• 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) >APPLICATION OF NEURAL NETWORKS TO THE INSPECTION OF RAILROAD RAIL
【24h】

APPLICATION OF NEURAL NETWORKS TO THE INSPECTION OF RAILROAD RAIL

机译：神经网络在铁路轨道检查中的应用

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

Railroad rails are routinely inspected by electro-magnetic induction and/or ultrasonic methods to detect flaws and to identify their type. The operator in a detection car inspects the railroad rails using processed ultrasonic data. In this paper we report on a feasibility study of using neural networks in railroad rail flaw detection and identification. Neural networks, which are inspired by the structure and operation of the human brain, have been extensively applied to damage detection and identification. Literature on the application of neural networks in NDE and NDT problems is extensive and will not be cited here. One of the first applications of neural networks was in damage detection in structures (Barai and Pandey; Wu et al.), where neural networks were used to detect damage signatures in the static or dynamic response of the structure. In the NDE/NDT problems, neural networks are used to perform a pattern classification. In the initial phase of this study the same processed data that the operator sees, is used in the neural network study. It is hoped that the successful development and implementation of neural network-based flaw detection techniques will assist the operators and will improve the reliability and efficiency of railroad rail flaw detection. Neural networks are trained for both the detection and identification of the flaws. The study is performed in two parts. In the first part, the data from twelve runs on Sperry Rail Service's test track at Danbury, Connecticut, which contains a number of known defects, is used to train neural networks. The trained neural networks are then applied to flaw detection and identification in data collected on the actual railroad rail inspection runs.
机译：常规地通过电磁感应和/或超声方法对铁轨进行检查，以检测缺陷并确定其类型。检测车中的操作员使用已处理的超声数据检查铁轨。在本文中，我们报告了在铁路缺陷检测和识别中使用神经网络的可行性研究。受人脑结构和操作启发的神经网络已广泛应用于损伤检测和识别。关于神经网络在NDE和NDT问题中的应用的文献非常广泛，这里不再引用。神经网络的最早应用之一是在结构的损伤检测中（Barai和Pandey； Wu等人），其中神经网络用于检测结构的静态或动态响应中的损伤特征。在NDE / NDT问题中，神经网络用于执行模式分类。在本研究的初始阶段，神经网络研究使用了操作员看到的相同处理数据。希望基于神经网络的探伤技术的成功开发和实施能够为操作人员提供帮助，并提高铁路探伤的可靠性和效率。对神经网络进行了训练，以检测和识别缺陷。该研究分为两个部分。在第一部分中，来自Sperry Rail Service在康涅狄格州丹伯里（Danbury）的测试轨道上进行的十二次运行的数据包含了许多已知的缺陷，用于训练神经网络。然后将训练有素的神经网络应用于实际铁路检查运行中收集的数据中的缺陷检测和识别。

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