四旋翼无人机的主动容错控制

Active Fault Tolerant Control of Quadrotor UAV

针对四旋翼无人机PID控制器参数通过经验试凑难以获得最优和执行器部分失效问题,提出了基于PID控制器参数优化的容错控制器设计方法。首先利用遗传算法离线优化PID参数,然后引入故障补偿机制,设计5个基于区间故障的容错控制器,使其可以通过深度置信网络和softmax对故障进行区间分类来调用相应的控制器,对故障进行容错处理。最后,在Matlab实验平台上对所提方法的可行性和有效性进行仿真验证,结果表明提出的方法可以明显改善四旋翼无人机的飞行效果及对故障的处理能力。

Aiming at the problem that the parameters of the four-rotor UAV PID controller are difficult to obtain optimal and the partial failure of the actuator,the design of the fault-tolerant controller based on the parameter optimization of the PID controller is proposed. Firstly,the genetic algorithm is used to optimize the PID parameters offline,and then the fault compensation mechanism is introduced to design five similar passive fault-tolerant controllers,so that the fault can be classified by DBN and softmax to call the corresponding controller,and fault-tolerant processing is performed. Finally,the feasibility and effectiveness of the proposed method are verified by the matlab experimental platform. The results show that the proposed method can significantly improve the flight effect and fault handling ability of the quadrotor UAV.