In order to ensure the flight safety of small unmanned aerial vehicles (UAVs), a deep neural network-fused mathematical modeling approach is put up for reliable flight control of small UAVs. First, engine torque, thrust eccentricity and initial stop angle are taken into full consideration. A six-degree-of-freedom nonlinear model is formulated for small UAVs, concerning both ground taxiing and air flight status. Then, the model was linearized using the principle of small disturbances. The linearized model expressions for both ground taxiing and air flight were provided. In addition, radial basis function neural networks are used for online approximation to address the nonlinearity and uncertainty caused by changes in aircraft aerodynamic parameters. At the same time, to compensate for the external disturbance and the approximation error of the neural network, the system robustness is improved by selecting reasonable design parameters. This helps the whole flight control system obtain better tracking control performance. At last, some simulation experiments are carried out to evaluate the performance of the proposed mathematical modeling framework. The simulation results show that the proposal has stronger convergence ability, smaller prediction error, and better performance. Thus, proper proactivity can be acknowledged.

为了保证小型无人机的飞行安全，提出了一种融合深度神经网络的数学建模方法，对小型无人机进行可靠的飞行控制。首先，充分考虑发动机扭矩、推力偏心率和初停角。针对小型无人机，建立了涉及地面滑行和空中飞行状态的六自由度非线性模型。然后，利用小扰动原理对模型进行线性化。提供了地面滑行和空中飞行的线性化模型表达式。此外，利用径向基函数神经网络进行在线逼近，解决飞机气动参数变化带来的非线性和不确定性。同时，为了补偿外界干扰和神经网络的逼近误差，通过选择合理的设计参数来提高系统的鲁棒性。这有助于整个飞行控制系统获得更好的跟踪控制性能。最后，进行了一些仿真实验来评估所提出的数学建模框架的性能。仿真结果表明该方案具有更强的收敛能力、更小的预测误差和更好的性能。因此，适当的主动性可以得到认可。