SIA OpenIR  > 工业控制网络与系统研究室
Fiber-LIBS技术结合SVM鉴定铝合金牌号
Alternative TitleIdentification of Aluminum Alloy Grades by Fiber-LIBS Technology Combined with SVM
周中寒; 田雪咏; 孙兰香; 张鹏; 郭志卫; 齐立峰
Department工业控制网络与系统研究室
Source Publication激光与光电子学进展
ISSN1006-4125
2018
Volume55Issue:6Pages:1-7
Indexed ByCSCD
CSCD IDCSCD:6266980
Contribution Rank1
Funding Organization国家自然科学基金资助项目(61473279)、国家重点研发计划项目(2016YFF0102502)、中国科学院前沿科学重点研究计划(QYZDJ-SSW-JSC037)、中国科学院青年创新促进会、沈阳市科技计划项目(Z17-7-006)
Keyword激光诱导击穿光谱 光纤激光器 支持向量机 牌号鉴定
Abstract

相比于传统的固体激光器,光纤激光器的使用有利于设备的小型化和激光诱导击穿光谱(Laser induced breakdown spectroscopy,LIBS)技术的推广。本文将光纤激光器LIBS(Fiber-LIBS)技术应用于铝合金牌号识别,采用数据筛选、归一化、支持向量机和主成分分析相结合的分类算法。实验中对6种牌号共24块铝合金样品按牌号分类。结果表明,相比单纯应用支持向量机的分类算法,数据筛选、归一化、支持向量机和主成分分析相结合的分类算法能够将平均预测准确率从92.34%提高到99.83%,并且可将建模时间缩短一个数量级以上。实验结果表明了光纤激光器应用于LIBS系统中进行金属牌号识别的可行性。

Other Abstract

Compared with the traditional solid state lasers, the use of fiber lasers is conducive to the miniaturization of devices and the promotion of Laser induced breakdown spectroscopy (LIBS) technology. In this paper, fiber laser LIBS (Fiber-LIBS) technology is applied to grade identification of aluminum alloy. Data classification, normalization, support vector machines and principal component analysis are used to classify the grades. In the experiment, 24 samples of 6 kinds of aluminum alloy were classified according to grade. The results show that, compared with the simple classification algorithm based on support vector machine classification algorithm, data filtering, normalization, and support vector machine combined with principal component analysis can make the average prediction accuracy rate increased from 92.34% to 99.83%, and can shorten the modeling time more than one order of magnitude. The experimental results show the feasibility of fiber laser used in LIBS system for metal grade recognition.

Language中文
Citation statistics
Cited Times:1[CSCD]   [CSCD Record]
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/21484
Collection工业控制网络与系统研究室
Corresponding Author孙兰香
Affiliation1.中国科学院沈阳自动化研究所
2.中国科学院大学
3.新松机器人自动化股份有限公司中央研究院
4.东北大学信息科学与工程学院
Recommended Citation
GB/T 7714
周中寒,田雪咏,孙兰香,等. Fiber-LIBS技术结合SVM鉴定铝合金牌号[J]. 激光与光电子学进展,2018,55(6):1-7.
APA 周中寒,田雪咏,孙兰香,张鹏,郭志卫,&齐立峰.(2018).Fiber-LIBS技术结合SVM鉴定铝合金牌号.激光与光电子学进展,55(6),1-7.
MLA 周中寒,et al."Fiber-LIBS技术结合SVM鉴定铝合金牌号".激光与光电子学进展 55.6(2018):1-7.
Files in This Item: Download All
File Name/Size DocType Version Access License
Fiber_LIBS技术结合SVM鉴定铝(1819KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[周中寒]'s Articles
[田雪咏]'s Articles
[孙兰香]'s Articles
Baidu academic
Similar articles in Baidu academic
[周中寒]'s Articles
[田雪咏]'s Articles
[孙兰香]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[周中寒]'s Articles
[田雪咏]'s Articles
[孙兰香]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Fiber_LIBS技术结合SVM鉴定铝合金牌号.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.