Feature Extraction of Double Pulse Metal Inert Gas Welding Based on Broadband Mode Decomposition and Locality Preserving Projection
A novel adaptive signal decomposition algorithm, broadband mode decomposition (BMD), is proposed for analyzing nonstationary broadband signals. Unavoidable error will occur when applying former time-frequency methods to broadband signals, which is caused by Gibbs phenomenon and the calculation of ex...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2020-01-01
|
Series: | Mathematical Problems in Engineering |
Online Access: | http://dx.doi.org/10.1155/2020/7576034 |
id |
doaj-782b1905539a4c69bbdaca6fe1a7ef14 |
---|---|
record_format |
Article |
spelling |
doaj-782b1905539a4c69bbdaca6fe1a7ef142020-11-25T03:27:59ZengHindawi LimitedMathematical Problems in Engineering1024-123X1563-51472020-01-01202010.1155/2020/75760347576034Feature Extraction of Double Pulse Metal Inert Gas Welding Based on Broadband Mode Decomposition and Locality Preserving ProjectionYanfeng Peng0Zucheng Wang1Kuanfang He2Yanfei Liu3Qingxian Li4Liangjiang Liu5Xianyu Zhu6Hunan Provincial Key Laboratory of Health Maintenance for Mechanical Equipment, Hunan University of Science and Technology, Xiangtan 411201, ChinaHunan Provincial Key Laboratory of Health Maintenance for Mechanical Equipment, Hunan University of Science and Technology, Xiangtan 411201, ChinaHunan Provincial Key Laboratory of Health Maintenance for Mechanical Equipment, Hunan University of Science and Technology, Xiangtan 411201, ChinaCollege of Mechanical and Vehicle Engineering, Hunan University, Changsha 410082, ChinaHunan Institute of Metrology and Test, Changsha 410014, ChinaHunan Institute of Metrology and Test, Changsha 410014, ChinaHunan Institute of Metrology and Test, Changsha 410014, ChinaA novel adaptive signal decomposition algorithm, broadband mode decomposition (BMD), is proposed for analyzing nonstationary broadband signals. Unavoidable error will occur when applying former time-frequency methods to broadband signals, which is caused by Gibbs phenomenon and the calculation of extrema. To overcome that problem, BMD is proposed by searching in the associative dictionary that contains both broadband and narrowband signals. The procedure of the proposed method is as follows: First, the collected datasets are analyzed by BMD and the composite multiscale fuzzy entropies (CMFEs) of the obtained effective components are calculated. Then, locality preserving projection (LPP) is applied for further feature extraction. Analysis results show BMD is more effective when drawing broadband feature from noise and BMD is adaptive for the quality monitoring of DPMIG welding.http://dx.doi.org/10.1155/2020/7576034 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yanfeng Peng Zucheng Wang Kuanfang He Yanfei Liu Qingxian Li Liangjiang Liu Xianyu Zhu |
spellingShingle |
Yanfeng Peng Zucheng Wang Kuanfang He Yanfei Liu Qingxian Li Liangjiang Liu Xianyu Zhu Feature Extraction of Double Pulse Metal Inert Gas Welding Based on Broadband Mode Decomposition and Locality Preserving Projection Mathematical Problems in Engineering |
author_facet |
Yanfeng Peng Zucheng Wang Kuanfang He Yanfei Liu Qingxian Li Liangjiang Liu Xianyu Zhu |
author_sort |
Yanfeng Peng |
title |
Feature Extraction of Double Pulse Metal Inert Gas Welding Based on Broadband Mode Decomposition and Locality Preserving Projection |
title_short |
Feature Extraction of Double Pulse Metal Inert Gas Welding Based on Broadband Mode Decomposition and Locality Preserving Projection |
title_full |
Feature Extraction of Double Pulse Metal Inert Gas Welding Based on Broadband Mode Decomposition and Locality Preserving Projection |
title_fullStr |
Feature Extraction of Double Pulse Metal Inert Gas Welding Based on Broadband Mode Decomposition and Locality Preserving Projection |
title_full_unstemmed |
Feature Extraction of Double Pulse Metal Inert Gas Welding Based on Broadband Mode Decomposition and Locality Preserving Projection |
title_sort |
feature extraction of double pulse metal inert gas welding based on broadband mode decomposition and locality preserving projection |
publisher |
Hindawi Limited |
series |
Mathematical Problems in Engineering |
issn |
1024-123X 1563-5147 |
publishDate |
2020-01-01 |
description |
A novel adaptive signal decomposition algorithm, broadband mode decomposition (BMD), is proposed for analyzing nonstationary broadband signals. Unavoidable error will occur when applying former time-frequency methods to broadband signals, which is caused by Gibbs phenomenon and the calculation of extrema. To overcome that problem, BMD is proposed by searching in the associative dictionary that contains both broadband and narrowband signals. The procedure of the proposed method is as follows: First, the collected datasets are analyzed by BMD and the composite multiscale fuzzy entropies (CMFEs) of the obtained effective components are calculated. Then, locality preserving projection (LPP) is applied for further feature extraction. Analysis results show BMD is more effective when drawing broadband feature from noise and BMD is adaptive for the quality monitoring of DPMIG welding. |
url |
http://dx.doi.org/10.1155/2020/7576034 |
work_keys_str_mv |
AT yanfengpeng featureextractionofdoublepulsemetalinertgasweldingbasedonbroadbandmodedecompositionandlocalitypreservingprojection AT zuchengwang featureextractionofdoublepulsemetalinertgasweldingbasedonbroadbandmodedecompositionandlocalitypreservingprojection AT kuanfanghe featureextractionofdoublepulsemetalinertgasweldingbasedonbroadbandmodedecompositionandlocalitypreservingprojection AT yanfeiliu featureextractionofdoublepulsemetalinertgasweldingbasedonbroadbandmodedecompositionandlocalitypreservingprojection AT qingxianli featureextractionofdoublepulsemetalinertgasweldingbasedonbroadbandmodedecompositionandlocalitypreservingprojection AT liangjiangliu featureextractionofdoublepulsemetalinertgasweldingbasedonbroadbandmodedecompositionandlocalitypreservingprojection AT xianyuzhu featureextractionofdoublepulsemetalinertgasweldingbasedonbroadbandmodedecompositionandlocalitypreservingprojection |
_version_ |
1715207099473985536 |