Abstract
Roller bearing plays a significant role in industrial sectors. To improve the ability of roller bearing fault diagnosis under multi-rotating situation, this paper proposes a novel roller bearing fault characteristic: the Amplitude Modulation (AM) based correntropy extracted from the Intrinsic Mode Functions (IMFs), which are decomposed by Fast Ensemble Empirical mode decomposition (FEEMD) and employ Least Square Support Vector Machine (LSSVM) to implement intelligent fault identification. Firstly, the roller bearing vibration acceleration signal is decomposed by FEEMD to extract IMFs. Secondly, IMF correntropy matrix (IMFCM) as the fault feature matrix is calculated from the AM-correntropy model of the primary vibration signal and IMFs. Furthermore, depending on LSSVM, the fault identification results of the roller bearing are obtained. Through the bearing identification experiments in stationary rotating conditions, it was verified that IMFCM generates more stable and higher diagnosis accuracy than conventional fault features such as energy moment, fuzzy entropy, and spectral kurtosis. Additionally, it proves that IMFCM has more diagnosis robustness than conventional fault features under cross-mixed roller bearing operating conditions. The diagnosis accuracy was more than 84% for the cross-mixed operating condition, which is much higher than the traditional features. In conclusion, it was proven that FEEMD-IMFCM-LSSVM is a reliable technology for roller bearing fault diagnosis under the constant or multi-positioned operating conditions, and as such, it possesses potential prospects for a broad application of uses.
Highlights
As one of the pivotal mechanized devices, roller bearings constantly rotate in harsh industrial environments that often feature high temperatures, variable rotational speeds, and big loads; as such, they have a high breakdown probability [1]
To extract the cachets comprehensively, here we propose the Intrinsic Mode Functions (IMFs) correntropy matrix (IMFCM) which is comprised of four dimensions which are: fault state class, total number of sample data, data length, and IMF number in each Fast Ensemble Empirical mode decomposition (FEEMD) process
In which θ is CR, η is MR, μ is AR, and their values all range from 0 to 1. λ is the sample number recognized correctly among the specific category samples, χ refers to the sum of the tested samples of the specific category, τ is the number of other recognized as the specific of the specific category, τ issample the sample number ofcategories other categories recognized as thecategory, specific ζcategory, is the sum of all samples, ψ is the sum of all class identification accuracy, and υ is the number ζ is the sum of all samples, ψ is the sum of all class identification accuracy, and υ is the of categories
Summary
As one of the pivotal mechanized devices, roller bearings constantly rotate in harsh industrial environments that often feature high temperatures, variable rotational speeds, and big loads; as such, they have a high breakdown probability [1]. It is of great significance to develop identification techniques for determining the condition of roller bearings in order to ensure the safety. Entropy 2016, 18, 242 of the facility and its operations For this reason, the fault diagnosis of roller bearings has been a research focus in various related fields. Pattern recognition is one of the popular roller bearing fault diagnosis approaches which has constantly been developing from its initial form of distinguishing the condition of roller bearings by analyzing sound differences. Many approaches have been proposed to achieve successful roller bearing fault diagnosis [2,3,4]. The current fault diagnosis technical structure includes two aspects: feature extraction and pattern identification [5]. In order to fundamentally improve the fault diagnosis ability, it is more convincing to determine a fault divisible feature, which can be revealed in a variety of forms in order to show the diagnosis results
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
