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,并采用混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体积分数比原型发动机降低8.61%,NOx体积分数降低12.83%;HC体积分数降低7.68%,取得了较好的排放性能。
Based on the theories and methods of the FLS-SVM, a soft-measuring model of timing difference 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 of FLS-SVM was optimized by using chaos quantum genetic algorithm. The results show that the relative error of the prediction model is less than 1.00%, and there are at least 8.61%, 12.83% and 7.68% decrease in the discharge of CO, NOx and HC compared with those of the original engine, which indicates that this soft-measuring model can effectively improve the emission behavior of gasoline engine.
出处
《中南大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2013年第5期1855-1860,共6页
Journal of Central South University:Science and Technology
基金
湖南省自然科学基金资助项目(09JJ6077)
湖南省教育厅科学研究项目(12C0861)
