基于FLS-SVM的火花塞离子电流点火信号时间差软测量模型及其应用.pdfVIP

Vo l.44 No .5 第 44 卷第 5 J!lJ 中南大学学报(自然科学版) 2013 年 5 月 Journal of Central South University (Science and Technology) May 2013 基于 FLS-SVM 的火花塞离子电流点火信号时间差 软测量模型及其应用 邓清方，袁文华 (邵阳学院机械与能源工程系，湖南邵阳， 422004) 摘要:根据模糊最小二乘支持向量机的理论方法，提出一种基于发动机的转矩、转速以及点火提前角为特征参数 的火花塞离子电流点火信号时间差软测量模型，并采用海沌量子遗传算法对模糊最小二乘支持向量机的惩罚函数 C和核参数σ 进行优化。研究结果表明:该软测量模型所得参数相对误差小于1.00%; 其优化控制后的发动机CO 体积分数降低 体积分数比原型发动机降低 8.61% ， NO 12.83%; HC 体积分数降低 7.68%，取得了较好的排放性能。 x 关键词:汽油机:模糊最小二乘支持向量机:火花塞离子电流;点火信号;软测量模型 中图分类号: TK421 文献标志码:A 文章编号: 1672一7207(2013)05-185 5-06 Soft-measuring model of timing difference between ignition signal and ion current of spark plug based on FLS-SVM DENG Qingfang , YUAN Wenhua (Department of Mechanical and Energy Engineering , Shaoyang College , Shaoyang 422004 , China) Abstract: Based on the theories and methods ofthe FLS-SVM , a soft-m巳asuring model of timing diffl盯ence between ion current and ignition signal of spark plug was put forward by using the pre-ignition angle, engine torque and rotate speed as characteristic parameters. The parameters ofFLS-SVM was optimized by using chaos quantum g巳netic algorithm. Th巳 results show that the relative error of the prediction model is less than 1.00%, and there 缸e at 1目st 8.61%, 12.83% and 7.68% decrease in the discharge ofCO , NOxand HC compared with those ofthe original engine , which indicates that thi8 80亿measuring model can effectively improve the emission behavior of gasoline engine. Key words: gasoline engine; FLS-SVM; ion current ofspark plug; ignition signal; soft-measuring