基于信息熵和深度置信网络的涡轮发动机在有限传感器下的故障诊断仿真研究

De-long FENG; Ming-qing XIAO; Ying-xi LIU; Hai-fang SONG; Zhao YANG; Ze-wen HU

doi:10.1631/FITEE.1601365

Your Location：

Home >

Browse articles >

基于信息熵和深度置信网络的涡轮发动机在有限传感器下的故障诊断仿真研究

常规文章 | Updated：2022-05-19

- 基于信息熵和深度置信网络的涡轮发动机在有限传感器下的故障诊断仿真研究
- Finite-sensor fault-diagnosis simulation study of gas turbine engine using information entropy and deep belief networks
- 信息与电子工程前沿（英文） 2016年17卷第12期页码：1287-1304
- Affiliations：
  
  1Aeronautics and Astronautics Engineering College, Air Force Engineering University, Xi'an 710038, China
  2Air Force Xi'an Flight Academy, Xi'an 710306, China
- Author bio：
  
  E-mail:fengdelong101@foxmail.com
- Funds：
- DOI：10.1631/FITEE.1601365
  中图分类号： TP391;V267.3
- 收稿：2015-07-05，
  
  录用：2016-10-9，
  
  纸质出版：2016-12
- Accepted：
Scan QR Code
基于信息熵和深度置信网络的涡轮发动机在有限传感器下的故障诊断仿真研究[J]. 信息与电子工程前沿（英文）, 2016,17(12):1287-1304.

De-long FENG, Ming-qing XIAO, Ying-xi LIU, et al. Finite-sensor fault-diagnosis simulation study of gas turbine engine using information entropy and deep belief networks[J]. Frontiers of Information Technology & Electronic Engineering, 2016, 17(12): 1287-1304.
基于信息熵和深度置信网络的涡轮发动机在有限传感器下的故障诊断仿真研究[J]. 信息与电子工程前沿（英文）, 2016,17(12):1287-1304. DOI： 10.1631/FITEE.1601365.

De-long FENG, Ming-qing XIAO, Ying-xi LIU, et al. Finite-sensor fault-diagnosis simulation study of gas turbine engine using information entropy and deep belief networks[J]. Frontiers of Information Technology & Electronic Engineering, 2016, 17(12): 1287-1304. DOI： 10.1631/FITEE.1601365.

摘要

精确故障诊断是预测与健康管理的一个重要部分。它能避免事故的发生，延长设备使用寿命，还能降低设备维修保养费用。本文研究涡轮发动机的故障诊断。由于发动机工作在高温、高压、高转速的严峻环境中，不能安装过多传感器，因此我们无法获得足够多的传感器数据，以至于采用现有算法不能进行精确的潜在故障诊断。本文针对复杂环境下有限传感器数据的发动机故障诊断问题，提出了一种基于信息熵的深度置信网络方法。首先介绍了几种信息熵，并基于单信号熵提出了联合复杂信息熵。其次，分析了深度置信网络的构成，提出了基于信息熵的深度置信网络方法。验证实验表明，与现有的机器学习算法比较，该方法的诊断精度大大提高。

Abstract

Precise fault diagnosis is an important part of prognostics and health management. It can avoid accidents

extend the service life of the machine

and also reduce maintenance costs. For gas turbine engine fault diagnosis

we cannot install too many sensors in the engine because the operating environment of the engine is harsh and the sensors will not work in high temperature

at high rotation speed

or under high pressure. Thus

there is not enough sensory data from the working engine to diagnose potential failures using existing approaches. In this paper

we consider the problem of engine fault diagnosis using finite sensory data under complicated circumstances

and propose deep belief networks based on information entropy

IE-DBNs

for engine fault diagnosis. We first introduce several information entropies and propose joint complexity entropy based on single signal entropy. Second

the deep belief networks (DBNs) is analyzed and a logistic regression layer is added to the output of the DBNs. Then

information entropy is used in fault diagnosis and as the input for the DBNs. Comparison between the proposed IE-DBNs method and state-of-the-art machine learning approaches shows that the IE-DBNs method achieves higher accuracy.

关键词

Keywords

references

V Aguiar , , , I Guedes . . Shannon entropy, Fisher information and uncertainty relations for log-periodic oscillators . . Phys. A , , 2015 . . 423 72 - - 79 . . DOI: 10.1016/j.physa.2014.12.031 http://doi.org/10.1016/j.physa.2014.12.031 . .

Y Bengio . . Learning Deep Architectures for AI . . 2009 . . Available from: http://www.iro.umontreal.ca/~bengioy/papers/ftml.pdf http://www.iro.umontreal.ca/~bengioy/papers/ftml.pdf . .

