Key Information Perception and Control Strategy of Intellignet Welding Under Complex Scene
CHEN Huabin, CHEN Shanben()
School of Materials Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
Cite this article:
CHEN Huabin, CHEN Shanben. Key Information Perception and Control Strategy of Intellignet Welding Under Complex Scene. Acta Metall Sin, 2022, 58(4): 541-550.
The robotic arc welding equipment and automated welding system can not fulfill the requirements in self-sensing, intelligent decision-making,and robust process-controlling in the complex welding environment. Artificial intelligence techniques were used to simulate observation actions, knowledge,and behavior of experienced welders, to realize functions,such as multi-mode information perception, knowledge judgment, and intelligent control during the welding process. Essential techniques in intelligent robotic welding as well as intelligent modeling and its coordinate control strategies of flexible welding manufacturing system were also proposed. These formed the technique,structure,and theoretical framework of intelligent welding manufacturing technique and system. They also provided a scientific method and technical realization to solve problems in intelligent manufacturing techniques and systems of other complex materials forming processes.
Fig.1 Typical tungsten inert-gas welding (TIG) weld pool images of Al alloy (a) and multipath weld pool image processing (b) (l1—length 1, l2—length 2)[42]
Fig.2 Weld pool image sequence (a), a generative adversarial network via arc light filter for weld pool (b), and weld pool edge extraction by ensembles of regression trees (ERT) algorithm (c) (t—time, x—input weld pool image in the source domain, y—target domain, G—generator, D—discriminator, G(x)—the result of generator)[43]
Fig.3 In situ studies of full field strain and stress characterization using digital image correlation method (IR—infrared radiation)[53]
Fig.4 Autonomious robotic welding technelogy based on laser vision sensor
Fig.5 Architecture of intelligent welding manufacturing system based on multi-agent system and internet of things (MAS-IOT) (MIG—metal inter gas welding, MAG—metal active gas arc welding, GTAW—gas metal arc welding)
Fig.6 Intelligent management and control of welding data and quality evaluation based on Internet of things
1
Zhou J, Zhou Y H, Wang B C, et al. Human-cyber-physical systems (HCPSs) in the context of new-generation intelligent manufacturing [J]. Engineering, 2019, 5: 624
2
Wang B C, Hu S J, Sun L, et al. Intelligent welding system technologies: State-of-the-art review and perspectives [J]. J. Manuf. Syst., 2020, 56: 373
3
Zhang G J, Li Y Z. Towards intelligent welding in the context of industry 4.0 [J]. Aeronaut. Manuf. Technol., 2016, (11): 28
David S A, Chen J, Gibson B T, et al. Intelligent weld manufacturing: Role of integrated computational welding engineering [A]. Transactions on Intelligent Welding Manufacturing [M]. Singapore: Springer, 2018: 3
5
Ogbemhe J, Mpofu K. Towards achieving a fully intelligent robotic arc welding: A review [J]. Ind. Robot: Int. J., 2015, 42: 475
6
Jin Z S, Li H C, Jia G Q, et al. Dynamic nonlinear modeling of 3D weld pool surface in GTAW [J]. Robot. Comput. Integr. Manuf., 2016, 39: 1
7
Severson K, Chaiwatanodom P, Braatz R D. Perspectives on process monitoring of industrial systems [J]. Ann. Rev. Cont., 2016, 42: 190
8
Yin S, Ding S X, Xie X C, et al. A review on basic data-driven approaches for industrial process monitoring [J]. IEEE Trans. Ind. Electron., 2014, 61: 6418
9
Wang Q Y, Jiao W H, Zhang Y M. Deep learning-empowered digital twin for visualized weld joint growth monitoring and penetration control [J]. J. Manuf. Sys., 2020, 57: 429
10
Park H, Trautmann M, Tanaka K, et al. Mixing of multiple metal vapours into an arc plasma in gas tungsten arc welding of stainless steel [J]. J. Phys., 2017, 50D: 43LT03
11
Tanaka K, Shigeta M, Tanaka M, et al. Investigation of the bilayer region of metal vapor in a helium tungsten inert gas arc plasma on stainless steel by imaging spectroscopy [J]. J. Phys., 2019, 52D: 354003
12
Wu S J, Gao H M, Zhang W, et al. Analytic weld pool model calibrated by measurements—Part 1: Principles [J]. Weld. J., 2017, 96: 193
13
