Resonance-based sparse improved fast independent component analysis and its application to the feature extraction of pla
- PDF / 2,365,043 Bytes
- 10 Pages / 595.22 x 842 pts (A4) Page_size
- 79 Downloads / 143 Views
DOI 10.1007/s12206-020-1007-5
Journal of Mechanical Science and Technology 34 (11) 2020 Original Article DOI 10.1007/s12206-020-1007-5 Keywords: · Fast independent component analysis · Fault diagnosis · Planetary gearbox · Resonance sparse signal decomposition
Correspondence to: Aidong Deng [email protected]
Citation: Zhu, J., Deng, A., Li, J., Deng, M., Sun, W., Cheng, Q., Liu, Y. (2020). Resonance-based sparse improved fast independent component analysis and its application to the feature extraction of planetary gearboxes. Journal of Mechanical Science and Technology 34 (11) (2020) 4465~4474. http://doi.org/10.1007/s12206-020-1007-5
Received February 17th, 2020 Revised
June 22th, 2020
Accepted August 6th, 2020
Resonance-based sparse improved fast independent component analysis and its application to the feature extraction of planetary gearboxes Jing Zhu1, Aidong Deng1, Jing Li2, Minqiang Deng1, Wenqing Sun1, Qiang Cheng1 and Yang Liu1 1
2
School of Energy and Environment, Southeast University, Nanjing, CO 210009, China, School of Information Engineering, Nanjing Audit University, Nanjing, CO 210009, China
Abstract
A resonance-based sparse improved fast independent component analysis (ICA) (RSIFICA) is proposed to extract the fault characteristics of planetary gearbox. First, the signal is decomposed using resonance sparse signal decomposition (RSSD). Second, highresonance components were retained while others were eliminated. Finally, the signal after dimension reduction was analyzed using ICA, and the fault characteristic frequency was extracted through envelope spectrum analysis. In this process, the preset Q parameter of RSSD is optimized on the basis of fuzzy entropy and ant-lion optimization algorithm. The accuracy of RSSD was improved by performing time-frequency entropy component selection. FastICA was improved, and the slow convergence problem of ICA was solved. Results showed that RSIFICA could extract the fault characteristic frequency accurately, and the calculation efficiency of FastICA increased by 21.49 %. In terms of extracting the fault features, its performance could be better than EMD-FastICA.
† Recommended by Editor No-cheol Park
1. Introduction
© The Korean Society of Mechanical Engineers and Springer-Verlag GmbH Germany, part of Springer Nature 2020
Planetary gearboxes have large power transmission capacity in a compact structure, small volume, light weight, big transmission ratio, and high transmission efficiency. Based on the aforementioned advantages, these gearboxes occupy the main position in the field of industrial production and engineering, such as in wind turbines, helicopters, construction machines, and other types of transmission systems. However, most planetary gearboxes are prone to failure because of adverse working conditions and alternating loads [1]. Therefore, fault diagnosis and monitoring of planetary gearbox are important to ensure the normal and safe operations of a mechanical system. In practical engineering applications, the vibration signal of the planetar
Data Loading...
