采用关联进化策略的RWCE算法应用于换热网络优化  

An improved RWCE combined with correlated evolutionary strategy for heat exchanger networks

作　　者：李万总 崔国民[1] 孙涛[1] 赵兵涛[1] Ll Wan-zong;CUI Guo-min;SUN Tao;ZHAO Bing-tao(Institute of New Energy Science and Technology,University of Shanghai for Science and Technology,Shanghai,China,200093)

机构地区：[1]上海理工大学新能源科学与工程研究所,上海200093

出　　处：《热能动力工程》2020年第2期18-25,共8页Journal of Engineering for Thermal Energy and Power

基　　金：国家自然科学基金(51176125)。

摘　　要：换热单元之间的耦合关系导致其在优化过程中相互制约,造成强制进化随机游走算法应用于换热网络时后期优化停滞。因此,提出一种关联进化策略实现换热单元间的联动进化。首先对换热网络中换热单元的关联关系进行了分析,评估了这种关联关系对进化算法的制约及效率的影响;在此基础上,建立了关联换热单元的联动进化机制,克服了优化过程中的关联制约,提升了进化的效率。最后,将采用单元关联进化策略的算法应用于15SP、16SP2算例,分别得到了年综合费用(TAC)为1513253和6849252$/a的结果,其中15SP算例的TAC较文献最优结果下降了5715$/a,验证了改进后的算法能有效地提高搜索质量。The coupling relationship among heat units in heat exchanger network causes to the restriction of units and the stagnation of optimization using random walk algorithm with compulsive evolution.Therefore,a correlated evolutionary strategy is proposed to realize the linked evolution for heat units.Firstly,the correlated relationship among heat units is analyzed with respect to the effects on the efficiency of evolutionary algorithm.On this basis,a linked evolutionary mechanism for correlated heat units is established to overcome the correlated restriction and enhance the evolution efficiency.Finally,the strategy is integrated with RWCE and applied to two cases,15 SP and 16SP2.Two optimal structures with TAC of 1513253$/a and 6849252$/a were achieved,where the one in 15SP decreased by 5715$/a compared with the best result in literatures,which demonstrating the efficiency in improving the search quality of algorithm.

关 键 词：换热网络优化 耦合 关联进化 

分 类 号：TK124[动力工程及工程热物理—工程热物理]