农用柴油机的DPF再生条件与排放性能智能多目标优化  

Intelligent multi-objective optimization of DPF regeneration conditions and emission performance for agricultural diesel engines

作　　者：王煜华 王贵勇[1] 陈贵升[1] 李进龙 何述超 WANG Yuhua;WANG Guiyong;CHEN Guisheng;LI Jinlong;HE Shuchao(Yunnan Key Laboratory of the Internal Combustion Engine,Kunming University of Science and Technology,Kunming 650500,China;Yunnei Power Co.,Ltd,Kunming 675699,China)

机构地区：[1]昆明理工大学云南省内燃机重点实验室,昆明650500 [2]云内动力集团,昆明675699

出　　处：《农业工程学报》2024年第15期34-43,共10页Transactions of the Chinese Society of Agricultural Engineering

基　　金：云南省重大科技专项计划项目(202402AE090009);云南省基础科学研究项目(202401AS070102)。

摘　　要：为提升农用柴油机的DPF(diesel particulate filters)再生性能、排放和燃油经济性,该研究提出了基于增强循环训练的智能多目标优化方法。通过BP(backpropagation)神经网络构建了DPF再生条件预测模型,并提出AMSO(adaptive memory gull optimization)算法提高预测精度。基于NSGA-Ⅲ(non-dominated sorting genetic algorithm-Ⅲ)对多个控制参数进行优化,并通过稳态和WHTC瞬态循环试验验证。结果表明:在稳态试验验证中,优化后DPF入口和出口温度平均增加了6.10%和2.90%,O_(2)浓度增加了18.86%,同时,NOx、烟度和BSFC(brakespecificfuel consumption)的平均降低分别为10.72%、11.48%和0.24%,确保了DPF的高效安全再生。在瞬态测试验证中,DOC(diesel oxidation catalyst)入口温度、DPF入口温度和O_(2)浓度明显改善,分别增加了31.00%、2.60%和0.50%,同时,NOx和烟度排放分别降低了10.40%和0.80%,燃油消耗减少了3.5%。证明了提出的优化方法解决了农用柴油机DPF再生与排放优化问题,为柴油机再生模式下控制参数优化提供指导。Agricultural diesel engines can be operated continuously under complex and variable conditions for extended periods.The higher requirements are posed on the Diesel Particulate Filter(DPF)regeneration and reliability.This study aims to enhance the safe and efficient performance of DPF regeneration,emissions,and fuel economy of agricultural diesel engines.An intelligent multi-objective optimization was also proposed to enhance multiple cyclic training.Taking the agricultural engines as the research object,the sample data of the bench test was obtained after experimental design.A prediction model was then constructed in the conditions of DPF regeneration using a Back Propagation neural network(BPNN).According to the Seagull Optimization Algorithm(SOA),the Adaptive Memory Seagull Optimization(AMSO)was proposed to optimize the structure parameters of the BPNN model,in order to meet the requirements of precision.The targets of optimization included T4,T5,O_(2) concentration,Brake Specific Fuel Consumption(BSFC),NOx,and smoke opacity.In the specific conditions of agricultural diesel engines,multi-objective optimization of injection and intake control parameters was realized under regeneration mode using the Non-dominated Sorting Genetic Algorithm(NSGA)-III.The AMSO-BP prediction model was used to evaluate the fitness of the Pareto optimal solutions,in order to validate the NSGA-III optimal dataset.The optimized MAP values were written into the Engine Control Unit(ECU)after bench tests.Steady-state and World Harmonized Transient Cycle(WHTC)experiments were carried out to verify the multi-objective optimization of the model.The results indicate that the AMSO significantly outperformed the SOA in the optimization of the BPNN prediction model.The AMSO-BPNN prediction model more accurately utilized experimental data to predict the T4,T5,O_(2) concentration,BSFC,NOx,and smoke opacity,with the R2 values of 0.97,0.99,0.95,0.99,0.98,and 0.95,respectively,on the validation set.Furthermore,the Mean Absolute Percentage Errors(MAPE)

关 键 词：柴油机 排放 神经网络 多目标 DPF 再生条件 

分 类 号：S126[农业科学—农业基础科学]