Cavitation State Recognition of Centrifugal Pump Based on Deep Learning

doi:10.7652/xjtuxb201711023

您当前的位置：

首页 >

文章列表页 >

Cavitation State Recognition of Centrifugal Pump Based on Deep Learning

更新时间：2025-07-09

- Cavitation State Recognition of Centrifugal Pump Based on Deep Learning
- Vol. 51, Issue 11, Pages: 165-171(2017)
- 作者机构：
  
  海军工程大学动力工程学院,武汉,430033
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb201711023
  CLC： U664.33
- Online First：10 November 2017，
  
  Published：2017
- 稿件说明：
移动端阅览
Cavitation State Recognition of Centrifugal Pump Based on Deep Learning[J]. 2017, 51(11): 165-171.
DOI：

Cavitation State Recognition of Centrifugal Pump Based on Deep Learning[J]. 2017, 51(11): 165-171. DOI： 10.7652/xjtuxb201711023.

摘要

空化状态识别是离心泵状态监测的难点之一

为了提高空化状态识别的效果

提出了一种基于深度学习的离心泵空化状态识别方法。首先

采集了在3种工况下泵壳的振动信号

分别构建了振动信号的改进倍频带特征矩阵和时频特征矩阵; 然后

基于自动编码器构建了深度学习网络

通过无监督训练自动学习输入数据的特征

利用监督训练对网络的参数进行了调整; 最后

运用深度学习网络

对离心泵的4类空化状态进行了分类识别。研究表明

无论是基于改进倍频带特征矩阵还是基于时频特征矩阵

深度学习网络对4类空化状态都有很好的识别效果

尤其是对于弱空化状态

深度学习网络比BP神经网络更有效。

Abstract

Cavitation state recognition is one of the difficulties in condition monitoring of centrifugal pump. A method for cavitation state recognition of centrifugal pump based on deep learning is developed. The vibration signals on pump casing under three conditions are collected

and the band matrixes of modified octave as well as matrixes of time-frequency features of vibration signals are established. The deep learning network is constructed based on auto-encoder

the features of input data are learned automatically by unsupervised training

and the parameters of the network are adjusted by supervised training. Four cavitation states of centrifugal pump are recognized by deep learning network. It demonstrates that based on band matrixes of modified octave or matrixes of time-frequency features

the deep learning network is effective for recognizing four cavitation states and outperforms BP neural network

especially for slight cavitation state.

关键词

Keywords

references

JOHANN F G. Centrifugal pumps [M]. Berlin, Germany: Springer, 2014: 287-292.

KIM K H, J P FRANC, CHAHINE G, et al. Advanced experimental and numerical techniques for cavitation erosion prediction [M]. Berlin, Germany: Springer, 2014: 3-6.

AL-HASHMI S, GU F, LI Y, et al. Cavitation detection of a centrifugal pump using instantaneous angular speed [C]∥Proceedings of ESDA04 7th Biennial Conference on Engineering Systems Design and Analysis. New York, USA: ASME, 2004: 185-190.

CHINI S F, RAHIMZADEH H, BAHRAMI M. Cavitation detection of a centrifugal pump using noise spectrum [C]∥ASME 2005 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. New York, USA: ASME, 2005: 13-19.

ESCALER X, FARHAT M, AUSONI P, et al. Cavitation monitoring of hydroturbines: tests in a Francis turbine model [C]∥6th International Symposium on Cavitation. Wageningen, Netherlands: CAV, 2006: 1-5.

STOPA M M, CARDOSO F B J, MARTINEZ C B. Detection of incipient cavitation phenomenon in a centrifugal pump [C]∥IEEE Industry Applications Society Annual Meeting. Piscataway, NJ, USA: IEEE, 2012: 1-6.

MI Y, ISHII M, TSOUKALAS L H. Vertical two-phase flow identification using advanced instrumentation and neural networks [J]. Nuclear Engineering and Design, 1998, 184(2): 409-420.

MI Y, ISHII M, TSOUKALAS L H. Flow regime identification methodology with neural networks and two-phase flow models [J]. Nuclear Engineering and Design, 2001, 204(1): 87-100.

苏永生, 王永生, 段向阳. 基于多传感器数据融合的喷水推进泵空化分类识别 [J]. 振动与冲击, 2012, 31(18): 93-96.

SU Yongsheng, WANG Yongsheng, DUAN Xiangyang. Classification of cavitation in a waterjet pump based on multi-sensor data fusion [J]. Journal of Vibration and Shock, 2012, 31(18): 93-96.

DE GIORGI M G, BELLO D, FICARELLA A. An artificial neural network approach to investigate cavitating flow regime at different temperatures [J]. Measurement, 2014, 47: 971-981.

DE GIORGI M G, FICARELLA A, LAY-EKUAKILLE A. Cavitation regime detection by LS-SVM and ANN with wavelet decomposition based on pressure sensor signals [J]. IEEE Sensors Journal, 2015, 15(10): 5701-5708.

HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks [J]. Science, 2006, 313(5786): 504-507.

HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets [J]. Neural computation, 2006, 18(7): 1527-1554.

CIREGAN D, MEIER U, SCHMIDHUBER J. Multi-column deep neural networks for image classification [C]∥IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2012: 3642-3649.

HINTON G, DENG L, YU D, et al. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups [J]. IEEE Signal Processing Magazine, 2012, 29(6): 82-97.

KRIZHEVSKY A, HINTON G. Learning multiple layers of features from tiny images [D]. Toronto: University of Toronto, 2009.[17] ZHOU H, LOPEZ-ARTEAGA I, NIJMEIJER H. Broadband planar nearfield acoustic holography based on one-third-octave band analysis [J]. Applied Acoustics, 2016, 109: 18-26.

苏永生, 王永生, 段向阳. 离心泵空化试验研究 [J]. 农业机械学报, 2010, 41(3): 77-80.

SU Yongsheng, WANG Yongsheng, DUAN Xiangyang. Cavitation experimental research on centrifugal pump [J]. Transactions of the Chinese Society for Agricultural Machinery, 2010, 41(3): 77-80.

BENGIO Y, LAMBLIN P, POPOVICI D, et al.Greedy layerwise training of deep networks [EB/OL]. [2017-02-02]. http:∥papers.nips.cc/paper/3048-greedylayer-wise-training-of-deep-networks.pdf.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Improved Deep Learning Algorithm for Reproduction of Airfoil Flow Field

Reduced-Order Prediction Method for the Dynamic Thermal Response of Phase-Change Cooling Heat Exchangers

Intelligent Quantitative Non-Destructive Evaluation Method for Delamination of Carbon Fiber Composite Tube with Mirror-Reflection Infrared Thermography

Dynamic Flow Field Prediction Method for Compressed Air Storage Tanks Using Dynamic Mode Decomposition and Long Short-Term Memory Network

Model Predictive Control-Oriented Deep Koopman Global Linear Modeling Method for Wind Turbines

Related Author

杨从新 1

凌祖光 1

王岩 2

钱晨 1

赵斌 1

周楠楠 1

HAN Zeran

TANG Zicheng

Related Institution

兰州理工大学能源与动力工程学院

中国核动力研究设计院

School of Energy and Power Engineering，Xi’an Jiaotong University

Wuhan Second Ship Design and Research Institute

Shaanxi Engineering Research Center of Nondestructive Testing and Structural Integrity Evaluation，Xi’an Jiaotong University

⁰