Detection Method of Trace Multi-component Gases Based on SVM and PCA
YU Dao-Yang1,2, QI Gong-Mei2, QU Ding-Jun, LI Min-Qiang2, LIU Jin-Huai2
1.Department of Automation, University of Science and Technology of China, Hefei 230026 2.Nano-Materials and Environmental Detection Laboratory, Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei 230031
Abstract Gas sensors and optical sensors are difficult to detect trace multi-component gases. In this paper, a detection method of fast chromatography combined with gas sensor array is introduced to obtain the characteristic signal of trace multi-component gases. Support vector machine (SVM) is introduced to classify the samples according to the features. Then, to obtain a better gas identification model, particle swarm optimization algorithm is utilized to optimize the parameters of SVM. Based on actual sample detection and recognition, and compared to detection method by similar testing instrument, the proposed method has better selectivity of mixed gases. Using SVM、 PCA and PSO method is more suitable for processing and identification of small sample data. Developed multi-component gas detection prototype has better recognition rate, repeatability and stability.
[1] Wang S, Feng X L. Development of Multigas Analysis and Identifying Technology. Journal of Chongqing Institute of Technology: Natural Science Edition, 2007, 21(3): 78-81, 87 (in Chinese)(王 帅,冯新泸.多组分气体检测与识别技术进展.重庆工学院学报:自然科学版, 2007, 21(3): 78-81, 87) [2] Grall A J, Zellers E T, Sacks R D. High-Speed Analysis of Complex Indoor VOC Mixtures by Vacuum-Outlet GC with Air Carrier Gas and Programmable Retention. Environmental Science and Technology, 2001, 35(1): 163-169 [3] Samuelsson R, Burvall J, Jirjis R. Comparison of Different Methods for the Determination of Moisture Content in Biomass. Biomass and Bioenergy, 2006, 30(11): 929-934 [4] Shen C Y, Li J Q, Wang H M, et al. Real-Time Measurement of the Drug Precursor Chemicals with Proton Transfer Reaction Mass Spectrometry. Journal of Hunan University: Natural Sciences, 2009, 36(2): 75-79 (in Chinese) (沈成银,李建权,王鸿梅,等.易制毒化学品快速检测新技术.湖南大学学报:自然科学版, 2009, 36(2): 75-79) [5] Li J X, Wu B T, Wang X J. Recent Development Tendency and Application Foreground of Ion Mobility Spectrometry. Ship Science and Technology, 2006, 28(2): 13-15 (in Chinese) (李金香,武波涛,王兴军.离子迁移谱技术发展趋势和应用前景.舰船科学技术, 2006, 28(2): 13-15) [6] Qi R B, Yin X, Yang L, et al. Application of NIR Spectroscopy to Multiple Gas Components Identification. Spectroscopy and Spectral Analysis, 2008, 28(12): 2855-2858 (in Chinese) (齐汝宾,尹 新,杨 立,等.多成分有机气体的近红外光谱定量检测方法.光谱学与光谱分析, 2008, 28(12): 2855-2858) [7] Zhu H D, Luo Q, Zhou L, et al. Application Prospect of Natural Gas Component Analysis Using Laser Raman Spectroscopy. Natural Gas Industry, 2013, 33(11): 110-114 (in Chinese) (朱华东,罗 勤,周 理,等.激光拉曼光谱及其在天然气分析中的应用展望.天然气工业, 2013, 33(11): 110-114) [8] Hai Z, Wang J. Studies on Signal Feature Extraction and Sensor Optimization of an Electronic Nose. Chinese Journal of Sensors and Actuators, 2006, 19(3): 606-610 (in Chinese) (海 铮,王 俊.电子鼻信号特征提取与传感器优化的研究.传感技术学报, 2006, 19(3): 606-610) [9] Peng J. Study on Optimization of Sensor Array for E-nose System. Master Dissertation. Wuhan, China: Huazhong University of Science and Technology, 2008 (in Chinese) (彭 婧.气敏传感器阵列优化应用研究.硕士学位论文.武汉:华中科技大学, 2008) [10] Fan C Q. A Study of Feature Extraction for E-nose System. Master Dissertation. Wuhan, China: Huazhong University of Science and Technology, 2007 (in Chinese) (范超群.电子鼻系统中的特征提取研究.硕士学位论文.武汉:华中科技大学, 2007) [11] Melgani F, Bazi Y. Classification of Electrocardiogram Signals with Support Vector Machines and Particle Swarm Optimization. IEEE Trans on Information Technology in Biomedicine, 2008, 12(5):667- 677 [12] Haykin S. Neural Networks: A Comprehensive Foundation. 2nd Edition. Upper Saddle River, USA: Prentice Hall, 2001 [13] Yu Y, Wang B, Zhang L M. A Fast Data-Oriented Algorithm for Principal Component Analysis. Pattern Recognition and Artificial Intelligence, 2009, 22(4): 567-573 (in Chinese) (余 映,王 斌,张立明.一种面向数据学习的快速PCA算法.模式识别与人工智能, 2009, 22(4): 567-573) [14] Lin S W, Ying K C, Chen S C, et al. Particle Swarm Optimization for Parameter Determination and Feature Selection of Support Vector Machines. Expert Systems with Applications, 2008, 35(4): 1817-1824 [15] Huang C L, Dun J F. A Distributed PSO-SVM Hybrid System with Feature Selection and Parameter Optimization. Applied Soft Computing, 2008, 8(4): 1381-1391 [16] Shen Q, Shi W M, Kong W, et al. A Combination of Modified Particle Swarm Optimization Algorithm and Support Vector Machine for Gene Selection and Tumor Classification. Talanta, 2007, 71(4): 1679-1683 [17] Yuan S F, Chu F L. Fault Diagnostics Based on Particle Swarm Optimization and Support Vector Machines. Mechanical Systems and Signal Processing, 2007, 21(4): 1787-1798 [18] Trelea I C. The Particle Swarm Optimization Algorithm: Convergence Analysis and Parameter Selection. Information Processing Letters, 2003, 85(6): 317-325 [19] Ni Q J, Xing H C, Zhang Z Z, et al. Survey of Particle Swarm Optimization Algorithm. Pattern Recognition and Artificial Intelligence, 2007, 20(3): 349-357 (in Chinese) (倪庆剑,邢汉承,张志政,等.粒子群优化算法研究进展.模式识别与人工智能, 2007, 20(3): 349-357) [20] Shao X G, Yang H Z, Chen G. Parameters Selection and Application of Support Vector Machines Based on Particle Swarm Optimization Algorithm. Control Theory & Applications, 2006, 23(5): 740-743, 748 (in Chinese) (邵信光,杨慧中,陈 刚.基于粒子群优化算法的支持向量机参数选择及其应用.控制理论与应用, 2006, 23(5): 740-743,748)
2015, Vol. 28 
