摘要
为了选择最优的切削工艺参数,提出一种改进的量子粒子群优化算法。在改进的量子粒子群优化算法中,采用双层多种群的优化策略提高整个种群的寻优能力。在每个子群中使用差分进化和混沌反向学习增强子群的寻优能力。通过对切削工艺参数的优化实验表明,与现有的量子粒子群优化算法相比,改进的量子粒子群优化算法具有更好的寻优能力和收敛性。
To select the optimum cutting process parameters,proposes an improved quantum-behaved particle swarm optimization.In the improved quantum-behaved particle swarm optimization,uses a two-layer multi-swarm strategy to improve the global search ability.Utilizes differential evolution algorithm and chaotic opposition-based learning in each sub-swarm to enhance the searching ability of sub-swarm.The experimental results of cutting process parameters optimization show that the proposed quantum-behaved particle swarm optimization has better optimization ability and convergence than the existing quantum particle swarm optimization algorithms.
作者
贾伟
赵雪芬
JIA Wei;ZHAO Xue-fen(Xinhua College,Ningxia University,Yinchuan 750021)
出处
《现代计算机》
2019年第5期8-12,共5页
Modern Computer
基金
宁夏高等学校科学技术研究项目(No.NGY2017225)
关键词
切削工艺参数
量子粒子群优化算法
多种群
差分进化算法
混沌反向学习
Cutting Process Parameter
Quantum-Behaved Particle Swarm Optimization Algorithm
Multi-Swarm
Differential Evolution Algorithm
Chaotic Opposition-Based Learning
