Selection of Spectral Data for Classification of Steels Using Laser-Induced Breakdown Spectroscopy

KONG Haiyang (孔海洋); SUN Lanxiang (孙兰香); HU Jingtao (胡静涛); XIN Yong (辛勇); CONG Zhibo (丛智博)

doi:10.1088/1009-0630/17/11/14

Plasma Science and Technology > 2015 > 17(11): 964-970. > DOI: 10.1088/1009-0630/17/11/14

KONG Haiyang (孔海洋), SUN Lanxiang (孙兰香), HU Jingtao (胡静涛), XIN Yong (辛勇), CONG Zhibo (丛智博). Selection of Spectral Data for Classification of Steels Using Laser-Induced Breakdown Spectroscopy[J]. Plasma Science and Technology, 2015, 17(11): 964-970. DOI: 10.1088/1009-0630/17/11/14

Citation:

PDF (6571 KB)

Selection of Spectral Data for Classification of Steels Using Laser-Induced Breakdown Spectroscopy

1Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China 2University of Chinese Academy of Sciences, Beijing 100049, China 3CAS Key Laboratory of Networked Control System, Shenyang 110016, China

Funds: supported by the National High Technology Research and Development Program of China (863 Program) (No. 2012AA040608), National Natural Science Foundation of China (Nos. 61473279, 61004131) and the Development of Scientific Research Equipment Program of Chinese Academy of Sciences (No. YZ201247)

More Information

Received Date: January 18, 2015

Graphical Abstract

Abstract

Abstract

Principal component analysis (PCA) combined with artificial neural networks was used to classify the spectra of 27 steel samples acquired using laser-induced breakdown spec?troscopy. Three methods of spectral data selection, selecting all the peak lines of the spectra, selecting intensive spectral partitions and the whole spectra, were utilized to compare the influ?ence of different inputs of PCA on the classification of steels. Three intensive partitions were selected based on experience and prior knowledge to compare the classification, as the partitions can obtain the best results compared to all peak lines and the whole spectra. We also used two test data sets, mean spectra after being averaged and raw spectra without any pretreatment, to verify the results of the classification. The results of this comprehensive comparison show that a back propagation network trained using the principal components of appropriate, carefully se?lected spectral partitions can obtain the best results. A perfect result with 100% classification accuracy can be achieved using the intensive spectral partitions ranging of 357-367 nm.

FullText(HTML)

References (1)

References

1 Zhai X. 2012, Resource Recycling, 2012: 11 (in Chinese) 2 Qiu D, Wang C, Jiang P. 2001, Nonferrous Metals, 53:35 (in Chinese) 3 Wang M, Sui Z, Tu H. 2005, China Resources Comprehensive Utilization, 2005: 10 (in Chinese) 4 Sirven J B, Salle B, Mauchien P, et al. 2007, Journal of Analytical Atomic Spectrometry, 22: 1471 5 Unnikrishnan V K, Choudhari K S, Kulkarni S D,et al. 2013, RSC Adv., 3: 25872 6 Diego-Vallejo D, Ashkenasi D, Lemke A, et al. 2013,Spectrochimica Acta Part B: Atomic Spectroscopy, 87:92 7 Wang Z, Yuan T B, Hou Z Y, et al. 2013, Front. Phys.,9: 1 8 Dong F Z, Chen X L, Wang Q, et al. 2012, Front.Phys., 7: 679 9 Martin M Z, Labbe N, Rials T G, et al. 2005, Spectrochimica Acta Part B: Atomic Spectroscopy, 60:1179 10 Labbe N, Swamidoss I M, Andre N, et al. 2008, Applied Optics, 47: G158 11 Gottfried J L, De Lucia J F C, Munson C A, et al.2008, Journal of Analytical Atomic Spectrometry, 23:205 12 Gottfried J L, Harmon R S, De Lucia F C, et al. 2009,Spectrochimica Acta Part B: Atomic Spectroscopy, 64:1009 13 Clegg S M, Sklute E, Dyar M D, et al. 2009, Spectrochimica Acta Part B: Atomic Spectroscopy, 64: 79 14 Anzano J, Bonilla B, Montull-Ibor B, et al. 2011, J.Appl. Polym. Sci., 121: 2710 15 Zhang D, Huang K. 2013, Information and Control,42: 583 (in Chinese) 16 Sirven J B, Bousquet B, Canioni L, et al. 2006, Anal.Bioanal. Chem., 385: 256 17 Ramil A, Lopez A J, Yanez A. 2008, Appl. Phys. A:Mater. Sci. Process., 92: 197 18 V′ ?tková G, Novotn′ y K, Prokeˇ s L, et al. 2012, Spectrochimica Acta Part B: Atomic Spectroscopy, 73: 1 19 Wang Q, Huang Z, Liu K, et al. 2012, Spectroscopy and Spectral Analysis, 32: 3179 (in Chinese) 20 Boueri M, Motto-Ros V, Lei W Q, et al. 2011, Appl.Spectrosc., 65: 307 21 Koujelev A, Sabsabi M, Motto-Ros V, et al. 2010,Planet Space Sci., 58: 682 22 Amato G, Cristoforetti G, Legnaioli S, et al. 2010,Spectrochimica Acta Part B: Atomic Spectroscopy, 65:664 23 Feng J, Wang Z, West L, et al. 2011, Anal. Bioanal.Chem., 400: 3261 24 Feng J, Wang Z, Li L, et al. 2013, Appl. Spectrosc.,67: 291 25 D’Andrea E, Pagnotta S, Grifoni E, et al. 2014, Spectrochimica Acta Part B: Atomic Spectroscopy, 99: 52 26 Sun L, Yu H, Cong Z, et al. 2010, Acta Optica Sinica,30: 2757 (in Chinese) 27 Sun L, Yu H, Xin Y, et al. 2010, Spectroscopy and Spectral Analysis, 30: 3186 (in Chinese) 28 Zhang B, Yu H B, Sun L X, et al. 2013, Appl. Spectrosc., 67: 1087

Cited By