摘要
在金属塑性成形的研究中 ,数值模拟被广泛地使用 ,但在其结果数据中许多潜在有价值的规律未被发现。在各种机器学习算法中 ,决策树以其简单容易实现等特点被认可。本文对具有代表性的方盒件拉深进行了数值模拟 ,研究各种工艺和几何参数对其成形的影响 ,并采用决策树C4 .5算法对其结果数据进行知识提取 ,挖掘其中对产品工艺设计有意义的指导性知识。
In the studies of metal forming process, the numerical simulation is used widely, but the potential and valuable rules hid in the result data have not been discovered. The algorithm of decision trees is well known due to simpleness and easy to realize in machine learning. In this paper, the numerical simulation of the box drawing process was performed and the effect of various parameters on the drawing was investigated. The decision tree algorithm,C4.5,was used to acquire the instructive knowledge.
出处
《机械科学与技术》
CSCD
北大核心
2004年第12期1506-1508,1514,共4页
Mechanical Science and Technology for Aerospace Engineering
基金
上海市科技启明星计划跟踪项目 (0 1QMH14 11)资助
关键词
塑性成形
数值模拟
决策树
知识获取
Plastic forming
Numerical simulation
Decision trees
Knowledge acquisition