煤矿井下供水管道泄漏孔径识别与定位研究
DOI:
作者:
作者单位:

1.西安科技大学电气与控制工程学院;2.西安科技大学通信与信息工程学院;3.西安科技大学机械工程学院

作者简介:

通讯作者:

中图分类号:

TP277

基金项目:

陕西省自然科学基础研究计划项目(2023-JC-YB-362)


Research on identification and location of leakage aperture of underground water supply pipeline in coal mine
Author:
Affiliation:

1.College of Electrical and Control Engineering, Xi'2.'3.an University of Science and Technology

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    为快速识别煤矿井下泄漏点的位置及泄漏孔径,本文利用供水管道泄漏时产生的压力及流量信号,提出了一种泄漏孔径识别与定位模型。本文首先利用模态能量熵和遗传算法结合包络熵对变分模态分解(variational mode decomposition,VMD)进行参数优化,再使用VMD对压力信号进行降噪处理;采用卷积神经网络(convolutional neural networks, CNN)提取压力及流量信号的深层特征序列,长短时记忆网络(Long short- term memory, LSTM)提取深层特征序列的时序特征,进行泄漏孔径识别与定位。实验结果表明:经过参数优化的变分模态分解,相较卡尔曼滤波、均值滤波、低通滤波在均方根误差(root mean square error, RMSE)、平均绝对误差(mean absolute error, MAE)、信噪比(signal to noise ratio, SNR)、归一化互相关系数(normalized cross correlation, NCC)上均有提高,表明其能够有效降低噪声成分,保留有效信号;CNN-LSTM相较LSTM,在泄漏点定位中,MAE降低了65.97%,平均绝对百分比误差(mean absolute percentage error, MAPE) 降低了61.22%,RMSE降低了59.11%。在泄漏孔径识别中,MAE降低了12.04%,MAPE降低了22.45%,RMSE降低了3.29%,证明CNN-LSTM可以充分利用管道压力及流量信号的空间及时间特征进行泄漏位置及孔径的识别,其检测效果相较LSTM更加准确和稳定。

    Abstract:

    In order to quickly identify the location of the leakage point and the leak aperture in the coal mine, this paper presents a model for identifying and locating the leak aperture by using the pressure and flow signals generated when the water supply pipeline leaks. In this paper, modal energy entropy and genetic algorithm combined with envelope entropy are used to optimize the parameters of variational mode decomposition (VMD), and then VMD is used to denoise the pressure signal. Convolutional neural network(CNN) was used to extract the deep feature sequence of pressure and flow signal, and the long short-term memory network(LSTM) was used to extract the time sequence of deep feature sequence to identify and locate the leak aperture. The experimental results show that compared with Kalman filter, mean value filter and low-pass filter, the variational modal decomposition with optimized parameters has higher root-mean-square error (RMSE), mean absolute error(MAE), signal-to-noise ratio(SNR) and normalized cross correlation(NCC), which indicates that it can effectively reduce noise components and retain effective signals. Compared with LSTM, the MAE, mean absolute percentage error (MAPE) and RMSE of CNN-LSTM in leak location decreased by 65.97%, 61.22% and 59.11%. In the identification of leak aperture, MAE decreased by 12.04%, MAPE decreased by 22.45%, and RMSE decreased by 3.29%, which proves that CNN-LSTM can make full use of the spatial and temporal characteristics of pipeline pressure and flow signals to identify the leak location and aperture, and its detection effect is more accurate and stable than LSTM.

    参考文献
    相似文献
    引证文献
引用本文

杜京义,陈镇,张嘉伟,等. 煤矿井下供水管道泄漏孔径识别与定位研究[J]. 科学技术与工程, , ():

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2024-03-21
  • 最后修改日期:2024-06-07
  • 录用日期:2024-07-09
  • 在线发布日期:
  • 出版日期:
×
亟待确认版面费归属稿件,敬请作者关注
《科学技术与工程》入选维普《中文科技期刊数据库》自然科学类期刊月度下载排行榜TOP10