摘要
单元式生产方式可以提高制造企业满足多元化、定制化市场需求的能力。针对制造单元划分问题,以单元加工密度和成组功效为优化目标并引入权重因子q建立数学模型,结合肘部法则和K-Means++确认最佳单元数量,在此基础上提出了改进鲸鱼算法(improved whale optimization algorithm,IWOA),根据数学模型特点,采用浮点数编码策略分配机器和零件;为提高算法全局寻优能力,引入随机学习策略提高个体信息分享能力及种群多样性;为提高算法收敛速度和稳定性,设计自适应权重策略;为避免算法陷入局部最优,引入柯西变异策略。基于改进期望函数确认最佳单元划分方案。以工业汽轮机企业为实际案例,设计对比3种算法验证了该算法的有效性。
Cell production method can improve the ability of manufacturing enterprises to meet the needs of a diversified and customized market.Regarding the issue of manufacturing cell division,a mathematical model was established with the optimization goals of cell processing density and group efficiency,and the weight factor q was introduced.The optimal number of cells was determined by combining the elbow method and K-Means+[KG-2]+.Based on this,the improved whale optimization algorithm(IWOA)was proposed.Machines and parts were allocated using a floating-point encoding strategy according to the characteristics of the mathematical model.To enhance the algorithm′s global optimization capability,a random learning strategy was introduced to improve individual information sharing and population diversity.To increase the algorithm′s convergence speed and stability,an adaptive weight strategy was designed.To prevent the algorithm from getting trapped in local optima,a Cauchy mutation strategy was introduced.The optimal cell division scheme was determined based on the Improved expectation function.Using an industrial steam turbine enterprise as a case study,the effectiveness of the algorithm was validated by comparing it with three other algorithms.
作者
程学宇
王迎春
张琪
王垠凯
CHENG Xueyu;WANG Yingchun;ZHANG Qi;WANG Yinkai(School of Mechanical Engineering,Shenyang University of Technology,Shenyang 110870,China)
出处
《组合机床与自动化加工技术》
北大核心
2025年第5期7-13,共7页
Modular Machine Tool & Automatic Manufacturing Technique
关键词
单元划分
改进鲸鱼算法
期望函数
多目标优化
cell division
IWOA
expectation function
multi-objective optimization
