基于NSGA-Ⅱ优化算法的混合动力专用柴油机多目标优化研究  

Multi-objective Optimization Study Based on NSGA-ⅡOptimization Algorithm for Hybrid Diesel Engine

作　　者：杨庆汉 魏明亮 王斌 段誉 朱晶宇 YANG Qinghan;WEI Mingliang;WANG Bin;DUAN Yu;ZHU Jingyu(Dalian University of Technology,Dalian 116024,China;State Key Laboratory of Intelligent Agricultural Power Equipment,Luoyang 471039,China)

机构地区：[1]大连理工大学能源与动力学院,辽宁大连116024 [2]智能农业动力装备全国重点实验室,河南洛阳4710039

出　　处：《拖拉机与农用运输车》2025年第1期48-55,共8页Tractor & Farm Transporter

基　　金：智能农业动力装备全国重点实验室开放课题(SKLIAPE2023003);天津大学内燃机燃烧学国家重点实验室开放课题(K2023-08)。

摘　　要：随着全球对环境保护和能源效率的关注不断加深,柴油机在交通和工业领域的重要性愈发凸显。然而,目前针对混动专用柴油机的优化研究仍显不足。本文基于混动专用柴油机参数和实验数据构建了GT-power柴油机模型,并采用神经网络进行柴油机排放预测。研究以柴油机的比油耗、NO x排放和排气烟度为优化目标,对常用工况点进行优化。采用NSGA-Ⅱ算法,以喷油正时、进气凸轮正时、排气凸轮正时和EGR阀开度作为优化参数,求解全局最优解。优化结果显示,通过调节控制参数,可以有效降低比油耗和排放,其中NO x平均降低12.3%,排气烟度平均降低26%,比油耗平均改善7.79%。As the global focus on environmental protection and energy efficiency continues to deepen,the importance of diesel engines in the transportation and industrial sectors is becoming increasingly apparent.However,current research on optimization of hybrid-specific engines remains insufficient.In this study,a diesel engine model for hybrid-specific engines was built based on parameters and experimental data using GT-power,and neural networks were used for diesel engine emission prediction.The study optimized the commonly used operating points of the diesel engine by setting the specific fuel consumption,NO x emissions,and exhaust smoke as the optimization objectives.The NSGA-Ⅱalgorithm was used to solve the global optimal solution with the injection timing,intake camshaft timing,exhaust camshaft timing,and EGR valve opening as the optimization parameters.The optimization results show that by adjusting the control parameters,it is possible to effectively reduce the specific fuel consumption and emissions.The NO x emissions were reduced by an average of 12.3%,and the exhaust smoke was reduced by an average of 26%.The specific fuel consumption was improved by an average of 7.79%.

关 键 词：柴油机 NSGA-Ⅱ 多目标优化 

分 类 号：S219[农业科学—农业机械化工程]