Inverse Model Control for a Quad-rotor Aircraft Using TS-fuzzy Support Vector Regression

作     者：Zhiyu Li Hanxin Chen Congqing Wang Kaijia Xue 

作者机构：Institute of Unmanned Aircraft Research Nanjing University of Aeronautics and Astronautics Nanjing 210016 China College of Automation Engineering Nanjing University of Aeronautics and Astronautics Nanjing 210016 China 

出 版 物：《Journal of Harbin Institute of Technology(New Series)》 (哈尔滨工业大学学报（英文版）)

年 卷 期：2017年第24卷第6期

页      面：73-79页

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Sponsored by the Science and Technology Support Program of Jiangsu Province(Grant No.SBE2014070836) 

主　　题：support vector regression TS-fuzzy SVR inverse model control quad-rotor aircraft attitude control 

摘      要：An inverse model control based on TS-fuzzy support vector regression( TS-fuzzy SVR) for a quadrotor aircraft is developed. The TS-kernel is the product of linear combination of input and a cluster of output corresponding to a cluster of TS-type fuzzy rules. The output of TS-fuzzy SVR is a linear weighted sum of the TSkernels. The dynamical model of the quad-rotor aircraft is derived. A new control scheme combined with TSfuzzy SVR inverse model control and PID control is presented so that the TS-fuzzy SVR inverse model control enhances capabilities of disturbance rejection and the robustness while the PID control enhances fast responsiveness and reliability of the system. Simulation results show the capabilities of the developed control for the attitude system of quad-rotor aircraft.