Please wait a minute...
工程设计学报
Chin J Eng Design  2022, Vol. 29 Issue (3): 272-278    DOI: 10.3785/j.issn.1006-754X.2022.00.045
Design Theory and Method     
Detection method of post-weld residual stress treatment quality based on acoustic signal recognition
Yi-fan CHEN(),Qian WU,Ling JIANG(),Liang HUA
College of Electrical Engineering, Nantong University, Nantong 226000, China
Download: HTML     PDF(2653KB)
Export: BibTeX | EndNote (RIS)      

Abstract  

The post-weld residual stress treatment process has high nonlinearity and strong parameter coupling, which leads to unstable treatment quality. However, the existing detection method only performs sampling detection, which has the problems of low detection accuracy, longperiod, and can not carry out real-time online detection. Therefore, a new online detection method of post-weld residual stress treatment quality based on the acoustic signal recognition was proposed. In this method, the acoustic signal in the post-weld residual stress treatment process was collected in real time and its features were extracted, and then a post-weld residual stress treatment quality detection model based on the multi-weight neural network was constructed to realize online recognition. The experimental results showed that, compared with traditional detection methods, the proposed method could realize the online detection of post-weld residual stress treatment quality, which could provide reference for parameter optimization and quality control in the post-weld treatment process.

Key words： post-weld residual stress treatment      multi-weight neural network      feature extraction      quality detection     
Received: 15 September 2021      Published: 05 July 2022
CLC:  TG 441.8  
Corresponding Authors: Ling JIANG     E-mail: 825569568@qq.com;ntujiangling@163.com
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Yi-fan CHEN
Qian WU
Ling JIANG
Liang HUA
Cite this article:

Yi-fan CHEN,Qian WU,Ling JIANG,Liang HUA. Detection method of post-weld residual stress treatment quality based on acoustic signal recognition. Chin J Eng Design, 2022, 29(3): 272-278.

URL:

https://www.zjujournals.com/gcsjxb/10.3785/j.issn.1006-754X.2022.00.045     OR     https://www.zjujournals.com/gcsjxb/Y2022/V29/I3/272


基于声信号识别的焊后残余应力处理质量检测方法

焊后残余应力处理过程的非线性程度高且参数耦合性强，导致处理质量不稳定。而现有检测方法仅做抽样检测，存在检测精度低、周期长等问题，且无法进行实时在线检测。为此，提出一种新的基于声信号识别的焊后残余应力处理质量在线检测方法。该方法先实时采集焊后残余应力处理过程中的声信号并提取其特征，然后构建基于多权值神经网络的焊后残余应力处理质量检测模型，以实现在线识别。实验结果表明，相比于传统检测方法，所提出方法可实现焊后残余应力处理质量的在线检测，可为焊后处理过程中的参数优化和质量控制提供参考。


关键词： 焊后残余应力处理,  多权值神经网络,  特征提取,  质量检测 
Fig.1 Ultrasonic impact test platform

实验参数（冲击速度、冲击频率、

冲击压力、板材厚度）

残余应力处理结果
16 cm/min、18 kHz、30 N、6 cm不合格
16 cm/min、25 kHz、30 N、8 cm合格
16 cm/min、18 kHz、40 N、8 cm不合格
16 cm/min、25 kHz、50 N、10 cm合格
16 cm/min、25 kHz、50 N、12 cm合格
32 cm/min、25 kHz、30 N、6 cm合格
32 cm/min、18 kHz、30 N、8 cm不合格
32 cm/min、18 kHz、40 N、10 cm不合格
32 cm/min、25 kHz、50 N、10 cm合格
32 cm/min、25 kHz、50 N、10 cm不合格
Table 1 Judgment results of post-weld residual stress treatment quality of Q235 welding test plate (part)
Fig.2 Acoustic signal acquisition platform
Fig.3 Spectrogram comparison of acoustic signals before and after filtering
Fig.4 Comparison of short-time average zero-crossing rate of acoustic signals with different qualities of post-weld residual stress treatment
Fig.5 Comparison of Mel-cepstrogram of acoustic signals with different qualities of post-weld residual stress treatment
Fig.6 Comparison of combined features of acoustic signals with different qualities of post-weld residual stress treatment
Fig.7 Comparison of recognition results of detection model of post-weld residual stress treatment quality based on multi-weight neural network
识别算法训练样本数量/组识别数量/组识别率/%

