How yugamdeepgoyal/predictive_maintenance works
This educational Streamlit product estimates jet-engine remaining useful life from NASA C-MAPSS FD001 data. The main workflow loads engine histories, accepts uploaded, manually entered, or example readings, prepares per-engine features, runs a selected XGBoost or LSTM model, and presents estimates and status; multi-engine results can be downloaded. The analyst dashboard adds replay, fault injection, fleet scoring, and an OOP view, while a separate in-app manual explains usage. The app is a monolith, so several interface responsibilities share app.py. Dashboard details beyond the sampled excerpts are represented from the README.
Main entry points: app.py App entry point · base.py Model and prep contracts · models.py XGBoost model · handle_data.py C-MAPSS loader
Components 21
Streamlit interface
- App entry point
app.py - Prediction inputs
app.py - Prediction results
app.py - Analyst dashboard
app.py - In-app manual
app.py
Data preparation
- FD001 data
CMaps - C-MAPSS loader
src/handle_data.py - Input parsing
app.py - Tabular features
src/models.py - Sequence features
src/models.py
RUL prediction
- Model and prep contracts
src/base.py - XGBoost model
src/models.py - LSTM model
src/models.py - Saved XGBoost
xgb_model.json - Saved LSTM
lstm_model.keras - Regression metrics
src/base.py
Analysis and guidance
- Live replay
app.py - Fault injection
app.py - Fleet view
app.py - OOP view
app.py
Other components
- Engine analyst
Connections 25
- Engine analyst → App entry point: uses
README.md - App entry point → C-MAPSS loader: loads data
app.py - C-MAPSS loader → FD001 data: reads files
src/handle_data.py - Engine analyst → Prediction inputs: provides readings
README.md - Prediction inputs → Input parsing: parses input
README.md - Input parsing → Tabular features: prepares inputs
app.py - App entry point → Tabular features: prepares data
app.py - App entry point → Sequence features: prepares data
app.py - App entry point → XGBoost model: loads or trains
app.py - App entry point → LSTM model: loads model
app.py - Tabular features → Model and prep contracts: implements contract
src/models.py - Sequence features → Model and prep contracts: implements contract
src/models.py - XGBoost model → Model and prep contracts: implements contract
src/models.py - LSTM model → Model and prep contracts: implements contract
src/models.py - App entry point → Saved XGBoost: loads or saves
README.md - App entry point → Saved LSTM: loads
README.md - App entry point → Prediction results: shows estimates
README.md - Engine analyst → Analyst dashboard: opens
README.md - Analyst dashboard → Live replay: offers replay
README.md - Analyst dashboard → Fault injection: offers injection
README.md - Analyst dashboard → Fleet view: offers fleet view
README.md - Analyst dashboard → OOP view: offers OOP view
README.md - Engine analyst → In-app manual: opens
README.md - XGBoost model → Regression metrics: evaluates with
src/models.py - LSTM model → Regression metrics: evaluates with
src/models.py