Prediction Research on the Failure of Steam Turbine Based on Fruit Fly Optimization Algorithm Support Vector Regression

被引：5

作者：

Shi, Zhibiao ^{[1
]}

Miao, Ying ^{[1
]}

机构：

[1] Northeast Dianli Univ, Sch Mech Engn, Changchun 132012, Jilin, Peoples R China

来源：

ADVANCES IN POWER AND ELECTRICAL ENGINEERING, PTS 1 AND 2 | 2013年 / 614-615卷

关键词：

Fruit fly optimization algorithm; Support vector regression; Steam turbine; Failure prediction;

D O I：

10.4028/www.scientific.net/AMR.614-615.409

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In order to solve the blindness of the parameter selection in the Support Vector Regression (SVR) algorithm, we use the Fruit Fly Optimization Algorithm (FOA) to optimize the parameters in SVR, and then propose the optimization algorithm on the parameters in SVR based on FOA to fitting and simulate the experimental data of the turbine's failures. This algorithm could optimize the parameters in SVR automatically, and achieve ideal global optimal solution. By comparing with the commonly used methods such as Support Vector Regression and Radial Basis Function neural network, it can be shown that the forecast results of FOA_SVR more accurate and the forecast speed is the fastest.

引用

页码：409 / +

页数：2