Abstract
This paper addresses the problem of fault diagnosis performed on a mechanical system, based on acquired vibrations from bearings. In this aim, an optimization algorithm resulted from the alliance between a time–frequency–scale signal processing method (the matching pursuit) and an evolutionary computing technique (mainly, a genetic algorithm) is introduced. The matching pursuit method itself leads to a NP-hard procedure, but, with the help of a metaheuristic, the procedure becomes computationally efficient. A generalization of Baker’s procedure implementing the stochastic universal sampling mechanism, as well as a new concept, namely the Boltzmann annealing selection, is introduced, in order to design the genetic algorithm appropriately. This latter not only plays an important role in convergence speed, but also constitutes the basis of a (self) adaptive mechanism aiming to keep in balance the exploration and exploitation features. Based on the optimal solution found through the genetic matching pursuit procedure, the bearings fault diagnosis can successfully be performed, even in case of multiple defects and without prior training of some defect classification model.
Similar content being viewed by others
Abbreviations
- ABCM:
-
Algorithm based on bees collaborative model
- ANN:
-
Artificial neural networks
- bma(s):
-
Best matching atom(s)
- BMPA:
-
Bees matching pursuit algorithm
- BPFI:
-
Ball pass frequency on inner race
- BPFO:
-
Ball pass frequency on outer race
- dB:
-
Decibel(s)
- EA:
-
Envelope analysis
- EC:
-
Evolutionary computing
- ES:
-
Exhaustive search
- FT:
-
Fourier transform
- GA:
-
Genetic algorithm(s)
- GMPA:
-
Genetic matching pursuit algorithm
- LSB:
-
Least significant bit
- MPA:
-
Matching pursuit algorithm
- mw:
-
Mother waveform
- PSO:
-
Particle swarm optimization
- SA:
-
Simulated annealing
- SNR:
-
Signal-to-noise ratio
- SP:
-
Signal processing
- SUS:
-
Stochastic universal sampling
- SVM:
-
Support vector machines
- tf:
-
Time–frequency
- tfs:
-
Time–frequency–scale
- UP:
-
Uncertainty principle
References
Azovtsev YA, Barkov AV, Yudin IA (1994) Automatic diagnostics and condition prediction of rolling element bearings using enveloping methods. In: Proceedings of the 18-th annual meeting of the vibration institute, Saint Louis, June 1994, pp 249–258
Azovtsev YA, Barkov AV, Carter DL (1996) Improving the accuracy of rolling element bearing condition assessment. In: Proceedings of the 20-th annual meeting of the vibration institute, Saint Louis, 27–30 June 1996
Azovtsev YA, Barkov AV, Carter DL (1997) Fluid film bearings diagnostics using envelope spectra. Preprint provided by authors
Baker JE (1985) Adaptive selection methods for genetic algorithms. In: Proceedings of the first international conference on GA and their applications, pp 101–111
Baker JE (1987) Reducing bias and inefficiency in the selection algorithm. In: Proceedings of the 2nd international conference on GA and their applications, pp 14–21
Cohen L (1995) Time–frequency analysis. Prentice Hall, New Jersey
Cui L, Wang J, Lee S (2014) Matching pursuit of an adaptive impulse dictionary for bearing fault diagnosis. J Sound Vib 333(10):2840–2862
Darwin CR (1859) On the origin of species by means of natural selection. London Press, London. http://www.literature.org/authors/darwin-charles/the-origin-of-species/
Darwin CR (1871) The descent of man and selection in relation to sex. London Press, London. http://www.literature.org/authors/darwin-charles/the-descent-of-man/
Edgar G (2004) Classics on fractals. Westview Press, Boulder
Fag OEM, Handel AG (1997a) Rolling bearing diag-nosis with FAG devices and services, Technical report no. WL 80-60 E
Fag OEM, Handel AG (1997b) Rolling bearings—state-of-the-art, condition-related monitoring of plants and machines with digital FAG vibration monitors. Technical report no. WL 80-65 E
Figueras i Ventura RM, Vandergheynst P (2001) Matching pursuit through genetic algorithms. Technical Report, Signal Processing Laboratory (LTS), École Polytechnique Fédérale de Lausanne, Switzerland
Goldberg DE (1982) Simple genetic algorithms. Research Report, University of Michigan, Dept. of Civil Engineering, Ann Arbor
Goldberg DE (1989) Genetic algorithms in search, optimization and machine learning. Addison Wesley, New York
Goldberg DE (1990) A note on Boltzmann tournament selection for genetic algorithms and population-oriented simulated annealing. Complex Syst 4:445–460
Holland JH (1975) Adaptation in natural and artificial systems, 2nd edn. The MIT Press, Cambridge
Holland JH (1992) Adaptation in natural and artificial systems, 1st edn. University of Michigan Press, Ann Arbor
