论文部分内容阅读
四旋翼飞行器运行中具有不稳定、非线性和强耦合特性,较难建立其准确的数学模型,针对这个问题,提出了基于RBFARX模型的预测控制设计方法;RBF-ARX模型是线性自回归(Auto-Regressive eXogenous,ARX)模型和高斯径向基函数(Radial Basis Function,RBF)神经网络相结合设计的模型,可用于建立非线性系统的全局模型,描述非线性系统的非线性特征。预测控制算法根据系统输入、输出信号预测对象未来输出变化趋势,并将其与系统实际输出的误差反馈校正,使误差最小;该法首先建立四旋翼飞行器的RBF-ARX模型结构,就模型参数的辨识、优化给出了详细分析;并基于该模型设计了系统预测控制器,最后通过仿真和实时控制效果证实了该方法的可行性和有效性。
In order to solve this problem, a predictive control design method based on RBFARX model is proposed. The RBF-ARX model is a linear auto-regressive -Regressive eXogenous (ARX) model and Radial Basis Function (RBF) neural network can be used to establish the global model of nonlinear systems and describe the nonlinear characteristics of nonlinear systems. The predictive control algorithm predicts the future output change trend of the object based on the input and output signals of the system and feedbacks the error with the actual output of the system so as to minimize the error. The method firstly constructs the RBF-ARX model structure of the quadrotor, Identification and optimization. The system predictive controller is designed based on the model. Finally, the feasibility and effectiveness of the proposed method are verified by simulation and real-time control effects.