改进的遗传算法应用于电控蓄压式喷油系统  

Application of Improved Genetic Algorithms to the Electronically Controlled Pressure-accumulation Fuel Injection System

作　　者：张红光[1] 孙永霞[1] 韩宇石[1] 李智慧[1] 

机构地区：[1]北京工业大学环境与能源工程学院,北京100022

出　　处：《北京工业大学学报》2005年第1期66-71,共6页Journal of Beijing University of Technology

基　　金：北京市自然科学基金资助项目(3012005)北京市优秀人才专项基金资助项目(I050501-02).

摘　　要：为了使柴油机电控蓄压式喷油系统达到最理想的喷油效果,需要对其重要参数(结构参数和运行参数) 进行优化设计,其中涉及到的参数多而且参数之间存在着复杂的耦合关系.在柴油机电控蓄压式喷油系统的参 数优化设计过程中,以其工作过程的数字仿真为前提,在简单遗传算法的基础上,采用了几种改进的遗传算法对 参数进行优化.对各种改进遗传算法的参数优化过程进行了全面的、简要的说明.由优化结果可知,就达到最大 适应度的累积个体数来看,自适应遗传算法比简单遗传算法多355个最优个体,自适应及最优保留策略的遗传 算法比简单遗传算法多392个最优个体,重复交叉及最优保留策略的遗传算法比简单遗传算法多397个最优 个体.In order to optimize fuel injection results of the electronically-controlled pressure-accumulation system for diesel engines, the optimization of its parameters including structure parameters and function parameters is required. The number of related parameters is large and complex relation between them is present. According to numerical simulation of the working process, based on the simple genetic algorithm (SGA), some types of improved genetic algorithms are applied to optimize the parameters. In this paper, the process of the parameter optimization designed for each improved genetic algorithm (GA) is explained briefly and discussed in many of its respects. The optimized results show that, in the total number of the largest fitness, AGA is 355 times more than SGA, AORGA is 392 times more than it, and REGA is 397 times more than it.

关 键 词：数字仿真 遗传算法 电控蓄压式喷油系统 

分 类 号：TK421[动力工程及工程热物理—动力机械及工程]