Elevator Predictive Maintenance System

This project focuses on monitoring elevator components in real-time and predicting maintenance dates to enhance safety and minimize downtime. By collecting data from various sensors and utilizing machine learning, the system efficiently identifies maintenance needs and prevents failures.

Features:

1. Real-Time Data Collection

   • Sensors used: Accelerometer, Infrared (IR), DHT (temperature and humidity), and sound sensors.
   • Monitors environmental conditions, steel rope wear, and brake speed.

2. Predictive Maintenance

   • Developed a Random Forest model with 95% accuracy to forecast service dates.
   • Proactively identifies maintenance needs to avoid unexpected breakdowns.

3. Real-Time Monitoring

   • Integrated a Flask server with Arduino for real-time data communication.
   • Built a user-friendly frontend app to monitor component health and service requirements.

4. Results

   • Reduced downtime by 30%.
   • Improved safety by addressing maintenance needs in advance.

Technical Details:

• Machine Learning: Random Forest model for predictions.
• Backend: Flask server for handling sensor data and predictions.
• Hardware: Arduino board connected to sensors.
• Frontend: Real-time app to display the health status of components.

Impact:

This project successfully minimized elevator downtime and improved safety, showcasing the potential of predictive maintenance systems in preventing failures and optimizing operations.

---

License

This project is licensed under the MIT License.### Elevator Predictive Maintenance System

This project focuses on monitoring elevator components in real-time and predicting maintenance dates to enhance safety and minimize downtime. By collecting data from various sensors and utilizing machine learning, the system efficiently identifies maintenance needs and prevents failures.

Features:

1. Real-Time Data Collection

   • Sensors used: Accelerometer, Infrared (IR), DHT (temperature and humidity), and sound sensors.
   • Monitors environmental conditions, steel rope wear, and brake speed.

2. Predictive Maintenance

   • Developed a Random Forest model with 95% accuracy to forecast service dates.
   • Proactively identifies maintenance needs to avoid unexpected breakdowns.

3. Real-Time Monitoring

   • Integrated a Flask server with Arduino for real-time data communication.
   • Built a user-friendly frontend app to monitor component health and service requirements.

4. Results

   • Reduced downtime by 30%.
   • Improved safety by addressing maintenance needs in advance.

Technical Details:

• Machine Learning: Random Forest model for predictions.
• Backend: Flask server for handling sensor data and predictions.
• Hardware: Arduino board connected to sensors.
• Frontend: Real-time app to display the health status of components.

Impact:

This project successfully minimized elevator downtime and improved safety, showcasing the potential of predictive maintenance systems in preventing failures and optimizing operations.