LS-SVM的矩形窗算法及其在非线性系统建模中的应用  

LS-SVM Rectangle Window Algorithm and Its Application in Modelling of Nonlinear System

作　　者：杨庆华 时磊[2] 

机构地区：[1]海装驻西安地区军事代表局,陕西西安710054 [2]防空兵指挥学院作战指挥系,河南郑州450052

出　　处：《火炮发射与控制学报》2009年第4期22-25,共4页Journal of Gun Launch & Control

摘　　要：最小二乘支持向量机是支持向量机的一种重要方法,但该方法不能用于在线辨识,并且可能导致计算膨胀问题。将最小二乘支持向量机与矩形窗算法相结合,可形成最小二乘支持向量机的矩形窗算法。由于该方法采用了在线递推,可有效克服坏数据对参数估计的影响,并可避免计算膨胀问题,提高了最小二乘支持向量机的计算速度。最后将该方法应用于非线性系统的建模中,仿真实例验证了该方法的有效性。The least square support vector machine （LS-SVM） is an important method to support vector machine theory, but it cannot be used in online identification, and it maybe lead to the problem of calculation inflation. Combined the LS-SVM with rectangle window algorithm, the rectangle window algorithm of LS-SVM was formed. By use of online iteration, the algorithm can overcome the effect of bad data on parameter estimation and can avoid the problem of calculation inflation. This method can improve the calculation speed of the least square support vector machine. The presented method was applied to the modelling of nonlinear system, and the verified simulation example showed that the proposed method is validity.

关 键 词：应用数学 支持向量机 最小二乘法 矩形窗 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]