基于神经网络的磨削参数智能选择

Chooseing Grinding Parameters Intelligently Based on the Artificial Neural Networks

作者：罗红波(四川大学制造科学与工程学院四川成都 610065)；孟令锋(四川大学制造科学与工程学院四川成都 610065)；唐才学(四川大学制造科学与工程学院四川成都 610065)

Author：(School of Manufacturing Sci and Eng, Sichuan Univ.,Chengdu 610065,China)；(School of Manufacturing Sci and Eng, Sichuan Univ.,Chengdu 610065,China)；(School of Manufacturing Sci and Eng, Sichuan Univ.,Chengdu 610065,China)

收稿日期：2007-09-13 年卷（期）页码：2008,40(4):176-180

期刊名称：工程科学与技术

Journal Name：Advanced Engineering Sciences

关键字：磨削参数；GCAQBP算法；神经网络

Key words：grinding parameters; GCAQBP algorithm; neural network

基金项目：四川省应用基础资助项目(2000JS1121)

中文摘要

在用人工神经网络来确定磨削参数的过程中，在传统 BP算法的基础上，采用改进了的GCAQBP算法。同时考虑了砂轮材料和粒度对磨削过程的影响，把它们增加为神经网络系统的输入参数；并对输入参数的编码进行了细化，最终建立了磨削参数智能选择系统。用样本进行训练后有效率达到了80%以上，与传统方法相比提高了磨削加工的效率和精度。

英文摘要

In the process of choosing grinding parameters using the method of the artificial neural networks, an improved GCAQBP algorithm on the basis of the BP algorithm was used to establish the mathematical model. The material and granularity of the grinding wheel were considered as the input parameters of the artificial neural networks, and the encoding of the input parameters was refined. Test results showed that the correct rate was more than 80 percent,compared with the traditional method.

【关闭】

论文摘要

基于神经网络的磨削参数智能选择

Chooseing Grinding Parameters Intelligently Based on the Artificial Neural Networks