Abstract
With the development of information technology in hardware, more and more photosensitive elements are integrated by charge coupled device (CCD), which makes the arc spectrum data collected by linear array CCD exhibit many characteristics such as large number of dimensions, large scale and complicated structure. How to efficiently and accurately dig out the characteristic information from the rich spectral data that can be used to guide the welding process monitoring is a difficult problem that needs to be solved. Dimension reduction is one of the effective solutions. It can remove redundant data information, reduce computational complexity, improve analysis efficiency, and realize high-dimensional data classification and visualization. It is widely used in the processing of massive high-dimensional data, including images, hyperspectral, etc. In this chapter, the AC P-GTAW welding of 5A06 aluminum alloys is taken as the application background. In view of the complex and changeable arc spectral information, dimensional reduction of spectral data is conducted to analyze and compare the effects of different methods on arc spectral data. Finally, a local linear embedding (LLE) algorithm suitable for welding arc spectral data processing is selected. Aiming at solving the limitations of LLE algorithm, a supervised method based on maximum margin criterion (MMC) was proposed to extract effective features and improve the classification recognition rate. Furthermore, he relationship between these features and welding defects in the dynamic welding process was studied. Then, in order to improve the classification accuracy of pores, a statistical analysis was conducted on the hydrogen spectral lines and six characteristic values were extracted. Combining with the characteristics of light intensity ratio, a high classification accuracy of pores was realized with the support vector machine (SVM) whose optimal parameters were found based on the genetic algorithm (GA).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Schölkopf B, Smola A, Müller KR (1998) Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput 10(5):1299–1319
Wang L, Chan KL, Xue P et al (2008) A kernel-induced space selection approach to model selection in KLDA. IEEE Trans Neural Networks 19(12):2116–2131
He X, Yan S, Hu Y et al (2005) Face recognition using laplacianfaces. IEEE Trans Pattern Anal Mach Intell 27(3):328–340
Tenenbaum JB, De Silva V, Langford JC (2000) A global geometric framework for nonlinear dimensionality reduction. Science 290(5500):2319–2323
Roweis ST, Saul LK (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500):2323–2326
Donoho DL, Grimes C (2003) Hessian eigenmaps: locally linear embedding techniques for high-dimensional data. Proc Natl Acad Sci 100(10):5591–5596
Belkin M, Niyogi P (2002) Laplacian eigenmaps and spectral techniques for embedding and clustering. In: Advances in neural information processing systems, pp 585–591
Yan S, Xu D, Zhang B et al (2007) Graph embedding and extensions: a general framework for dimensionality reduction. IEEE Trans Pattern Anal Mach Intell 29(1):40–51
Saul LK, Roweis ST (2003) Think globally, fit locally: unsupervised learning of low dimensional manifolds. J Mach Learn Res 4(Jun):119–155
Pan Y, Ge SS, Al Mamun A (2009) Weighted locally linear embedding for dimension reduction. Pattern Recogn 42(5):798–811
Wong WK, Zhao HT (2012) Supervised optimal locality preserving projection. Pattern Recogn 45(1):186–197
Kouropteva O, Okun O, Pietikäinen M (2003) Supervised locally linear embedding algorithm for pattern recognition. In: Pattern recognition and image analysis, pp 386–394
Li H, Jiang T, Zhang K (2004) Efficient and robust feature extraction by maximum margin criterion. In: Advances in neural information processing systems, pp 97–104
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Huang, Y., Chen, S. (2020). Dimension Reduction of Arc Spectrum for Porosity Detection in P-GTAW Process. In: Key Technologies of Intelligentized Welding Manufacturing. Springer, Singapore. https://doi.org/10.1007/978-981-13-7549-1_5
Download citation
DOI: https://doi.org/10.1007/978-981-13-7549-1_5
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-7548-4
Online ISBN: 978-981-13-7549-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)