一种多子群协进化的粒子群算法同步综合换热网络

A Multi-subpopulation Co-evolutionary Particle Swarm Optimization Algorithm for Simultaneous Synthesis of Heat Exchanger Networks

针对同时存在整型变量及连续变量的换热网络优化问题,提出一种多子群协进化的粒子群算法。为了增强粒子群算法的全局搜索能力,将种群按精英个体、一般个体、较差个体划分为3个子群,针对每个子群的粒子进化状态提出不同的学习算子,用于丰富粒子的进化方式,增加种群多样性;同时建立协进化机制,动态地更新子群,以实现粒子之间的良性竞争,更好地引导粒子进化。采用结构优化策略处理整型变量,并与多子群协进化的粒子群算法结合,实现了连续变量与整型变量的同步优化。通过两个优化实例验证算法的性能,优化结果表明了新方法的有效性。

To solve the mixed-integer nonlinear programming problem in optimizing heat exchanger networks,a multi-subpopulation co-evolutionary particle swarm optimization(PSO) algorithm was proposed. To improve the global search ability of PSO,the population in the algorithm was divided into three subpopulations based on the performance of individuals,namely,good,general and bad individuals. For each subpopulation,different update strategies were applied to adapt different evolution state,further enhancing the diversity of the whole population. Meanwhile,the coevolution mechanism was established to update the sub-populations dynamically for the benign competition among particles.Moreover,the structure optimization strategy was incorporated with the proposed PSO to simultaneously optimize the continuous and integer variables. Two verification cases performed clearly indicated the feasibility of the presented algorithm.