Skip to main content
SpringerLink
Log in

An improvement growing neural gas method for online anomaly detection of aerospace payloads

  • Methodologies and Application
  • Published:
Soft Computing Aims and scope Submit manuscript

Abstract

The unfluctuating running of on-orbit spacecraft equipment has a decisive impact on the smooth implementation of space exploration mission. However, due to the adverse work conditions and complex running states, it is really a challenge for the online monitoring of aerospace equipment. In this paper, an improved growing neural gas method based on incremental learning is proposed, which is dedicated to solving the problem of online anomaly detection. The learning rate of the proposed method is adaptively adjusted according to the process of model training, ensuring the weights update quickly at the beginning of model construction and converge steady at the end of model training. The optimized insertion mechanisms of neurons ensure that the necessary new neurons are inserted at the right time and location dynamically, while the innovative deletion mechanisms of neurons ensure that the worthless neurons be deleted timely and at the same time guarantee the representation ability of model. The comparison results with the conventional methods on public datasets show that the proposed method achieves the better performance obviously, both in the aspects of detection accuracy and computational efficiency, respectively. At last, as a case study, the proposed method is used for online anomaly detection of a real aerospace device, i.e., a gamma ray detector, and the final F1 score of anomaly detection is as high as 98.78%. The results show that the proposed method can be applied to online detection of aerospace equipment health conditions effectively.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Abbreviations

A :

Set of all neurons

a :

Threshold for the insertion of neurons

a m :

Maximum of edge’s age

C :

The set of edges connecting neurons

c n :

Winning times of the nth neuron

d p :

Distance from the valid set to the model constructed by the parameter set p

e s :

Cumulative error of neuron s

f :

F1 score

N d :

Number of samples in data set

N m :

Limitations on the number of nodes

N w :

Threshold for the deletion of isolated neurons

n(s):

The set of neurons that connect to the neuron s

p :

Precision

p s :

Parameter set

p s,0 :

Initial parameter set

r :

Recall

s p :

Score of the current parameter

s x :

Anomaly score

t d :

Time taken to process all data

v 1 :

Average velocity of model establishment, dot/s

v 2 :

Average velocity of anomaly detection, dot/s

w n :

Weight of the winning neuron n

x :

The current sample

ε 1 :

Learning rate of winning neuron

ε 2 :

Learning rate of neuron in the neighborhood of winning neuron

η 0 :

Initial learning rate

λ :

Step size of inserting neurons

μ :

Attenuation coefficient of cumulative error

CHL:

Competitive Hebbian learning

CNN:

Convolutional neural network

DNN:

Deep neural network

GAN:

Generative adversarial networks

GNG:

Growing neural gas

ICA:

Independent component analysis

LSTM:

Long short-term memory

MLP:

Multi-layer perception

NG:

Neural gas

SAA:

South atlantic anomaly

SVM:

Support vector machine

FPR:

False positive rate

TPR:

True positive rate

References

  • Anaissi A, Khoa NLD, Rakotoarivelo T et al (2018) Adaptive online one-class support vector machines with applications in structural health monitoring. ACM Trans Intell Syst Technol 9(6):1–20

    Google Scholar 

  • Angiulli F, Pizzuti C (2002) Fast outlier detection in high dimensional spaces. In: Principles of data mining and knowledge discovery, 6th European conference, PKDD 2002, Helsinki, Finland, 19–23 Aug 2002. Proceedings. Springer

  • Breunig MM, Kriegel HP, Ng RT et al (2000) LOF: identifying density-based local outliers. ACM Sigmod Rec 29(2):93–104

    Google Scholar 

  • Cao Z, Zhu Y, Sun Z et al (2018) Improving prediction accuracy in LSTM network model for aircraft testing flight data. In: 2018 IEEE international conference on smart cloud (SmartCloud). IEEE, pp 7–12

  • Celik M, Dadasercelik F, Dokuz AS (2011) Anomaly detection in temperature data using DBSCAN algorithm. In: International symposium on innovations in intelligent systems and applications. IEEE

  • Chandola V, Banerjee A, Kumar V (2009) Anomaly detection: a survey. ACM Comput Surv 41(3):15

