基于进化神经网络的电火花铣削加工电极损耗预测

›› 2004, Vol. 40 ›› Issue (3): 61-65.

基于进化神经网络的电火花铣削加工电极损耗预测

李翔龙;殷国富;林朝镛

四川大学制造科学与工程学院

发布日期:2004-03-15

TOOL WEAR PREDICTION IN ELECTRICAL DISCHARGE MILLING MACHINING BASED ON EVOLUTIONARY NEURAL NETWORK

Li Xianglong;Yin Guofu;Lin Chaoyong

Sichuan University

Published:2004-03-15

摘要/Abstract

摘要： 针对电火花铣削加工的时变非线性特性，提出基于神经网络的电火花铣削加工电极损耗预测模型，利用该网络预测加工速度和工具的相对损耗，从而可在加工中实时计算出工具实际损耗量，为实现电极损耗的在线动态补偿打下基础。针对神经网络传统训练算法-BP算法的不足，提出了一种自适应调节变异率和变异量的进化算法来优化网络权值和网络结构，提高了网络的逼近精度和进化速度。

关键词: 电火花铣削加工, 工具损耗预测, 进化神经网络

Abstract: In according with the non-linear character in the process of EDMM, a tool wear prediction model is established based on artificial neural network. The tool relative wear and machining rate can be predicted by the network, which makes foundation for tool’s dynamic compensation in EDMM. An improved evolutionary algorithm which could adaptively adjust mutation rate and magnitude of mutation is presented to optimize the neural network’s weights and topology in case of local extre-mums obtained from traditional BP algorithm.

Key words: Electrical discharge milling machining, Evolutionary neural network, Tool wear prediction

中图分类号:

TH16

李翔龙;殷国富;林朝镛. 基于进化神经网络的电火花铣削加工电极损耗预测[J]. , 2004, 40(3): 61-65.

Li Xianglong;Yin Guofu;Lin Chaoyong. TOOL WEAR PREDICTION IN ELECTRICAL DISCHARGE MILLING MACHINING BASED ON EVOLUTIONARY NEURAL NETWORK[J]. , 2004, 40(3): 61-65.