Defect intelligent identification in resistance spot welding ultrasonic detection based on wavelet packet and neural network

Jing Liu; Guocheng Xu; Lei Ren; Zhihui Qian; Luquan Ren

doi:10.1007/s00170-016-9588-y

Defect intelligent identification in resistance spot welding ultrasonic detection based on wavelet packet and neural network

Jing Liu, Guocheng Xu, Lei Ren, Zhihui Qian, Luquan Ren

Jilin University

Research output: Contribution to journal › Article › peer-review

224 Downloads (Pure)

Abstract

In this paper, ultrasonic echo signals of four kinds of stainless steel resistance spot welds, namely failed weld, stick weld, good weld, and defective weld with gas pore, are analyzed in the time domain, frequency domain, and time-frequency domain based on wavelet packet transform. Fourteen ultrasonic characteristic signals which can reflect the different kinds of spot welds are extracted and can be automatically identified and classified by back-propagation (BP) neural network. The method of this paper can realize the intelligent identification of resistance spot welding defects, and the feasibility of this method has been verified in the experiment.

Original language	English
Pages (from-to)	2581-2588
Journal	International Journal of Advanced Manufacturing Technology
Volume	90
Early online date	19 Oct 2016
DOIs	https://doi.org/10.1007/s00170-016-9588-y
Publication status	Published - Jun 2017

Keywords

Ultrasonic detection Defect intelligent identification Resistance spot welding BP neural network Wavelet packet transform

Access to Document

10.1007/s00170-016-9588-y

Defect intelligent identification in resistance spot welding ultrasonic detection based on wavelet packet and neural networkAccepted author manuscript, 9.28 MB

Cite this

@article{7f82c8471aee4264a30dfb534a7b7805,

title = "Defect intelligent identification in resistance spot welding ultrasonic detection based on wavelet packet and neural network",

abstract = "In this paper, ultrasonic echo signals of four kinds of stainless steel resistance spot welds, namely failed weld, stick weld, good weld, and defective weld with gas pore, are analyzed in the time domain, frequency domain, and time-frequency domain based on wavelet packet transform. Fourteen ultrasonic characteristic signals which can reflect the different kinds of spot welds are extracted and can be automatically identified and classified by back-propagation (BP) neural network. The method of this paper can realize the intelligent identification of resistance spot welding defects, and the feasibility of this method has been verified in the experiment.",

keywords = "Ultrasonic detection Defect intelligent identification Resistance spot welding BP neural network Wavelet packet transform",

author = "Jing Liu and Guocheng Xu and Lei Ren and Zhihui Qian and Luquan Ren",

year = "2017",

month = jun,

doi = "10.1007/s00170-016-9588-y",

language = "English",

volume = "90",

pages = "2581--2588",

journal = "International Journal of Advanced Manufacturing Technology",

issn = "0268-3768",

publisher = "Springer London",

}

TY - JOUR

T1 - Defect intelligent identification in resistance spot welding ultrasonic detection based on wavelet packet and neural network

AU - Liu, Jing

AU - Xu, Guocheng

AU - Ren, Lei

AU - Qian, Zhihui

AU - Ren, Luquan

PY - 2017/6

Y1 - 2017/6

N2 - In this paper, ultrasonic echo signals of four kinds of stainless steel resistance spot welds, namely failed weld, stick weld, good weld, and defective weld with gas pore, are analyzed in the time domain, frequency domain, and time-frequency domain based on wavelet packet transform. Fourteen ultrasonic characteristic signals which can reflect the different kinds of spot welds are extracted and can be automatically identified and classified by back-propagation (BP) neural network. The method of this paper can realize the intelligent identification of resistance spot welding defects, and the feasibility of this method has been verified in the experiment.

AB - In this paper, ultrasonic echo signals of four kinds of stainless steel resistance spot welds, namely failed weld, stick weld, good weld, and defective weld with gas pore, are analyzed in the time domain, frequency domain, and time-frequency domain based on wavelet packet transform. Fourteen ultrasonic characteristic signals which can reflect the different kinds of spot welds are extracted and can be automatically identified and classified by back-propagation (BP) neural network. The method of this paper can realize the intelligent identification of resistance spot welding defects, and the feasibility of this method has been verified in the experiment.

KW - Ultrasonic detection Defect intelligent identification Resistance spot welding BP neural network Wavelet packet transform

U2 - 10.1007/s00170-016-9588-y

DO - 10.1007/s00170-016-9588-y

M3 - Article

SN - 0268-3768

VL - 90

SP - 2581

EP - 2588

JO - International Journal of Advanced Manufacturing Technology

JF - International Journal of Advanced Manufacturing Technology

ER -

Defect intelligent identification in resistance spot welding ultrasonic detection based on wavelet packet and neural network

Abstract

Keywords

Access to Document

Fingerprint

Cite this