |

---

## ⚙️ How to Use
1. **Enter Sensor Readings:** Adjust the sliders in the sidebar with data from your test set.
2. **Analyze:** Click the "Analyze Engine Health" button.
3. **Review Results:** The Gauge chart will indicate the remaining life. If the RUL is below 30 cycles, a **Critical Warning** will be triggered.

---

## 👨‍🎓 Author
**[Your Name]** 3rd Year B.Tech, AI & Data Science  
[Your University Name]