This paper describes a technique for determining the position of a friction stir welding (FSW) tool with respect to the weld seam during welding. Forces are used as a feedback signal, and a general regression neural network is trained to predict offset position given weld forces. Experimental results demonstrate the accuracy of the developed position predictor. This technique is proposed for online misalignment detection or as a position estimator for in-process tracking of the weld seam for FSW and robotic FSW.
MishraR. S. and MaZ. Y.: Mater. Sci. Eng. R Rep., 2005, 50, (1–2), 1–78.
2.
ThomasW. M., NicholasE. D., NeedhamJ. C., MurchM. G., Temple-SmithP. and DawesC. J.: GB patent application 9125978·8, 1991.
3.
DawesC. J. and ThomasW. M.: TWI Bull., 1995, 120–128.
4.
LeonardA. J. and LockyerS. A.: Proc. 4th Int. Symp. on ‘Friction stir welding’, Park City, UT, USA, May 2003, TWI. Author: Please provide paper/page no.
5.
ErbslohK., DonneC. D. and LohwasserD.: Mater. Sci. Forum, 2003, 426–432, 2965–2970.
6.
FiliceL., BuffaG., FratiniL. and GagliardiF.: Proc. Inst. Mech. Eng. B, J. Eng. Manuf., 2006, 220, 669–676.
7.
BoldsaikhanE., CorwinE., LogarA. and ArbegastW.: Proc. 6th Int. Symp. on ‘Friction Stir Welding’, Saint-Sauveur, Quebec, Canada, October 2007, TWI.
8.
HattinghD. G., van NiekerkT. I., BlignaultC., KrugerG. and JamesM. N.: Weld. World, 2004, 48, 50–58.
9.
FlemingP. A., LammleinD. H., WilkesD. M., FlemingK. A., BloodworthT. S., CookG. E., StraussA. M., DeLappD., LienertT. J., BementM. and PraterT.: Sensor Rev., 2008, 28, (1), 62–67.
10.
KintonJ. D. and TlustyJ.: US patent 6050475, 2000.
11.
StotlerT. V. and TrappT. J.: US patent 7216793, B2, 2007.
12.
DevoreJ. and FarnumN.: ‘Applied statistics for engineers and scientists’, 2nd edn; 1999, Pacific Grove, CA, Duxbury Press.
