Advertisement

Weld penetration in situ prediction from keyhole dynamic behavior under time-varying VPPAW pools via the OS-ELM model

  • Di Wu
  • Jieshi ChenEmail author
  • Hongbing LiuEmail author
  • Peilei Zhang
  • Zhishui Yu
  • Huabin Chen
  • Shanben Chen
ORIGINAL ARTICLE
  • 72 Downloads

Abstract

In situ monitoring and accurate detecting of welding quality have been one of the common challenges of automatic welding process. This paper contributes an intelligent decision-making framework for the weld penetration prediction from the keyhole dynamic behavior under time-varying VPPAW pools. Initially, a series of dynamic experiments under different welding conditions were conducted to acquire the backside images of keyhole and corresponding backside bead width. Then, the geometry appearance of keyhole was described by the supervised descent method (SDM)–based image processing algorithm. Subsequently, the internal correlation between the keyhole characteristics and the backside width was further derived to help understand the nonlinear and time-varying VPPAW process. Finally, a novel dynamic model based on an online sequential extreme learning machine (OS-ELM) was designed to predict the weld penetration as measured by the backside bead width in real time. Extensive experiment results further verify and validate that the proposed dynamic OS-ELM model is significantly better than other state-of-the-art algorithms in terms of predicting accuracy, efficiency, and robustness.

Keywords

Backside bead width In situ prediction Keyhole behavior OS-ELM Supervised descent method Weld penetration 

Notes

Funding information

This work was supported in part by Shanghai Higher Education Young Elite Teacher Sailing-Plan (19YF1418100), National Natural Science Foundation of China (51805316 and 51605276), and Zhejiang Key Project of Research and Development Plan (2019C01114).

