Gearbox Fault Diagnosis Based on AIS-ICA Algorithm

Jin Ying Huang; Hong Xia Pan; Ya Hui Lu; Yue Li

doi:10.4028/www.scientific.net/AMM.121-126.4476

Paper Titles

Empirical Analysis of Express Service Quality Based on Fuzzy Comprehensive Evaluation
p.4456

The Development of Lungmen ABWR TRACE Safety Analysis Model
p.4461

Establishment of Virtual Orthopaedic Surgery System
p.4466

Fault Prediction for Nonlinear Time Series Based on Temporal Pattern Estimation
p.4471

Gearbox Fault Diagnosis Based on AIS-ICA Algorithm
p.4476

General Fault Monitoring and Diagnosis Expert System Based on Fault Tree and Multi-Sensor Information
p.4481

Girth Calculative Rules Research of Female Lower Body Torso Based on Three Dimensional Cloud Point Data
p.4486

Grid-Based Task Scheduling PMTS Algorithm
p.4491

LZW Algorithm Research and Amelioration Based on Pointer Trace
p.4498

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 121-126Gearbox Fault Diagnosis Based on AIS-ICA Algorithm

Gearbox Fault Diagnosis Based on AIS-ICA Algorithm

Abstract:

Immune theory is applied to independent component analysis in this paper. By elaborated on blind source separation procedure, the blind source separation based on immune optimization algorithm is put forward, that is AIS-ICA algorithm. The paper carried out simulation experiments of mixing and separation for four specific signals. The experimental results show that the convergence speed and separation precision is high, and it has good stability. The new algorithm is used to gearbox vibration signals for blind source separation and fault diagnosis, fault information carried by vibration signals enhanced. Results show that the algorithm used to separate vibration signals of gearbox can greatly enhance fault information, reducing difficulty of gearbox fault diagnosis.

You might also be interested in these eBooks

Frontiers of Manufacturing and Design Science II

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 121-126)

Pages:

4476-4480

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.121-126.4476

Citation:

Cite this paper

Online since:

October 2011

Authors:

Jin Ying Huang, Hong Xia Pan, Ya Hui Lu, Yue Li

Keywords:

AIS-ICA, Artificial Immunity, Fault Diagnosis, Independent Component Analysis (ICA)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Chen Chang-zheng, etc. Condition monitoring and fault diagnosis of gear box based on blind source separation. Journal of Shenyang University of Technology, 2008, 30(14): 444-448.

Google Scholar

[2] Shi Qing-bin, Ma Jian-cang. Study on Blind Source Separation of Mechanical Vibration Signal. Measurement & Control Technology, 2008, 27(5): 78-80.

Google Scholar

[3] Aapo Hyv¨arinen. Fast and Robust Fixed-Point Algorithms for Independent Component Analysis. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10(3), pp.626-634.

DOI: 10.1109/72.761722

Google Scholar

[4] Zhang Jin-yu, etc. A comparison of several blind-source-separation algorithms for mechanical signal processing. Journal of Vibration Engineering, 2008, 121(4): 409-416.

Google Scholar

[5] Gang Shi, etc. Research of Improved Immune Clonal Algorithms and its Applications. CIMSA (2009).

Google Scholar

[6] Wang Kun, Zhang Wei. The Application and Comparison of Two Evolution Algorithm in Blind Source Separation. Journal of Xi'an University of Arts & Science, 2009, 12(2): 36-39.

Google Scholar