基于直觉模糊支配的混合多目标粒子群算法

Hybrid Multi-objective Particle Swarm Optimization Based on Intuitionistic Fuzzy Dominance

为提高求解多目标优化问题的精确性和解集分布的均匀性,提出了一种基于直觉模糊支配的混合粒子群算法。通过引入种群全局目标值标量参数、直觉模糊隶属度和排序方法,定义一种新的最优解支配关系;采用基于模拟退火的Meta-Lamarckian局部学习策略,结合粒子群算法,以避免算法陷入局部最优和早熟;此外,定义种群同构因子来衡量种群多样性,以自适应调节惯性权重和加速因子;提出一种递减扰动策略对粒子飞行速度进行扰动;最后,与多种经典多目标优化算法进行仿真测试比较,结果表明该算法在求解精度、解集分布均匀性上具有明显优势。

To improve the precision and distribute uniformity of multi-objective optimization problem, a hybrid multi- objective particle swarm optimization based on intuitionistic fuzzy dominance （IFDHPSO） was proposed. By introducing the scalar factor, this paper utilizeed intuitionistie fuzzy membership and rank method to define a new dominance strate- gy. Then, we proposed a meta-lamarekian local learning strategy to reduce the probability of being trapped into the local optima and premature convergence, which is based on simulated annealing algorithm. Then, the PSO identical factor was defined to adjust inertia weight and acceleration operator adaptively. Furthermore, a decline disturbance strategy was proposed to disturb particle ~ s velocity. Finally, the simulation results comparing with other typical optimization algo- rithm shows that the proposed algorithm performs better in solution precision, uniformity and convergence.