Adaptive neural network motion control for aircraft under uncertainty conditions

2017 Workshop on Materials and Engineering in Aeronautics

材料科学;航空航天工程

Efremov, A.V.^1 ; Tiaglik, M.S.^1 ; Tiumentsev, Yu V.^1

Flight Dynamics and Control Department, Moscow Aviation Institute (National Research University), Moscow, Russia^1

关键词: Adaptive Control;    Adaptive control law;    Adaptive neural networks;    ANN modeling;    Control laws;    Control objects;    Network technologies;    Non linear control;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/312/1/012006/pdf
DOI  :  10.1088/1757-899X/312/1/012006

来源: IOP

【 摘 要 】

We need to provide motion control of modern and advanced aircraft under diverse uncertainty conditions. This problem can be solved by using adaptive control laws. We carry out an analysis of the capabilities of these laws for such adaptive systems as MRAC (Model Reference Adaptive Control) and MPC (Model Predictive Control). In the case of a nonlinear control object, the most efficient solution to the adaptive control problem is the use of neural network technologies. These technologies are suitable for the development of both a control object model and a control law for the object. The approximate nature of the ANN model was taken into account by introducing additional compensating feedback into the control system. The capabilities of adaptive control laws under uncertainty in the source data are considered. We also conduct simulations to assess the contribution of adaptivity to the behavior of the system.