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.
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
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.
H. Löfsten, Measuring maintenance performance — in search for a maintenance productivity index, International Journal of Production Economics, 63 (1) (2000) 47–58.
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.
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.
M. Carnero, An evaluation system of the setting up of predictive maintenance programmes, Reliability Engineering and System Safety, 91 (8) (2006) 945–963.
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.
G. Vachtsevanos et al., Intelligent Fault Diagnosis and Prognosis for Engineering Systems, John Wiley & Sons, Inc., Hoboken (2006).
S. J. Qin, Survey on data-driven industrial process monitoring and diagnosis, Annual Reviews in Control, 36 (2) (2012) 220–234.
G. A. Susto et al., Machine learning for predictive maintenance: a multiple classifier approach, IEEE Transactions on Industrial Informatics, 11 (3) (2015) 812–820.
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.
R. Liu et al., Artificial intelligence for fault diagnosis of rotating machinery: a review, Mechanical Systems and Signal Processing, 108 (2018) 33–47.
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.
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.
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.
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.
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.
D. E. Goldberg and J. H. Holland, Genetic algorithms and machine learning, Machine Learning, 3 (2/3) (1988) 95–99.
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.
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.
C. Cortes and V. Vapnik, Support-vector networks, Machine Learning, 20 (3) (1995) 273–297.
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.
Z. He, X. Xu and S. Deng, Discovering cluster-based local outliers, Pattern Recognition Letters, 24 (9–10) (2003) 1641–1650.
S. Jiang and Q. An, Clustering-based outlier detection method, 2008 Fifth International Conference on Fuzzy Systems and Knowledge Discovery (2008).
A. Smiti, A critical overview of outlier detection methods, Computer Science Review, 38 (2020) 100306.
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.
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.
P. J. Rousseeuw and K. V. Driessen, A fast algorithm for the minimum covariance deTerminant estimator, Technometrics, 41 (3) (1999) 212–223.
F. T. Liu, K. M. Ting and Z.-H. Zhou, Isolation forest, 2008 Eighth IEEE International Conference on Data Mining (2008).
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.
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.
S. Yin, X. Zhu and C. Jing, Fault detection based on a robust one class support vector machine, Neurocomputing, 145 (2014) 263–268.
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.
J. E. Jackson and G. S. Mudholkar, Control procedures for residuals associated with principal component analysis, Technometrics, 21 (3) (1979) 341–349.
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
Corresponding author
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
About this article
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
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12206-023-0201-7