改进粒子群算法在陶瓷配方问题上的应用  

Application of Improved Particle Swarm Optimization Algorithm to Ceramic Formula Problem

作　　者：贺楚寒 刘宇娇 汤可宗 HE Chuhan;LIU Yujiao;TANG Kezong(Department of Information Technology,Jingdezhen Ceramic University,Jingdezhen,China,333403)

机构地区：[1]景德镇陶瓷大学信息工程学院,江西景德镇333403

出　　处：《福建电脑》2023年第7期25-29,共5页Journal of Fujian Computer

基　　金：演化计算方法在多模态优化问题中的应用研究(No.GJJ211331)资助。

摘　　要：为更好地求解陶瓷配方设计问题,本文提出一种改进的自适应粒子群优化算法。该算法采用一种新的自适应惯性权重策略及设置学习因子随迭代次数非线性变化,有效平衡了粒子种群的全局和局部搜索性能。在一组陶瓷配方设计问题的仿真实验的结果表明,该算法比其他测试算法在收敛速度、配方精度上有均有明显的优势,能有效应用于陶瓷配方设计问题。In order to better solve the ceramic formula design problem,this paper proposes an improved adaptive particle swarm optimization algorithm APSO.The algorithm adopts a new adaptive inertia weight strategy and sets a learning factor that varies nonlinearly with the number of iterations,effectively balancing the global and local search performance of the particle population.The results of simulation experiments on a group of ceramic formula design problems show that the APSO algorithm has significant advantages over other test algorithms in terms of convergence speed and formula accuracy,and can be effectively applied to ceramic formula design problems.

关 键 词：粒子群算法 陶瓷配方设计 最优化问题 

分 类 号：TP3-05[自动化与计算机技术—计算机科学与技术]