0
Research Papers

ANFIS Modeling of Human Welder's Response to Three-Dimensional Weld Pool Surface in GTAW

[+] Author and Article Information
YuMing Zhang

e-mail: yuming.zhang@uky.edu
Institute for Sustainable Manufacturing and Department of Electrical and Computer Engineering,
University of Kentucky,
Lexington, KY 40506

1Corresponding author.

Contributed by the Manufacturing Engineering Division of ASME for publication in the JOURNAL OF MANUFACTURING SCIENCE AND ENGINEERING. Manuscript received February 22, 2012; final manuscript received November 7, 2012; published online March 22, 2013. Assoc. Editor: Robert Gao.

J. Manuf. Sci. Eng 135(2), 021010 (Mar 22, 2013) (11 pages) Paper No: MANU-12-1059; doi: 10.1115/1.4023269 History: Received February 22, 2012; Revised November 07, 2012

Understanding and modeling of the human welder's response to three-dimensional (3D) weld pool surface may help develop next generation intelligent welding machines and train welders faster. In this paper, human welder's adjustment on the welding current as a response to the 3D weld pool surface characterized by its width, length, and convexity is studied. An innovative vision system is used to real-time measure the specular 3D weld pool surface under strong arc in gas tungsten arc welding (GTAW). Experiments are designed to produce random changes in the welding speed resulting in fluctuations in the weld pool surface. Adaptive neuro-fuzzy inference system (ANFIS) is proposed to correlate the human welder's response to the 3D weld pool surface using three inputs including the weld pool width, length and convexity. The human welder's behavior is not only related to the 3D weld pool geometry but also relies on the welder's previous adjustment. In this sense, a four input ANFIS model adding the previous human welder's response as a model input is developed and compared with the fitted linear model. It is found that the proposed ANFIS model can derive a more accurate correlation between the human welder's responses and the weld pool geometry and help understand the nonlinear response of the human welder to 3D weld pool surfaces.

Copyright © 2013 by ASME
Your Session has timed out. Please sign back in to continue.

References

Uttrachi, G. D., 2007, “Welder Shortage Requires New Thinking,” Weld. J., 86(1), p. 6.
Richardson, R. W., and Edwards, F. S., 1995, “Controlling GT Arc Length From Arc Light Emissions,” Trends in Welding Research, Proceedings of the 4th International Conference, Gatlinburg, TN.
Li, P. J., and Zhang, Y. M., 2001, “Precision Sensing of Arc Length in GTAW Based on Arc Light Spectrum,” ASME J. Manuf. Sci. Eng., 123(1), pp. 62–65. [CrossRef]
Ma, H. B., and Wei, S. C., 2010, “Binocular Vision System for Both Weld Pool and Root Gap in Robot Welding Process,” Sens. Rev., 30(2), pp. 116–123. [CrossRef]
Fan, C. J., Lv, F., and Chen, S., 2009, “Visual Sensing and Penetration Control in Aluminum Alloy Pulsed GTA Welding,” Int. J. Adv. Manuf. Technol., 42(1–2), pp. 126–137. [CrossRef]
Hartman, D. A., DeLapp, D. R., Barnett, R. J., and Cook, G. E., 1998, “A Neural Network/Fuzzy Logic System for Weld Penetration Control,” Trends in Welding Research, Proceedings of the 5th International Conference, Pine Mountain, GA.
Balfour, C., Smith, J. S., and Al-Shamma'a, A. I., 2006, “A Novel Edge Feature Correlation Algorithm for Real-Time Computer Vision-Based Molten Weld Pool Measurements,” Weld. J., 85(1), pp. 1–8.
Song, H. S., and Zhang, Y. M., 2009, “Error Analysis of a Three-Dimensional GTA Weld Pool Surface Measurement System,” Weld. J., 88(7), pp. 141–148.
Lin, M. L., and Eagar, T. W., 1985, “Influence of Arc Pressure on Weld Pool Geometry,” Weld. J., 64(6), pp. 163–169.
Rokhlin, S. I., and Guu, A. C., 1993, “A Study of Arc Force, Pool Depression, and Weld Penetration During Gas Tungsten Arc Welding,” Weld. J., 72(8), pp. 381–390.
Zhang, Y. M., Li, L., and Kovacevic, R., 1997, “Dynamic Estimation of Full Penetration Using Geometry of Adjacent Weld Pools,” ASME J. Manuf. Sci. Eng., 19(4A), pp. 631–643. [CrossRef]
Kovacevic, R., and Zhang, Y. M., 1996, “Sensing Free Surface of Arc Weld Pool Using Specular Reflection: Principle and Analysis,” Proc. Inst. Mech. Eng. B: J. Eng. Manuf., 210(6), pp. 553–564. [CrossRef]
Zhang, W. J., Liu, Y. K., Wang, X., and Zhang, Y. M., 2012, “Characterization of Three-Dimensional Weld Pool Surface in GTAW,” Weld. J., 91, pp. 195s–203s.
Haykin, S., 1994, Neural Networks: A Comprehensive Foundation, Macmillan College Publishing Company, Inc., New York.
Takagi, T., and Sugeno, M., 1985, “Fuzzy Identification of Systems and Its Application to Modeling and Control,” IEEE Trans. Syst., Man, Cybern., 15(1), pp. 116–132. [CrossRef]
Mamdani, E. H., and Assilian, S., 1975, “An Experiment in Linguistic Synthesis With a Fuzzy Logic Controller,” Int. J. Man-Mach. Stud., 7(1), pp. 1–13. [CrossRef]
Hayashi, K., Shimizu, Y., Dote, Y., Takayama, A., and Hirako, A., 1995, “Neuro Fuzzy Transmission Control for Automobile With Variable Loads,” IEEE Trans. Control Syst. Technol., 3(1), pp. 49–53. [CrossRef]
Tanaka, K., Sano, M., and Watanabe, H., 1995, “Modeling and Control of Carbon Monoxide Concentration Using a Neuro-Fuzzy Technique,” IEEE Trans. Fuzzy Syst., 3(3), pp. 271–279. [CrossRef]
Kovacevic, R., and Zhang, Y. M., 1997, “Neurofuzzy Model-Based Weld Fusion State Estimation,” IEEE Control Syst. Mag., 17(2), pp. 30–42. [CrossRef]
Zhang, Y. M., and Kovacevic, R., 1998, “Neurofuzzy Model Based Control of Weld Fusion Zone Geometry,” IEEE Trans. Fuzzy Syst., 6(3), pp. 389–401. [CrossRef]
Jang, J. S. R., and Sun, C. T., 1995, “Neuro-Fuzzy Modeling and Control,” Proc. IEEE, 83(3), pp. 378–406. [CrossRef]
Jang, J. S. R., 1993, “ANFIS: Adaptive-Network-Based Fuzzy Inference System,” IEEE Trans. Syst., Man, Cybern., 23(3), pp. 665–685. [CrossRef]
Lih, W.-C., Bukkapatnam, S. T. S., Rao, P., Chandrasekharan, N., and Komanduri, R., 2008, “Adaptive Neuro-Fuzzy Inference System Modeling of MRR and WIWNU in CMP Process With Sparse Experimental Data,” IEEE Trans. Autom. Sci. Eng., 5(1), pp. 71–83. [CrossRef]
Zhai, J.,Zhou, J., Zhang, L., Zhao, J., and Hong, W., 2009, “The Dynamic Behavioral Model of RF Power Amplifiers With the Modified ANFIS,” IEEE Trans. Microwave Theory Tech., 57(1), pp. 27–35. [CrossRef]
Imen, M., Mansouri, M., and Shoorehdeli, M. A., 2011, “Tracking Control of Mobile Robot Using ANFIS,” Proceedings of the 2011 IEEE International Conference on Mechatronics and Automation, Beijing, China. [CrossRef]

