Concept of automated fault detection of large turbomachinery using Machine Learning on transient data
Tomasz Barszcz 1  
More details
Hide details
Akademia Górniczo-Hutnicza
General Electric Sp. z o.o., Elblag, Poland
Tomasz Barszcz   

Akademia Górniczo-Hutnicza, Al. Mickiewicza 30, 30-059 Kraków, Polska
Online publish date: 2018-12-17
Publish date: 2018-12-17
Submission date: 2018-08-25
Final revision date: 2018-11-22
Acceptance date: 2018-11-29
Diagnostyka 2019;20(1):63–71
Large turbosets constitute a major source of electric energy in the world. They are critical machines which are vulnerable to several malfunctions which can decrease their availability and degrade the operation of the national electric grid system. The best source of data for assessment of the technical state are the transient data, measured during run-ups and coast-downs. The size of this data is very large and its analysis can be only performed by highly skilled vibration experts. The goal of this paper is to propose a method, which can apply Machine Learning for automated fault detection. In order to improve the quality of the learning process the method is accompanied by the ‘Digital Twin’ approach, where the simplified analytical rotordynamic model is tuned to a particular turboset and used in the learning process.
1. Baranowski A, Chmiel J, Ciura Sz. The future of conventional power industry in Poland – report of discussion panel. Silesian Electrical Journal. 2017;134:12–19. Polish.
2. Bently D, Hatch CT. Fundamentals of Rotating Machinery Diagnostics. 1st ed. Canada. 2002.
3. Vance JM. Rotordynamics of turbomachinery. Wiley. 1988.
4. Muszyńska A. Rotordynamics. 1st ed. USA; 2005.
5. Kiciński J. Dynamika wirników i łożysk ślizgowych. Polish (Dynamics of shafts and hydrodynamic bearings). 2005.
6. Pennacchi P, Vania A, Chatterton S. Identification of mechanical faults in rotating machinery for power generation. IEEE International Symposium on Industrial Electronics. 2010.
7. Bachschmid N, Pennacchi P, Chatterton S, Ricci R. On model updating of turbo-generator sets. Journal of Vibroengineering. 2009;11:379-391.
8. Abu Mostafa Y. Magdon-Ismail M, Lin HT. Learning From Data. AML Book. 2012.
9. Bishop CM. Pattern recognition and machine learning. Springer. 2011.
10. Dou D, Zhou Z. Comparison of four direct classification methods for intelligent fault diagnosis of rotating machinery. Applied Soft Computing. 2016; 46:459–468.
11. Fawzi A, Fawzi O, Frossard P. Analysis of classifiers’ robustness to adversarial perturbations. Mach Learn. 2018:107:481–508.
12. Shen Ch, Wang D, Kong F, Tse PW. Fault diagnosis of rotating machinery based on the statistical parameters of wavelet packet paving and a generic support vector regressive classifier. Measurement. 2013. 46:1551–1564.
13. Zhong JH, Wong PK, Yang ZX. Fault diagnosis of rotating machinery based on multiple probabilistic classifiers. Mechanical Systems and Signal Processing. 2018;108:99–114.
14. Haidong S, Hongkai J, Huiwei Z, Fuan W. A novel deep autoencoder feature learning method for rotating machinery fault diagnosis. Mechanical Systems and Signal Processing. 2017;95:187–204.
15. Deng L, Zhao R. A vibration analysis method based on hybrid techniques and its application to rotating machinery. Measurement. 2013;46:3671–3682.
16. Liu Z, Guo W, Hu J, Ma W. A hybrid intelligent multi-fault detection method for rotating machinery based on RSGWPT. KPCA and Twin SVM, ISA Transactions. 2017;6:249–261.
17. Jia F, Lei Y, Lin J, Zhou X, Lu N. Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. Mechanical Systems and Signal Processing. 2016;72-73:303–315.
18. Li W, Zhu Z, Jiang F, Zhou G, Chen G. Fault diagnosis of rotating machinery with a novel statistical feature extraction and evaluation method. Mechanical Systems and Signal Processing. 2015;50-51:414–426.
19. Khosravifar B, Bouguessa M. Using Support Vector Machines for Intelligent Service Agents Decision Making, P. Perner (Ed.): MLDM 2016, LNAI 9729. 2016:73–87.
20. Khadersab A, Dr.Shivakumar S. Vibration analysis techniques for rotating machinery and its effect on bearing faults. Procedia Manufacturing. 2018:20 247–252.
21. Fu C, Ren X, Yang Y, Xia Y, Deng W. An interval precise integration method for transient unbalance response analysis of rotor system with uncertainty. Mechanical Systems and Signal Processing. 2018;107:137–148.
22. Li C, Cabrera D, Oliveira JV, Sanchez RV, Cerrada M, Zurita G. Extracting repetitive transients for rotating machinery diagnosis using multiscale cluster gray infogram. Mechanical Systems and Signal Processing. 2016;76-77:157–173.
23. Antoni J. The infogram: Entropic evidence of the signature of repetitive transients. Mechanical Systems and Signal Processing. 2016;74:73–94.
24. Kalita M, Kakoty SK. Analysis of whirl speeds for rotor-bearing systems supported on fluid film bearings. Mechanical Systems and Signal Processing 2004;18:1369–1380.
25. Torkhani M, May L, Voinis P. Light, medium and heavy partial rubs during speed transients of rotating machines: Numerical simulation and experimental observation. Mechanical Systems and Signal Processing. 2012;29:45–66.