CAJ | 학술논문

针对四旋翼飞行器的非线性控制问题，提出了一种分散PID神经元网络（PIDNN）控制方法。首先通过牛顿-欧拉方程建立了四旋翼飞行器的动力学模型。其次，提出了一种嵌套控制器，内环基于分散PIDNN方法以实现姿态控制，外环采用经典的PID控制方法，PIDNN控制器的在线学习通过误差反向传播法实现。搭建了自主研制的四旋翼飞行器系统，并通过实验的方式研究了控制器的控制性能。实验结果表明控制器具有较强的控制稳定性、机动性和鲁棒性。
침대사선익비행기적비선성공제문제，제출료일충분산PID신경원망락（PIDNN）공제방법。수선통과우돈-구랍방정건립료사선익비행기적동역학모형。기차，제출료일충감투공제기，내배기우분산PIDNN방법이실현자태공제，외배채용경전적PID공제방법，PIDNN공제기적재선학습통과오차반향전파법실현。탑건료자주연제적사선익비행기계통，병통과실험적방식연구료공제기적공제성능。실험결과표명공제기구유교강적공제은정성、궤동성화로봉성。
A decentralized PID neural network(PIDNN) control scheme is proposed to solve the nonlinear control problems in quadrotor helicopter. First, the dynamic model is established via Newton-Euler formalism. Then, a nested loop control approach is proposed to solve the stabilization and navigation problems in the quadrotor. A decentralized PIDNN controller is designed for the inner loop to stabilize the attitude angle. A conventional PID controller is used for the outer loop in order to generate the reference path for the inner loop. Moreover, the connective weights of the PIDNN are trained on-line by error back-propagation method. The experiment is made to study the performance of controller based on the independently developed quadrotor helicopter system, which shows that the controller has good stability, maneuverability and robustness.