Wu S J, Gao H M, Zhang W, et al. Analytic weld pool model calibrated by measurements—Part 2: Verification and robustness [J]. Weld. J., 2017, 96: 250
14
Chen C, Lv N, Chen S B. Welding penetration monitoring for pulsed GTAW using visual sensor based on AAM and random forests [J]. J. Manuf. Process, 2021, 63: 152
15
Zhang Z F, Wen G R, Chen S B. Audible sound-based intelligent evaluation for aluminum alloy in robotic pulsed GTAW: Mechanism, feature selection, and defect detection [J]. IEEE Trans. Ind. Inform., 2017, 14: 2973
16
Zhang W J, Zhang Y M. Modeling of human welder response to 3D weld pool surface: Part I—principles [J]. Weld. J., 2012, 91: 310S
17
Chen S B, Lv N. Research evolution on intelligentized technologies for arc welding process [J]. J. Manuf. Process, 2014, 16: 109
18
Liu Y K, Zhang W J, Zhang Y M. Estimation of weld joint penetration under varying GTA pools [J]. Weld. J., 2013, 92: 313S
19
Zhang S Q, Hu S S, Wang Z J. Weld penetration sensing in pulsed gas tungsten arc welding based on arc voltage [J]. J. Mater. Process. Technol., 2016, 229: 520
20
Huang J K, Yang M H, Chen J S, et al. The oscillation of stationary weld pool surface in the GTA welding [J]. J. Mater. Process. Technol., 2018, 256: 57
21
Zhang K, Zhang Y M, Chen J S, et al. Observation and analysis of three-dimensional weld pool oscillation dynamic behaviors [J]. Weld. J., 2017, 96: 143S
22
Coniglio N, Mathieu A, Aubreton O, et al. Plasma effect on weld pool surface reconstruction by shape-from-polarization analysis [J]. Appl. Phys. Lett., 2014, 104: 131603
23
Feng Z, Chen J, Chen Z. Monitoring weld pool surface and penetration using reversed electrode images [J]. Weld. J., 2017, 96: 367S
24
Chen Z Y, Chen J, Feng Z L. Welding penetration prediction with passive vision system [J]. J. Manuf. Process., 2018, 36: 224
25
Tarn J, Huissoon J. Developing psycho-acoustic experiments in gas metal arc welding [A]. IEEE International Conference Mechatronics and Automation, 2005 [C]. Niagara Falls: IEEE, 2005: 1112
26
Asif K, Zhang L, Derrible S, et al. Machine learning model to predict welding quality using air-coupled acoustic emission and weld inputs [J]. J. Intell. Manuf., 2022, 33: 881
27
Wang J F, Chen B, Chen H B, et al. Analysis of arc sound characteristics for gas tungsten argon welding [J]. Sensor Rev., 2009, 29: 240
28
Wang J F, Yu H D, Qian Y Z, et al. Feature extraction in welding penetration monitoring with arc sound signals [J]. Proc. Inst. Mech. Eng., 2011, 225B: 1683
29
Lv N, Fang G, Xu Y L, et al. Real-time monitoring of welding path in pulse metal-inert gas robotic welding using a dual-microphone array [J]. Int. J. Adv. Manuf. Technol., 2017, 90: 2955
30
Wang J F. Study on recognition method of penetration states based on welding sound feature [D]. Shanghai: Shanghai Jiao Tong University, 2009
王继锋. 基于焊接声音信号特征的熔透状态识别方法研究 [D]. 上海: 上海交通大学, 2009
31
Song S, Chen H B, Lin T, et al. Penetration state recognition based on the double-sound-sources characteristic of VPPAW and hidden Markov Model [J]. J. Mater. Process. Technol., 2016, 234: 33
32
Wu D, Chen H B, Huang Y M, et al. Monitoring of weld joint penetration during variable polarity plasma arc welding based on the keyhole characteristics and PSO-ANFIS [J]. J. Mater. Process. Technol., 2017, 239: 113
33
Yu H W. Research on dynamic process and defect features of aluminum alloy pulsed GTAW based on the welding arc spectral information [D]. Shanghai: Shanghai Jiao Tong University, 2013
Katayama S, Uchiumi S, Mizutani M, et al. Penetration and porosity prevention mechanism in YAG laser-MIG hybrid welding [J]. Weld. Int., 2007, 21: 25
35
Tanaka M, Tashiro S, Tsujimura Y. Visualizations and predictions of welding arcs [J]. Trans JWRI, 2012, 41: 1
36
Liu L M, Hao X F. Study of the effect of low-power pulse laser on arc plasma and magnesium alloy target in hybrid welding by spectral diagnosis technique [J]. J. Phys.. 2008, 41D: 205202
37
Hao X F, Liu L M. Effect of laser pulse on arc plasma and magnesium target in low-power laser/arc hybrid welding [J]. IEEE Trans. Plasma Sci., 2009, 37: 2197
38
Yu H W, Chen H B, Xu Y L, et al. Spectroscopic diagnostics of pulsed gas tungsten arc welding plasma and its effect on weld formation of aluminum-magnesium alloy [J]. Spectrosc. Lett., 2013, 46: 350
