[1]王新颖,张惠然,黄旭安,等.深度信念网络在管道故障诊断中的应用[J].常州大学学报(自然科学版),2020,32(03):71-78.[doi:10.3969/j.issn.2095-0411.2020.03.010]
　WANG Xinying,ZHANG Huiran,HUANG Xu'an,et al.Application Research of Deep Belief Network in Pipeline Fault Identification[J].Journal of Changzhou University(Natural Science Edition),2020,32(03):71-78.[doi:10.3969/j.issn.2095-0411.2020.03.010]
点击复制

深度信念网络在管道故障诊断中的应用()
分享到：

常州大学学报(自然科学版)[ISSN:2095-0411/CN:32-1822/N]

卷:
第32卷
期数:
2020年03期
页码:
71-78
栏目:
安全工程
出版日期:
2020-05-28

文章信息/Info

Title:
Application Research of Deep Belief Network in Pipeline Fault Identification
文章编号:
2095-0411(2020)03-0071-08
作者:
王新颖;  张惠然;  黄旭安;  张瑞程;  赵 斌;  张 颖
(常州大学 环境与安全工程学院, 江苏 常州 213164)
Author(s):
WANG Xinying;  ZHANG Huiran;  HUANG Xu'an;  ZHANG Ruicheng;  ZHAO Bin;  ZHANG Ying
(School of Environmental & Safety Engineering, Changzhou University, Changzhou 213164, China)
关键词:
安全检测技术;  燃气管道;  特征提取;  深度信念网络;  故障分类;  无损检测
Keywords:
safety detection technology;  gas pipeline;  feature extraction;  deep belief network;  fault classification;  nondestructive testing
分类号:
X 937
DOI:
10.3969/j.issn.2095-0411.2020.03.010
文献标志码:
A
摘要:
为了减少管道故障诊断过程中人工提取与筛选特征存在的不稳定性影响,提出一种利用深度置信网络重构特征参数并建模的故障诊断方法。在实验室条件下,采集管道在正常及不同故障状态下的声发射信号,提取特征参数,利用深度置信网络重构特征参数并建立分类模型,再根据采集到的样本数据特点调整模型节点数等参数,优化模型后得出最终的诊断结果。研究表明:在同等条件下,采用深度置信网络重构特征参数后建立的分类模型具有更好的稳定性和更高的准确率。
Abstract:
In order to reduce the instability of manual extraction and screening features in pipeline fault diagnosis, a fault diagnosis method based on deep confidence network to reconstruct feature parameters and model is proposed. Under laboratory conditions, the acoustic emission signals of the pipeline under normal and different fault conditions are collected, the characteristic parameters are extracted, the characteristic parameters are reconstructed by the deep confidence network and the classification model is established, and the number of model nodes is adjusted according to the characteristics of the collected sample data, and the parameter optimization model is obtained after the final diagnosis. The studies have shown that: under the same conditions, using the classification model established after the reconstruction of the depth of belief networks characteristic parameters have better stability and higher accuracy.

参考文献/References:

[1]于洋,刘德俊,孙东旭.基于漏磁内检测与分级理念的管道完整性评价[J].中国安全科学学报,2017,27(1):169-174.
[2]许永勃. 输油管道负压波法泄漏检测技术研究[D].西安:西安石油大学,2018.
[3]NIESEN V, GOULD M. Detecting pipeline leaks[J]. Mechanical Engineering,2017,139(11):34-39.
[4]GONZÁLEZ O, VERDE C, TORRES L. Leak estimation method for complex pipelines with branch junctions[J]. Pressure Vessel Technol,2016,139(2):021701-1-021701-8.
[5]柴艳丽,朱岩,王建强.融合循环自相关函数的小波分析算法在微裂缝检测中的应用[J].测试技术学报,2019(2):116 -120.
[6]饶永超,才政,陈磊,等.伴管式天然气管道泄漏在线监测系统[J].常州大学学报(自然科学版),2017,29(4):73-79.
[7]裴峻峰,代云聪,孙旭,等.原油管式加热炉对流室炉管腐蚀程度的声发射检测[J].常州大学学报(自然科学版),2015,27(1):16-20.
[8]ELLEUCH M, TAGOUGUI N, KHERALLAH M. Optimization of DBN using regularization methods applied for recognizing arabic handwritten script[J]. Procedia Computer Science, 2017,108(6):2292-2297.
[9]YU L, ZHOU R, TANG L,et al. A DBN-based resampling SVM ensemble learning paradigm for credit classification with imbalanced data[J]. Applied Soft Computing, 2018, 69(8): 192-202.
[10]KRAUSE O, FISCHER A, IGEL C. Population-contrastive-divergence: does consistency help with RBM training?[J]. Pattern Recognition Letters, 2018,102(1):1-7.
[11]ZHAO R, YAN R Q, CHEN Z H,et al. Deep learning and its applications to machine health monitoring[J]. Mechanical Systems and Signal Processing,2019,15(1): 213-237.
[12]段锁林,顾川林.基于BP神经网络视频火灾火焰检测方法[J].常州大学学报(自然科学版),2017,29(2):65-70.
[13]肖启阳,李健,孙洁娣.基于EWT及互时频的天然气管道泄漏定位[J].仪器仪表学报,2016,37(12):2735-2742.
[14]汪洋,王俊刚.基于深度学习算法的铁路列车运行安全检测[J].中国安全科学学报,2018,28(s2):41-45.
[15]王振华. 基于深度学习的野外巡线系统图像目标检测研究[D].北京:中国地质大学(北京),2018.
[16]王新颖,江志伟,于永亮.多信息融合的城市燃气管道泄漏诊断技术研究[J].中国安全科学学报,2014,24(6):165-170.
[17]于蕊. 泄漏声发射信号特征提取与识别方法研究[D].昆明:昆明理工大学, 2016.

备注/Memo

备注/Memo:
收稿日期:2019-12-06。
基金项目:江苏省研究生科研与实践创新计划资助项目(KYCX19_1791)。
作者简介:王新颖(1976—),女,黑龙江海伦人,硕士,副教授。E-mail: wangxy@cczu.edu.cn
引用本文:王新颖,张惠然,黄旭安,等. 深度信念网络在管道故障诊断中的应用[J]. 常州大学学报(自然科学版),2020,32(3):71-78.
更新日期/Last Update: 2020-06-11