CAJ | 학술논문

在四缸柴油机的进气管上安装喷嘴来喷射甲醇,实现甲醇-柴油混合燃烧模式。试验通过燃烧甲醇-柴油和纯柴油混合燃料两种模式进行对比。然后用Levenberg-Marquardt(LM)算法来预测发动机分别燃烧甲醇-柴油混合燃料和纯柴油的BSFC(制动燃料消耗率),CO(碳氧化合物)和HC(未燃烧碳氢化合物)等废气排放特性,以及AFR(空燃比),并与实际测得数据进行对比分析。试验结果表明,LM的学习能力对BSFC,CO,HC和AFR的预测是相当有效,而且和纯柴油相比,甲醇改善了排放特性。
재사항시유궤적진기관상안장분취래분사갑순,실현갑순-시유혼합연소모식。시험통과연소갑순-시유화순시유혼합연료량충모식진행대비。연후용Levenberg-Marquardt(LM)산법래예측발동궤분별연소갑순-시유혼합연료화순시유적BSFC(제동연료소모솔),CO(탄양화합물)화HC(미연소탄경화합물)등폐기배방특성,이급AFR(공연비),병여실제측득수거진행대비분석。시험결과표명,LM적학습능력대BSFC,CO,HC화AFR적예측시상당유효,이차화순시유상비,갑순개선료배방특성。
The nozzles are respectively instal ed on the inlet pipes of the four cylinders which are spraying methanol, in order to realizing combustion mode for methanol-diesel hybrid engine. Combustion mode for methanol-diesel hybrid is compared with combustion mode for diesel only in this lab.Then using Levenberg-Marquardt to predict BSFC (break specific fuel consumption), exhaust emissions that are CO (carbon monoxide) and HC (unburned hydrocarbon), and AFR (airefuel ratio) which operates with methanol-diesel blend fuel and diesel, and compared with actual measured data analysis. The test results show that the LM learning ability to BSFC, CO, HC and AFR prediction is quite effective, and compared with the pure diesel fuel, methanol to improve the emission characteristics.