Sage Journals: Discover world-class research

Abstract

The condition monitoring of a rolling element bearing requires a thorough understanding of the bearing and online evaluation of system health. This paper presents a generic scheme for health monitoring of rolling element bearings. The approach contains vibration modeling and online fault dimension estimation. The parameters of a vibration model are obtained via offline training. A genetic algorithm is applied to a set of data with various operating conditions and fault dimensions to achieve the optimal model parameters. The trained model is then used online in parallel with a real system in service to realize model-based fault detection and diagnosis. To increase the accuracy of diagnosis, an extended Kalman filter is used to address the noises and uncertainties associated with fault dimension estimation. The proposed system is implemented on a case study of rolling element bearing health monitoring and experimental results demonstrate the efficiency of the proposed method.

Keywords

Extended Kalman filtering fault diagnosis genetic algorithm rolling element bearing vibration modeling

Get full access to this article

View all access options for this article.

References

Antoni

Randall

(2003) A stochastic model for simulation and diagnostics of rolling element bearings with localized fault. Journal of Vibration and Acoustics 125: 282–289.

Ayhan

Chow

M-Y

Song

M-H

(2006) Multiple discriminant analysis and neural network based monolith and partition fault detection schemes for broken rotor bar in induction motors. IEEE Transactions Industrial Electronics 53: 1298–1308.

Bai

Hsiao

Tsai

Lin

(2000) Development of an online diagnosis system for rotor vibration via model-based intelligent inference. Journal of the Acoustical Society of America 107(1): 315–323.

Braun

(1980) The signature analysis of sonic bearing vibrations. IEEE Transactions on Sonics and Ultrasonics SU-27: 317–328.

Brie

(2000) Modeling of the spalled rolling element bearing vibration signal: an overview and some new results. Mechanical Systems and Signal Processing 14(3): 353–369.

Chiementin

Kilundu

Dron

Dehombreux

Debray

(2011) Effect of cascade methods on vibration defects detection. Journal of Vibration and Control 17: 567–577.

Chui

Chen

(1998) Kalman Filtering With Real-time Applications. Berlin: Springer.

Ericsson

Grip

Johansson

Persson

Sjoberg

Strmberg

(2005) Towards automatic detection of local bearing defects in rotating machines. Mechanical Systems and Signal Processing 9: 509–535.

10.

Hashemi

Kargarnovin

(2007) Vibration base identification of impact force using genetic algorithm. World Academy of Science, Engineering and Technology 36: 147–153.

11.

Randall

(2000) Optimization of bearing diagnostic techniques using simulated and actual bearing fault signals. Mechanical System and Signal Processing 14(5): 765–788.

12.

Howard

(1994) A review of rolling element bearing vibration: detection, diagnosis and prognosis. DSTO Research report 0013. Melbourne: DSTO.

13.

14.

15.

Kiral

Karagulle

(2003) Simulation and analysis of vibration signal generated by rolling element bearing with defects. Tribology International 36: 667–678.

16.

17.

Marichal

Artés

García-Prada

(2011) An intelligent system for faulty-bearing detection based on vibration spectra. Journal of Vibration and Control 17: 931–942.

18.

McFadden

Smith

(1984) Model for the vibration produced by a single point defect in a rolling element bearing. Journal of Sound and Vibration 96: 69–82.

19.

Plotnik

Longman

(1999) Subtleties in the use of zero-phase low-pass filtering and cliff filtering for long term stability. Advances in the Astronautical Sciences 102: 243–263.

20.

Randall

Antoni

Chobsaard

(2001) The relationship between spectral correlation and envelope analysis in the diagnostics of bearing faults and other cyclostationary machine signals. Mechanical System and Signal Processing 15(5): 945–962.

21.

Saravanan

Cholairajan

Ramachandran

(2009) Vibration-based fault diagnosis of spur bevel gear box using fuzzy technique. Expert Systems with Applications 30(2): 3119–3135.

22.

Srinivas

Patnaik

(1994) Adaptive probabilities of crossover and mutation in GA. IEEE Transactions on Systems Man and Cybernetics 24(4): 656–667.

23.

Suggs

Wade

(2008) Vibration based maintenance credits for the UH-60 oil cooler fan assembly. AHS Specialists' Meeting on Condition Based Maintenance (CBM) Huntsville, AL: pp. 12–13. February 13.

24.

Wang

Y-F

Kootsookos

(1998) Modeling of low shaft speed bearing faults for condition monitoring. Mechanical Systems and Signal Processing 12(3): 415–426.