Method of Infrared Spectrum On-Line Pattern Recognition of Mixed Gas Distribution Based on SVM
BAI Peng1,2,JI Juan-zao3,ZHANG Fa-qi3,LI Yan2,LIU Jun-hua4, ZHU Chang-chun1
1. School of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an 710049, China 2. Science Institute, Air Force Engineering University, Xi’an 710051, China 3. Engineering Institute, Air Force Engineering University, Xi’an 710038, China 4. School of Electrical Engineering, Xi’an Jiaotong University, Xi’an 710049, China
Abstract：In order to solve the difficulties that the spectrum training data samples of the massive mixed gas cannot be actually obtained, the analysis precision is low and it is not real time online analysis in the analysis of mixed gas component concentration, the support vector machine, a new information processing method, was used in the mixed gas infrared spectrum analysis, and the concept of mixed gas distribution pattern was proposed in the present paper. Based on the thought that the mixed gas distribution pattern recognition is carried out first, and then the analysis work of mixed gas component concentration is done, sixty kinds of mixed gas distribution pattern were determined after investigation and study, and 6 000 mixed gas spectrum data samples were used for model training and testing. Sequential minimal optimization algorithm was applied to realize the decrement and the increase of online learning, and finally the model of infrared spectrum online pattern recognition of mixed gas distribution based on SVM was established. The model structure is composed of 2 levels, pattern recognition level and result output level. The pattern recognition level completes the task of mixed gas distribution pattern recognition; while the result output level is composed of 60 SVM calibration models, and it completes the task of mixed gas concentration analysis. Experimental results show that the correct recognition rate of mixture gas distribution pattern is not lower than 98.8%, and that the method can be used for online recognition of mixed gas distribution pattern under the conditions of small samples of a mixed gas, and can add new mixed gas online, and it has the practical application value.
白鹏1,2,冀捐灶3,张发启3,李彦2,刘君华4,朱长纯1 . 基于SVM的混合气体分布模式红外光谱在线识别方法[J]. 光谱学与光谱分析, 2008, 28(10): 2278-2281.
BAI Peng1,2,JI Juan-zao3,ZHANG Fa-qi3,LI Yan2,LIU Jun-hua4, ZHU Chang-chun1. Method of Infrared Spectrum On-Line Pattern Recognition of Mixed Gas Distribution Based on SVM. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2008, 28(10): 2278-2281.
[1] Blanco M, Villarroya I. Trends in Analytical Chemistry,2002,21(4): 240. [2] WANG Hai-shui, WANG Dong-mei, XI Shi-quan(王海水，汪冬梅，席时权). Analysis and Testing Technology and Instruments(分析测试技术与仪器),2002, 8(3): 136. [3] LIAN Chen-zhou, L Zi-an, XU Xu-chang(连晨舟, 吕子安, 徐旭常). Environmental Monitoring in China(中国环境监测),2004,20(2): 17. [4] LU Wan-zhen, YUAN Hong-fu, XU Guang-tong, et al(陆婉珍, 袁洪福, 徐广通, 等). Modern Near Infrared Spectroscopic Analysis Techniques(现代近红外光谱分析技术). Beijing: China Petrochemical Press(北京: 中国石化出版社),2000. [5] SUN Xiu-yun, LI Yan, WANG Jun-de(孙秀云, 李 燕, 王俊德). Spectroscopy and Spectral Analysis(光谱学与光谱分析),2003,23(4): 739. [6] JI Hai-yan, YAN Yan-lu(吉海彦, 严衍禄). Journal of Instrumental Analysis(分析测试学报), 1999, 18(3): 12. [7] Vapnik V N. The Nature of Statistical Learning. New York: Springer, 1995. [8] Vapnik V N. Statistical Learning Theory. New York: John Wiley & Sons Inc, 1998. [9] CHANG Chih-chung, LIN Chih-jen.http://www.csie.ntu.edu.tw/~cjlin/papers/libsvm.pdf. [10] DU Pei-jun, FANG Tao, TANG Hong, et al(杜培军, 方 涛, 唐 宏, 等). Acta Photonica Sinica(光子学报),2005, 34(2): 293. [11] PANG Shi-ping, ZHENG Xiao-ling, HE Ying, et al(庞士平, 郑晓玲, 何 鹰, 等). Advances in Marine Science(海洋科学进展),2007,25(1): 91. [12] BAI Peng, XIE Wen-jun, LIU Jun-hua(白 鹏, 谢文俊, 刘君华). Opto-Electronic Engineering(光电工程),2006, 33(8): 37. [13] LIN Ji-peng, LIU Jun-hua(林继鹏, 刘君华). Acta Photonica Sinica(光子学报),2006, 35(3): 408. [14] SUN Su-qin, TANG Jun-ming, YUAN Zi-min, et al(孙素琴, 汤俊明, 袁子民, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析),2003,23(2): 258. [15] NIE Lei, LUO Guo-an, CAO Jin, et al(聂 磊, 罗国安, 曹 进, 等). Acta Pharmaceutica Sinica(药学学报),2004, 39(2): 136. [16] YING Wei, WANG Zheng-ou, AN Jin-long(应 伟, 王正欧, 安金龙). Computer Engineering(计算机工程),2006, 32(16): 74. [17] PENG Bin-bin, JIN Xiang-yu, XU Xiao-gang, et al(彭彬彬, 金翔宇, 徐晓刚, 等). Computer Science(计算机科学),2003, 30(3): 75. [18] ZENG Wen-hua, MA Jian(曾文华, 马 健). Journal of Xiamen University(Natural Science) (厦门大学学报·自然科学版),2002, 41(6): 687. [19] XIAO Rong, WANG Ji-cheng, SUN Zheng-xing, et al(萧 嵘, 王继成, 孙正兴, 等). Journal of NanJing University(Natural Sciences)(南京大学学报·自然科学版),2002, 38(2): 152.