39
Otaki S, Matsuida T, Nomura K, et al. In-situ measurement of weld quality during MAG welding using laser ultrasonic [J]. Weld. Int., 2019, 33: 450
40
Feng Y H, Chen Z Y, Wang D L, et al. DeepWelding: A deep learning enhanced approach to GTAW using multisource sensing images [J]. IEEE Trans. Ind. Inform., 2019, 16: 465
41
Wang Q Y, Jiao W H, Yu R, et al. Modeling of human welders' operations in virtual reality human-robot interaction [J]. IEEE Robot. Autom. Lett., 2019, 4: 2958
42
Fan C J. Weld pool characters extraction visual sensing and intelligent control during varied gap aluminum alloy [D]. Shanghai: Shanghai Jiao Tong University, 2008
Jiang Z. Multi-source information representation and penetration prediction and control for robotic TIG welding of aluminum alloy [D]. Shanghai: Shanghai Jiao Tong University, 2020
Wu D, Huang Y M, Zhang P L, et al. Visual-acoustic penetration recognition in variable polarity plasma arc welding process using hybrid deep learning approach [J]. IEEE Access, 2020, 8: 120417
45
Wu D, Chen J S, Liu H B, et al. Weld penetration in situ prediction from keyhole dynamic behavior under time-varying VPPAW pools via the OS-ELM model [J]. Int. J. Adv. Manuf. Technol., 2019, 104: 3929
46
Wu D, Huang Y M, Chen H B, et al. VPPAW penetration monitoring based on fusion of visual and acoustic signals using t-SNE and DBN model [J]. Mater. Des., 2017, 123: 1
47
Chen C, Xiao R Q, Chen H B, et al. Arc sound model for pulsed GTAW and recognition of different penetration states [J]. Int. J. Adv. Manuf. Technol., 2020, 108: 3175
48
Chen C, Xiao R Q, Chen H B, et al. Prediction of welding quality characteristics during pulsed GTAW process of aluminum alloy by multisensory fusion and hybrid network model [J]. J. Manuf. Process., 2021, 68: 209
49
Huang Y M, Li S S, Li J H, et al. Spectral diagnosis and defects prediction based on ELM during the GTAW of Al alloys [J]. Measurement, 2019, 136: 405
50
Huang Y M, Zhao D J, Chen H B, et al. Porosity detection in pulsed GTA welding of 5A06 Al alloy through spectral analysis [J]. J. Mater. Process Technol., 2018, 259: 332
51
Huang Y M, Wu D, Zhang Z F, et al. EMD-based pulsed TIG welding process porosity defect detection and defect diagnosis using GA-SVM [J]. J. Mater. Process. Technol., 2017, 239: 92
52
Chen H B, Song Y L, Chen X Q, et al. In situ studies of full-field residual stress mapping of SS304 stainless steel welds using DIC [J]. Int. J. Adv. Manuf. Technol., 2020, 109: 45
53
Song Y L. In situ studies of full field strain and residual stress of welding heat affect zone using digital image correlation [D]. Shanghai: Shanghai Jiao Tong University, 2019
Zhang Z F, Chen H B, Xu Y L, et al. Multisensor-based real-time quality monitoring by means of feature extraction, selection and modeling for Al alloy in arc welding [J]. Mech. Syst. Signal Process., 2015, 60-61: 151
55
Ma H B, Wei S C, Lin T, et al. Mixed logical dynamical model for back bead width prediction of pulsed GTAW process with misalignment [J]. J. Mater. Process. Technol., 2010, 210: 2036
56
Wu D, Chen H B, Huang Y M, et al. Online monitoring and model-free adaptive control of weld penetration in VPPAW based on extreme learning machine [J]. IEEE Trans. Ind. Inform., 2019, 15: 2732
57
Lv F L, Chen H B, Fan C J, et al. A novel control algorithm for weld pool control [J]. Ind. Robot, 2010, 37: 89
58
Ye Z, Fang G, Chen S B, et al. Passive vision based seam tracking system for pulse-MAG welding [J]. Int. J. Adv. Manuf. Technol., 2013, 67: 1987
59
Ye Z, Fang G, Chen S B, et al. A robust algorithm for weld seam extraction based on prior knowledge of weld seam [J]. Sensor Rev., 2013, 33: 125
60
Hou Z, Xu Y L, Xiao R Q, et al. A teaching-free welding method based on laser visual sensing system in robotic GMAW [J]. Int. J. Adv. Manuf. Technol., 2020, 109: 1755
61
Xiao R Q, Xu Y L, Hou Z, et al. An adaptive feature extraction algorithm for multiple typical seam tracking based on vision sensor in robotic arc welding [J]. Sens. Actuators, 2019, 297A: 111533
62
Lin S Y, Yang X Q, Xu A J, et al. Recent advances in intelligentized robotic welding technologies and its application in launch vehicle tank [J]. Aerosp. Shanghai, 2021, 38(3): 8