Skip to main content

Advertisement

SpringerLink
Log in

Modeling and real-time prediction for complex welding process based on weld pool

  • ORIGINAL ARTICLE
  • Published:
The International Journal of Advanced Manufacturing Technology Aims and scope Submit manuscript

Abstract

A major assumption in developing intelligent robot in industrial fields is that the intelligence has to be from senior human workers. However, in many industrial applications, this assumption may not hold. For example, in welding process, a senior welder can continually choose proper weld parameters and tune weld performance based on their observations of the liquid weld pool. But a robot with better pool shape measurement system and quicker respond speed may outperform human welders. In such cases, intelligent welding agents, if developed successfully, would greatly reduce welding cost by avoiding much expensive human training efforts and improve the welding performance. In recent years, machine learning techniques have emerged as a new learning framework to address such problem. The theory of machine learning provides a normative account of how agents may predict their future action based on a model structure, in which the training and future data have to be in the same feature space and have the same distribution. In this paper, Gaussian Process Regression (GPR) is proposed to model real-time welding process. Gas tungsten arc welding experiments were performed and the experimental data are utilized to validate the proposed method. We train the model using 1284 pairs of data in one experiment and test this model on a challenging domain of 4 other experiments by 11,642 pairs of data, using the same algorithm, GPR architectures, and hyperparameters. Bayesian Optimization Algorithm (BOA) surrogated with GPR is proposed to provide robust prediction results. This paper opens a door for enabling robot with industrial skills, resulting in the first artificial welder that is capable to respond real-time observations and provide robust predictions.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Uttrachi GD (2007) Welder shortage requires new thinking. Weld J 86(1):6–15

    Google Scholar 

  2. Erden MS, Billard A (2015) Hand impedance measurements during interactive manual welding with a robot[J]. IEEE Trans Robot 31(1):168–179

    Article  Google Scholar 

  3. Liu YK, Zhang WJ, Zhang YM (2014) A tutorial on learning human welder’s behavior: sensing, modeling, and control[J]. J Manuf Process 16(1):123–136

    Article  Google Scholar 

  4. Moon HS, Kim YB, Beattie RJ (2006) Multi sensor data fusion for improving performance and reliability of fully automatic welding system. Int J Adv Manuf Technol 28(3–4):286–293

    Article  Google Scholar 

  5. Fan CJ, Lv FL, Chen SB (2009) Visual sensing and penetration control in aluminum alloy pulsed GTA welding. Int J Adv Manuf Technol 42(1–2):126–137

    Article  Google Scholar 

  6. You D, Gao X, Katayama S (2016) Data-driven based analyzing and modeling of MIMO laser welding process by integration of six advanced sensors. Int J Adv Manuf Technol 82:1127

    Article  Google Scholar 

  7. Li K, Zhang YM (2010) Interval model control of consumable double-electrode gas metal arc welding process[J]. IEEE Trans Autom Sci Eng 7(4):826–839

    Article  Google Scholar 

  8. Liu YK, Zhang YM (2015) Iterative local ANFIS-based human welder intelligence modeling and control in pipe GTAW process: a data-driven approach[J]. IEEE/ASME Trans Mechatron 20(3):1079–1088

    Article  Google Scholar 

  9. Liu YK, Zhang WJ, Zhang Y (2013) Neuro-fuzzy based human intelligence modeling and robust control in Gas Tungsten Arc Welding process[C]. //American Control Conference (ACC). IEEE 2013:5631–5636

    Google Scholar 

  10. Chen B, Wang J, Chen S (2010) Prediction of pulsed GTAW penetration status based on BP neural network and DS evidence theory information fusion[J]. Int J Adv Manuf Technol 48(1–4):83–94

    Article  Google Scholar 

  11. Wang XW, Li RR (2014) Intelligent modelling of back-side weld bead geometry using weld pool surface characteristic parameters[J]. J Intell Manuf 25(6):1301–1313

    Article  Google Scholar 

  12. Wang XW (2015) Three-dimensional vision applications in GTAW process modeling and control[J]. Int J Adv Manuf Technol:81

  13. Munoz-Gonzalez L, Lazaro-Gredilla M, Figueiras-Vidal AR (2014) Divisive Gaussian processes for nonstationary regression[J]. IEEE Trans Neural Netw Learn Syst 25(11):1991–2003

    Article  Google Scholar 

  14. Schneider M, Ertel W (2010) Robot learning by demonstration with local gaussian process regression[C]. In: 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, pp 255–260

  15. Yang K, Keat Gan S, Sukkarieh S (2013) A Gaussian process-based RRT planner for the exploration of an unknown and cluttered environment with a UAV[J]. Adv Robot 27(6):431–443

