应用于换热网络优化的混合遗传算法性能研究  

Characteristics of Hybrid Genetic Algorithms in Optimization of Heat Exchanger Networks

作　　者：刘新文[1,2] 毛政涛 

机构地区：[1]宁波工程学院,浙江宁波315016 [2]上海理工大学,上海200093

出　　处：《宁波工程学院学报》2014年第3期22-28,46,共8页Journal of Ningbo University of Technology

基　　金：宁波市教育科学规划课题成果(项目编号:YGH032);"王伟明助创基金"项目(项目编号:2013006)

摘　　要：换热网络综合优化属于系统热集成技术的重要研究方向。换热网络综合优化技术研究对于节约能源、保护环境和提高高耗能企业的市场竞争力具有重要意义。然而,由于换热网络综合优化模型本身属于MINLP问题,形式复杂且解空间大,经典的梯度寻优很难凑效。本文建立了以年总费用函数为优化目标的换热网络综合优化模型,提出了应用改进的混合遗传算法用于换热网络综合优化,并以基本遗传算法为对照,对混合遗传算法的用于换热网络综合的性能进行了研究。实例研究表明改进的混合遗传算法能更有效地进行换热网络综合优化。The synthesis of heat exchanger networks is an important direction for the investigation of systematic heat integration. The related research is of great importance for high energy consumption enterprises to save energy, protect environment and improve market competition. Yet the mathematical model of HEN synthesis is itself the mixed integer non-linear program （MINLP） problem with complex form and large solution space, therefore, the classical optimization method with gradient optimization is difficult for solving it. In this paper, the object function with the annual total cost of HEN is built and the hybrid genetic algorithm developed to optimize HEN. Compared with the single genetic algorithm, the characteristics of hybrid genetic algorithms are studied. The example is taken to show the better effect of hybrid genetic algorithm for optimizing the synthesis of HEN.

关 键 词：换热网络 综合优化 混合遗传算法 性能 

分 类 号：TK513[动力工程及工程热物理—热能工程]