HUST bearing: a practical dataset for ball bearing fault diagnosis

• Published in: BMC research notes Vol. 16; no. 1; pp. 138 - 3
• Main Authors: Thuan, Nguyen Duc, Hong, Hoang Si
• Format: Journal Article
• Language: English
• Published: London BioMed Central 06.07.2023; BioMed Central Ltd; BMC
• Subjects: Automation; Ball bearings; Bearing fault; Biomedical and Life Sciences; Biomedicine; Data acquisition; Data entry; Data Note; Data Notes; Dataset; Datasets; Defects; Electric motors; Engineering research; Fault diagnosis; Fault location (Engineering); Life Sciences; Machine Learning; Mechanical properties; Medicine/Public Health; Methods; Neural networks; Reproducibility of Results; Signal processing; Software; Vibration; Working Conditions; Vietnam; Fault diagnosis; Bearing fault; Dataset
• ISSN: 1756-0500; 1756-0500
• DOI: 10.1186/s13104-023-06400-4

Objectives The rapid growth of machine learning methods has led to an increase in the demand for data. For bearing fault diagnosis, the data acquisition is time-consuming with complicated processes. Existing datasets are only focused on only one type of bearing, which limits real-world applications. Therefore, the objective of this work is to propose a diverse dataset for ball bearing fault diagnosis based on vibration. Data description In this work, we introduce a practical dataset named HUST bearing , which provides a large set of vibration data on different ball bearings. This dataset contains 99 raw vibration signals of 6 types of defects (inner crack, outer crack, ball crack, and their 2-combinations) on 5 types of bearing (6204, 6205, 6206, 6207, and 6208) at 3 working conditions (0 W, 200 W, and 400 W). Each vibration signal is sampled at a rate of 51,200 samples per second for 10 s. The data acquisition system is elaborately designed with high reliability.