基于模糊神经网络的质量矩拦截弹动态逆控制

质量矩控制是一种全新的飞行控制方法,与广泛应用的空气动力控制相比,可以避免飞行器在超高马赫数飞行时舵面的气动加热问题,而且,可以提高飞行器的机动性和敏捷性。以所建立的质量矩拦截弹数学模型为基础,通过对模型合理的简化,得到一个耦合的非线性动力学系统。考虑到系统的鲁棒性要求和三个滑块的协调控制问题,应用双时标分解的方法,提出将拦截弹动力学分离为快变状态动力学和慢变状态动力学。然后,设计了拦截弹模糊动态逆飞行控制系统,分别针对快变和慢变子系统,提出了一种基于模糊神经网络(FNN)的动态逆误差补偿方法,可以有效地抑制气动参数摄动而引起的控制系统性能的下降,提高了控制系统的鲁棒性。仿真结果表明系统性能指标满足设计要求,只需微调滑块位置,即可以实现拦截弹的飞行控制。

Dynamic Inversion Control for Mass Moment Interception Missile Based on Fuzzy Neural Network

As a novel method,mass moment control offers significant advantages over conventional aerodynamic control systems in applications such as the control of missiles at extreme Mach numbers,where the aerodynamic heating can make it impractical to deploy control surfaces.Furthermore,it can meet the demands of the maneuverability and agility of flight vehicles.Based on the constructed model of mass moment interception missile(MMIM),a coupled nonlinear system is presented by rational simplification in this paper.To meet the demands of the robustness of missiles and the co-ordination of the three masses control,based on the two time-scale separation assumption,the dynamics of the MMIM are separated into two parts: the dynamics of fast state and the dynamics of slow state.And then,in order to keep the robust track performance of the system by considering aerodynamic parameter perturbation,flight control system is developed for the two subsystems respectively via utilizing the proposed fuzzy neural network control approach.It can not only control flight overload of the interception missile but also meet a given set of performance indexes by moving the three masses in missiles slightly.