    Article  Google Scholar 

  16. Schreiter J, Englert P, Nguyen-Tuong D et al (2015) Sparse Gaussian process regression for compliant, real-time robot control[C]. In: 2015 IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp 2586–2591

  17. Yun Y, Deshpande AD (2014) Control in the reliable region of a statistical model with Gaussian process regression[C]. In: 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE, pp 654–660

  18. Girard A, Murray-Smith R (2005) Prediction at a noisy input and application to iterative multiple-step ahead forecasting of time-series[M]//Switching and Learning in Feedback Systems. Springer, Berlin, pp 158–184

    MATH  Google Scholar 

  19. Dong H, Cong M, Liu Y et al (2016) Predicting characteristic performance for arc welding process[C]. In: 2016 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER). IEEE, pp 7–12

  20. Bishop CM (2006) Pattern recognition[J]. Mach Learn 2006:128

    Google Scholar 

  21. Brochu E, Cora VM, De Freitas N (2010) A tutorial on Bayesian optimization of expensive cost functions, with application toactive user modeling and hierarchical reinforcement learning[J]. arXiv:1012.2599

  22. Jones DR, Schonlau M, Welch WJ (1998) Efficient global optimization of expensive black-box functions[J]. J Global Optim 13(4):455–492

    Article  MathSciNet  MATH  Google Scholar 

  23. Rasmussen CE (2006) Gaussian processes for machine learning. MIT Press, Cambridge

    MATH  Google Scholar 

  24. Cheng H, Chen H (2014) Online parameter optimization in robotic force controlled assembly processes[C]. In: 2014 IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp 3465–3470

  25. Chen H, Li B, Gravel D et al (2015) Robot learning for complex manufacturing process[C]. In: 2015 IEEE International Conference on Industrial Technology (ICIT). IEEE, pp 3207– 3211

  26. Chen H, Xu J (2015) Exploring optimal controller parameters for complex industrial systems[C]. In: 2015 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER). IEEE, pp 383–388

  27. Chen P, Merrick BM, Brazil TJ (2015) Bayesian optimization for broadband high-efficiency power amplifier designs[J]. IEEE Trans Microwave Theory Tech 63(12):4263–4272

    Article  Google Scholar 

  28. Zhang WJ, Liu YK, Wang X et al (2012) Characterization of three dimensional weld pool surface in GTAW[J]. Welding J 91(7):195s–203s

    Google Scholar 

  29. Yin Y, Yang X, Cui L et al (2015) Investigation on welding parameters and bonding characteristics of underwater wet friction taper plug welding for pipeline steel. Int J Adv Manuf Technol 81(5-8):851–861

    Article  Google Scholar 

  30. Wang ZZ (2014) Monitoring of GMAW weld pool from the reflected laser lines for real-time control[J]. IEEE Trans Ind Inf 10(4):2073–2083

    Article  Google Scholar 

  31. Seni G, Elder JF (2010) Ensemble methods in data mining: improving accuracy through combining predictions[J]. Synth Lect Data Min Knowl Discov 2(1):1–126

    Article  Google Scholar 

  32. McLachlan G, Do KA, Ambroise C (2005) Analyzing microarray gene expression data[M]. Wiley, New York

    MATH  Google Scholar 

  33. Brochu E, Cora VM, De Freitas N (2010) A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning[J]. arXiv:http://arxiv.org/sbs/1012.2599

  34. Song H, Zhang YM (2008) Measurement and analysis of three dimensional specular gas tungsten arc weld pool surface. Weld Res[J] 87(4):85–95

    Google Scholar 

Download references

Acknowledgment

The first author would like to thank Chinese Scholarship Council to provide the financial support for his one-year (2015–2016) exchange Ph.D. studentship at Taxes State University (TSU).

Author information

Authors and Affiliations

  1. Department of Mechanical Engineering, Dalian University of Technology, Dalian, China

    Hang Dong & Ming Cong

  2. Department of Electrical and Computer Engineering, University of Kentucky, Lexington, KY, 40506, USA

    Yuming Zhang & Yukang Liu

  3. Ingram School of Engineering, Texas State University, San Marcos, TX, 78666, USA

    Heping Chen

Authors
  1. Hang Dong
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ming Cong
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yuming Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yukang Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Heping Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ming Cong.

Additional information

This work is supported by Dalian Science and Technology Project Foundation #2014A11GX028 to M. Cong.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Dong, H., Cong, M., Zhang, Y. et al. Modeling and real-time prediction for complex welding process based on weld pool. Int J Adv Manuf Technol 96, 2495–2508 (2018). https://doi.org/10.1007/s00170-018-1685-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00170-018-1685-7

Keywords

Search

Navigation