Attitude adjustment strategy of rocket based on MPC and RBF neural network
The precise flight control of rockets represents a topic of significant interest within the context of military research,both domestically and internationally.In order to address the issue of how rockets can be better struck in order to achieve precision strikes,an effective rocket attitude adjustment strategy based on the combination of model predictive control and radial basis function neural network is proposed.The strategy employs the model predictive control algorithm to predict the optimal motor correction value necessary for attitude adjustment.Subsequently,the radial basis function neural network algorithm is utilized to achieve a rapid adjustment response to the motor,thereby facilitating the desired attitude adjustment and trajectory correction.The simulation results demonstrate that the rudder control system exhibits minimal error,rapid response,and effective tracking,while the overall strategy demonstrates excellent control performance.The robustness and rapidity of the rocket flight attitude control system have been significantly enhanced.The advantages of the model prediction algorithm and the radial basis function neural network algorithm have been effectively integrated.
rocket projectilerudder control systembrushless DC motorballistic correctionattitude controlmodel predictive controlradial basis functionnetwork
万方数据
维普
