The Dynamic Compensation Method for Virtual Instrument Based on Least Squares Support Vector Machines

摘要：

The standard support vector machine (SVM) and the least squares support vector machine (LS-SVM) was compared and described in this paper. On the basis of the compared results, a novel method using LS-SVM model to correct dynamic measurement errors of sensors is developed, The design steps and learning algorithm are also addressed. Compared with the standard SVM -compensation methods, the constraints of inequalities in the standard SVM approach are replaced by equality-type constraints in LS-SVM and the LS-SVM solution follows directly from solving a set of linear equations instead of quadratic programming. As a result, the dynamic compensation method of LS-SVM is higher in accuracy, much capability of noise resistance, so the LS-SVM is better for virtual instrument dynamic system.

关键词： Support vector machines (SVM) Least squares support vector machines (LS-SVM) Sensors Dynamic compensation

作者: MA Chao LI Shi-ping ZHANG Jin

作者单位: Test and Control Lab, The Second Artillery Engineering College, Xian, Shaanxi, China, 710025

会议类型: 国际会议

会议名称: 第八届国际测试技术研讨会(8th International Symposium on Test and Measurement)

会议地点: 重庆

会议语种:英文

页码: 147-150

在线出版日期: 2009-08-01（万方平台首次上网日期，不代表论文的发表时间）