Application of Fruit Fly Optimization Algorithm-Least Square Support Vector Machine in Fault Diagnosis of Fans

Abstract:

The parameter selection problem of kernel function in support vector machine directly affects the generalization ability of support vector machine model .In order to improve the accuracy of the fault classification of centrifugal fan ,the classification method based the Drosophila algorithm optimizes least square support vector machine is proposed In this paper .First, it uses the eigenvectors based on the fan vibration frequency domain as learning samples .Then it uses the improved least square support vector machine model to recognise the patten of the energy feature of fan vibration signal .This article also uses the particle swarm and ant colony algorithm to optimize least square support vector machine .The simulation results show that the method of least square support vector machine based on Drosophila optimization has the advantages of high recognition rate and high diagnostic speed .And the method is feasible and effective.

• Periodical: Advanced Materials Research (Volumes 860-863)
• Pages: 1510-1516
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.860-863.1510
• Online since: December 2013
• Authors: Wen Peng Hong, Ming Jun Liao
• Keywords: Centrifugal Fan, Fault Diagnosis, Fruit Fly Optimization Algorithm, Least Square Support Vector Machine

References

[1] Burges C J C．A tutorial on support vector machines for pattern recognition[J]．Data Mining and Knowledge Discovery，1998，2(2)：121-167.

[2] Zhao Wenqing，Zhu Yongli，Zhang Xiaoqi．Combinational forecast for transformer faults based on support vector machine[J]．Proceedings of the CSEE，2008，28(25)：14-18.

[3] Suykens J A K，Vandewalle J．Least squares support vector machine classifiers[J]．Neural Processing Letters，1999，9(3)：293-300.

[4] Wen-Tsao Pan. A new Fruit Fly Optimization Algorithm: Taking the financial distress model as an example [J]. Knowledge-Based Systens, 2012, 26: 69-74.

DOI: 10.1016/j.knosys.2011.07.001

[5] Zhao Li. Intelligent fault diagnoses of rectifier circuit based on particle swarm optimization neural network [D]. Cental South University, (2008).

[6] Eberhart R C，Kennedy J．A new optimizer using particle swarm theory[C]．Proceedings Sixth Symposium on Micro Machine and Human Science，Nagoya，1995：39-43.

DOI: 10.1109/mhs.1995.494215

[7] Dorigo M，Maniezzo V，Colorni A．Ant system optimization by acolony of cooperating agents[J]．IEEE Transactions on System, Man and Cybernetics-Part B：Cybernetics，1996， 26(1)：29-41.

DOI: 10.1109/3477.484436

[8] Lu Jing. Research of ant colony algorithm in transformer fault diagnosis[D]. Nanjing：Nanjing University of Aeronautics and Astronautics, (2008).

[9] Kristiaan Pelckmans, Jos De Brabanter, J A K Suykens. The differogram: Non-parametric noise variance estimation and its use for model selection [J]. Neurocomputing (S0925-2312), 2005, 69(3): 100-122.

DOI: 10.1016/j.neucom.2005.02.015

[10] Pan Wenchao, Drosophila optimization algorithm[M]. Taiwan: John Wiley & Sons, (2011).

[11] Zhou Yunlong, Wang Suobin. Application of EMD and auto-regressive model in centrifugalFan misalignment fault analysis[J]. Journal of Vibration, Measurement &Diagnosis, 2011, 31(5): 582-585.