Huang Zhengguo, Chen Mou, Shi Peng, Shen Hao
IEEE Trans Neural Netw Learn Syst. 2025 Jun;36(6):11520-11533. doi: 10.1109/TNNLS.2024.3477745.
The adaptive neural network (NN) control for the fixed-wing unmanned aerial vehicle (FUAV) under the unmodeled dynamics and the time-varying switching disturbance (TVSD) is investigated in this article. To better describe the TVSD induced by the change in the flight area of the FUAV, a switching augmented model (SAM) based on the known information about the TVSD is proposed first. The parameter adaptation technique is used to estimate the related TVSD. Thereafter, the time-varying disturbance that cannot be described by the SAM is estimated by the disturbance observer (DO). The radial basis function NN (RBFNN) is adopted to approximate the unknown unmodeled dynamics. The coupling terms derived from the co-design of DO and the parameter adaptation (PA) are separated by some inequality techniques. Then, the separated unknown terms are eliminated by designing the parameters of the controller and that of the adaptive law. The separated known terms are tackled by adding robust control terms to the controller. In addition, to improve the estimation performance for the TVSD and RBFNN, the auxiliary system in the DO form is designed. Sufficient stable conditions about the closed-loop switched system (CLSS) are obtained with and without the inequality about the switching times. Finally, an illustrative example is given to show the feasibility and advantage of the proposed control strategy by the attitude model of the FUAV.
本文研究了固定翼无人机（FUAV）在未建模动态和时变切换干扰（TVSD）下的自适应神经网络（NN）控制。为了更好地描述由FUAV飞行区域变化引起的TVSD，首先基于关于TVSD的已知信息提出了一种切换增强模型（SAM）。采用参数自适应技术来估计相关的TVSD。此后，由干扰观测器（DO）估计SAM无法描述的时变干扰。采用径向基函数神经网络（RBFNN）来逼近未知的未建模动态。通过一些不等式技术分离由DO和参数自适应（PA）协同设计产生的耦合项。然后，通过设计控制器参数和自适应律参数来消除分离出的未知项。通过向控制器添加鲁棒控制项来处理分离出的已知项。此外，为了提高对TVSD和RBFNN的估计性能，设计了DO形式的辅助系统。在有和没有关于切换次数的不等式的情况下，都获得了关于闭环切换系统（CLSS）的充分稳定条件。最后，通过FUAV的姿态模型给出了一个说明性例子，以展示所提出控制策略的可行性和优势。