    Google Scholar 

  • Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2:1–27

    Google Scholar 

  • Chen Z, Yeo CK, Lee BS et al (2018) Evolutionary multi-objective optimization based ensemble autoencoders for image outlier detection. Neurocomputing 309:192–200

    Google Scholar 

  • Chu F, Zaniolo C (2004) Fast and light boosting for adaptive mining of data streams. Lect Notes Comput Sci 3056:282–292

    Google Scholar 

  • Ding S, Wang G (2017) Research on intrusion detection technology based on deep learning. In: 2017 3rd IEEE international conference on computer and communications (ICCC). IEEE, pp 1474–1478

  • Dua D, Graff C (2019) UCI machine learning repository. University of California, School of Information and Computer Science, Irvine

    Google Scholar 

  • FrezzaBuet H (2008) Following non-stationary distributions by controlling the vector quantization accuracy of a growing neural gas network. Elsevier, Amsterdam

    Google Scholar 

  • Fritzke B (1994) A growing neural gas network learns topologies. In: International conference on neural information processing systems. MIT Press

  • Fritzke B (1997) A self-organizing network that can follow non-stationary distributions. In: International conference on artificial neural networks. Springer, Berlin, pp 613–618

  • Fu X, Luo H, Zhong S et al (2019) Aircraft engine fault detection based on grouped convolutional denoising autoencoders. Chin J Aeronaut 32(2):296–307

    Google Scholar 

  • Furao S, Hasegawa O (2006) An incremental network for on-line unsupervised classification and topology learning. Neural Netw 19(1):90–106

    MATH  Google Scholar 

  • Furao S, Ogura T, Hasegawa O (2007) An enhanced self-organizing incremental neural network for online unsupervised learning. Neural Netw 20(8):893–903

    MATH  Google Scholar 

  • Gokcesu K, Neyshabouri MM, Gokcesu H et al (2019) Sequential outlier detection based on incremental decision trees. IEEE Trans Signal Process 67(4):993–1005

    MathSciNet  MATH  Google Scholar 

  • Goldstein M (2015a) Unsupervised anomaly detection benchmark, V1 edn. Harvard Dataverse (aloi-unsupervised-ad.tab)

  • Goldstein M (2015b) Unsupervised anomaly detection benchmark, V1 edn. Harvard Dataverse (shuttle-unsupervised-ad.tab)

  • Goldstein M (2015c) Unsupervised anomaly detection benchmark, V1 edn. Harvard Dataverse (kdd99-unsupervised-ad.tab)

  • Grossberg S (1988) The ART of adaptive pattern recognition by a self-organizing neural network. Computer 21:77–88

    Google Scholar 

  • Hebb DO (1949) The organization of behavior, vol 65. Wiley, New York

  • Kohonen T (1995) Self organizing maps. Ser Inf Sci 30(4):266–270

    MathSciNet  Google Scholar 

  • Li P, Niggemann O (2017) Improving clustering based anomaly detection with concave hull: an application in fault diagnosis of wind turbines. In: IEEE international conference on industrial informatics. IEEE

  • Li KL, Huang HK, Tian SF et al (2003) Improving one-class SVM for anomaly detection. In: International conference on machine learning and cybernetics. IEEE

  • Lu S, Wei X, Li Y, Wang L (2018) Detecting anomaly in big data system logs using convolutional neural network. In: 2018 IEEE 16th international conference on dependable, autonomic and secure computing, 16th international conference on pervasive intelligence and computing, 4th international conference on big data intelligence and computing and cyber science and technology congress (DASC/PiCom/DataCom/CyberSciTech), Athens, pp 151–158

  • Marsland S, Shapiro J, Nehmzow U (2002) A self-organising network that grows when required. Neural Netw 15(8):1041–1058

    Google Scholar 

  • Martinetz TM, Berkovich SG, Schulten KJ (1993) Neural-gas’ network for vector quantization and its application to time-series prediction. IEEE Trans Neural Netw 4(4):558–569