Jia F, Lei Y, Shan H et al (2015) Early fault diagnosis of bearings using an improved spectral kurtosis by maximum correlated kurtosis deconvolution. Sensors 15(11):29363–29377
Karaboga D (2005) An idea based on honey bee swarm for numerical optimization. Technical Report TROG, Ercizes University, Computer Engineering Department
Kennedy J, Eberhart RC (1995) Particle swarm optimization. In: Proceedings of the IEEE international conference on neural networks, pp 1942–1948
Kirkpatrick S, Gelatt CD, Vecchi MP (1983) Optimization by simulated annealing. Science 220:671–680
Liu RN, Yang BY, Zhang XL, Wang SB, Chen XF (2016) Time–frequency atoms-driven support vector machine method for bearings incipient fault diagnosis. Mech Syst Signal Process 75:345–370
Mallat S, Zhang S (1993) Matching pursuits with time–frequency dictionaries. IEEE Trans Signal Process 41(12):3397–3415
Mitchell M (1995) An introduction to genetic algorithms. MIT Press, Cambridge
Moumene I, Ouelaa N (2016) Application of the wavelets multiresolution analysis and the high-frequency resonance technique for gears and bearings fault diagnosis. Int J Adv Manuf Technol 83(5–8):1315–1339
Nix AE, Vose MD (1991) Modeling genetic algorithms with Markov Chains. Ann Math Artif Intell 5:79–88
Pandya DH, Upadhyay SH, Harsha SP (2014) Fault diagnosis of rolling element bearing by using multinomial logistic regression and wavelet packet transform. Soft Comput 18(2):255–266
Proakis JG, Manolakis DG (1996) Digital signal processing. Principles, algorithms and applications, 3rd edn. Prentice Hall, Upper Saddle River
Rawlins G, Whitley LD (1993) Foundations of genetic algorithms. Morgan Kaufmann, Los Altos
Russell S, Norvig P (1995) Artificial intelligence—a modern approach. Prentice-Hall, Englewood Cliffs
Samanta B, Al-Balushi KR, Al-Araimi SA (2006) Artificial neural networks and genetic algorithm for bearing fault detection. Soft Comput 10(3):264–271
Seera M, Wong M, Nandi AK (2017) Classification of ball bearing faults using a hybrid intelligent model. Appl Soft Comput 57:427–435
Shi J, Liang M (2016) Intelligent bearing fault signature extraction via iterative oscillatory behavior based signal decomposition. Expert Syst Appl 45:40–55
Stefanoiu D, Culita J (2008) Signal compaction by maximum verisimilitude. “Politehnica” Univ Buchar Sci Bull C Ser Electr Eng 70(3):59–74
Stefanoiu D, Ionescu F (2006) Chapter: fuzzy-statistical reasoning in fault diagnosis. In: Palade V, Bocaniala CD, Jain L (eds) Computational intelligence in fault diagnosis. Springer, London, pp 125–178
Stefanoiu D, Borne P, Popescu D, Filip GhF, El Kamel A (2014) Optimization in engineering sciences—metaheuristics, stochastic methods and decision support. Wiley, London
Stefanoiu D, Dumitrascu A, Culita J (2016) Lossy vibration compression through matching pursuit. Control Eng Appl Inform 18(4):45–56
Sun HL, He ZJ, Zi YY, Yuan J, Wang XD, Chen JL, He SL (2014) Multiwavelet transform and its applications in mechanical fault diagnosis—a review. Mech Syst Signal Process 43(1–2):1–24
Vakharia V, Gupta VK, Kankar PK (2016) A comparison of feature ranking techniques for fault diagnosis of ball bearing. Soft Comput 20(4):1601–1619
Wu J-D, Hsu C-C (2009) Fault gear identification using vibration signal with discrete wavelet transform technique and fuzzy–logic inference. Expert Syst Appl 36:3785–3794
Yao X (1991) Optimization by genetic annealing. In: Proceedings of the 2nd Australian conference on neural networks, ACNN’91, pp 94–97
Yu J (2017) Adaptive hidden Markov model-based online learning framework for bearing faulty detection and performance degradation monitoring. Mech Syst Signal Process 83:149–162
Ziani R, Felkaoui A, Zegadi R (2017) Bearing fault diagnosis using multiclass support vector machines with binary particle swarm optimization and regularized Fisher’s criterion. J Intell Manuf 28(2):405–417
Funding
This research has been developed with the support of Alexander von Humboldt Foundation in Bonn, Germany. The Project was hosted by the University of Applied Sciences in Constance, Germany. The authors would like to express their most sincere gratitude to those institutions.
Author information
Authors and Affiliations
Corresponding author
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.
Rights and permissions
About this article
Cite this article
Stefanoiu, D., Culita, J. & Ionescu, F. Vibration fault diagnosis through genetic matching pursuit optimization. Soft Comput 23, 8131–8157 (2019). https://doi.org/10.1007/s00500-018-3450-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-018-3450-0