Figures

Grahic Jump Location
Fig. 1

Diagram of the human welder's behavior

Grahic Jump Location
Fig. 2

Vision-based sensing system

Grahic Jump Location
Fig. 3

Example of 3D reconstruction of GTAW weld pool

Grahic Jump Location
Fig. 4

Diagrams of the weld pool (a) 2D boundary and (b) longitudinal intercepted area

Grahic Jump Location
Fig. 5

Manual control system of GTAW process

Grahic Jump Location
Fig. 6

Measured weld pool parameters (width, length, and convexity) and human welder's responses (current changes) from the three dynamic experiments with random traveling speed

Grahic Jump Location
Fig. 7

Distribution of inputs in the dynamic experiments

Grahic Jump Location
Fig. 8

Four input one output ANFIS scheme

Grahic Jump Location
Fig. 9

Fuzzy membership functions for width, length, and convexity before and after ANFIS training process

Grahic Jump Location
Fig. 10

ANFIS fitting of the human welder operation (dCurrent) using three inputs (width, length, and convexity)

Grahic Jump Location
Fig. 11

Fuzzy membership functions for width, length, convexity, and dCurrentp before and after ANFIS training process

Grahic Jump Location
Fig. 12

ANFIS fitting of the human welder operation (dCurrent) using four inputs (width, length, convexity, and dCurrentp)

Grahic Jump Location
Fig. 13

Linear fitting of the human welder operation (dCurrent) using three inputs (width, length, and convexity)

Grahic Jump Location
Fig. 14

Linear fitting of the human welder operation (dCurrent) using four inputs (width, length, convexity, and dCurrentp)

Grahic Jump Location
Fig. 15

Three input ANFIS model surface with different input parameters (a) width and length (convexity = 0.2427 mm), (b) width and convexity (length = 5.504 mm), and (c) length and convexity (width = 4.146 mm)

Grahic Jump Location
Fig. 16

Four input ANFIS model surface with different input parameters (a) width and length (convexity = 0.2427 mm, dCurrentp = 0.2511 A), (b) width and convexity (length = 5.504 mm, dCurrentp = 0.2511 A), (c) width and dCurrentp (length = 5.504 mm, convexity = 0.2427 mm), (d) length and convexity (width = 4.146 mm, dCurrentp = 0.2511 A), (e) length and dCurrentp (width = 4.146 mm, convexity = 0.2427 mm), and (f) convexity and dCurrentp (width = 4.146 mm, length = 5.504 mm)

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In