As the nonlinear effect and coupling character of the flight dynamics become a big problem to the blended aero and reaction jet flight control systems, the base control law is dynamic inversion that is sensitive to the accurateness. Considering fitting characteristics of neural network, we designed an adaptive Neural Network controller with Particle Swarm optimization (PSO) to account for the Dynamic Inverse error. The method avoided the neural network of local optimization and improve the learning efficiency .The simulation results proves that the new flight control system conquered the aerodynamic modeling inaccuracies and the external disturbances. The compensation of the inverse error is effective, and the robustness of the control system is improved greatly.% 针对直/气复合控制导弹的模型和参数的不确定性和多操纵机构的耦合问题,采用动态逆作为基本控制律,利用神经网络对非线性函数的逼近特性,设计在线模型参考自适应神经网络对慢回路的逆误差进行补偿,并用粒子群算法优化神经网络的参数,避免了局部寻优并提高了学习效率。通过仿真证明该方法克服了模型和参数不确定性以及外来干扰对系统稳定性的影响,对逆误差进行了有效的补偿,提高了系统的鲁棒性。
展开▼