摘要
针对常规遗传算法全局寻优效率偏低的弱点,提出了一种优进策略,用以改进常规遗传算法。该策略将从繁衍过程中获取进化信息,自适应地改进子代分布,适时引入确定性操作,以提高全局寻优性能。提出的相关技术包括维持种群的多样性、改进交叉算子、增加Powell寻优算子等。实例测试表明这种优进策略效果良好,并已成功地应用于重油热解三集总动力学复杂数学模型的非线性参数估计。
A eugenic evolution strategy was proposed to improve the searching efficiency of the conventional simple genetic algorithm (SGA). The eugenic evolution genetic algorithm (EEGA) collects the population information along the evolution of children generations and constructs a deterministic optimization algorithm, which will be embedded in the evolution process at appropriate stage to speed up the genetic algorithm searching. Besides, the SGA is also modified by proposing an adaptive variation factor to keep the diversity of population, and a novel crossover rule to widen the distribution space of children generation. Within the possible deterministic searching methods, the Powell method is found to be feasible in integrating with the genetic algorithm. Two typical examples indicated the good performance of the proposed method. Finally, we have applied the EGA successfully to the nonlinear parameter estimation of mathematical model for heavy oil thermal cracking.
出处
《高校化学工程学报》
EI
CAS
CSCD
北大核心
2003年第4期411-417,共7页
Journal of Chemical Engineering of Chinese Universities
基金
国家自然科学基金资助项目(20076041)
关键词
优进策略
遗传算法
重油热解
非线性参数估计
Cracking (chemical)
Genetic algorithms
Mathematical models
Optimization
Parameter estimation
