A Comparative Study of Two Data Reduction Methods for Steel Classification Based on LIBS

Abstract:

Spectra of 27 steel samples were acquired by Laser-Induced Breakdown Spectroscopy (LIBS) for steel classification. Two methods were used to reduce dimensions: the first is to select characteristic lines of elements contained in the samples manually and the second is to do principal component analysis (PCA) of original spectra. Then the data after reducing dimensions was used as the input of artificial neural networks (ANN) to classify steel samples. The results show that, the better result can be achieved by selecting peak lines manually, but this solution needs much priori knowledge and wastes much time. The principal components (PCs) of original spectra were utilized as the input of artificial neural networks can also attain a good result nevertheless and this method can be developed into an automatic solution without any priori knowledge.

• Periodical: Applied Mechanics and Materials (Volumes 644-650)
• Pages: 4722-4725
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.644-650.4722
• Online since: September 2014
• Authors: Hai Yang Kong, Lan Xiang Sun*, Jing Tao Hu, Yong Xin, Zhi Bo Cong
• Keywords: Artificial Neural Network (ANN), Classification of Steels, Laser-Induced Breakdown Spectroscopy, Principal Component Analysis (PCA)

References

[1] Qiu D, Wang C, Jiang P, Nonferrous Metals. 53 (2001) 35-8.

[2] Wang M, Sui Z, Tu H, China Resources Comprehensive Utilization. 2005 (2005) 10-3.

[3] Zhai X, Resource Recycling. 2012 (2012) 11-5.

[4] Diego-Vallejo D, Ashkenasi D, Lemke A, Eichler HJ, Spectrochimica Acta Part B-Atomic Spectroscopy. 87 (2013) 92-9.

DOI: 10.1016/j.sab.2013.06.012

[5] Unnikrishnan VK, Choudhari KS, Kulkarni SD, Nayak R, Kartha VB, Santhosh C, RSC Adv. 3 (2013) 25872-80.

DOI: 10.1039/c3ra44946g

[6] Wang Z, Yuan T-B, Hou Z-Y, Zhou W-D, Lu J-D, Ding H-B, et al., Front Phys. (2013) 1-19.

[7] Martin MZ, Labbe N, Rials TG, Wullschleger SD, Spectrochimica Acta Part B-Atomic Spectroscopy. 60 (2005) 1179-85.

[8] Anzano J, Bonilla B, Montull-Ibor B, Casas-Gonzalez J, J Appl Polym Sci. 121 (2011) 2710-6.

DOI: 10.1002/app.33801

[9] Boueri M, Motto-Ros V, Lei WQ, Ma QL, Zheng LJ, Zeng HP, et al., Appl Spectrosc. 65 (2011) 307-14.

[10] Sirven JB, Bousquet B, Canioni L, Sarger L, Tellier S, Potin-Gautier M, et al., Anal Bioanal Chem. 385 (2006) 256-62.

DOI: 10.1007/s00216-006-0322-8

[11] Ramil A, Lopez AJ, Yanez A, Appl Phys A-Mater Sci Process. 92 (2008) 197-202.

[12] Sun L, Yu H, Cong Z, Xin Y, Acta Optica Sinica. 30 (2010) 2757-65.

[13] Wang Q, Huang Z, Liu K, Li W, Yan J, Spectroscopy and Spectral Analysis. 32 (2012) 3179-82.

[14] Zhang D, Huang K, Information and Control. 42 (2013) 583-8.