用神经网络求实时控制的电化学齿轮修形过程的施电规律  

A Method for Solving the Control Law for Electrochemical Gear-tooth Profile Modification by ANN

作　　者：YI Jian-jun YANG Tao ZHOU Jin-jin 易建军[2] 杨涛[2] 周锦进[3] 王彤波[3] 

机构地区：[1]CAD Center, School of Mechanical Science and Engineering, Huazhong University of Science and Technology, [2]华中理工大学 CAD中心, [3]大连理工大学 机械学院,

出　　处：《机械科学与技术》2001年第1期102-105,共4页Mechanical Science and Technology for Aerospace Engineering

摘　　要：提出了一种基于实时控制的电化学齿轮修形的新方法，设计并制作了电化学齿轮修形的加工装置，建立了修形齿面去除规律的数学模型。利用人工神经网络的方法在已知修形量及修形区域的情况下求取了加工施电规律，应用满足加工条件的试验数据对网络进行了学习训练，使网络映射成功，以此为基础，根据要求修形量及修形特点，反求取实时控制的电化学修形的施电规律。通过着色试验和所测得的齿形齿向曲线，证明了该修形工艺方法的可行性，在实际生产中有较大的应用与推广价值。We developed a new method for electrochemical tooth-profile modification based on real-time controlling, and established the mathematical model of electrochemical tooth-profile modification process. We obtained the law of processing electric current with an artificial neural network(ANN) when the tooth-profile modification quantity and its fields is given. We trained the ANN with the testing data which satisfy the processing condition, and it is mapped successffully. The method was proved efficient through practical processing and testing.

关 键 词：人工神经网络 电化学齿轮修形 实时控制 施电规律 

分 类 号：TG662[金属学及工艺—金属切削加工及机床] TG619