[1]仲志丹,樊浩杰,李鹏辉.基于稀疏自编码神经网络的抽油机井故障诊断[J].西安科技大学学报,2018,(04):669-675.[doi:10.13800/j.cnki.xakjdxxb.2018.0422 ]
 ZHONG Zhi-dan,FAN Hao-jie,LI Peng-hui.Fault diagnosis of pumping well based on sparse auto-encoder neural network[J].Journal of Xi'an University of Science and Technology,2018,(04):669-675.[doi:10.13800/j.cnki.xakjdxxb.2018.0422 ]
点击复制

基于稀疏自编码神经网络的抽油机井故障诊断(/HTML)
分享到:

西安科技大学学报[ISSN:1672-9315/CN:61-1434/N]

卷:
期数:
2018年04期
页码:
669-675
栏目:
出版日期:
2018-07-15

文章信息/Info

Title:
Fault diagnosis of pumping well based on sparse auto-encoder neural network
文章编号:
1672-9315(2018)04-0669-07
作者:
仲志丹1樊浩杰1李鹏辉2
1.河南科技大学 机电工程学院,河南 洛阳 471003; 2.洛阳乾禾仪器有限公司,河南 洛阳 471000
Author(s):
ZHONG Zhi-dan1FAN Hao-jie1LI Peng-hui2
(1.School of Mechanical and Electrical Engineering,Henan University of Science and Technology,Luoyang 471003,China; 2.Luoyang Qianhe Instrument Company,Luoyang 471000,China)
关键词:
稀疏自编码器 示功图识别 故障诊断 深度学习 无监督学习
Keywords:
sparse auto-encoder indicator diagram recognition fault diagnosis deep learning unsupervised learning
分类号:
TE 938; TP 183; TH 165.3
DOI:
10.13800/j.cnki.xakjdxxb.2018.0422
文献标志码:
A
摘要:
针对传统示功图识别方法对抽油机井进行故障诊断存在人工选取示功图几何特征,识别准确度低等问题,提出一种基于稀疏自编码神经网络的示功图智能识别模型。采用无监督学习方式的稀疏自编码器构建特征学习网络自动提取无标签示功图训练集图像特征,然后采用有标签示功图训练集对softmax分类器进行有监督训练,最后通过稀疏自编码神经网络对学习到的有标签示功图测试集特征进行分类并给出故障诊断结果。结果表明,将稀疏自编码神经网络应用于示功图识别,测试准确度能够达到99.44%,优于其它分类模型。稀疏自编码神经网络直接从像素层面提取所需要的特征,不需要人为选定设计特征,为提高示功图识别准确度提供了帮助,进而解决了抽油机井故障难以准确诊断的难题。
Abstract:
There are two main problems of thepumping well fault diagnosis by the traditional indicator diagram recognition methods:manual selection of indicator diagram's geometric characteristics and low recognition accuracy.An intelligent recognition model of indicator diagram based on sparse auto-encoder neural network is proposed.The sparse auto-encoder of unsupervised learning method is used to construct feature learning network to automatically extract the image features of the unlabeled indicator diagram training set.Then the softmax classifier is supervised training by the labeled indicator diagram training set.Finally,the learned features of the labeled indicator diagram test set are classified and the fault diagnosis results are given by sparse auto-encoder neural network.The experimental results show that when sparse auto-encoder neural network is applied to indicator diagram recognition,its accuracy reaches 99.44%,which is better than that of other classification models.The sparse auto-encoder neural network extracts the required features directly from the pixel level,and doesn't require the artificial features selection and design,which provides help to improve the recognition accuracy of indicator diagram and solves the problem of difficult to accurately diagnose the fault of pumping well.

参考文献/References:

