Intelligent ball screw fault diagnosis using a deep domain adaptation methodology. (September 2020)

• Record Type: Journal Article
• Authors: Azamfar, Moslem; Li, Xiang; Lee, Jay
• Is Part Of: Mechanism and machine theory. Volume 151(2020)
• Publication Date: 2020-09
• Subjects: Fault diagnosis -- Ball screw -- Deep learning -- Domain adaptation -- Raw data; Machine theory -- Periodicals; Machinery -- Periodicals; Machines -- Périodiques; Génie mécanique -- Périodiques; Machine theory; Machinery; Periodicals; 621.81
• DOI: 10.1016/j.mechmachtheory.2020.103932
• Languages: English
• ISSNs: 0094-114X

Abstract

Highlights: A deep learning-based cross-domain fault diagnosis method is proposed for ball screw. Raw torque data are directly used for diagnostics, rather than the popular vibration data. A domain adaptation approach is proposed to extract generalized features for diagnostics. A data segmentation method is introduced for sample preparation in the complex operations of the ball screw. The experimental results on a real-world ball screw dataset validate the effectiveness and superiority of the proposed method. Abstract: Intelligent data-driven fault diagnosis methods have been successfully developed in the recent years. However, as one of the most important machines in the industries, the ball screw health monitoring problem has received less attention, due to the complex operating patterns and sophisticated mechanical structures. In practice, the working conditions of the ball screws usually change, that further makes the fault diagnosis problem more challenging since the data distributions are not the same. In order to address this issue, a deep learning-based domain adaptation method is proposed for the cross-domain ball screw fault diagnosis problem. The deep convolutional neural network is adopted for feature extraction and health condition classification. The maximum mean discrepancy metric is proposed to measure and optimize the data distributions of different operating conditions. A data segmentation method which is specially designed for the ball screw is further integrated. The experiments on the real ball screw condition monitoring data are carried out for validation. The results indicate the proposed approach is promising for the cross-domain diagnostic tasks of the ball screw in the real industries.