首页> 外文会议>Smart Structures and Materials 1994: Smart Materials >Approach to modeling the spray-forming process with artificial neural networks
【24h】

Approach to modeling the spray-forming process with artificial neural networks

机译:用人工神经网络建模喷雾成型过程的方法

获取原文
获取原文并翻译 | 示例

摘要

Abstract: In this study artificial neural networks were used tomodel the spray forming process. Networks weredeveloped and trained using process parameter andproduct quality data collected from a series of fivespray forming runs. Process parameters of time intorun, melt temperature, and gas to metal ratio were usedas inputs and the networks were trained to predict thecorresponding values of exhaust gas temperature,preform surface roughness, and porosity in the product.These networks were then tested with actual andhypothetical data. The results of the study showed thatthe networks can determine relationships betweenprocess parameters and the end product quality. It wasalso shown that the networks can be used to predict theeffect on product quality from changes in processparameters. Additional work is in progress to create alarger data set for training over a broader region ofthe operating envelope. The result of this ongoing workwill provide greater reliability in network prediction.!9
机译:摘要:在这项研究中,人工神经网络被用来模拟喷射成形过程。使用从一系列五次喷雾成型运行中收集的工艺参数和产品质量数据开发和培训网络。以运行时间,熔融温度和气金属比的工艺参数为输入,并训练网络来预测产品中废气温度,瓶坯表面粗糙度和孔隙率的相应值,然后使用实际和假设数据对这些网络进行测试。研究结果表明,该网络可以确定工艺参数与最终产品质量之间的关系。还表明,该网络可用于根据工艺参数的变化预测对产品质量的影响。正在进行其他工作来创建更大的数据集,以在操作范围的更广区域上进行训练。正在进行的工作的结果将为网络预测提供更高的可靠性。9

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