基于FOA-SVM的汽轮机振动故障诊断

PDF(1600 KB)

振动与冲击 ›› 2014, Vol. 33 ›› Issue (22) : 111-114.

论文

基于FOA-SVM的汽轮机振动故障诊断

石志标，苗莹

作者信息 +

Vibration Fault Diagnosis for Steam Turbine Based on Fruit Fly Optimization Algorithm Support Vector Machine

Shi Zhi-biao，Miao-Ying

Author information +

文章历史 +

摘要

为了解决支持向量机算法(Support Vector Machine，SVM)的核函数参数和惩罚因子参数选取的盲目性，利用果蝇优化算法（Fruit Fly Optimization Algorithm，FOA），对SVM中的参数进行优化。提出了基于FOA的SVM故障诊断算法，并对汽轮机故障实验数据进行了模式识别。算法能够对SVM相关参数自动寻优，并且能达到较为理想的全局最优解。通过与目前常用的粒子群算法(Particle Swarm Optimization ，PSO)和遗传算法(Genetic Algorithm ，GA)优化后的支持向量机进行对比，结果表明：FOA-SVM算法稳定、识别速度最快、识别率最高。

Abstract

In order to solve the problem that the selection of the kernel function parameters and penalty factor parameters in the support vector machine(SVM)algorithm is blindfold，we use the fruit fly optimization algorithm(FOA)to optimize the parameters in SVM．A fault diagnosis algorithm of SVM based on FOA is put forward，and then we use it to execute the pattern recognition of the turbine failure experimental data．This algorithm could optimize the SVM parameters automatically，and achieve ideal global optimal solution．Comparing with the SVM which optimized by the common used methods of the particle swarm optimization(PSO) and the Genetic Algorithm (GA) currently，the results demonstrate that FOA-SVM has the fastest recognition speed and the highest recognition rate．

导出引用

石志标;苗莹. 基于FOA-SVM的汽轮机振动故障诊断[J]. 振动与冲击, 2014, 33(22): 111-114

Shi Zhi-biao;Miao-Ying. Vibration Fault Diagnosis for Steam Turbine Based on Fruit Fly Optimization Algorithm Support Vector Machine[J]. Journal of Vibration and Shock, 2014, 33(22): 111-114