Computer Engineering and Applications ›› 2013, Vol. 49 ›› Issue (24): 249-252.

Previous Articles     Next Articles

CO concentration detection based on OBLPSO-LSSVM

ZHANG Yu1, TONG Minming2, DAI Guiping1   

  1. 1.School of Electronic & Information Engineering, Suzhou Vocational University, Suzhou, Jiangsu 215104, China
    2.School of Information & Electric Engineering, China University of Mining and Technology, Xuzhou, Jiangsu 221008, China
  • Online:2013-12-15 Published:2013-12-11

基于OBLPSO-LSSVM的一氧化碳浓度检测

张  愉1,童敏明2,戴桂平1   

  1. 1.苏州市职业大学 电子信息工程学院,江苏 苏州 215104
    2.中国矿业大学 信电学院,江苏 徐州 221008

Abstract: In order to improve the detection accuracy of CO concentration, this paper proposes a CO concentration detection model based Opposition-Based Learning Particle Swarm Optimization algorithm and Least Squares Support Vector Machine(OBLPSO-LSSVM). The samples of CO concentration detection are composed, and then the samples are input to LSSVM to train, and the optimal parameters of LSSVM are obtained by Particle Swarm Optimization algorithm in which opposition-based learning mechanism is introduced and the CO concentration detection model is established. The simulation experiment is carried out to test the performance of model in MATLAB 2012. The results show that the proposed model can describe the nonlinear relationship between the input and output of CO detection system and has improved the detection accuracy of CO concentration, and it has good practical application value.

Key words: CO concentration, Particle Swarm Optimization(PSO) algorithm, opposition-based learning, Least Squares Support Vector Machine(LSSVM), gas detection

摘要: 为了提高CO浓度检测精度,提出一种反向学习机制粒子群算法(OBLPSO)优化最小二乘支持向量机(LSSVM)的CO浓度检测模型(OBLPSO-LSSVM)。构建CO浓度检测的学习样本,输入到LSSVM中训练,通过引入反向学习机制的粒子群算法找到LSSVM的最优参数建立CO浓度检测模型,在Matlab 2012平台对模型性能进行仿真测试。结果表明,OBLPSO-LSSVM可以精确描述CO检测系统的输入与输出间的非线性变化关系,提高了CO浓度检测精度,具有一定的实际应用价值。

关键词: 一氧化碳浓度, 粒子群优化算法, 反向学习, 最小二乘支持向量机, 气体检测