Cargando…

Fault Diagnosis of Rotary Parts of a Heavy-Duty Horizontal Lathe Based on Wavelet Packet Transform and Support Vector Machine

The spindle box is responsible for power transmission, supporting the rotating parts and ensuring the rotary accuracy of the workpiece in the heavy-duty machine tool. Its assembly quality is crucial to ensure the reliable power supply and stable operation of the machine tool in the process of large...

Descripción completa

Detalles Bibliográficos
Autores principales: Jin, Hongyu, Titus, Avitus, Liu, Yulong, Wang, Yang, Han, Zhenyu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6806313/
https://www.ncbi.nlm.nih.gov/pubmed/31547146
http://dx.doi.org/10.3390/s19194069
_version_ 1783461601273184256
author Jin, Hongyu
Titus, Avitus
Liu, Yulong
Wang, Yang
Han, Zhenyu
author_facet Jin, Hongyu
Titus, Avitus
Liu, Yulong
Wang, Yang
Han, Zhenyu
author_sort Jin, Hongyu
collection PubMed
description The spindle box is responsible for power transmission, supporting the rotating parts and ensuring the rotary accuracy of the workpiece in the heavy-duty machine tool. Its assembly quality is crucial to ensure the reliable power supply and stable operation of the machine tool in the process of large load and cutting force. Therefore, accurate diagnosis of assembly faults is of great significance for improving assembly efficiency and ensuring outgoing quality. In this paper, the common fault types and characteristics of the spindle box of heavy horizontal lathe are analyzed first, and original vibration signals of various fault types are collected. The wavelet packet is used to decompose the signal into different frequency bands and reconstruct the nodes in the frequency band where the characteristic frequency points are located. Then, the power spectrum analysis is carried out on the reconstructed signal, so that the fault features in the signal can be clearly expressed. The structure of the feature vector used for fault diagnosis is analyzed and the feature vector is extracted from the collected signals. Finally, the intelligent pattern recognition method based on support vector machine is used to classify the fault types. The results show that the method proposed in this paper can quickly and accurately judge the fault types.
format Online
Article
Text
id pubmed-6806313
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-68063132019-11-07 Fault Diagnosis of Rotary Parts of a Heavy-Duty Horizontal Lathe Based on Wavelet Packet Transform and Support Vector Machine Jin, Hongyu Titus, Avitus Liu, Yulong Wang, Yang Han, Zhenyu Sensors (Basel) Article The spindle box is responsible for power transmission, supporting the rotating parts and ensuring the rotary accuracy of the workpiece in the heavy-duty machine tool. Its assembly quality is crucial to ensure the reliable power supply and stable operation of the machine tool in the process of large load and cutting force. Therefore, accurate diagnosis of assembly faults is of great significance for improving assembly efficiency and ensuring outgoing quality. In this paper, the common fault types and characteristics of the spindle box of heavy horizontal lathe are analyzed first, and original vibration signals of various fault types are collected. The wavelet packet is used to decompose the signal into different frequency bands and reconstruct the nodes in the frequency band where the characteristic frequency points are located. Then, the power spectrum analysis is carried out on the reconstructed signal, so that the fault features in the signal can be clearly expressed. The structure of the feature vector used for fault diagnosis is analyzed and the feature vector is extracted from the collected signals. Finally, the intelligent pattern recognition method based on support vector machine is used to classify the fault types. The results show that the method proposed in this paper can quickly and accurately judge the fault types. MDPI 2019-09-20 /pmc/articles/PMC6806313/ /pubmed/31547146 http://dx.doi.org/10.3390/s19194069 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Jin, Hongyu
Titus, Avitus
Liu, Yulong
Wang, Yang
Han, Zhenyu
Fault Diagnosis of Rotary Parts of a Heavy-Duty Horizontal Lathe Based on Wavelet Packet Transform and Support Vector Machine
title Fault Diagnosis of Rotary Parts of a Heavy-Duty Horizontal Lathe Based on Wavelet Packet Transform and Support Vector Machine
title_full Fault Diagnosis of Rotary Parts of a Heavy-Duty Horizontal Lathe Based on Wavelet Packet Transform and Support Vector Machine
title_fullStr Fault Diagnosis of Rotary Parts of a Heavy-Duty Horizontal Lathe Based on Wavelet Packet Transform and Support Vector Machine
title_full_unstemmed Fault Diagnosis of Rotary Parts of a Heavy-Duty Horizontal Lathe Based on Wavelet Packet Transform and Support Vector Machine
title_short Fault Diagnosis of Rotary Parts of a Heavy-Duty Horizontal Lathe Based on Wavelet Packet Transform and Support Vector Machine
title_sort fault diagnosis of rotary parts of a heavy-duty horizontal lathe based on wavelet packet transform and support vector machine
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6806313/
https://www.ncbi.nlm.nih.gov/pubmed/31547146
http://dx.doi.org/10.3390/s19194069
work_keys_str_mv AT jinhongyu faultdiagnosisofrotarypartsofaheavydutyhorizontallathebasedonwaveletpackettransformandsupportvectormachine
AT titusavitus faultdiagnosisofrotarypartsofaheavydutyhorizontallathebasedonwaveletpackettransformandsupportvectormachine
AT liuyulong faultdiagnosisofrotarypartsofaheavydutyhorizontallathebasedonwaveletpackettransformandsupportvectormachine
AT wangyang faultdiagnosisofrotarypartsofaheavydutyhorizontallathebasedonwaveletpackettransformandsupportvectormachine
AT hanzhenyu faultdiagnosisofrotarypartsofaheavydutyhorizontallathebasedonwaveletpackettransformandsupportvectormachine