机械加工
能源消耗
过程(计算)
符号
灵活性(工程)
柔性制造系统
计算机科学
数学优化
工业工程
工程类
机械工程
数学
调度(生产过程)
电气工程
操作系统
统计
算术
作者
Xikun Zhao,Congbo Li,Ying Tang,Yan Lv
标识
DOI:10.1109/tase.2023.3315546
摘要
The integration of flexible process planning and cutting parameter optimization is of great significance to reduce energy consumption and shorten production time. Flexible manufacturing system brings great uncertainty to the flexible process planning and cutting parameter optimization. Most studies are conducted in a static manufacturing environment and lack of adaptive capacity to the uncertainty of the machining resources. To this end, an integrated decision-making method of flexible process plan and cutting parameter is proposed to improve energy efficiency. Specifically, the improved AND/OR network graph is employed to describe various types of process flexibility. Secondly, the coupling characteristics between energy consumption and machining resources, cutting parameters, and operation sequences are analyzed. Then, a Markov Decision Process is utilized to simulate the dynamic generation process of flexible process plans and cutting parameters, and the integrated decision-making method considering dynamic machining resources is designed with actor-critic framework. Finally, extensive comparative experiments are carried out to verify the validity of the proposed method. Experimental results indicate that: 1) the proposed method can determine flexible process plans and cutting parameters to adapt to the dynamics of machining resources. 2) The integrated optimization method reduces $E_{total} $ and $T_{p}$ by 3.59% and 3.45% compared to the two-stage optimization method Note to Practitioners —Decision making of flexible process plans and cutting parameters relies on machining resources in the machining process. Dynamic changes in machining resources make the energy-aware decision of the flexible process plans and cutting parameters a challenging problem. To the best of our knowledge, this paper develops an integrated method of flexible process planning and cutting parameter optimization considering dynamic machining resources that can adapt to the change of machining resources. It may assist decision-makers to provide more practical flexible process plans and cutting parameters based on dynamic machining resources in the machining process.
科研通智能强力驱动
Strongly Powered by AbleSci AI