# harigittihub/nasa-turbofan-predictive_maintenance architecture

> Architecture diagram of the GitHub repository harigittihub/nasa-turbofan-predictive_maintenance, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-03). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/harigittihub/nasa-turbofan-predictive_maintenance
- Repository: https://github.com/harigittihub/nasa-turbofan-predictive_maintenance

## Overview

This repository is a NASA CMAPSS turbofan Remaining Useful Life prediction project, with a Streamlit interface as its user-facing workflow: upload engine data, inspect and select an engine, view a sensor trend, then request an LSTM prediction. The README also documents an offline data-preparation and model-comparison pipeline, including XGBoost and LSTM. The tree and excerpts do not include training code or model artifacts; those documented stages are represented at the existing `src` directory, and their links rely on README descriptions rather than inspected implementation.

Main entry points: [`src`](https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/tree/main/src) (RUL clipping), [`app/streamlit_app.py`](https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/app/streamlit_app.py) (Selected engine), [`src/inference/predict.py`](https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/src/inference/predict.py) (RUL inference), [`src/data/load_data.py`](https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/src/data/load_data.py) (Raw data loading)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_data["Data preparation"]
  node_dataset[("CMAPSS data")]
  node_loader["Raw data loading<br/>[load_data.py]"]
  node_labels["RUL labels<br/>[make_dataset.py]"]
  node_eda["Exploratory analysis"]
  node_selection["Sensor selection"]
  node_windows["Sliding windows"]
  node_scaling["Feature scaling"]
  node_clipping["RUL clipping"]
end

subgraph group_modeling["Model development"]
  node_xgboost["XGBoost model"]
  node_lstm["LSTM model<br/>[predict.py]"]
  node_artifacts[("Model artifacts")]
end

subgraph group_app["Interactive inference"]
  node_streamlit["Streamlit interface<br/>[streamlit_app.py]"]
  node_upload["Uploaded data<br/>[streamlit_app.py]"]
  node_engine["Selected engine<br/>[streamlit_app.py]"]
  node_trend["Sensor visualization<br/>[streamlit_app.py]"]
  node_predictor["RUL inference<br/>[predict.py]"]
  node_result["Predicted RUL<br/>[streamlit_app.py]"]
  node_comparison["Performance comparison<br/>[streamlit_app.py]"]
end

node_operator(("User"))

node_operator -->|"uses"| node_streamlit
node_dataset -->|"loads"| node_loader
node_loader -->|"engineers RUL"| node_labels
node_labels -->|"analyzes"| node_eda
node_eda -->|"identifies sensors"| node_selection
node_selection -->|"selects features"| node_windows
node_windows -->|"creates samples for"| node_scaling
node_scaling -->|"prepares features for"| node_clipping
node_clipping -->|"trains"| node_xgboost
node_clipping -->|"trains"| node_lstm
node_operator -->|"uploads"| node_upload
node_upload -->|"selects engine"| node_engine
node_engine -->|"plots sensors"| node_trend
node_engine -->|"requests prediction"| node_predictor
node_artifacts -->|"loads for inference"| node_predictor
node_predictor -->|"returns prediction"| node_result
node_operator -->|"views metrics"| node_comparison
node_xgboost -->|"compared in"| node_comparison
node_lstm -->|"compared in"| node_comparison

click node_loader "https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/src/data/load_data.py"
click node_labels "https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/src/data/make_dataset.py"
click node_eda "https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/tree/main/src"
click node_selection "https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/tree/main/src"
click node_windows "https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/tree/main/src"
click node_scaling "https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/tree/main/src"
click node_clipping "https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/tree/main/src"
click node_xgboost "https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/tree/main/src"
click node_lstm "https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/src/inference/predict.py"
click node_streamlit "https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/app/streamlit_app.py"
click node_upload "https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/app/streamlit_app.py"
click node_engine "https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/app/streamlit_app.py"
click node_trend "https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/app/streamlit_app.py"
click node_predictor "https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/src/inference/predict.py"
click node_result "https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/app/streamlit_app.py"
click node_comparison "https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/app/streamlit_app.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_dataset,node_loader,node_labels,node_eda,node_selection,node_windows,node_scaling,node_clipping,node_operator toneBlue
class node_xgboost,node_lstm,node_artifacts toneAmber
class node_streamlit,node_upload,node_engine,node_trend,node_predictor,node_result,node_comparison toneMint
```

## Components

### Data preparation

- **CMAPSS data**
- [Raw data loading](https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/src/data/load_data.py): `src/data/load_data.py`
- [RUL labels](https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/src/data/make_dataset.py): `src/data/make_dataset.py`
- [Exploratory analysis](https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/tree/main/src): `src`
- [Sensor selection](https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/tree/main/src): `src`
- [Sliding windows](https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/tree/main/src): `src`
- [Feature scaling](https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/tree/main/src): `src`
- [RUL clipping](https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/tree/main/src): `src`

### Model development

- [XGBoost model](https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/tree/main/src): `src`
- [LSTM model](https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/src/inference/predict.py): `src/inference/predict.py`
- **Model artifacts**

### Interactive inference

- [Streamlit interface](https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/app/streamlit_app.py): `app/streamlit_app.py`
- [Uploaded data](https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/app/streamlit_app.py): `app/streamlit_app.py`
- [Selected engine](https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/app/streamlit_app.py): `app/streamlit_app.py`
- [Sensor visualization](https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/app/streamlit_app.py): `app/streamlit_app.py`
- [RUL inference](https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/src/inference/predict.py): `src/inference/predict.py`
- [Predicted RUL](https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/app/streamlit_app.py): `app/streamlit_app.py`
- [Performance comparison](https://github.com/harigittihub/nasa-turbofan-predictive_maintenance/blob/main/app/streamlit_app.py): `app/streamlit_app.py`

### Other components

- **User**

## Connections

- User → Streamlit interface: uses (evidence: `README.md`)
- CMAPSS data → Raw data loading: loads (evidence: `src/data/load_data.py`)
- Raw data loading → RUL labels: engineers RUL (evidence: `README.md`)
- RUL labels → Exploratory analysis: analyzes (evidence: `README.md`)
- Exploratory analysis → Sensor selection: identifies sensors (evidence: `README.md`)
- Sensor selection → Sliding windows: selects features (evidence: `README.md`)
- Sliding windows → Feature scaling: creates samples for (evidence: `README.md`)
- Feature scaling → RUL clipping: prepares features for (evidence: `README.md`)
- RUL clipping → XGBoost model: trains (evidence: `README.md`)
- RUL clipping → LSTM model: trains (evidence: `README.md`)
- User → Uploaded data: uploads (evidence: `app/streamlit_app.py`)
- Uploaded data → Selected engine: selects engine (evidence: `app/streamlit_app.py`)
- Selected engine → Sensor visualization: plots sensors (evidence: `app/streamlit_app.py`)
- Selected engine → RUL inference: requests prediction (evidence: `app/streamlit_app.py`)
- Model artifacts → RUL inference: loads for inference (evidence: `src/inference/predict.py`)
- RUL inference → Predicted RUL: returns prediction (evidence: `app/streamlit_app.py`)
- User → Performance comparison: views metrics (evidence: `app/streamlit_app.py`)
- XGBoost model → Performance comparison: compared in (evidence: `README.md`)
- LSTM model → Performance comparison: compared in (evidence: `README.md`)
