• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
成果搜索

Inventor:

Yao;Ligang (Yao;Ligang.) [1] (Scholars:姚立纲) | Wang;Zhenya (Wang;Zhenya.) [2] | Li;Gaosong (Li;Gaosong.) [3] | Chen;Gang (Chen;Gang.) [4] | Ding;Jiaxin (Ding;Jiaxin.) [5]

Indexed by:

incoPat

Abstract:

ABSTRACT  The invention relates to a planetary gearbox fault diagnosis method. First of all,  the signal is  decomposed and reconstructed by using the Salp Swarm Optimization algorithm to optimize  the Variational Mode Decomposition algorithm (SSO-VMD). Then,  the fault features are  extracted from multiple domains,  and the improved supervised self-organizing incremental  learning neural network landmark point isometric mapping (ISSL-Isomap) manifold learning  algorithm is used to reduce the dimensionality. Finally,  the Artificial Bee Colony Optimization  Support Vector Machine (ABC-SVM) classifier is used for diagnosis and recognition. The  invention overcomes the problem of parameter selection in the VMD algorithm and solves the  problem of information redundancy existing in multi-domain features. The experimental  results of the planetary gearbox fault diagnosis show that the proposed method can effectively  identify the types of faults and has great practical value. 1/7  FIGURES  vibration acceleration signals  SSO-VMD decomposition andi reconstruction  timle-domint,  frequency-domain scale-domain  construct multi-dimensional fault features set  se SSL-Isomap to perform dimensionality reduction  low-dimensional features set of trainngsamnpless low-dlimei nsional features set of test saimples set  train ABC-SVM classifier trained ABC-SVM classifier model  diagnose fault type  Figure 1  0 01  Normal 0 00  0.01 '  0.00 0.05 010 0.15 0.20  times  0.05 1  Wear 0.00 IIII  0.0  .00 0.05 010 015 020  time/s  Crack 0. 00  S 0.02----- 0 0.00 0.05 0.10 0.15 0.20  time/s  0. 0 2  - hI. -l...L.L.d uAJ a 16 uw L..   Brokenteeth 0.00  0.02  0.00 0.05 0.10 0.15 0.20  times  Figure 2

Keyword:

Reprint 's Address:

Email:

Show more details

Related Keywords:

Related Article:

Patent Info :

Type: 实用新型

Patent No.: AU2021105779

Filing Date: 2021-08-18

Publication Date: 2021-10-21

Pub. No.: AU2021105779A4

公开国别: AU

Applicants: Fuzhou;University

Legal Status: 授权

Cited Count:

WoS CC Cited Count: 0

SCOPUS Cited Count:

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 0

Online/Total:40/10100950
Address:FZU Library(No.2 Xuyuan Road, Fuzhou, Fujian, PRC Post Code:350116) Contact Us:0591-22865326
Copyright:FZU Library Technical Support:Beijing Aegean Software Co., Ltd. 闽ICP备05005463号-1