Abstract
The Ensemble Empirical Mode Decomposition (EEMD) algorithm has been used in bearing fault diagnosis. In order to overcome the blindness in the selection of white noise amplitude coefficient e in EEMD, an improved artificial bee colony algorithm (IABC) is proposed to obtain it adaptively, which providing a new idea for the selection of EEMD parameters. In the improved algorithm, chaos initialization is introduced in the artificial bee colony (ABC) algorithm to insure the diversity of the population and the ergodicity of the population search process. On the other hand, the collecting bees are divided into two parts in the improved algorithm, one part collects the optimal information of the region according to the original algorithm, the other does Levy flight around the current global best solution to improve its global search capabilities. Four standard test functions are used to show the superiority of the proposed method. The application of the IABC and EEMD algorithm in bearing fault diagnosis proves its effectiveness.
Highlights
A bearing is an essential part in a rotating machine, which can be damaged
The scholars’ research on bearing fault diagnosis can be roughly divided into the following: signal analysis based on vibration [1,2,3,4], monitoring based on temperature [5], and analysis based on acoustic emission [6,7], etc
This paper proposes a new idea of using an improved artificial bee colony (ABC) optimization method to select the Ensemble Empirical Mode Decomposition (EEMD) parameter e, which reduces the blindness of selecting e when extracting the fault features and improves the applicability of EEMD
Summary
A bearing is an essential part in a rotating machine, which can be damaged. At present, the scholars’ research on bearing fault diagnosis can be roughly divided into the following: signal analysis based on vibration [1,2,3,4], monitoring based on temperature [5], and analysis based on acoustic emission [6,7], etc. The time domain method extracts the time domain characteristics by calculating the time domain parameters of the vibration signal This method can directly reflect the characteristic information, and the calculation is simple [9]. The frequency domain diagnosis method analyzes the fault by identifying the difference in the frequency characteristics of the vibration signal between the fault and the normal state. It is based on the theory of Fourier transform [10], which is a global transformation, and unable to perform local analysis for non-stationary and nonlinear signals, it is a pure frequency domain analysis method.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