[1] 钟功祥,邹明铭.往复泵故障示功图灰度矩阵法特征量研究[J].机械科学与技术,2016,35(2):279-284. ZHONG Gong-xiang,ZOU Ming-ming.Exploring failure characteristic of indicator diagram of reciprocating pump based on gray matrix[J].Mechanical Science and Technology for Aerospace Engineering,2016,35(2):279-284. [2] 赵可新,马晓辉,马彦芬,等.人工神经网络在油井故障诊断中的优化[J].煤炭技术,2011,30(5):196-198. ZHAO Ke-xin,MA Xiao-hui,MA Yan-fen,et al.Optimization of ANN in fault diagnosis of oil wells[J].Coal Technology,2011,30(5):196-198. [3] 郑 劼,邵艳婷.抽油机检测系统的设计与应用分析[J].工矿自动化,2013,39(7):96-98. ZHENG Jie,SHAO Yan-ting.Design and application analysis of detection system of pumping unit[J].Industry and Mine Automation,2013,39(7):96-98. [4] 刘 卓,罗明良,刘 飞,等.基于BP神经网络和不变矩特征的泵功图诊断方法研究[J].制造业自动化,2013,35(10):7-9. LIU Zhuo,LUO Ming-liang,LIU Fei,et al.Method of fault diagnosis for pump dynamograph based on BP neural network and invariant moment features[J].Manufacturing Automation,2013,35(10):7-9. [5] 曲文尧,王春华.人工神经网络法用于抽油机井故障诊断[J].油气田地面工程,2013,32(8):14-15. QU Wen-yao,WANG Chun-hua.Application of artificial neural network to fault diagnosis of pumping well[J].Oil-Gasfield Surface Engineering,2013,32(8):14-15. [6]李春生,苏晓伟,魏 军,等.基于支持向量机的抽油机井功图识别研究[J].计算机技术与发展,2014,24(8):215-218. LI Chun-sheng,SU Xiao-wei,WEI Jun,et al.Research on diagrams identification of pumping unit based on support vector machine[J].Computer Technology and Development,2014,24(8):215-218. [7] 魏 军.基于支持向量机的抽油机井故障诊断模型研究[J].计算机与数字工程,2014,42(11):2094-2098. WEI Jun.Pumping unit well fault diagnosis model based on support vector machine[J].Computer and Digital Engineering,2014,42(11):2094-2098. [8] Hinton G E,Salakhutdinov R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507. [9] Cheriyadat A M.Unsupervised feature learning for aerial scene classification[J].IEEE Transactions on Geoscience & Remote Sensing,2013,52(1):439-451. [10]HU Wei-peng,HU Hai-feng.Heterogeneous face recognition based on modality-independent Kernel Fisher discriminant analysis joint sparse auto-encoder[J].Electronics Letters,2016,52(21):1753-1755. [11]XU Jun,XIANG Lei,LIU Qin-shan,et al.Stacked sparse autoencoder(SSAE)for nuclei detection on breast cancer histopathology images[J].IEEE Transactions on Medical Imaging,2016,35(1):119-130. [12]Wright J,Ma Y,Mairal J,et al.Sparse representation for computer vision and pattern recognition[J].Proceedings of the IEEE,2010,98(6):1031-1044. [13]Hinton G,Deng L,Yu D,et al.Deep neural networks for acoustic modeling in speech recognition:the shared views of four research group[J].IEEE Signal Processing Magazine,2012,29(6):82-97. [14]王雅思,姚鸿勋,孙晓帅,等.深度学习中的自编码器的表达能力研究[J].计算机科学,2015,42(9):56-60. WANG Ya-si,YAO Hong-xun,SUN Xiao-shuai,et al.Representation ability research of auto-encoders in deep learning[J].Computer Science,2015,42(9):56-60. [15]张绍辉.基于多路稀疏自编码的轴承状态动态监测[J].振动与冲击,2016,35(19):125-131. ZHANG Shao-hui.Bearing condition dynamic monitoring based on multi-way sparse autocoder[J].Journal of Vibration and Shock,2016,35(19):125-131. [16]Shin H C,Orton M R,Collins D J,et al.Stacked autoencoders for unsupervised feature learning and multiple organ detection in a pilot study using 4d patient data[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(8):1930-1943. [17]Olshausen B A,Field D J.Emergence of simple-cell receptive field properties by learning a sparse code for natural images[J].Nature,1996,381(6583):607-609. [18]王知音,禹 龙,田生伟,等.基于栈式自编码的水体提取方法[J].计算机应用,2015,35(9):2706-2709. WANG Zhi-yin,YU Long,TIAN Sheng-wei,et al.Water body extraction method based on stacked autoencoder[J].Journal of Computer Applications,2015,35(9):2706-2709. [19]Yoon H,Park C S,Kim J S,et al.Algorithm learning based neural network integrating feature selection and classification[J].Expert Systems with Applications,2013,40(1):231-241. [20]王 勇,赵俭辉,章登义,等.基于稀疏自编码深度神经网络的林火图像分类[J].计算机工程与应用,2014,50(24):173-177. WANG Yong,ZHAO Jian-hui,ZHANG Deng-yi,et al.Forest fire image classification based on deep neural network of sparse autoencoder[J].Computer Engineering and Applications,2014,50(24):173-177.

备注/Memo

备注/Memo:
收稿日期:2018-03-10 责任编辑:刘 洁
基金项目:河南省高等学校重点科研项目(15A460023); 国家自然科学基金(50906022)
通信作者:樊浩杰(1994-),男,河南周口人,硕士研究生,E-mail:634364097@qq.com
更新日期/Last Update: 2018-08-29