• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Annual Symposium on Quantitative Nondestructive Evaluation; 19980719-24; Snowbird,UT(US) >A SYSTEMATIC APPROACH TO ULTRASONIC PATTERN RECOGNITION FOR REAL-TIME INTELLIGENT FLAW CLASSIFICATION IN WELDMENTS
【24h】

A SYSTEMATIC APPROACH TO ULTRASONIC PATTERN RECOGNITION FOR REAL-TIME INTELLIGENT FLAW CLASSIFICATION IN WELDMENTS

机译：焊缝实时智能缺陷分类的超声模式识别系统方法

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this work, we have developed a systematic approach to ultrasonic pattern recognition for real-time intelligent flaw classification in weldments, which involves 1) the development of a PC-based real-time ultrasonic testing system which can captured the digitized ultrasonic flaw signal and apply the pattern recognition software in a real-time fashion, 2) the construction of a database which contains 760 waveforms from cracks, porosity and slag inclusions, 3) the proposal of the normalized features which are very robust to the training sets or operation variables, and finally 4) the development of an intelligent software for invariant ultrasonic flaw classification in weldments. Normalized features proposed in this work demonstrates their capability to reduce the effect of the operational variables not only on the ultrasonic features but also on the bias in the classification due to the variation in the training and the test sets. Thus we feel that using these normalized features an invariant ultrasonic pattern recognition can be realized very efficiently. In fact, as a natural extension of this study, the real-time intelligent ultrasonic flaw classification system is available shortly.
机译：在这项工作中，我们开发了一种系统化的方法，用于对焊件中的实时智能缺陷分类进行超声模式识别，其中包括：1）开发基于PC的实时超声测试系统，该系统可以捕获数字化的超声缺陷信号，并实时应用模式识别软件； 2）建立数据库，其中包含来自裂缝，孔隙和夹渣的760个波形； 3）建议对训练集或操作变量非常可靠的归一化特征，最后4）开发了用于焊件不变超声缺陷分类的智能软件。这项工作中提出的归一化特征展示了其减少操作变量不仅对超声特征的影响，而且还减少了归因于训练和测试集变化的分类偏差的能力。因此，我们认为使用这些归一化特征可以非常有效地实现不变的超声模式识别。实际上，作为这项研究的自然扩展，实时智能超声波缺陷分类系统很快就会面市。

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