Y Bengio . . Practical recommendations for gradient-based training of deep architectures . . LNCS , , 2012 . . 7700 437 - - 478 . . DOI: 10.1007/978-3-642-35289-8_26 http://doi.org/10.1007/978-3-642-35289-8_26 . .

Y Bengio , , , A Courville , , , P Vincent . . Representation learning: a review and new perspectives . . IEEE Trans. Patt. Anal. Mach. Intell. , , 2013 . . 35 ( ( 8 ): ): 1798 - - 1828 . . DOI: 10.1109/TPAMI.2013.50 http://doi.org/10.1109/TPAMI.2013.50 . .

L Bottou . . Stochastic gradient descent tricks . . LNCS , , 2012 . . 7700 421 - - 436 . . DOI: 10.1007/978-3-642-35289-8_25 http://doi.org/10.1007/978-3-642-35289-8_25 . .

YS Chen , , , X Zhao , , , XP Jia . . Spectral-spatial classification of hyperspectral data based on deep belief network . . IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens. , , 2015 . . 8 ( ( 6 ): ): 2381 - - 2392 . . DOI: 10.1109/JSTARS.2015.2388577 http://doi.org/10.1109/JSTARS.2015.2388577 . .

HX Cui , , , LB Zhang , , , RY Kang , , , 等 . . Research on fault diagnosis for reciprocating compressor valve using information entropy and SVM method . . J. Loss Prevent. Process Ind. , , 2009 . . 22 ( ( 6 ): ): 864 - - 867 . . DOI: 10.1016/j.jlp.2009.08.012 http://doi.org/10.1016/j.jlp.2009.08.012 . .

JH Dai , , , HW Tian . . Entropy measures and granularity measures for set-valued information systems . . Inform. Sci. , , 2013 . . 240 72 - - 82 . . DOI: 10.1016/j.ins.2013.03.045 http://doi.org/10.1016/j.ins.2013.03.045 . .

A Ferrer . . Multivariate statistical process control based on principal component analysis (MSPC-PCA): some reflections and a case study in an autobody assembly process . . Qual. Eng. , , 2007 . . 19 ( ( 4 ): ): 311 - - 325 . . DOI: 10.1080/08982110701621304 http://doi.org/10.1080/08982110701621304 . .

JB Geng , , , SH Huang , , , JS Jin , , , 等 . . A method of rotating machinery fault diagnosis based on the close degree of information entropy . . Int. J. Plant Eng. Manag. , , 2006 . . 11 ( ( 3 ): ): 137 - - 144 . . DOI: 10.13434/j.ckni.1007-4546.2006.03.002 http://doi.org/10.13434/j.ckni.1007-4546.2006.03.002 . .

GE Hinton . . A Practical Guide to Training Restricted Boltzmann Machines . . 2010 . . Available from: https://www.cs.toronto.edu/~hinton/absps/guideTR.pdf https://www.cs.toronto.edu/~hinton/absps/guideTR.pdf . .

GE Hinton , , , S Osindero , , , YW Teh . . A fast learning algorithm for deep belief nets . . Neur. Comput. , , 2006 . . 18 ( ( 7 ): ): 1527 - - 1554 . . DOI: 10.1162/neco.2006.18.7.1527 http://doi.org/10.1162/neco.2006.18.7.1527 . .

GE Hinton , , , L Deng , , , D Yu , , , 等 . . Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups . . IEEE Signal Process. Mag. , , 2012 . . 29 ( ( 6 ): ): 82 - - 97 . . DOI: 10.1109/MSP.2012.2205597 http://doi.org/10.1109/MSP.2012.2205597 . .

CX Jin , , , FC Li , , , Y Li . . A generalized fuzzy ID3 algorithm using generalized information entropy . . Knowl.-Based Syst. , , 2014 . . 64 13 - - 21 . . DOI: 10.1016/j.knosys.2014.03.014 http://doi.org/10.1016/j.knosys.2014.03.014 . .

VP Koverda , , , VN Skokov . . Maximum entropy in a nonlinear system with a 1/f power spectrum . . Phys. A , , 2012 . . 391 ( ( 1-2 ): ): 21 - - 28 . . DOI: 10.1016/j.physa.2011.07.015 http://doi.org/10.1016/j.physa.2011.07.015 . .

H Larochelle , , , Y Bengio , , , J Louradour , , , 等 . . Exploring strategies for training deep neural networks . . J. Mach. Learn. Res. , , 2009 . . 10 ( ( 10 ): ): 1 - - 40 . . . .

FC Li , , , Z Zhang , , , CX Jin . . Feature selection with partition differentiation entropy for large-scale data sets . . Inform. Sci. , , 2016 . . 329 690 - - 700 . . DOI: 10.1016/j.ins.2015.10.002 http://doi.org/10.1016/j.ins.2015.10.002 . .

