Abstract
Investigation on the arc sound has been made to find the features which can represent the welding penetration. We first acquired original features of the signal by using wavelet packet decomposition. By the Branch and Bound (BB) method, we reduced the number of features and finally obtained a combination of features with certain representation. The result suggests that energy characteristics in some frequency ranges might be effective features to describe the acoustic signal which can be used for predicting welding penetrations.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Research Data, No 72-178, joint Committee with Arc Physics and Welding Metallurgy (November 1976) (in Japanese)
Futamata, M., Toh, T., Inoue, K., Arata, Y.: Investigation on welding arc sound-effect of welding method and welding condition of welding arc sound (report 1). Transactions of JWRI 11, 25–31 (1979)
Saini, D., Floyd, S.: An investigation of gas metal arc welding sound signature for online quality control. Welding Journal 77(4), 172–179 (1998)
Tam, J.: Methods of Characterizing Gas-Metal Arc Welding Acoustics for process Automation. The University of Waterloo
Wang, Y.-w., Chen, Q., Sun, Z.-g., et al.: Relationship between sound signal and weld pool status in plasma arc welding. Trans. Nonferrous Met. Soc. China 11(1), 54–57 (2001)
Wang, J.F., Fenglin, L., Chen, S.B.: Analysis of arc sound characteristics for Gas tungsten argon welding. Sensor Review 29(3), 240–249 (2009)
Somol, P., Pudil, P., Ferri, F., Kittler, J.: Fast branch and bound algorithm in feature selection. In: Sanchez, B., Pineda, J., Wolfmann, J., Bellahsense, Z., Ferri, F. (eds.) Proceedings of SCI/ISAS 2000 World Multi Conference on Systemics, Cybernetics and Informatics (SCI), vol. VII, pp. 646–651 (2000)
Wang, J.F., Chen, B., Chen, S.B.: Feature Extraction in Welding Penetration Monitoring with Arc Acoustic signals. The International Journal of Advanced Manufacturing Technology (Review NO. #IJAMT3966)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ye, Z., Wang, J., Chen, S. (2011). Feature Selection of Arc Acoustic Signals Used for Penetration Monitoring. In: Tarn, TJ., Chen, SB., Fang, G. (eds) Robotic Welding, Intelligence and Automation. Lecture Notes in Electrical Engineering, vol 88. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19959-2_25
Download citation
DOI: https://doi.org/10.1007/978-3-642-19959-2_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19958-5
Online ISBN: 978-3-642-19959-2
eBook Packages: EngineeringEngineering (R0)