A fault diagnosis method of rolling bearing based on VMD Tsallis entropy and FCM clustering
- PDF / 1,495,497 Bytes
- 17 Pages / 439.37 x 666.142 pts Page_size
- 40 Downloads / 188 Views
A fault diagnosis method of rolling bearing based on VMD Tsallis entropy and FCM clustering Xing Ting-ting 1,2 & Zeng Yan 2
1
& Meng Zong & Guo Xiao-lin
1
Received: 11 November 2019 / Revised: 29 July 2020 / Accepted: 4 August 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
A new fault diagnosis method of rolling bearings was presented based on variational mode decomposition (VMD), Tsallis entropy and Fuzzy C-means clustering (FCM) algorithm. Firstly, the measured vibration signals were decomposed with VMD in different scales to obtain a series of band-limited intrinsic modal function (BIMF). The VMD parameters were determined according to the change of the BIMF center frequency. Then, the Tsallis entropy of BIMF components were calculated and used as the signal features. Finally, the features were put into FCM classifier to recognize different fault types. It is proved by experiments that this method is feasible and the proposed approach could obtain better result compared with the method based on mode decomposition (EMD) and local mean decomposition (LMD). Keywords Variational mode decomposition (VMD) . Tsallis entropy . Fuzzy C-means clustering (FCM) algorithm . Fault diagnosis . Rolling bearing
1 Introduction Rolling bearing is an important component of rotation machinery, its operation directly affects the working condition of the whole mechanical equipment. The bearing failure will cause huge security risks in the manufacturing process. Therefore, it has a very import significant for online monitoring and fault-diagnosis of rolling bearings [2, 28]. This is why fault diagnosis of rolling bearing becomes a research focus, and many the vibration analysis methodologies have been proposed. When a rolling bearing fails, the collision occurs between the faulty part and other components, and non-stationary, non-linear shock signals can be obtained from the sensor installed on the device. This is also the basic principle of these analysis methodologies.
* Zeng Yan [email protected]
1
Key Laboratory of Measurement Technology and Instrumention of HeBei Province, Yanshan University, Qinhuangdao 066004 Hebei, China
2
Tangshan Polytechnic College, Tangshan 063299 Hebei, China
Multimedia Tools and Applications
Most methods include two typical steps: feature extraction and selection, condition classification. In the first step, time domain, frequency domain, and time-frequency domain analysis are often applied [21]. The extracted time domain features like peak-to-peak value, root mean square value, kurtosis indicator, etc. obtained from the raw signals can be used, but some information are not easily observed. Frequency domain analysis could solve this problem which conduct FFT on the raw vibration signal, then analyzing the power spectrum, kurtosis spectrum, order cepstrum, envelope spectrum, etc. for diagnosis [5, 11, 32]. However, frequency domain analysis has limited analytical capabilities for non-stationary signals and this is why time-frequency domain analysis have
Data Loading...
