Abstract
Condition diagnosis of bearings is one of the most common plant maintenance activities in manufacturing industries. It is essential to detect bearing faults early to avoid unexpected breakdown of plant due to undetected faulty bearings. Many meta-heuristics techniques for condition diagnosis of single bearing systems have been developed. The techniques, however, are not effectively applicable for multiple bearing systems. In this paper, a new hybrid technique of genetic algorithms (GAs) with adaptive operator probabilities (AGAs) and back propagation neural networks (BPNNs), called AGAs–BPNNs, is proposed specifically for condition diagnosis of multiple bearing systems. In this technique, AGAs are integrated with BPNNs to attain better initial weights for the BPNNs and hence reduce their learning time. We tested the proposed technique on a two bearing systems, and used ten extracted features from the system’s vibration signals data as input and sixteen bearing condition classes as target output. The experimental results show that the AGAs–BPNNs technique obtains much higher classification accuracy in shorter CPU time and number of iterations compared with the standard BPNNs, and the hybrid of standard GAs and BPNNs.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Harris TA, Kotzalas MN (2007) Rolling bearing analysis: essential concepts of bearing technology, 5th edn. Taylor and Francis Group, London
Harnoy A (2003) Bearing design in machinery: engineering tribology and lubrication. Marcel Dekker Inc., New York
Rodriguez PVJ, Arkkio A (2008) Detection of stator winding fault in induction motor using fuzzy logic. Appl Soft Comput 8:1112–1120
Min X, Fanrang K, Fei H (2011) An approach for bearing fault diagnosis based on PCA and multiple classifier fusion. In: Information technology and artificial intelligence conference (ITAIC), 2011 6th IEEE joint international
Su YT, Lin SJ (1992) On initial fault detection of a tapered roller bearing: frequency domain analysis. J Sound Vib 155(1):75–84
Mori K et al (1996) Prediction of spalling on a ball bearing by applying the discrete wavelet transform to vibration signals. Wear 195:162–168
Heng RBW, Nor MJM (1998) Statistical analysis of sound and vibration signals for monitoring rolling element bearing condition. Appl Acoust 53(1–3):211–226
Yu D, Cheng J, Yang Y (2005) Application of EMD method and Hilbert spectrum to the fault diagnosis of roller bearings. Mech Syst Signal Process 19:259–270
Al-Raheem KF et al (2007) Rolling element bearing fault diagnosis using Laplace-wavelet envelope power spectrum. EURASIP J Adv Signal Process 2007:1–14
Wen F, Han Z (1995) Fault section estimation in power system using a genetic algorithm. Electr Power Syst Res 34:165–172
Rafiee J et al (2007) Intelligent condition monitoring of a gearbox using artificial neural network. Mech Syst Signal Process 21:1746–1754
Jayaswal P, Verma SN, Wadhwani AK (2010) Methodology and theory application of ANN, fuzzy logic and wavelet transform in machine fault diagnosis using vibration signal analysis. J Qual Maint Eng 16(2):190–213
Tang JL, Cai QR, Liu YJ (2010) Gear fault diagnosis with neural network based on niche genetic algorithm. In: International conference on machine vision and human-machine interface, pp 596–599
Wulandhari LA, Wibowo A, Desa MI (2011) Hybrid neural network-genetic algorithms approach for fault diagnosis of bearing system. In: The 1st international conference on industrial engineering and service science (IESS 2011). Solo, Indonesia
Li W et al (2003) Feature extraction and classification of gear faults using principal component analysis. J Qual Maint Eng 9(2):132–143
Lei Y, He Z, Zi Y (2009) Application of an intelligent classification method to mechanical fault diagnosis. Expert Syst Appl 36:9941–9948
Mak KL, Wong YS, Wang XX (2000) An adaptive genetic algorithm for manufacturing cell formation. Int J Adv Manuf Technol 16:491–497
Aihong J, Lizhe Y (2010) Fault diagnosis based on adaptive genetic algorithm and BP neural network. In: 2010 2nd international conference on computer engineering and technology vol 6, pp 427–430
Srinivas M, Patnaik LM (1994) Adaptive probabilities of crossover and mutation in genetic algorithms. IEEE Trans Syst Man Cybern 24(4):656–667
Blum S et al. (2001) Adaptive mutation strategies for evolutionary algorithms. In: The annual conference: EVEN at Weimarer Optimierungsund Stochastiktage 2.0
Snasel V, Kromer P, Platos J (2008) Benchmarking hybrid selection and adaptive genetic operators. In: Václav S (ed) Znalosti 2008, ISBN 978-80-227-2827-0. FIIT STU Bratislava, Ústav informatiky a softvérového inzinierstva, pp 224–233
Acknowledgments
The authors thank to Universiti Teknologi Malaysia (UTM) and Ministry of High Education (MOHE) for Fundamental Research Grant Scheme (FRGS) Vote No. R.J130000.7828.4F084 and Research University Grant (RUG) Vote No. Q.J. 130000.7128.00J96. We also thank to UTM’s Research Management Center (RMC) for supporting this research project. The first author sincerely thanks to UTM for awarding International Doctoral Fellowship (IDF).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wulandhari, L.A., Wibowo, A. & Desa, M.I. Condition diagnosis of multiple bearings using adaptive operator probabilities in genetic algorithms and back propagation neural networks. Neural Comput & Applic 26, 57–65 (2015). https://doi.org/10.1007/s00521-014-1698-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-014-1698-6