首页> 外文会议>Advances and experiences with pipelines and trenchless technology for water, sewer, gas, and oil applications >Muti-layers Wavelet Kohonen Neural Network Model for Underground PipelineCoating Detection with Galvanostatic Transient Technique
【24h】

Muti-layers Wavelet Kohonen Neural Network Model for Underground PipelineCoating Detection with Galvanostatic Transient Technique

机译:恒电流瞬变技术用于地下管线涂层检测的多层小波Kohonen神经网络模型

获取原文
获取原文并翻译 | 示例

摘要

The galvanostatic transient response method was used to detect the undergroundrnpipeline coating on the spot without excavation. With wavelet and neural networkrnmethod a multi-layer model was established to analysis the detection information.rnThe model was made up based on Self-organization of Kohonen neural networks andrnthe advantage of wavelet to pike up the useful information. The model has threernparts, the front five layers have the ability to pike up the information, the weights ofrnthis part are the adaptive wavelet coefficient (filter). The sixth layer corresponding tornreconstruction of wavelet analysis, in this way some useful information can bernresumed. The last layer has the ability of self-training. After self-training the weightsrnwere remembered like BP neural network. It is confirmed that the method is correctrnand convenient for on-the-spot detection by the detection result of actual pipelinernbetween Dezhou and Puyang of Zhongyuan Oil Field.
机译:静电流瞬变响应法用于现场现场探测地下管线涂层而无需挖掘。利用小波和神经网络方法建立了多层模型,对检测信息进行了分析。基于Kohonen神经网络的自组织,利用小波提取有用信息,建立了该模型。该模型分为三个部分,前五层具有汇总信息的能力,该部分的权重为自适应小波系数(滤波器)。第六层对应于小波分析的重建,这样可以恢复一些有用的信息。最后一层具有自我训练的能力。经过自我训练后,像BP神经网络一样记住了权重。通过中原油田德州至Pu阳之间实际管道的检测结果,证实了该方法的正确性和简便性。

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