TY  - EJOU
AU  - Hua, Lianghao 
AU  - Zhang, Jianfeng 
AU  - Li, Dejie 
AU  - Xi, aobo 

TI  - Fractional Gradient Descent RBFNN for Active Fault-Tolerant Control of Plant Protection UAVs
T2  - Computer Modeling in Engineering \& Sciences

PY  - 2024
VL  - 138
IS  - 3
SN  - 1526-1506

AB  - With the increasing prevalence of high-order systems in engineering applications, these systems often exhibit significant disturbances and can be challenging to model accurately. As a result, the active disturbance rejection controller (ADRC) has been widely applied in various fields. However, in controlling plant protection unmanned aerial vehicles (UAVs), which are typically large and subject to significant disturbances, load disturbances and the possibility of multiple actuator faults during pesticide spraying pose significant challenges. To address these issues, this paper proposes a novel fault-tolerant control method that combines a radial basis function neural network (RBFNN) with a second-order ADRC and leverages a fractional gradient descent (FGD) algorithm. We integrate the plant protection UAV model’s uncertain parameters, load disturbance parameters, and actuator fault parameters and utilize the RBFNN for system parameter identification. The resulting ADRC exhibits load disturbance suppression and fault tolerance capabilities, and our proposed active fault-tolerant control law has Lyapunov stability implications. Experimental results obtained using a multi-rotor fault-tolerant test platform demonstrate that the proposed method outperforms other control strategies regarding load disturbance suppression and fault-tolerant performance.
KW  - Radial basis function neural network; plant protection unmanned aerial vehicle; active disturbance rejection controller; fractional gradient descent algorithm

DO  - 10.32604/cmes.2023.030535