基于PSO-LSSVM的小型无人直升机模型辨识  

Model identification of small unmanned helicopter based on PSO-LSSVM

作　　者：刘灵哲 周健[1] 卢健[1] 王耿[2] LIU Lingzhe;ZHOU Jian;LU Jian;WANG Geng(School of Electronic Information,Xi’an Polytechnic University,Xi’an 710048,China;Unmanned System Technology Research Institute,NWPU,Xi’an 710072,China)

机构地区：[1]西安工程大学电子信息学院,陕西西安710048 [2]西北工业大学无人系统技术研究院,陕西西安710072

出　　处：《飞行力学》2021年第6期89-94,共6页Flight Dynamics

摘　　要：针对小型无人直升机多变量、强耦合、复杂动力学特性下的建模问题,提出了一种基于粒子群优化最小二乘支持向量机(PSO-LSSVM)的小型无人直升机模型辨识方法。该方法以飞行数据为驱动,利用最小二乘支持向量机学习速度快、泛化能力强的优势,结合粒子群优化算法对最小二乘支持向量机的参数进行优化,最终建立小型无人直升机模型。在悬停及小速度前飞模态下,使用该方法对小型无人直升机纵、横向通道进行模型训练和验证。验证结果表明,模型具有较高的精度,能很好地反映小型无人直升机的动态特性。A small unmanned helicopter model identification method based on particle swarm optimization least square support vector machines(PSO-LSSVM)was proposed to solve the modeling problem of small unmanned helicopter under multivariable,strong coupling and complex dynamic characteristics.This method was driven by flight data,taking advantage of the least squares support vector machine,which had fast learning speed and strong generalization ability,and combined with particle swarm optimization algorithm to optimize the parameters of the least squares support vector machine,and finally established a small unmanned helicopter model.The method is used to train and verify the longitudinal and lateral channels of a small unmanned helicopter in hovering and low speed forward flight modes.Verification results show that the model has high accuracy and can reflect the dynamic characteristics of small unmanned helicopter well.

关 键 词：小型无人直升机 模型辨识 最小二乘支持向量机 粒子群优化算法 

分 类 号：V212.4[航空宇航科学与技术—航空宇航推进理论与工程] V279