检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:田景海 齐凯华 陈江义[1] TIAN Jing-hai;QI Kai-hua;CHEN Jiang-yi(School of Mechanical and Power Engineering,Zhengzhou University,Zhengzhou 450001,China)
机构地区:[1]郑州大学机械与动力工程学院,郑州450001
出 处:《组合机床与自动化加工技术》2020年第10期27-30,34,共5页Modular Machine Tool & Automatic Manufacturing Technique
基 金:河南省重大科技专项资助(171100210300-01)。
摘 要:为了提高数控机床切削实例推理准确度,近一步细化实例属性,在分析各种实例推理改进算法特性的基础上,提出了采用分级策略计算相似度的方法。该策略与传统相似度计算策略不同,在属性细化的基础上,对属性进行了分级,相似度计算是由第一级向最后一级依次进行。同时考虑了权重系数的取值问题,采用主观权重与客观权重相结合,以乘法合成法计算出的组合权重来反映各实例属性的重要程度。最后,将分级策略应用于切削实例推理过程当中,从历史实例中检索出与设计实例最相似的实例,并将其与一般实例推理结果做了对比。结果表明,分级策略可使总相似度整体提高,推理结果合理、准确。In order to improve the reasoning accuracy of the cutting instance of CNC machine tools,the attributes of cutting instance were refined,and its hierarchical strategy was carried out based on the analyzation of modified algorithms′characteristics.This strategy classified the instance attributes on the basis of attribute refinement and carried out similarity calculation from the first level to the last level,which is different from the traditional one.At the same time,for calculating the weight coefficient,a method of combining subjective weight and objective weight by multiplication was used to reflect the importance of each attributes of the instance.Finally,the hierarchical strategy was applied to find the most similar instance from the historical instances,and the result was compared with the results of the general instance reasoning strategy,which shows that the modified strategy can improve the overall similarity,rationality and accuracy of the instance reasoning process.
分 类 号:TH162[机械工程—机械制造及自动化] TG659[金属学及工艺—金属切削加工及机床]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.33