基于OBLPSO-LSSVM的一氧化碳浓度检测  

CO concentration detection based on OBLPSO-LSSVM

作　　者：张愉[1] 童敏明[2] 戴桂平[1] 

机构地区：[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

出　　处：《计算机工程与应用》2013年第24期249-252,261,共5页Computer Engineering and Applications

基　　金：国家自然科学基金国际合作重大项目(No.60910005);苏州市2013年度工业科技指导性计划项目(No.SGZ2013136);苏州市职业大学成果创新基金资助项目(No.2012SZDCC05)

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。In order to improve the detection accuracy of CO concentration, this paper proposes a CO concentration cletectaon model based OppositionBased Learning Particle Swarm Optimization algorithm and Least Squares Support Vector Machine （OBLPSOLSSVM）. 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 oppositionbased 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 rela tionship 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.

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 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]