Fault Diagnosis Based on BP Neural Network Optimized by Beetle Algorithm

Abstract In the process of Wavelet Analysis, only the low-frequency signals are re-decomposed, and the high-frequency signals are no longer decomposed, resulting in a decrease in frequency resolution with increasing frequency. Therefore, in this paper, firstly, Wavelet Packet Decomposition is used f...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Maohua Xiao, Wei Zhang, Kai Wen, Yue Zhu, Yilidaer Yiliyasi
Formato: article
Lenguaje:EN
Publicado: SpringerOpen 2021
Materias:
Acceso en línea:https://doaj.org/article/11a1eb1c7ca14b978561f57af6242e3e
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:11a1eb1c7ca14b978561f57af6242e3e
record_format dspace
spelling oai:doaj.org-article:11a1eb1c7ca14b978561f57af6242e3e2021-12-05T12:03:38ZFault Diagnosis Based on BP Neural Network Optimized by Beetle Algorithm10.1186/s10033-021-00648-21000-93452192-8258https://doaj.org/article/11a1eb1c7ca14b978561f57af6242e3e2021-12-01T00:00:00Zhttps://doi.org/10.1186/s10033-021-00648-2https://doaj.org/toc/1000-9345https://doaj.org/toc/2192-8258Abstract In the process of Wavelet Analysis, only the low-frequency signals are re-decomposed, and the high-frequency signals are no longer decomposed, resulting in a decrease in frequency resolution with increasing frequency. Therefore, in this paper, firstly, Wavelet Packet Decomposition is used for feature extraction of vibration signals, which makes up for the shortcomings of Wavelet Analysis in extracting fault features of nonlinear vibration signals, and different energy values in different frequency bands are obtained by Wavelet Packet Decomposition. The features are visualized by the K-Means clustering method, and the results show that the extracted energy features can accurately distinguish the different states of the bearing. Then a fault diagnosis model based on BP Neural Network optimized by Beetle Algorithm is proposed to identify the bearing faults. Compared with the Particle Swarm Algorithm, Beetle Algorithm can quickly find the error extreme value, which greatly reduces the training time of the model. At last, two experiments are conducted, which show that the accuracy of the model can reach more than 95%, and the model has a certain anti-interference ability.Maohua XiaoWei ZhangKai WenYue ZhuYilidaer YiliyasiSpringerOpenarticleRolling bearingBP neural networkBeetle algorithmWavelet packet transformOcean engineeringTC1501-1800Mechanical engineering and machineryTJ1-1570ENChinese Journal of Mechanical Engineering, Vol 34, Iss 1, Pp 1-10 (2021)
institution DOAJ
collection DOAJ
language EN
topic Rolling bearing
BP neural network
Beetle algorithm
Wavelet packet transform
Ocean engineering
TC1501-1800
Mechanical engineering and machinery
TJ1-1570
spellingShingle Rolling bearing
BP neural network
Beetle algorithm
Wavelet packet transform
Ocean engineering
TC1501-1800
Mechanical engineering and machinery
TJ1-1570
Maohua Xiao
Wei Zhang
Kai Wen
Yue Zhu
Yilidaer Yiliyasi
Fault Diagnosis Based on BP Neural Network Optimized by Beetle Algorithm
description Abstract In the process of Wavelet Analysis, only the low-frequency signals are re-decomposed, and the high-frequency signals are no longer decomposed, resulting in a decrease in frequency resolution with increasing frequency. Therefore, in this paper, firstly, Wavelet Packet Decomposition is used for feature extraction of vibration signals, which makes up for the shortcomings of Wavelet Analysis in extracting fault features of nonlinear vibration signals, and different energy values in different frequency bands are obtained by Wavelet Packet Decomposition. The features are visualized by the K-Means clustering method, and the results show that the extracted energy features can accurately distinguish the different states of the bearing. Then a fault diagnosis model based on BP Neural Network optimized by Beetle Algorithm is proposed to identify the bearing faults. Compared with the Particle Swarm Algorithm, Beetle Algorithm can quickly find the error extreme value, which greatly reduces the training time of the model. At last, two experiments are conducted, which show that the accuracy of the model can reach more than 95%, and the model has a certain anti-interference ability.
format article
author Maohua Xiao
Wei Zhang
Kai Wen
Yue Zhu
Yilidaer Yiliyasi
author_facet Maohua Xiao
Wei Zhang
Kai Wen
Yue Zhu
Yilidaer Yiliyasi
author_sort Maohua Xiao
title Fault Diagnosis Based on BP Neural Network Optimized by Beetle Algorithm
title_short Fault Diagnosis Based on BP Neural Network Optimized by Beetle Algorithm
title_full Fault Diagnosis Based on BP Neural Network Optimized by Beetle Algorithm
title_fullStr Fault Diagnosis Based on BP Neural Network Optimized by Beetle Algorithm
title_full_unstemmed Fault Diagnosis Based on BP Neural Network Optimized by Beetle Algorithm
title_sort fault diagnosis based on bp neural network optimized by beetle algorithm
publisher SpringerOpen
publishDate 2021
url https://doaj.org/article/11a1eb1c7ca14b978561f57af6242e3e
work_keys_str_mv AT maohuaxiao faultdiagnosisbasedonbpneuralnetworkoptimizedbybeetlealgorithm
AT weizhang faultdiagnosisbasedonbpneuralnetworkoptimizedbybeetlealgorithm
AT kaiwen faultdiagnosisbasedonbpneuralnetworkoptimizedbybeetlealgorithm
AT yuezhu faultdiagnosisbasedonbpneuralnetworkoptimizedbybeetlealgorithm
AT yilidaeryiliyasi faultdiagnosisbasedonbpneuralnetworkoptimizedbybeetlealgorithm
_version_ 1718372298009870336