摘要
为了实现F-T煤制油在柴油机上低排放燃烧的目的,选取柴油机典型工况,采用Box-Benhnken方法进行试验设计,通过支持向量机和响应面方法建立喷油参数与排放指标之间的数值模型,在对比分析模型性能的基础上,对柴油机排放指标进行多目标优化研究。分析表明:响应面模型选择二次回归方程进行拟合分析,支持向量机模型(SVM)选用RBF核函数时,两种模型的预测精度最高。试验工况下,响应面模型对SOOT和NOx预测的最低精度分别是77.4%和97.1%,SVM模型对SOOT和NOx预测的最低精度分别是40.1%和90.8%,在试验样本较少状况下响应面模型预测精度高于SVM模型,可以准确表达喷油参数与排放指标之间的关系。在测试工况下,采用响应面模型对柴油机排放指标进行优化分析,SOOT和NOx分别降低55.72%和7.43%。
In order to realize the low-emission combustion ofF-T coal-to-fuel on the diesel engine,the typical working conditions of the diesel engine were selected and the box-benhnken method was used for the test design.The numerical model between fuel injection parameters and emission index was established.The results show that the response surface model chooses quadratic regression equation for fitting analysis,and the support vector machine model(SVM)chooses RBF kernel function,and the two models have the highest prediction accuracy.Test conditions,the response surface to predict the minimum accuracy were 77.4% and 97.1%,respectively,the SVM model to predict the minimum accuracy were 40.1% and 90.8%,respectively,in a test sample is less condition prediction accuracy than the SVM model,the response surface model can effectively express the connection between the injection parameters and emissions targets.Indicators were optimized by using the response surface model on diesel engine exhaust emissions analysis,55.72% lower values of SOOT and NOx value by 17.43%.
作者
宇文浩男
王铁
石晋宏
张正午
YUWEN Hao-nan;WANG Tie;SHI Jin-hong;ZHANG Zheng-wu(College of Mechanical and Vehicle Engineering,Taiyuan University of Technology,Shanxi Taiyuan 030024,China)
出处
《机械设计与制造》
北大核心
2022年第6期189-192,198,共5页
Machinery Design & Manufacture
基金
中型载货车平台燃料电池动力系统与整车集成技术(20181102006)。
关键词
F-T煤制油
电控柴油机
数值建模
排放特性
多目标优化
F-T Dieselignition
Electronic Control Diesel Engine
Numerical Modeling
Emission Performance
Multi-Objective Optimization
