---
title: "Combined_All_Data"
description: "conditions, including normal mode and many open-circuit fault scenarios. This dataset is designed for: ✔ Machine Learning (ML) & Deep Learning (DL) ✔ Fault detection and classification ✔ Power electronics research ✔ Predictive maintenance ✔ University courses & academic projects ✔ Digital Twin model"
url: "https://ouro.foundation/files/kbousbai-02/combined-all-data"
id: "0af3d065-2265-489f-8646-43804b7e6c2f"
type: "file"
---

# Combined_All_Data

File by @kbousbai-02 in #free-energy (all) · .rar · 7.3 MB

- Asset id: `0af3d065-2265-489f-8646-43804b7e6c2f`
- Page: https://ouro.foundation/files/kbousbai-02/combined-all-data

**conditions**, including normal mode and many open-circuit fault scenarios.

This dataset is designed for:

- ✔ Machine Learning (ML) & Deep Learning (DL)
- ✔ Fault detection and classification
- ✔ Power electronics research
- ✔ Predictive maintenance
- ✔ University courses & academic projects
- ✔ Digital Twin modeling

If you work in **electronics, energy systems, AI, or embedded systems**, this dataset will save you *weeks or months* of data collection and signal processing.

📦 **What’s Included**

When you purchase the full version, you receive:

### 📁 **1. Full Dataset (264,000 samples)**

- Format: **CSV**
- 6 columns:
`Time, Voltage, Signal1, Signal2, Signal3, Class`
- 12 labeled classes
- Multi-channel time-series
- Cleaned and formatted for immediate use

### 📘 **2. Full Documentation PDF (5 pages)**

- Dataset description
- System architecture
- Plots & class distribution
- Sample time-series signals

### 🎁 **4. Bonus Lite Dataset (FREE preview version)**

- 12,000 samples
- 1,000 rows per class
- Perfect for testing

---

📊 **Dataset Characteristics**

Samples: **264,000**

Classes: **12**

Channels: **4 signals**

Type: Time-series

Use cases: AI, ML, Power Electronics

File Type: CSV

---

🧠 **Applications**

You can use A3RC-12 to train:

- CNN, LSTM, Transformers
- Anomaly detection models
- Fault classification systems
- Digital Twins
- Condition monitoring algorithms

Perfect for research, development, and industrial prototypes.

---

💼 **Who Uses This Dataset?**

- Researchers & graduate students
- University laboratories
- AI engineers
- Power electronics developers
- Inverter/UPS/solar companies
- Industrial monitoring teams

---

🤖 **Class List (12 fault conditions)**

- Normal Condition (Data_N)
- Multiple open-circuit faults (S1, S2, S3, S4, S5, S6, etc.)
- Combined fault scenarios

## Use it

- Over Ouro MCP: `download_asset(id="0af3d065-2265-489f-8646-43804b7e6c2f")` returns the file or a download link.
- Find routes that take it: `get_compatible_routes(asset_id="0af3d065-2265-489f-8646-43804b7e6c2f")`, then pass it as `input_assets={"file": "0af3d065-2265-489f-8646-43804b7e6c2f"}`.
- From Python: `ouro.files.retrieve("0af3d065-2265-489f-8646-43804b7e6c2f")`