J Li . . Recognition of the optical image based on the wavelet space feature spectrum entropy . . Optik-Int. J. Light Electron Opt. , , 2015 . . 126 ( ( 23 ): ): 3931 - - 3935 . . DOI: 10.1016/j.ijleo.2015.07.166 http://doi.org/10.1016/j.ijleo.2015.07.166 . .

ZG Liu , , , QL Hu , , , Y Cui , , , 等 . . A new detection approach of transient disturbances combining wavelet packet and Tsallis entropy . . Neurocomputing , , 2014 . . 142 393 - - 407 . . DOI: 10.1016/j.neucom.2014.04.020 http://doi.org/10.1016/j.neucom.2014.04.020 . .

J Martens , , , I Sutskever . . Training deep and recurrent networks with Hessian-free optimization . . LCNS , , 2012 . . 7700 479 - - 535 . . DOI: 10.1007/978-3-642-35289-8_27 http://doi.org/10.1007/978-3-642-35289-8_27 . .

R Memisevic , , , GE Hinton . . Learning to represent spatial transformations with factored higher-order Boltzmann machine . . Neur. Comput. , , 2010 . . 22 ( ( 6 ): ): 1473 - - 1492 . . DOI: 10.1162/neco.2010.01-09-953 http://doi.org/10.1162/neco.2010.01-09-953 . .

AR Mohamed , , , GE Dahl , , , GE Hinton . . Acoustic modeling using deep belief networks . . IEEE Trans. Audio Speech Lang. Process. , , 2012 . . 20 ( ( 1 ): ): 14 - - 22 . . DOI: 10.1109/TASL.2011.2109382 http://doi.org/10.1109/TASL.2011.2109382 . .

JM Nichols , , , M Seaver , , , ST Trickey . . A method for detecting damage-induced nonlinearities in structures using information theory . . J. Sound Vibr. , , 2006 . . 297 ( ( 1-2 ): ): 1 - - 16 . . DOI: 10.1016/j.jsv.2006.01.025 http://doi.org/10.1016/j.jsv.2006.01.025 . .

J Niu , , , XZ Bu , , , Z Li , , , 等 . . An improved bilinear deep belief network algorithm for image classification . . 2014 . . 10th Int. Conf. on Computational Intelligence and Security . . 189 - - 192 . . DOI: 10.1109/CIS.2014.38 http://doi.org/10.1109/CIS.2014.38 . .

V Nourani , , , MT Alami , , , FD Vousoughi . . Wavelet-entropy data pre-processing approach for ANN-based groundwater level modeling . . J. Hydrol. , , 2015 . . 524 255 - - 269 . . DOI: 10.1016/j.jhydrol.2015.02.048 http://doi.org/10.1016/j.jhydrol.2015.02.048 . .

BT Ong , , , K Sugiura , , , K Zettsu . . Dynamic pre-training of deep recurrent neural networks for predicting environmental monitoring data . . 2014 . . IEEE Int. Conf. on Big Data . . 760 - - 765 . . DOI: 10.1109/BigData.2014.7004302 http://doi.org/10.1109/BigData.2014.7004302 . .

YB Pan , , , BL Yang , , , XW Zhou . . Feedstock molecular reconstruction for secondary reactions of fluid catalytic cracking gasoline by maximum information entropy method . . Chem. Eng. J. , , 2015 . . 281 945 - - 952 . . DOI: 10.1016/j.cej.2015.07.037 http://doi.org/10.1016/j.cej.2015.07.037 . .

AE Rastegin . . On generalized entropies and information-theoretic Bell inequalities under decoherence . . Ann. Phys. , , 2015 . . 355 241 - - 257 . . DOI: 10.1016/j.aop.2015.02.015 http://doi.org/10.1016/j.aop.2015.02.015 . .

PH Rodríguez , , , JB Alonso , , , MA Ferrer , , , 等 . . Application of the Teager-Kaiser energy operator in bearing fault diagnosis . . ISA Trans. , , 2013 . . 52 ( ( 2 ): ): 278 - - 284 . . DOI: 10.1016/j.isatra.2012.12.006 http://doi.org/10.1016/j.isatra.2012.12.006 . .

M Saimurugan , , , KI Ramachandran , , , V Sugumaran , , , 等 . . Multi component fault diagnosis of rotational mechanical system based on decision tree and support vector machine . . Expert Syst. Appl. , , 2011 . . 38 ( ( 4 ): ): 3819 - - 3826 . . DOI: 10.1016/j.eswa.2010.09.042 http://doi.org/10.1016/j.eswa.2010.09.042 . .

