改进的网格搜索算法在SVM故障诊断中的应用

Application of Improved Grid Search Algorithm on SVM for Fault Diagnosis

针对网格搜索法在支持向量机参数寻优时存在复杂度高、运算量大等不足,提出了一种改进的网格搜索SVM分类器的最佳参数选择算法,并将其应用于田纳西-伊士曼过程。实验表明,与改进前的算法相比,改进的网格搜索SVM分类器参数选择算法可以有效地减少SVM分类器的运算量、改进学习性能并提高识别率。

The grid search method has the disadvantages of high complexity and complex computation in parameter optimization of support vector machine（SVM）.An improved grid search algorithm is proposed to choose the optimal parameters of SVM,which is applied to tennessee-eastman process（TEP）.The experimental result shows that the improved grid search algorithm can reduce the SVM classifier＇s computation effectively and improve its performance and classification accuracy.