...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Information Technology Journal >A Binary ART Neural Network Methodolgy for Computer-Aided Process Palnning of Milling Parameters
【24h】

A Binary ART Neural Network Methodolgy for Computer-Aided Process Palnning of Milling Parameters

机译：用于铣削参数计算机辅助工艺规划的二进制ART神经网络方法

获取原文
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Artificial neural network have been successfully employed for providing efficient solutions for decision making problems and gained increased significance for their use in computer integrated manufacturing environment as effective tools for improving productivity and decision quality. The function of process planning in machining operations is a prominent one for neural network applications since it has direct impact on overall manufacturing productivity. This paper presents analysis and results of applying self-organizing neural network s to the selection of machining parameters of milling processes. The importance of this approach stems from the ability of neural nets to handle vague or ill-structured problems and the inherent capability of generalizing solutions to unseen problems. Furthermore, self-organizing neural network s do not require full knowledge of `output` data needed during the training phase; only a small portion of the data is needed for model calibiration. Simulations using ART1 neural model were applied to the selection of the tool material type and tool entry strategy, and the results demonstrated a high potential for the development of neural network modules for practical applications.
机译：人工神经网络已成功地用于为决策问题提供有效的解决方案，并已将其在计算机集成制造环境中用作提高生产率和决策质量的有效工具，其重要性日益提高。加工操作中的过程计划功能是神经网络应用程序中最重要的功能，因为它直接影响整体生产效率。本文介绍了将自组织神经网络应用于铣削加工参数选择的分析和结果。这种方法的重要性源于神经网络处理模糊或结构不良的问题的能力，以及对未解决问题进行泛化的固有能力。此外，自组织神经网络不需要训练阶段所需的“输出”数据的全部知识。模型校准只需要一小部分数据。使用ART1神经模型进行的仿真被应用于工具材料类型和工具进入策略的选择，结果证明了在实际应用中开发神经网络模块的巨大潜力。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号