摘要
针对柴油机SCR反应器结构参数的模糊特性,将CFD仿真得到的不同结构参数下柴油机SCR反应器在温度为380℃时的性能仿真结果作为训练集,采用混沌量子遗传算法对模糊最小二乘支持向量机的参数进行优化,建立柴油机SCR反应器性能FLS-SVM预测模型。研究结果表明:柴油机SCR反应器性能预测模型的相对预测误差均小于3.0%,表明柴油机SCR反应器性能仿真结果与FLS-SVM预测模型的结果具有较高的准确精度。
Due to the fuzzy speciality of structure parameters for SCR reactor of diesel engine, taking CFD simulation results for different diesel SCR reactor structural parameters at 380 ℃ as the training set, a new fuzzy least squares support vector machines model of prediction was established based on chaotic quantum-inspired genetic algorithm, in which the parameters of fuzzy least squares support vector machines was optimized by using chaos quantum genetic algorithm. The results show that the relative error of the prediction model is less than 3.0%, indicating that CFD simulation results and those of FLS-SVM prediction model have high accuracy and precision.
出处
《中南大学学报(自然科学版)》
EI
CAS
CSCD
北大核心
2012年第10期3906-3911,共6页
Journal of Central South University:Science and Technology
基金
国家高技术研究发展计划("863"计划)项目(2008AA11A116)
湖南省教育厅科学研究项目(11C0699)
关键词
混沌量子遗传算法
最小二乘支持向量机
柴油机
SCR反应器
chaotic quantum-inspired genetic algorithm
least squares support vector machines
diesel
SCR reactor