多权值神经

网络

53792.5
83895.0
103997.5
SVM53177.5
83382.5
103587.5
BP神经网络53280.0
83485.0
103587.5
Table 2 Comparison of recognition rate of detection model of post-weld residual stress treatment quality based on different algorithms
[1]   HENSEL J， NITSCHKE-PAGEL T， NGOULA D T， et al. Welding residual stresses as needed for the prediction of fatigue crack propagation and fatigue strength［J］. Engineering Fracture Mechanics， 2018， 198： 123-141. doi：10.1016/j.engfracmech.2017.10.024
doi: 10.1016/j.engfracmech.2017.10.024
[2]   ZHENG Jing， INCE Ayhan， TANG Lan-qing. Modeling and simulation of weld residual stresses and ultrasonic impact treatment of welded joints［J］. Procedia Engineering， 2018， 213： 36-47. doi：10.1016/j.proeng.2018. 02.005
doi: 10.1016/j.proeng.2018. 02.005
[3]   江长友，金辉，陈露.7XXX铝合金弹壳外表面残余应力分析［J］.热加工工艺，2021，50（12）：132-134，142. doi：10.1016/j.corsci.2021.109304
JIANG Chang-you， JIN Hui， CHEN Lu. Analysis on residual stress on external surface of 7XXX aluminum alloy shell case［J］. Hot Working Technology， 2021， 50（12）： 132-134， 142.
doi: 10.1016/j.corsci.2021.109304
[4]   何京波.基于超声波法的钢结构构件应力检测方法研究［D］.哈尔滨：哈尔滨工业大学，2014：9-10.
HE Jing-bo.Study on stress nondestructive testing for members of steel structure based on ultrasonic method［D］. Harbin： Harbin Institute of Technology， 2014： 9-10.
[5]   黄钢，张清东，王春海，等.钢板残余应力盲孔测量法试验及应用［J］.焊接学报，2020，41（9）：49-59，80. doi：10.12073/j.hjxb.20200403002
HUANG Gang， ZHANG Qing-dong， WANG Chun-hai， et al. Experimental research on the blind hole-drilling method for measuring residual stress of steel plate［J］. Transactions of the China Welding Institution， 2020， 41（9）： 49-59， 80.
doi: 10.12073/j.hjxb.20200403002
[6]   王险峰.凿岩台车臂架的自动化焊接工艺研究［J］.焊接技术，2020，49（9）：74-76. doi：10.13846/j.cnki.cn12-1070/tg.2020.09.020
WANG Xian-feng. Research on automatic welding process for boom of the rock drilling jumbo［J］. Welding Technology， 2020， 49（9）： 74-76.
doi: 10.13846/j.cnki.cn12-1070/tg.2020.09.020
[7]   徐春广，宋文涛，潘勤学，等.残余应力的超声检测方法［J］.无损检测，2014，36（7）：25-31. doi：10.1016/j.phpro.2015.08.030
XU Chun-guang， SONG Wen-tao， PAN Qin-xue， et al. Residual stress nondestructive testing method using ultrasonic［J］. Nondestructive Testing， 2014， 36（7）： 25-31.
doi: 10.1016/j.phpro.2015.08.030
[8]   刘录叶，邓淑文，杨随先.残余应力涡流热成像无损检测技术及应用［J］.无损检测，2018，40（10）：5-9，15. doi：10.11973/wsjc201810002
LIU Lu-ye， DENG Shu-wen， YANG Sui-xian， et al. Nondestructive testing technique for residual stress by using eddy current thermography and its application［J］. Nondestructive Testing， 2018， 40（10）： 5-9， 15.
doi: 10.11973/wsjc201810002
[9]   庞轶环，胡志忠.一种分数阶巴特沃斯滤波器的有源电路设计［J］.电子学报，2018，46（5）：1160-1165. doi：10.3969/j.issn.0372-2112.2018.05.021
PANG Yi-huan， HU Zhi-zhong. Active circuit design of a fractional order Butterworth filter［J］. Acta Electronica Sinica， 2018， 46（5）： 1160-1165.
doi: 10.3969/j.issn.0372-2112.2018.05.021
[10]   陈瀚翔，邱志斌，王海祥，等.基于MFCC特征与GMM的输电线路渉鸟故障相关鸟种智能识别［J］.水电能源科学，2021，39（7）：171-174，67.
CHEN Han-xiang， QIU Zhi-bin， WANG Hai-xiang， et al. Intelligent identification of bird species related to transmission line faults based on MFCC features and GMM［J］. Water Resources and Power， 2021， 39（7）： 171-174， 67.
[11]   刘鑫锦，苏国韶，冯夏庭，等.基于声音信号的室内岩爆动态预测方法［J］.岩土力学，2018，39（10）：3573-3580. doi：10.16285/j.rsm.2017.0187
LIU Xin-jin， SU Guo-shao， FENG Xia-ting， et al. Dynamic prediction method of laboratory rockburst using sound signals［J］. Rock and Soil Mechanics， 2018， 39（10）： 3573-3580.
doi: 10.16285/j.rsm.2017.0187