References

  1. 1.
    Chen SJ, Yan ZY, Jiang F (2019) Arc discharge and pressure characteristics in pulsed plasma gas of PAW. Int J Adv Manuf Technol:1–9Google Scholar
  2. 2.
    Li Y, Wang L, Wu CS (2018) Simulation of keyhole plasma arc welding with electro-magneto-thermo-hydrodynamic interactions. Int J Adv Manuf Technol:1–11Google Scholar
  3. 3.
    Pan JJ, Hu SX, Yang LJ, Chen SJ (2016) Numerical analysis of the heat transfer and material flow during keyhole plasma arc welding using a fully coupled tungsten-plasma-anode-model. Acta Mater 111:221–229CrossRefGoogle Scholar
  4. 4.
    Feng YH, Zhou JJ, Cai JJ, Zhang XX, Wu CS (2018) A 3-D lattice Boltzmann analysis of weld pool dynamic behaviors in plasma arc welding. Appl Therm Eng 139(5):623–635CrossRefGoogle Scholar
  5. 5.
    Xu B, Chen SJ, Jiang F, Le Phan H, Tashiro S, Tanaka M (2019) The influence mechanism of variable polarity plasma arc pressure on flat keyhole welding stability. J Manuf Process 37:519–528CrossRefGoogle Scholar
  6. 6.
    Zhang YM, Zhang SB, Liu YC (2001) A plasma cloud charge sensor for pulse keyhole process control. Meas Sci Technol 12(8):1365–1370CrossRefGoogle Scholar
  7. 7.
    Zhang SB, Zhang YM (2001) Efflux plasma charge-based sensing and control of joint penetration during keyhole plasma arc welding. Weld J 80(7):157–162Google Scholar
  8. 8.
    Song S, Chen HB, Lin T, Wu D, Chen SB (2016) Penetration state recognition based on the double-sound-sources characteristic of VPPAW and hidden Markov Model. J Mater Process Technol 234:33–44CrossRefGoogle Scholar
  9. 9.
    Lv N, Zhong JY, Chen HB, Lin T, Chen SB (2014) Real-time control of welding penetration during robotic GTAW dynamical process by audio sensing of arc length. Int J Adv Manuf Technol 74:235–249CrossRefGoogle Scholar
  10. 10.
    Zheng B, Wang HJ, Wang QL, Kovacevic R (2000) Control for weld penetration in VPPAW of aluminum alloys using the front weld pool image signal. Weld J 79(12):363–371Google Scholar
  11. 11.
    Wang WX, Wang Q, Yamane S, Hirano T, Hosoya K, Nakajima T, Yamamoto H (2018) Tracking using pattern matching of keyhole in visual robotic plasma welding. Int J Adv Manuf Technol 98:2127–2136CrossRefGoogle Scholar
  12. 12.
    Wang WX, Yamane S, Suzuki H, Toma J, Hosoya K, Nakajima T, Yamamoto H (2016) Tracking and height control in plasma robotic welding using digital CCD camera. Int J Adv Manuf Technol 87:531–542CrossRefGoogle Scholar
  13. 13.
    Liu ZM, Wu CS, Liu YK, Luo Z (2015) Keyhole behaviors influence weld defects in plasma arc welding process. Weld J 94(9):281–290Google Scholar
  14. 14.
    Wu D, Huang YM, Chen HB, He YS, Chen SB (2017) VPPAW penetration monitoring based on fusion of visual and acoustic signals using t-SNE and DBN model. Mater Des 123(5):1–14CrossRefGoogle Scholar
  15. 15.
    Wu D, Chen HB, He YS, Hu MH, Chen SB (2017) Monitoring of weld joint penetration during variable polarity plasma arc welding based on the keyhole characteristics and PSO-ANFIS. J Mater Process Technol 239:113–124CrossRefGoogle Scholar
  16. 16.
    Wang XW (2015) Three-dimensional vision applications in GTAW process modeling and control. Int J Adv Manuf Technol 80:601–1611Google Scholar
  17. 17.
    Jin ZS, Li HC, Gao HM (2019) An intelligent weld control strategy based on reinforcement learning approach. Int J Adv Manuf Technol 100:2163–2175CrossRefGoogle Scholar
  18. 18.
    Chen K, Chen HB, Liu L, Chen SB (2018) Prediction of weld bead geometry of MAG welding based on XGBoost algorithm. Int J Adv Manuf Technol:1–3Google Scholar
  19. 19.
    You DY, Gao XD, Katayama S (2015) WPD-PCA-based laser welding process monitoring and defects diagnosis by using FNN and SVM. IEEE Trans Ind Electron 62(1):628–636CrossRefGoogle Scholar
  20. 20.
    You DY, Gao XD, Katayama S (2012) Seam tracking monitoring based on adaptive Kalman filter embedded Elman neural network during high-power fiber laser welding. IEEE Trans Ind Electron 59(11):4315–4325CrossRefGoogle Scholar
  21. 21.
    Wu D, Chen HB, Huang YM, Chen SB (2018) On-line monitoring and model-free adaptive control of weld penetration in VPPAW based on extreme learning machine. IEEE Trans Ind Inf:1–1Google Scholar
  22. 22.
    Zhang ZF, Wen GR, Chen SB (2017) Audible sound-based intelligent evaluation for aluminum alloy in robotic pulsed GTAW: mechanism, feature selection and defect detection. IEEE Trans Ind Inf 14(7):2973–2983CrossRefGoogle Scholar
  23. 23.
    Cook GE, Barnett RJ, Andersen K, Strauss AM (1995) Weld modeling and control using artificial neural networks. IEEE Trans Ind Appl 31(6):824–830CrossRefGoogle Scholar
  24. 24.
    Chen SB, Lou YJ, Wu L, Zhao DB (2000) Intelligent methodology for sensing, modeling and control of pulsed GTAW: part 1: bead-on-plate welding. Weld J 79(6):151–163Google Scholar
  25. 25.
    Chen SB, Zhao DB, Wu L, Lou YJ (2000) Intelligent methodology for sensing, modeling and control of pulsed GTAW: part 2--butt joint welding. Weld J 79(6):164–170Google Scholar
  26. 26.
    Huang GB, Zhou HM, Ding XJ, Zhang R (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern 42(2):513–529CrossRefGoogle Scholar
  27. 27.
    Rafiei M, Niknam T, Khooban MH (2017) Probabilistic forecasting of hourly electricity price by generalization of ELM for usage in improved wavelet neural network. IEEE Trans Ind Inf 13(1):71–79CrossRefGoogle Scholar
  28. 28.
    Javed K, Gouriveau R, Zerhouni N, Nectoux P (2015) Enabling health monitoring approach based on vibration data for accurate prognostics. IEEE Trans Ind Electron 62(1):647–656CrossRefGoogle Scholar
  29. 29.
    Yang Z, Zhang P, Chen L (2016) RFID-enabled indoor positioning method for a real-time manufacturing execution system using OS-ELM. Neurocomputing 174:121–133CrossRefGoogle Scholar
  30. 30.
    Frances-Villora JV, Rosado-Muñoz A, Bataller-Mompean M, Barrios-Aviles J, Guerrero-Martinez JF (2018) Moving learning machine towards fast real-time applications: a high-speed FPGA-based implementation of the OS-ELM training algorithm. Electronics 7(11):308–318CrossRefGoogle Scholar
  31. 31.
    Yu H, Sun X, Wang J (2019) Ensemble OS-ELM based on combination weight for data stream classification. Appl Intell:1–9Google Scholar
  32. 32.
    Xiong XH, De la Torre F (2013) Supervised descent method and its applications to face alignment. CVPR:532–539Google Scholar
  33. 33.
    Neshov N, Manolova A (2015) Pain detection from facial characteristics using supervised descent method. IDAACS 1:251–256Google Scholar
  34. 34.
    Cheng Y (2016) Supervised descent method based on appearance and shape for face alignment. SOLI:184–189Google Scholar
  35. 35.
    Liu ZM, Wu CS, Gao JQ (2013) Vision-based observation of keyhole geometry in plasma arc welding. Int J Therm Sci 63:38–45CrossRefGoogle Scholar
  36. 36.
    Liang NY, Huang GB, Saratchandran P, Sundararajan N (2006) A fast and accurate online sequential learning algorithm for feedforward networks. IEEE Trans Neural Netw 17(6):1411–1423CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.Shanghai Collaborative Innovation Center of Laser Advanced Manufacturing TechnologyShanghai University of Engineering ScienceShanghaiPeople’s Republic of China
  2. 2.Shanghai Key Laboratory of Materials Laser Processing and Modification School of Materials Science and EngineeringShanghai Jiao Tong UniversityShanghaiPeople’s Republic of China

Personalised recommendations