Skip to main content
SpringerLink
Log in

Novelty class detection in machine learning-based condition diagnosis

  • Original Article
  • Published:
Journal of Mechanical Science and Technology Aims and scope Submit manuscript

Abstract

Industrial plant machines have a significantly lower frequency of defective data than the frequency of normal data. For this reason, machine learning is often applied using only some obtained state data. However, the low frequency of defect data does not guarantee that novel data occur, which is why detection of novelty class is required. This paper studies the novelty class detection method in multi-classification. Multi-class support vector machine was used for multi-classification. Cluster-based local outlier factor, histogram-based outlier score, outlier detection with minimum covariance deTerminant, isolation forest, and one-class support vector machine applied novelty class detection. Anomaly detection algorithms used the hard voting ensemble method. A feature engineering method that is advantageous for novelty class detection was confirmed by comparing the genetic algorithm (GA)-based feature selection and principal component analysis (PCA). Findings show that creating a model using GA-based feature selection for multi-classification and independent PCA for each class for novelty class detection is advantageous. With the use of an independent PCA, the problem was simplified to perform detection on a novelty class with a condition similar to the trained class.

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

Similar content being viewed by others

Abbreviations

N :

Total number of samples

P(n):

Random variable of time-domain signal

n :

Sample number

x(n):

Time-domain signal

\(\bar x\) :

Mean of time-domain signal

s(n):

Frequency-domain signal (fast Fourier transform from time domain signal)

\(\bar s\) :

Mean of time domain signal

σ :

Standard deviation of time domain signal

μ :

Mean of time domain signal

References

  1. J. Endrenyi et al., The present status of maintenance strategies and the impact of maintenance on reliability, IEEE Transactions on Power Systems, 16 (4) (2001) 638–646.

    Article  Google Scholar 

  2. H. Löfsten, Measuring maintenance performance — in search for a maintenance productivity index, International Journal of Production Economics, 63 (1) (2000) 47–58.

    Article  Google Scholar 

  3. C. Fu et al., Predictive maintenance in intelligent-control-maintenance-management system for hydroelectric generating unit, IEEE Transactions on Energy Conversion, 19 (1) (2004) 179–186.

    Article  MathSciNet  Google Scholar 

  4. G. Wei et al., Reliability modeling with condition-based maintenance for binary-state deteriorating systems considering zoned shock effects, Computers and Industrial Engineering, 130 (2019) 282–297.

    Article  Google Scholar 

  5. M. Carnero, An evaluation system of the setting up of predictive maintenance programmes, Reliability Engineering and System Safety, 91 (8) (2006) 945–963.

    Article  Google Scholar 

  6. S. Selcuk, Predictive maintenance, its implementation and latest trends, Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, 231 (9) (2016) 1670–1679.

    Article  Google Scholar 

  7. G. Vachtsevanos et al., Intelligent Fault Diagnosis and Prognosis for Engineering Systems, John Wiley & Sons, Inc., Hoboken (2006).

    Book  Google Scholar 

  8. S. J. Qin, Survey on data-driven industrial process monitoring and diagnosis, Annual Reviews in Control, 36 (2) (2012) 220–234.

    Article  Google Scholar 

  9. G. A. Susto et al., Machine learning for predictive maintenance: a multiple classifier approach, IEEE Transactions on Industrial Informatics, 11 (3) (2015) 812–820.

    Article  Google Scholar 

  10. D. Dou and S. Zhou, Comparison of four direct classification methods for intelligent fault diagnosis of rotating machinery, Applied Soft Computing, 46 (2016) 459–468.

    Article  Google Scholar 

  11. R. Liu et al., Artificial intelligence for fault diagnosis of rotating machinery: a review, Mechanical Systems and Signal Processing, 108 (2018) 33–47.

    Article  Google Scholar 

  12. W.-K. Lee et al., Performance improvement of feature-based fault classification for rotor system, International Journal of Precision Engineering and Manufacturing, 21 (6) (2020) 1065–1074.

    Article  Google Scholar 

  13. H. T. Yu et al., Study on rub vibration of rotary machine for turbine blade diagnosis, Transactions of the Korean Society for Noise and Vibration Engineering, 26 (2016) 714–720.

    Article  Google Scholar 

  14. H. J. Kim et al., Vibration signal analysis of gearbox fault according to feature, Transactions of the Korean Society for Noise and Vibration Engineering, 27 (4) (2017) 419–424.

    Article  Google Scholar 

  15. D. Y. Cheong et al., Feature-based trend monitoring of vibration signals according to severity of gear tooth breakage, Transaction of Korean Society for Noise and Vibration Engineering, 29 (2) (2019) 199–205.

    Article  Google Scholar 

  16. L. B. Jack and A. K. Nandi, Genetic algorithms for feature selection in machine condition monitoring with vibration signals, IEE Proceedings — Vision, Image, and Signal Processing, 147 (3) (2000) 205.

    Article  Google Scholar 

  17. D. E. Goldberg and J. H. Holland, Genetic algorithms and machine learning, Machine Learning, 3 (2/3) (1988) 95–99.

    Article  Google Scholar 

  18. B. Karaçalı, R. Ramanath and W. E. Snyder, A comparative analysis of structural risk minimization by support vector machines and nearest neighbor rule, Pattern Recognition Letters, 25 (1) (2004) 63–71.

    Article  Google Scholar 

  19. G.-M. Lim, D.-M. Bae and J.-H. Kim, Fault diagnosis of rotating machine by thermography method on support vector machine, Journal of Mechanical Science and Technology, 28 (8) (2014) 2947–2952.