[12]   李华，田国华.基于双权值神经网络的焊缝跟踪自适应控制设计［J］.测控技术，2015，34（6）：74-76. doi：10.3969/j.issn.1000-8829.2015.06.021
LI Hua， TIAN Guo-hua. Design of welding tracking adaptive controllor based on double-weights neural network［J］. Measurement and Control Technology， 2015， 34（6）： 74-76.
doi: 10.3969/j.issn.1000-8829.2015.06.021
[13]   羌予践，华亮，陈玲，等.基于多权值神经网络的老人跌倒智能识别研究［J］.科学技术与工程，2015，15（4）：119-124，130. doi：10.3969/j.issn.1671-1815.2015.04.024
QIANG Yu-jian， HUA Liang， CHEN Ling， et al. Research on the intelligent recognition of falling of aged people based on multi-weights neural network［J］. Science Technology and Engineering， 2015， 15（4）： 119-124， 130.
doi: 10.3969/j.issn.1671-1815.2015.04.024
[14]   袁静，王锐，江力.多自由度工业机器人基于神经网络的自适应PID控制［J］.计算机应用，2017，37（z1）：123-125，140.
YUAN Jing， WANG Rui， JIANG Li. Neural network PID based adaptive control for industrial welding robot with multi-degree of freedom［J］. Journal of Computer Applications， 2017， 37（z1）： 123-125， 140.
[15]   张以文，郭海帅，涂辉，等.基于随机隐含层权值神经网络的瓦斯浓度预测［J］.计算机工程与科学，2019，41（4）：699-707. doi：10.3969/j.issn.1007-130X.2019.04.017
ZHANG Yi-wen， GUO Hai-shuai， TU Hui， et al. Gas concentration prediction based on neural network with random hidden weight［J］. Computer Engineering & Science， 2019， 41（4）： 699-707.
doi: 10.3969/j.issn.1007-130X.2019.04.017
[16]   陆飞，王守觉.三角形坐标系下人脸图像连续性研究［J］.计算机辅助设计与图形学学报，2017，29（5）：821-828. doi：10.3969/j.issn.1003-9775.2017.05.005
LU Fei， WANG Shou-jue. Research on the continuation property of facial images based on the triangle coordinate［J］. Journal of Computer-Aided Design & Computer Graphics， 2017， 29（5）： 821-828.
doi: 10.3969/j.issn.1003-9775.2017.05.005
[17]   林剑楚，肖泉，王守觉.一种高保真人脸图像妆容移植方法［J］.计算机应用与软件，2015，32（8）：187-189，210. doi：10.3969/j.issn.1000-386x.2015.08.044
LIN Jian-chu， XIAO Quan， WANG Shou-jue. A high-fidelity makeup face image transplant method［J］. Computer Applications and Software， 2015， 32（8）： 187-189， 210.
doi: 10.3969/j.issn.1000-386x.2015.08.044
[18]   王守觉，王柏南.人工神经网络的多维空间几何分析及其理论［J］.电子学报，2002，30（1）：1-4. doi：10.3321/j.issn：0372-2112.2002.01.001
WANG Shou-jue， WANG Bo-nan. Analysis and theory of high-dimension space geometry for artificial neural networks［J］. Acta Electronica Sinica， 2002， 30（1）： 1-4.
doi: 10.3321/j.issn：0372-2112.2002.01.001
[19]   张松，李江涛，别东洋，等.一种基于单通道sEMG分解与LSTM神经网络相结合的手势识别方法［J］.仪器仪表学报，2021，42（4）：228-235. doi：10.19650/j.cnki.cjsi.J2006726
ZHANG Song， LI Jiang-tao， BIE Dong-yang， et al. Gesture recognition by single-channel sEMG decomposition and LSTM network［J］. Chinese Journal of Scientific Instrument， 2021， 42（4）： 228-235.
doi: 10.19650/j.cnki.cjsi.J2006726
[20]   王一波，宋小杉.基于SVM目标识别的图像特征选取研究［J］.电光与控制，2021，28（12）：36-39，51. doi：10.3969/j.issn.1671-637X.2021.12.008
WANG Yi-bo， SONG Xiao-shan. Image feature selection for military target recognition based on SVM［J］. Electronics Optics & Control， 2021， 28（12）： 36-39， 51.
doi: 10.3969/j.issn.1671-637X.2021.12.008
[1] Xiaodong JI,Tianyu CHENG,Liang HUA,Xinsong ZHANG. Research on detection method of underwater welding quality based on acoustic signal recognition[J]. Chin J Eng Design, 2023, 30(5): 562-570.
[2] Meng LI,Zong-jun YIN. Research on comprehensive quality assessment method for parts[J]. Chin J Eng Design, 2022, 29(4): 410-418.
[3] WANG Chun-Xiang, LI Le, WANG Jian-Guo. Geometric reverse resolution and model reconstruction of excavator dipper teeth based on feature extraction[J]. Chin J Eng Design, 2010, 17(3): 211-214.