Neural network-based flight control systems: Present and future

doi:10.1016/j.arcontrol.2022.04.006

2022-01-01

Seyyed Ali Emami

Paolo Castaldi

Afshin Banazadeh *

DOI：10.1016/j.arcontrol.2022.04.006

原文链接

查看原文

摘要

En 中文

As the first review in this field, this paper presents an in-depth mathematical view of Intelligent Flight ControlSystems (IFCSs), particularly those based on artificial neural networks. The rapid evolution of IFCSs in thelast two decades in both the methodological and technical aspects necessitates a comprehensive view of themto better demonstrate the current stage and the crucial remaining steps towards developing a truly intelligentflight management unit. To this end, in this paper, we will provide a detailed mathematical view of NeuralNetwork (NN)-based flight control systems and the challenging problems that still remain. The paper willcover both the model-based and model-free IFCSs. The model-based methods consist of the basic feedbackerror learning scheme, the pseudocontrol strategy, and the neural backstepping method. Besides, differentapproaches to analyze the closed-loop stability in IFCSs, their requirements, and their limitations will bediscussed in detail. Various supplementary features, which can be integrated with a basic IFCS such as the fault-tolerance capability, the consideration of system constraints, and the combination of NNs with other robust andadaptive elements like disturbance observers, would be covered, as well. On the other hand, concerning model-free flight controllers, both the indirect and direct adaptive control systems including indirect adaptive controlusing NN-based system identification, the approximate dynamic programming using NN, and the reinforcementlearning-based adaptive optimal control will be carefully addressed. Finally, by demonstrating a well-organizedview of the current stage in the development of IFCSs, the challenging issues, which are critical to be addressedin the future, are thoroughly identified. As a result, this paper can be considered as a comprehensive roadmap for all researchers interested in the design and development of intelligent control systems, particularly inthe field of aerospace applications.

Keyword:

Flight control

Intelligent control

Neural networks

Reinforcement learning