A Modeling Method Based on Multiple Kernel Learning

摘要：

Support Vector Machine (SVM) with good nonlinear mapping abilities can be applied to build simulation model of helicopter. But the parameter selection should to be done before training SVM. To avoid the problems, a dynamic modeling method for helicopter based on Multiple Kernel Learning (MKL) is proposed. Based on pretreatment of practical flight data, simulation model of helicopter in a special flight states were built. It is shown by simulation that the dynamic MKL modeling method owns some advantages such as fast convergence speed , simple structure, whilst maintain the generalization precision.

关键词： Multiple Kernel Learning Support Vector Machine Helicopter Simulation Model

作者: Shuzhou Wang Lianhe Li

作者单位: School of Electrical Engineering and Automation, TianjinKeyLABofAEEET, Tianjin Polytechnic Universit School of Electrical Engineering and Automation, TianjinKeyLABofAEEET, Tianjin Polytechnic Universit

会议类型: 国际会议

会议名称: The 24th Chinese Control and Decision Conference (第24届中国控制与决策学术年会 2012 CCDC)

会议地点: 太原

会议语种:英文

页码: 2388-2390

在线出版日期: 2012-05-23（万方平台首次上网日期，不代表论文的发表时间）