• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Applied Computational Electromagnetics Society journal >Non-Destructive Detection of Pipe Line Cracks Using Ultra Wide Band Antenna with Machine Learning Algorithm
【24h】

Non-Destructive Detection of Pipe Line Cracks Using Ultra Wide Band Antenna with Machine Learning Algorithm

机译：Non-Destructive Detection of Pipe Line Cracks Using Ultra Wide Band Antenna with Machine Learning Algorithm

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

摘要

In this article, an Ultra-Wide Band (UWB)antenna for the pipeline crack detection process is proposed.A UWB antenna has been designed with thedimension of 32 × 32 mm~2 and it resonates from 3 GHzto 10.8 GHz. The designed antenna produces a peak gainof 4.36 dB. A pair of UWB antennas are employed invarious pipeline scenarios and the received pulse fromantenna 1 to antenna 2 is used for further processingand detection of pipeline cracks. Through the suitablemachine learning data classifier algorithm the dimensionof the crack has been detected. The various featuressuch as mean, standard deviation (σ), mean averagedeviation (mad), skewness, and kurtosis have beenextracted from the received pulse. Then the three differentmachine learning algorithms namely Support VectorMachine (SVM), k-Nearest Neighbor (kNN), and Na¨?veBayse (NB) were trained and tested using extracted features,and the dimension of the void has been identified.Out of these three machine learning algorithms, kNNprovides better accuracy and precision. It predicts thesmall cracks with 100 accuracy having a dimension assmall as 1 mm width.

著录项

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