    Google Scholar 

  • Mohamed-Rafik B, Slawomir N, Payberah AH (2018) An adaptive algorithm for anomaly and novelty detection in evolving data streams. Data Min Knowl Discov 32(6):1597–1633

    MathSciNet  Google Scholar 

  • Mukkamala S, Janoski G, Sung A (2002) Intrusion detection using neural networks and support vector machines. In: International joint conference on neural networks. IEEE

  • Münz G, Li S, Carle G (2012) Traffic anomaly detection using K-means clustering. In: GI/ITG Workshop MMBnet, pp 13–14

  • Nguyen VQ, Van Ma L, Kim J et al (2018) Applications of anomaly detection using deep learning on time series data. In: 2018 IEEE 16th international conference on dependable, autonomic and secure computing, 16th international conference on pervasive intelligence and computing, 4th international conference on big data intelligence and computing and cyber science and technology congress (DASC/PiCom/DataCom/CyberSciTech). IEEE, pp 393–396

  • Postma EO, Hudson PTW (1995) Adaptive resonance theory. In: Artificial neural networks. Springer, Berlin, Heidelberg, pp 101–117

  • Rumelhart DE, Mcclelland JL (1986) Parallel distributed processing, vol 1. MIT Press

  • Schlegl T, Seebock P, Waldstein SM, Langs G, Schmidt-Erfurth U (2019) f-AnoGAN: fast unsupervised anomaly detection with generative adversarial networks. Med Image Anal 54:30–44

    Google Scholar 

  • Thi NN, Cao VL, Le-Khac N-A (2017) One-class collective anomaly detection based on LSTM-RNNs. In: Transactions on large-scale data-and knowledge-centered systems XXXVI. Springer, Berlin, Heidelberg, pp 73–85

  • Toma K, Sakamoto T, Zhang B et al (2009) Statistical properties of Gamma-ray burst polarization. American Institute of Physics, American Astronomical Society, Washington

    Google Scholar 

  • Wang GP, Yang JX (2019) SKICA: a feature extraction algorithm based on supervised ICA with kernel for anomaly detection. J Intell Fuzzy Syst 36(1):761–773

    Google Scholar 

  • Wang C, Zhang YM, Liu CL (2018) Anomaly detection via minimum likelihood generative adversarial networks. In: 2018 24th International conference on pattern recognition (ICPR). IEEE, pp 1121–1126

  • Wei YX, Wu M-Q (2008) KFDA and clustering based multiclass SVM for intrusion detection. J China Univ Posts Telecommun 15(1):123–128

    Google Scholar 

  • Xiao H, Dong Y, Wu B, Zhang S et al (2015) Gamma ray polarimeter POLAR of TG-2. Manned Spaceflight 2015:21

    Google Scholar 

  • Yao H, Fu X, Yang Y et al (2018) An incremental local outlier detection method in the data stream. Appl Sci 8(8):1248

    Google Scholar 

Download references

Acknowledgements

The dataset of gamma ray detector in this work is provided by Chinese Manned Space Flight Project. This study has been supported by the Foundation of Key Laboratory of Space Utilization, Technology and Engineering Center for Space utilization, Chinese Academy of Sciences (No. CSU-QZKT-2018-09) and the Open Project of Beijing key Laboratory of Measurement and Control of Mechanical and Electrical System (No. KF20181123205), China.

Author information

Author notes

  1. Lei Song and Taisheng Zheng have contributed equally to this study.

Authors and Affiliations

  1. Key Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, 100094, China

    Lei Song, Taisheng Zheng, Jianxing Wang & Lili Guo

  2. University of Chinese Academy of Sciences, Beijing, 100049, China

    Taisheng Zheng

  3. School of Software, Tsinghua University, Beijing, 100084, China

    Lili Guo

Authors
  1. Lei Song
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Taisheng Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jianxing Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Lili Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jianxing Wang.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Additional information

Communicated by V. Loia.

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Song, L., Zheng, T., Wang, J. et al. An improvement growing neural gas method for online anomaly detection of aerospace payloads. Soft Comput 24, 11393–11405 (2020). https://doi.org/10.1007/s00500-019-04603-1

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-019-04603-1

Keywords

Search

Navigation