    Article  Google Scholar 

  20. C. Cortes and V. Vapnik, Support-vector networks, Machine Learning, 20 (3) (1995) 273–297.

    Article  MATH  Google Scholar 

  21. A. Widodo and B.-S. Yang, Support vector machine in machine condition monitoring and fault diagnosis, Mechanical Systems and Signal Processing, 21 (6) (2007) 2560–2574.

    Article  Google Scholar 

  22. Z. He, X. Xu and S. Deng, Discovering cluster-based local outliers, Pattern Recognition Letters, 24 (9–10) (2003) 1641–1650.

    Article  MATH  Google Scholar 

  23. S. Jiang and Q. An, Clustering-based outlier detection method, 2008 Fifth International Conference on Fuzzy Systems and Knowledge Discovery (2008).

  24. A. Smiti, A critical overview of outlier detection methods, Computer Science Review, 38 (2020) 100306.

    Article  MathSciNet  MATH  Google Scholar 

  25. M. Goldstein and A. Dengel, Histogram-based outlier score (HBOS): A fast unsupervised anomaly detection algorithm, KI-2012: Poster and Demo Track (2012) 59–63.

  26. J. Hardin and D. M. Rocke, Outlier detection in the multiple cluster setting using the minimum covariance deTerminant estimator, Computational Statistics and Data Analysis, 44 (4) (2004) 625–638.

    Article  MathSciNet  MATH  Google Scholar 

  27. P. J. Rousseeuw and K. V. Driessen, A fast algorithm for the minimum covariance deTerminant estimator, Technometrics, 41 (3) (1999) 212–223.

    Article  Google Scholar 

  28. F. T. Liu, K. M. Ting and Z.-H. Zhou, Isolation forest, 2008 Eighth IEEE International Conference on Data Mining (2008).

  29. Z. Ding and M. Fei, An anomaly detection approach based on isolation forest algorithm for streaming data using sliding window, IFAC Proceedings Volumes, 46 (20) (2013) 12–17.

    Article  Google Scholar 

  30. Y. Xiao et al., Two methods of selecting Gaussian kernel parameters for one-class SVM and their application to fault detection, Knowledge-Based Systems, 59 (2014) 75–84.

    Article  Google Scholar 

  31. S. Yin, X. Zhu and C. Jing, Fault detection based on a robust one class support vector machine, Neurocomputing, 145 (2014) 263–268.

    Article  Google Scholar 

  32. E. P. Tao et al., Fault diagnosis based on PCA for sensors of laboratorial wastewater treatment process, Chemometrics and Intelligent Laboratory Systems, 128 (2013) 49–55.

    Article  Google Scholar 

  33. J. E. Jackson and G. S. Mudholkar, Control procedures for residuals associated with principal component analysis, Technometrics, 21 (3) (1979) 341–349.

    Article  MATH  Google Scholar 

Download references

Acknowledgments

This research was supported by the Industrial Technology Innovation Program of the Korean Institute of Energy Technology Evaluation and Planning, with financial resources granted by the Ministry of Trade, Industry, and Energy of the Republic of Korea (No. 20203510200060).

Author information

Authors and Affiliations

  1. Department of Energy and Mechanical Engineering, Gyeongsang National University, 2 Tongyeong-haean-ro, Tongyeong-si, 53064, Korea

    Hyeon Tak Yu, Dong Hee Park, Jeong Jun Lee & Byeong Keun Choi

  2. Mattron Corp., Gaposinhangnam-ro, Masanhappo-gu, Chang-won-si, Gyeongsangnam-do, Korea

    Hyeon Sik Kim

Authors
  1. Hyeon Tak Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Dong Hee Park
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jeong Jun Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hyeon Sik Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Byeong Keun Choi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Byeong Keun Choi.

Additional information

Hyeon-Tak Yu is pursuing his unified Master’s and Doctor’s degrees at the Department of Energy and Mechanical Engineering at Gyeongsang National University in Korea. His areas of research are dynamic analysis of the rotor and machine fault analysis.

Dong-Hee Park is pursuing his unified Master’s and Doctor’s degrees at the Department of Energy and Mechanical Engineering at Gyeongsang National University in Korea. His areas of research are dynamic analysis of the rotor and machine fault analysis.

Jeong-Jun Lee is pursuing his Doctor’s degree at the Department of Energy and Mechanical Engineering at Gyeongsang National University in Korea. His areas of research are dynamic analysis of the rotor and machine fault analysis.

Hyun-Sik Kim is a CEO at the Mattron Corp. in Korea. He received his Ph.D. in Material Engineering from Kyoungnam University, Korea, in 1998. Dr. Kim’s research interests include broadband power line communication and nanomaterials.

Byeong-Keun Choi is a Professor at the Department of Energy and Mechanical Engineering, Gyeongsang National University in Korea. He received his Ph.D. in Mechanical Engineering from Pukyong National University, Korea, in 1999. From 1999 to 2002, Dr. Choi worked at Arizona State University as an academic researcher. Dr. Choi’s research interests include vibration analysis and optimum design of rotating machinery, machine diagnosis, and prognosis and acoustic emission. He is listed on Who’s Who in the World, among others.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yu, H.T., Park, D.H., Lee, J.J. et al. Novelty class detection in machine learning-based condition diagnosis. J Mech Sci Technol 37, 1145–1154 (2023). https://doi.org/10.1007/s12206-023-0201-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12206-023-0201-7

Keywords

Search

Navigation