Our project, AI Predictive Maintenance System for Industrial Motors Using Digital Twin, was inspired by the need to reduce unexpected motor failures and improve industrial maintenance.
We developed a software-based solution using Python, a Random Forest machine learning model, and Streamlit. The system analyzes motor parameters such as temperature, current, vibration, RPM, voltage, and load to identify conditions including overheating, overloading, and mechanical faults. An interactive dashboard presents the predictions and motor information through visualizations.
During development, we learned about machine learning, data analysis, model integration, and Digital Twin concepts. Our main challenges were integrating the trained model with the dashboard, handling motor datasets, and presenting predictions clearly. This project helped us understand how AI can support smarter industrial monitoring and predictive maintenance.
Built With
- artificial-intelligence
- data-visualization
- digital-twin
- fault
- industrial-automation
- machine-learning
- motor
- pandas
- plotly
- predictive-maintenance
- python
- random-forest
- streamlit
Log in or sign up for Devpost to join the conversation.