Restricted accessResearch articleFirst published online 2015-9
The support vector machine parameter optimization method based on artificial chemical reaction optimization algorithm and its application to roller bearing fault diagnosis
The accuracy of a support vector machine (SVM) classifier is decided by the selection of optimal parameters for SVM. An artificial chemical reaction optimization algorithm (ACROA) is a new method to solve the global optimization problem and is adapted to optimize SVM parameters. In this paper, a SVM parameter optimization method based on ACROA (ACROA-SVM) is proposed. Furthermore, the ACROA-SVM is applied to diagnose roller bearing faults. Firstly, the original modulation roller bearing vibration signals are decomposed into product functions (PFs) by using the local mean decomposition (LMD) method. Secondly, the ratios of amplitudes at the different fault characteristic frequencies in the envelope spectra of some PFs that include dominant fault information are defined as the characteristic amplitude ratios. Finally, the characteristic amplitude ratios are used as input to the ACROA-SVM classifiers, and the fault patterns of the roller bearing are identified. The result shows that the combination of this ACROA-SVM classifiers and LMD method can effectively improve the accurate rate of fault diagnosis and reduce cost time.
AbdiMJHosseiniSMRezghiM (2012) A novel weighted support vector machine based on particle swarm optimization for gene selection and tumor classification. Computational and Mathematical Methods in Medicine2012. article ID 320698.
2.
AbeS (2005) Advances in Pattern Recognition, London: Springer-Verlag.
3.
AlatasB (2011) ACROA: Artificial Chemical Reaction Optimization Algorithm for global optimization. Expert Systems with Applications38: 13170–13180.
4.
AlatasB (2012) A novel chemistry based metaheuristic optimization method for mining of classification rules. Expert Systems with Applications39: 11080–11088.
5.
ArdjaniFSadouniK (2010) Optimization of SVM multiclass by particle swarm (PSO-SVM). International Journa ofModern Education and Computer Science2: 32–38.
6.
AriSHembramKSahaG (2010) Detection of cardiac abnormality from PCG signal using LMS based least square SVM classifier. Expert Systems with Applications37: 8019–8026.
7.
BingLShulinTQiangM (2011) Research on features for diagnostics of filtered analog circuits based on LS-SVM. In: AUTOTESTCON, 2011 IEEE, Baltimore, MD, 12--15 September 2011, pp. 360–366.
8.
BouhoucheSYazidLLHocineS (2010) Evaluation using online support-vector-machines and fuzzy reasoning. Application to condition monitoring of speeds rolling process. Control Engineering Practice18: 1060–1068.
9.
CapparucciaRDe LeoneRMarchittoE (2007) Integrating support vector machines and neural networks. Neural Networks20: 590–597.
10.
ChapelleOVapnikVBousquetO (2002) Choosing multiple parameter for support vector machines. Machine Learning46: 131–159.
11.
DuanKKeerthiSSPooAN (2003) Evaluation of simple performance measures for tuning SVM hyperparameters. Neurocomputing51: 41–59.
12.
FriedrichsFIgelC (2005) Evolutionary tuning of multiple SVM parameters. Neurocomputing64: 107–117.
13.
GuoLChenJLiX (2009) Rolling bearing fault classification based on envelope spectrum and support vector machine. Journal of Vibration and Control15: 1349–1363.
14.
HanMJHsuJHSongKT (2008) A new information fusion method for bimodal robotic emotion recognition. Journal of Computers3: 39–47.
15.
Imbault F and Lebart K (2004) A stochastic optimization approach for parameter tuning of Support Vector Machines. In: Proceedings of the 17th International Conference on Pattern Recognition, Cambridge, 23–26 August 2004, vol. 4: pp. 597–600.
16.
JangJParkKRKimJ (2008) New focus assessment method for iris recognition systems. Pattern Recognition Letters29: 1759–1767.
17.
JiaCLWuSHGongDW (2008) Coal demand prediction based on a support vector machine model. Journal of China University of Mining & Technology36: 107–110.
18.
KeerthiSS (2002) Efficient tuning of SVM hyperparameters using radius/margin bound and iterative algorithms. Transactions on Neural Networks13: 1225–1229.
19.
LaiXWTsePWZhangCG (2004) Classification of gear faults using cumulants and the radial basis function network. Mechanical Systems and Signal Processing18: 381–389.
20.
LauKWWuQH (2008) Local prediction of non-linear time series using support vector regression. Pattern Recognition41: 1539–1547.
LuC-JLeeT-SChiuC-C (2009) Financial time series forecasting using independent component analysis and support vector regression. Decision Support Systems47: 115–125.
23.
ManikandanJVenkataramaniB (2011) Design of a real time automatic speech recognition system using Modified One Against All SVM classifier. Microprocessors and Microsystems35: 568–578.
Omran M, Salman A and Engelbrecht AP (2002) Image classification using particle swarm optimization. In: Proceedings of the 4th Asia-Pacific Conference on Simulated Evolution and Learning 2002 (SEAL 2002), Singapore, 18–22 November 2002, pp. 370–374.
26.
ProakisJGManolakisDG (1992) Digital Signal Processing– Principles, Algorithms and Applications, 2nd edn. New York: Macmillan.
27.
SamantaB (2004) Artificial neural networks and genetic algorithms for gear fault detection. Mechanical Systems and Signal Processing18: 1273–1282.
28.
SmithJS (2005) The local mean decomposition and its application to EEG perception data. Journal of the Royal Society Interface2: 443–454.
29.
Tsung-JungHWei-ChangY (2011) Knowledge discovery employing grid scheme least squares support vector machines based on orthogonal design bee colony algorithm. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics41: 1198–1212.
30.
VapnikVN (1998) Statistical Learning Theory, NewYork: John Wiley.
31.
YangYYuDChengJ (2007) A fault diagnosis approach for roller bearing based on IMF envelope spectrum and SVM. Measurement40: 943–950.
32.
YuLChenHWangS (2009) Evolving least squares support vector machines for stock market trend mining. IEEE Transactions on Evolutionary Computation13: 87–102.
33.
ZacksenhouseMBraunSFeldmanM (2000) Toward helicopter gearbox diagnosis from a small number of examples. Mechanical Systems and Signal Processing14: 523–543.
34.
ZhangXChenXHeZ (2010) An ACO-based algorithm for parameter optimization of support vector machines. Expert Systems with Applications37: 6618–6628.
