Different working conditions affect the sensitivity of vibration signals’ features to fault level in rolling bearings’ performance degradation assessment. Selecting effective features applicable for condition assessment in early limited samples is the key to realize the online assessment of rolling bearings’ performance degradation level. Here, an early limited sample determination method named the limited feature select sample (LFSS) was proposed based on root mean square, then an improved binary bat algorithm (BBA) named the feedback seeking BBA (FSBBA) aiming at feature selection of performance degradation assessment was proposed. They overcame the disadvantage that BBA is easy to fall into local optimization when it is applied to select fault features in bearings’ early limited samples. The model for rolling bearings’ online condition assessment was constructed based on LFSS and FSBBA. This model was applied in two examples of rolling bearings’ whole life data feature selection. The analysis results of their performance degradation assessment indexes verified the effectiveness of the proposed method.
Key words
rolling bearing /
feature selection /
LSFF /
FSBBA /
online condition assessment
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
References
[1] Yang X S. Bat algorithm: a novel approach for global engineering optimization[M]. Chemical engineering reference manual :464-483.
[2] Luo J, Liu L, Wu X. A double-subpopulation variant of the bat algorithm[J].Applied Mathematics & Computation, 2015, 263(C):361-377.
[3] Hasançebi O, Teke T, Pekcan O. A bat-inspired algorithm for structural optimization[J]. Computers & Structures, 2013, 128(128):77–90.
[4] Sathya M R, Ansari M M T. Load frequency control using Bat inspired algorithm based dual mode gain scheduling of PI controllers for interconnected power system[J]. International Journal of Electrical Power & Energy Systems, 2015, 64(64):365-374.
[5] Rodrigues D, Pereira L A M, Nakamura R Y M, et al. A wrapper approach for feature selection based on Bat Algorithm and Optimum-Path Forest[J]. Expert Systems with Applications An International Journal, 2014, 41(5):2250-2258.
[6] Kang M, Kim J, Kim J M. Reliable fault diagnosis for incipient low-speed bearings using fault feature analysis based on a binary bat algorithm[J]. Information Sciences, 2015, 311(C):205-206.
[7] Yang X S. A New Metaheuristic Bat-Inspired Algorithm[J]. Computer Knowledge and Technology, 2010, 284:65-74.
[8]Case Westen Reserve University. Bearing data centerEB/OL. 2014-6.http://csegroups.case.edu/bearing data center/pages/welcome-case-western-reserve-university-bearing-data-center-website.
[9] Lee J., H. Qiu, G. Yu, J. Lin, and Rexnord Technical Services, 2007. 'Bearing Data Set', IMS, University of Cincinnati. NASA Ames Prognostics Data Repository, [http://ti.arc.nasa.g ov/project/prognostic-data-repository], NASA Ames, Moffett Field, CA.
{{custom_fnGroup.title_en}}
Footnotes
{{custom_fn.content}}
PDF(1520 KB)
