← Back to Projects Manufacturing 
Predictive Maintenance System
Deep learning CNN-LSTM architecture in PyTorch to predict equipment Remaining Useful Life from NASA C-MAPSS sensor data, with MC Dropout uncertainty and maintenance scheduling.
Overview
Predictive maintenance system using deep learning for remaining useful life estimation.
Architecture
- CNN-LSTM hybrid for sensor time-series
- MC Dropout for uncertainty quantification
- Maintenance scheduling optimizer
- NASA C-MAPSS benchmark dataset
- Streamlit monitoring dashboard
Key Features
- Remaining useful life prediction with confidence intervals
- Maintenance scheduling optimization
- Multi-sensor data fusion
- Interactive degradation monitoring