Curvature enhanced bearing fault diagnosis method using 2D vibration signal
- PDF / 1,927,179 Bytes
- 10 Pages / 595.22 x 842 pts (A4) Page_size
- 106 Downloads / 231 Views
DOI 10.1007/s12206-020-0501-0
Journal of Mechanical Science and Technology 34 (6) 2020 Original Article DOI 10.1007/s12206-020-0501-0 Keywords: · 2D vibration signal matrix · Curvature filtering · Fault detection · Histogram of oriented gradients (HOG) · Support vector machine (SVM)
Curvature enhanced bearing fault diagnosis method using 2D vibration signal Weifang Sun1 and Xincheng Cao2 1
College of Mechanical and Electrical Engineering, Wenzhou University, Wenzhou 325035, China, School of Aerospace Engineering, Xiamen University, Xiamen 361005, China
2
Correspondence to: Xincheng Cao [email protected]
Citation: Sun, W., Cao, X. (2020). Curvature enhanced bearing fault diagnosis method using 2D vibration signal. Journal of Mechanical Science and Technology 34 (6) (2020) 2257~2266. http://doi.org/10.1007/s12206-020-0501-0
Received June 9th, 2019 Revised
March 19th, 2020
Accepted April 6th, 2020 † Recommended by Editor No-cheol Park
Abstract
As a novel representation method, two dimensional (2D) segmentation is gaining ground as an effective condition monitoring method due to its high-level information descriptional ability. However, the accuracy of extracting frequency information is still limited by the finite gray-level and the extraction ability of distinguishable texture for each fault. To overcome these drawbacks, this research proposes a bearing fault diagnosis method using the converted 2D vibrational signal matrices. In this method, 1D vibration signals are converted into 2D matrices to exploit the fault signatures from the converted images. Curvature filtering (mean curvature) algorithm is applied to eliminate the overwhelming interfering contents and preserves the necessary edge information contained in the 2D matrix. In addition, the histogram of oriented gradients features is employed for the effective fault feature extraction. Finally, a one-versus-one support vector machine is utilized for the automatically fault classification. An experimental investigation was carried out for the performance evaluation of the proposed method. Comparison results indicate that the established method is capable of bearing fault detection with considerable accuracy.
1. Introduction
© The Korean Society of Mechanical Engineers and Springer-Verlag GmbH Germany, part of Springer Nature 2020
Rotating machines serve as the most important foundation in the prosperous development of the modern manufacturing industry [1]. The unexpected failure of the rotating machine may cause significant economic losses [2]. Therefore, effective health state monitoring is critical for machine performance preservation [3]. In engineering practices, the operational signals of rotating machines are collected using various types of sensors combined with data acquisition equipment [4]. The primary purpose of an acquisition system is to provide reliable information to monitor the operation state. A variety of sensing techniques have been used for this purpose, and these include force [5], acoustic emission (AE) [6], vibration [7], curre
Data Loading...
