Smart Factory

• 

  Smart industry

Inspiration

In many industries, machines are still maintained only after they fail, leading to unexpected downtime, safety risks, and production loss. We wanted to solve this by building an AI system that can predict failures early using sensor data and help engineers take preventive action.

What it does

Our Smart Factory AI Agent continuously monitors machine sensor data and detects anomalies in real time. It predicts possible failures like motor overheating, vibration issues, or pressure imbalance and generates early alerts so maintenance can be done before breakdowns occur.

How we built it

We built the frontend using React/HTML/CSS and connected it to a FastAPI backend. The system processes sensor-like data inputs and runs simple AI/logic-based anomaly detection models. We used REST APIs to connect frontend and backend and deployed the application using cloud hosting tools like Vercel/Render.

Challenges we ran into

We faced challenges in handling real-time data simulation and tuning anomaly detection thresholds to reduce false alerts. Integrating frontend with backend APIs and ensuring smooth deployment was also difficult initially.

Accomplishments that we're proud of

We successfully built a working end-to-end predictive maintenance system that can detect anomalies and generate alerts in real time. The UI is clean, responsive, and effectively visualizes machine health status.

What we learned

We learned how predictive maintenance works in real industrial systems, how to build full-stack applications using FastAPI and frontend frameworks, and how to integrate APIs for real-time data flow.

What's next for Smart Factory

Next, we plan to integrate advanced machine learning models for more accurate predictions, add live IoT sensor integration, and improve dashboard analytics with real-time graphs and cloud-based scaling.

Built With

• css
• html
• python
• restapi
• tailwand
• vercel