A comparative study of two data reduction methods for steel classification based on LIBS

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 信息服务与智能控制技术研究室

	A comparative study of two data reduction methods for steel classification based on LIBS
	Kong HY(孔海洋); Sun LX(孙兰香); Hu JT(胡静涛); Xin Y(辛勇); Cong ZB(丛智博)
	2014
会议名称	International Conference on Machine Tool Technology and Mechatronics Engineering (ICMTTME 2014)
会议日期	June 22-23, 2014
会议地点	Guilin, China
关键词	Artificial Neural Network (ANN) Classification of Steels Laser-Induced Breakdown Spectroscopy Principal Component Analysis (PCA)
页码	4722-4725
中文摘要	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.
收录类别	EI
产权排序	1
会议录	Applied Mechanics and Materials
会议录出版者	Trans Tech Publications
会议录出版地	Zurich-Durnten, Switzerland
语种	英语
ISSN号	1660-9336
ISBN号	978-3-03835-246-4
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/15415]
专题	沈阳自动化研究所_信息服务与智能控制技术研究室
推荐引用方式 GB/T 7714	Kong HY,Sun LX,Hu JT,et al. A comparative study of two data reduction methods for steel classification based on LIBS[C]. 见:International Conference on Machine Tool Technology and Mechatronics Engineering (ICMTTME 2014). Guilin, China. June 22-23, 2014.