摘要
为了对柴油机的经济性和排放参数进行高效、准确的预测,根据4190型船用柴油机实验数据与边界参数,建立AVL-BOOST甲醇/柴油混合燃料柴油机仿真模型;利用模型进行仿真实验,并建立甲醇掺混比、废气再循环(exhaust gas recirculation,EGR)率、喷油提前角和进气压力4个控制参数对有效油耗率和NO x排放预测数据集;利用该数据集对5种不同核函数的高斯过程回归(Gaussian process regression,GPR)模型进行训练;最后将最优的平方指数高斯过程回归(squared exponential-Gaussian process regression,SE-GPR)模型、AVL-BOOST仿真数据和柴油机实验数据进行对比。结果表明:在数据量为180组时,SE-GPR模型对有效油耗率和NO x排放均取得拟合关联度99%以上,均方根误差(root mean square error,RMSE)分别为1.859,0.3445,平均绝对误差(mean absolute error,MAE)分别为0.954,0.2489;并且,相较于AVL-BOOST仿真实验,SE-GPR模型对实验数据具有更好的拟合性。
In order to efficiently and accurately predict diesel engine economy and emission parameters,based on the experimental data of the 4190 type marine diesel engine and boundary parameters,an AVL-BOOST simulation model for diesel engines utilizing methanol/diesel blended fuels was established,and a dataset for predicting effective fuel consumption and NO x emissions was created by using this model,incorporating four operational parameters:methanol blending ratio,exhaust gas recirculation(EGR)rate,injection advance angle,and intake pressure.The dataset was employed to train Gaussian process regression(GPR)models with five different kernel functions.Finally,the best-performing squared exponential Gaussian process regression(SE-GPR)model was compared with AVL-BOOST simulation data and diesel engine experimental data.The results showed that the SE-GPR model achieves a correlation of over 99%for both effective fuel consumption and NO x emissions when the dataset contains 180 data sets,with root mean square error(RMSE)values of 1.859,0.3445,and mean absolute error(MAE)values of 0.954,0.2489.Moreover,compared to AVL-BOOST simulation experiments,the SE-GPR model exhibits a better fit to the experimental data.
作者
范金宇
才正
黄朝霞
杨晨曦
李品芳
黄加亮
FAN Jinyu;CAI Zheng;HUANG Zhaoxia;YANG Chenxi;LI Pinfang;HUANG Jialiang(School of Marine Engineering,Jimei University,Xiamen 361021,China;Fujian Provincial Key Laboratory of Naval Architecture and Ocean Engineering,Xiamen 361021,China;School of Science,Jimei University,Xiamen 361021,China)
出处
《集美大学学报（自然科学版）》
CAS
2024年第2期152-161,共10页
Journal of Jimei University：Natural Science
基金
福建省自然科学基金项目(2022J01812,2021J01849)
福建省教育厅项目(JAT210237)。
关键词
船用柴油机
甲醇
高斯过程回归
平方指数核函数
性能预测
marine diesel engine
methanol
Gaussian process regression
squared exponential kernel
performance prediction
