• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Annual International Workshop on Materials Science and Engineering >Thermal Error Predictive Model of Motorized Spindle Based on Self-recurrent Wavelet Neural Network
【24h】

Thermal Error Predictive Model of Motorized Spindle Based on Self-recurrent Wavelet Neural Network

机译：基于自复制小波神经网络的电动主轴热误差预测模型

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

摘要

A great challenge in improving the machining accuracy of high speed machine center is to establish accurate thermal error models for motorized spindle as its thermal errors are the main sources of inaccuracy. With the rising of the rotation speed, the spindle's temperature and thermal error increase gradually. In this paper, a new approach to derive an effective mathematic thermal model for motorized spindle is presented. The thermal errors accumulated are the combination of thermal distortions from different components with different thermal characteristics. The thermal deformation is a nonlinear procedure due to the variational working condition. By taking into consideration the thermal-elastic characteristics, a dynamic self-recurrent wavelet neural network is applied to capture the dynamics in order to assure thermal error predictive model accuracy. The structure of this model determines its dynamic characteristic with memory feedback loop. To evaluate the performance of proposed model, a verification experiment is carried out. The predictive results show the proposed model can improve the accuracy of motorized spindle effectively.
机译：提高高速机械中心加工精度的巨大挑战是为电动主轴建立精确的热误差模型，因为其热误差是不准确的主要源。随着轮换速度的上升，主轴的温度和热误差逐渐增加。本文提出了一种推导出用于电动主轴有效数学热模型的新方法。累积的热误差是具有不同热特性的不同部件的热扭曲的组合。由于变分的工作状态，热变形是非线性过程。考虑到热弹性特性，施加动态自回性小波神经网络以捕获动力学以确保热误差预测模型精度。该模型的结构确定了内存反馈回路的动态特性。为了评估所提出的模型的性能，进行了验证实验。预测结果表明，所提出的模型可以有效地提高电动主轴的精度。

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