基于合成核支持向量机的风力发电机故障诊断

Support Vector Machine with Composite Kernel in Fault Diagnosis of Wind Power Gearbox

采用合成核函数构造支持向量机模型,运用粒子群优化算法(PSO)对模型参数进行参数寻优,利用UCI数据集的数据进行分类验证。与单核SVM相比,该方法具有更好的分类能力和运算速度。将合成核SVM应用到风机齿轮箱的故障诊断中,取得了良好的效果。

The support vector machines （SVM） is a kind of novel statistics learning method.In the case of small samples,SVM has a higher classification capability.In this paper,SVM with composite kernels will be adopted to optimize the parameters of SVM with the particle swarm optimization （PSO） and to carry out the experiments on the UCI database.Compared with the single kernel SVM,the composite kernels can improve precision of classification and get a better classification performance.Finally,we use SVM with composite kernels in the fault diagnosis of wind power gearbox and have a good result.