Gearbox Fault Diagnosis Based on Selective Integrated Soft Competitive Learning Fuzzy Adaptive Resonance TheorySource: Journal of Computing and Information Science in Engineering:;2019:;volume( 019 ):;issue: 001::page 11008DOI: 10.1115/1.4041776Publisher: The American Society of Mechanical Engineers (ASME)
Abstract: In this work, a soft competitive learning fuzzy adaptive resonance theory (SFART) diagnosis model based on multifeature domain selection for the single symptom domain and the single-target model is proposed. In order to solve the problem that the performance of traditional fuzzy ART (FART) is affected by the order of sample input, the similarity criterion of YU norm is introduced into the fuzzy ART network. In the meanwhile, the lateral inhibition theory is introduced to solve the wasteful problem of fuzzy ART mode node. By combining YU norm and lateral inhibition theory with fuzzy ART network, a soft competitive learning ART neural network diagnosis model that allows multiple mode nodes to learn simultaneously is designed. The feature parameters are extracted from the perspectives of time domain, frequency domain, time series model, wavelet analysis, and wavelet packet energy spectrum analysis, respectively. To further improve the diagnostic accuracy, the selective weighted majority voting method is integrated into the diagnosis model. Finally, the selected feature parameters are inputted to the integrated model to complete the fault classification and diagnosis. Finally, the proposed method is verified with a gearbox fault diagnosis test.
|
Show full item record
contributor author | Wan, Xiao-Jin | |
contributor author | Liu, Licheng | |
contributor author | Xu, Zengbing | |
contributor author | Xu, Zhigang | |
date accessioned | 2019-03-17T10:55:37Z | |
date available | 2019-03-17T10:55:37Z | |
date copyright | 11/19/2018 12:00:00 AM | |
date issued | 2019 | |
identifier issn | 1530-9827 | |
identifier other | jcise_019_01_011008.pdf | |
identifier uri | http://yetl.yabesh.ir/yetl1/handle/yetl/4256404 | |
description abstract | In this work, a soft competitive learning fuzzy adaptive resonance theory (SFART) diagnosis model based on multifeature domain selection for the single symptom domain and the single-target model is proposed. In order to solve the problem that the performance of traditional fuzzy ART (FART) is affected by the order of sample input, the similarity criterion of YU norm is introduced into the fuzzy ART network. In the meanwhile, the lateral inhibition theory is introduced to solve the wasteful problem of fuzzy ART mode node. By combining YU norm and lateral inhibition theory with fuzzy ART network, a soft competitive learning ART neural network diagnosis model that allows multiple mode nodes to learn simultaneously is designed. The feature parameters are extracted from the perspectives of time domain, frequency domain, time series model, wavelet analysis, and wavelet packet energy spectrum analysis, respectively. To further improve the diagnostic accuracy, the selective weighted majority voting method is integrated into the diagnosis model. Finally, the selected feature parameters are inputted to the integrated model to complete the fault classification and diagnosis. Finally, the proposed method is verified with a gearbox fault diagnosis test. | |
publisher | The American Society of Mechanical Engineers (ASME) | |
title | Gearbox Fault Diagnosis Based on Selective Integrated Soft Competitive Learning Fuzzy Adaptive Resonance Theory | |
type | Journal Paper | |
journal volume | 19 | |
journal issue | 1 | |
journal title | Journal of Computing and Information Science in Engineering | |
identifier doi | 10.1115/1.4041776 | |
journal fristpage | 11008 | |
journal lastpage | 011008-13 | |
tree | Journal of Computing and Information Science in Engineering:;2019:;volume( 019 ):;issue: 001 | |
contenttype | Fulltext |