Next Article in Journal
The Stream Exchange Protocol: A Secure and Lightweight Tool for Decentralized Connection Establishment
Previous Article in Journal
Printed Circuit Board Defect Detection Using Deep Learning via A Skip-Connected Convolutional Autoencoder
Previous Article in Special Issue
Fault Diagnosis of Brake Train Based on Multi-Sensor Data Fusion
Article

Pre-Processing Method to Improve Cross-Domain Fault Diagnosis for Bearing

Machine Diagnosis Laboratory, Department of Mechanical Engineering, Ajou University, Suwon 16499, Korea
*
Author to whom correspondence should be addressed.
Academic Editors: Hamed Badihi, Tao Chen and Ningyun Lu
Sensors 2021, 21(15), 4970; https://doi.org/10.3390/s21154970
Received: 23 June 2021 / Revised: 16 July 2021 / Accepted: 17 July 2021 / Published: 21 July 2021
Models trained with one system fail to identify other systems accurately because of domain shifts. To perform domain adaptation, numerous studies have been conducted in many fields and have successfully aligned different domains into one domain. The domain shift problem is caused by the difference of distributions between two domains, which is solved by reducing this difference. Source domain data are labeled and used for training the models to extract the features while the target domain data are unlabeled or partially labeled and only used for aligning. Bearings play important roles in rotating machines, so many artificial intelligent models have been developed to diagnose bearings. Bearing diagnosis has also faced a domain shift problem due to various operating conditions such as experimental environment, number of balls, degree of defects, and rotational speed. Cross-domain fault diagnosis has been successfully performed when the systems are the same but operating conditions are different. However, the results are poor when diagnosing different bearing systems because the characteristics of the signals such as specific frequencies depend on the specifications. In this paper, the pre-processing method was used for improving the diagnosis without prior knowledge such as fault frequencies. The signals were first transformed to a common pattern space before entering the models. To develop and to validate the proposed method for different domains, vibration signals measured from two ball-bearing systems (Case Western Reserve University datasets and Paderborn University datasets) were used. One dimensional CNN models were utilized for verification of the proposed method and the results of the models using raw datasets and pre-processed datasets were compared. Even though each of the ball-bearing systems have their own specifications, using the proposed method was very helpful for domain adaptation, and cross-domain fault diagnosis was performed with high accuracy. View Full-Text
Keywords: bearing fault diagnosis; cross-domain fault diagnosis; domain adaptation; signal processing; transfer learning bearing fault diagnosis; cross-domain fault diagnosis; domain adaptation; signal processing; transfer learning
Show Figures

Figure 1

MDPI and ACS Style

Kim, T.; Chai, J. Pre-Processing Method to Improve Cross-Domain Fault Diagnosis for Bearing. Sensors 2021, 21, 4970. https://doi.org/10.3390/s21154970

AMA Style

Kim T, Chai J. Pre-Processing Method to Improve Cross-Domain Fault Diagnosis for Bearing. Sensors. 2021; 21(15):4970. https://doi.org/10.3390/s21154970

Chicago/Turabian Style

Kim, Taeyun, and Jangbom Chai. 2021. "Pre-Processing Method to Improve Cross-Domain Fault Diagnosis for Bearing" Sensors 21, no. 15: 4970. https://doi.org/10.3390/s21154970

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop