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

摘要

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.