VBL-VA001 — Lab-Scale Machine Vibration Fault Dataset [3.8 GB]
Abstract
"Lab-scale vibration dataset with 4,000 CSV files for normal, bearing fault, misalignment, and unbalance states. 3.8 GB ZIP for predictive-maintenance classification."
Description
Overview
VBL-VA001 is a lab-scale vibration analysis dataset for predictive maintenance and machine-condition classification.
It covers four machine conditions: normal, bearing fault, misalignment, and unbalance.
The dataset was collected from a Panasonic GP-129JXK machine using an enDAQ LOG-0002-100G-DC-8GB-PC shock and vibration sensor.
Column Schema
| Column | Description |
|---|---|
| x | Vibration signal on the x axis. |
| y | Vibration signal on the y axis. |
| z | Vibration signal on the z axis. |
| condition | Machine condition from folder structure: normal, bearing fault, misalignment, or unbalance. |
| file_id | CSV file identifier within each condition folder. |
Key Statistics
- Total Records: 4,000 CSV files
- Features: Three-axis vibration signals plus condition label from folder organization
- File Format: CSV files in ZIP archive
- File Size: 3.8 GB
- Sampling Rate: 20 kHz; 5 seconds per CSV file
Use Cases
- Predictive maintenance fault classification
- Bearing fault, misalignment, and unbalance detection
- Vibration signal analysis benchmarking
Source & Attribution
Created by Haris Ihsannur, Bagus Tris Atmaja, Suyanto, and Dhany Arifianto. Published on Zenodo with DOI 10.5281/zenodo.7006575.
View Data Structure
To explore column names, data types, and sample rows, visit the official dataset page on Zenodo.
Preview on ZenodoCite This Dataset
Ihsannur, Haris, Atmaja, Bagus Tris, Suyanto, & Arifianto, Dhany (2022). VBL-VA001 — Lab-Scale Machine Vibration Fault Dataset [3.8 GB]. [Dataset]. Zenodo. https://doi.org/10.5281/zenodo.7006575
Source: Zenodo (2022) · DOI: 10.5281/zenodo.7006575
Indexed by IoTDataset.com on Jun 06, 2026
Ready to Start Your Research?
Download this dataset directly from the official repository and start building your next breakthrough project.