摘要
表面粗糙度的大小直接关系到零件的使用性能、制造工艺、效率和成本控制等多个方面,而研究切削比能可以揭示不同切削参数对能耗的影响规律,为优化切削工艺参数、提高机床能效提供理论依据。以TA15钛合金为研究对象,设置三因素四水平的全因子铣削实验,以铣削比能和表面粗糙度为预测目标建立了WOA-BP神经网络多输入多输出预测模型,并将模型运用到NSGA-Ⅱ神经网络中,构建了以最低铣削比能和最佳表面质量为优化目标的多目标切削参数模型,并采用NSGA-Ⅱ遗传算法对该模型进行求解,得到最优解集,最后运用熵权TOPSIS法对最优解集进行决策,得出最优解。研究结果表明:优化后的切削参数组合相比工厂经验切削参数组合,节省能耗约10.7%,降低表面粗糙度约3.3%。
The size of surface roughness is directly related to the use of parts performance,manufacturing process,efficiency and cost control and many other aspects.And the study of cutting specific energy can reveal the influence law of different cutting parameters on energy consumption,which provides theoretical basis for optimizing cutting process parameters and improving energy efficiency of machine tools.This study takes TA15 titanium alloy as the research object,sets up a three-factor and four-level full factorial milling experiment,establishes a WOA-BP neural network multi-input multi-output prediction model with milling specific energy and surface roughness as the prediction objectives,and applies the model to NSGA-Ⅱneural network,develops a multi-objective optimization model for cutting parameters aiming to minimize milling energy consumption and maximize surface quality,and applies the NSGA-Ⅱgenetic algorithm to establish a multi-objective optimization model for cutting parameters with the objective of the lowest milling specific energy and the best surface quality.NSGA-Ⅱgenetic algorithm is used to solve the multi-objective optimization model to obtain the optimal solution set,and finally the entropy weight TOPSIS method is used to make a decision on the optimal solution set to obtain the optimal solution.The results show that the optimized cutting parameter combination saves energy consumption by about 10.7%and reduces surface roughness by about 3.3%compared with the empirical cutting parameter combination in the factory.
作者
欧丽
尹瑞雪
赵雪峰
OU Li;YIN Ruixue;ZHAO Xuefeng(School of Mechanical Engineering,Guizhou University,Guiyang 550025,China)
出处
《组合机床与自动化加工技术》
北大核心
2025年第5期168-173,共6页
Modular Machine Tool & Automatic Manufacturing Technique
基金
国家自然科学基金项目(52065012)
贵州省科技计划项目(黔科合基础-ZK[2022]一般153)。