TN Sainath , , , B Kingsbury , , , H Soltau , , , 等 . . Optimization techniques to improve training speed of deep neural networks for large speech tasks . . IEEE Trans. Audio Speech Lang. Process. , , 2013 . . 21 ( ( 11 ): ): 2267 - - 2276 . . DOI: 10.1109/TASL.2013.2284378 http://doi.org/10.1109/TASL.2013.2284378 . .

TN Sainath , , , B Kingsbury , , , G Saon , , , 等 . . Deep convolutional neural networks for large-scale speech tasks . . Neur. Networks , , 2015 . . 64 39 - - 48 . . DOI: 10.1016/j.neunet.2014.08.005 http://doi.org/10.1016/j.neunet.2014.08.005 . .

RF Sekerka . . Entropy and information theory. In: Thermal Physics: Thermodynamics and Statistical Mechanics for Scientists and Engineers . . Elsevier , , 2015 . . 247 - - 256 . . DOI: 10.1016/B978-0-12-803304-3.00015-6 http://doi.org/10.1016/B978-0-12-803304-3.00015-6 . .

P Sermanet , , , S Chintala , , , Y LeCun . . Convolutional neural networks applied to house numbers digit classification . . 2012 . . 21st Int. Conf. on Pattern Recognition . . 3288 - - 3291 . . . .

XD Song , , , GH Sun , , , SH Dong . . Shannon information entropy for an infinite circular well . . Phys. Lett. A , , 2015 . . 379 ( ( 22-23 ): ): 1402 - - 1408 . . DOI: 10.1016/j.physleta.2015.03.020 http://doi.org/10.1016/j.physleta.2015.03.020 . .

HT Su , , , GJY You . . Developing an entropy-based model of spatial information estimation and its application in the design of precipitation gauge networks . . J. Hydrol. , , 2014 . . 519 ( ( D ): ): 3316 - - 3327 . . DOI: 10.1016/j.jhydrol.2014.10.022 http://doi.org/10.1016/j.jhydrol.2014.10.022 . .

S Susan , , , M Hanmandlu . . A non-extensive entropy feature and its application to texture classification . . Neurocomputing , , 2013 . . 120 214 - - 225 . . DOI: 10.1016/j.neucom.2012.08.059 http://doi.org/10.1016/j.neucom.2012.08.059 . .

I Sutskever , , , GE Hinton , , , GW Taylor . . The recurrent temporal restricted Boltzmann machine . . 2008 . . Proc. 22nd Annual Conf. on Neural Information Processing Systems . . 1601 - - 1608 . . . .

P Tamilselvan , , , PF Wang . . Failure diagnosis using deep belief learning based health state classification . . Reliab. Eng. Syst. Safety , , 2013 . . 115 124 - - 135 . . DOI: 10.1016/j.ress.2013.02.022 http://doi.org/10.1016/j.ress.2013.02.022 . .

P Tamilselvan , , , PF Wang , , , BD Youn . . Multi-sensor health diagnosis using deep belief network based state classification . . ASME Int. Design Engineering Technical Conf. & Computers and Information in Engineering Conf. , , 2011 . . 749 - - 758 . . DOI: 10.1115/DETC2011-48352 http://doi.org/10.1115/DETC2011-48352 . .

VT Tran , , , F AlThobiani , , , A Ball . . An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks . . Expert Syst. Appl. , , 2014 . . 41 ( ( 9 ): ): 4113 - - 4122 . . DOI: 10.1016/j.eswa.2013.12.026 http://doi.org/10.1016/j.eswa.2013.12.026 . .

Y Xie , , , T Zhang . . A fault diagnosis approach using SVM with data dimension reduction by PCA and LDA method . . 2005 . . Chinese Automation Congress . . 869 - - 874 . . DOI: 10.1109/CAC.2015.7382620 http://doi.org/10.1109/CAC.2015.7382620 . .

WL Zhang , , , RJ Li , , , HT Deng , , , 等 . . Deep convolutional neural networks for multi-modality isointense infant brain image segmentation . . NeuroImage , , 2015 . . 108 214 - - 224 . . DOI: 10.1016/j.neuroimage.2014.12.061 http://doi.org/10.1016/j.neuroimage.2014.12.061 . .

XZ Zhao , , , BY Ye . . Singular value decomposition packet and its application to extraction of weak fault feature . . Mech. Syst. Signal Process. , , 2016 . . 70-71 73 - - 86 . . DOI: 10.1016/j.ymssp.2015.08.033 http://doi.org/10.1016/j.ymssp.2015.08.033 . .

SS Zhou , , , QC Chen , , , XL Wang . . Deep adaptive networks for visual data classification . . J. Multim. , , 2014 . . 9 ( ( 10 ): ): 1142 - - 1151 . . . .

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

暂无数据