Machine Learning-Based L1 Adaptive Control for a Class of Chaotic Systems


Tian M. Yan S. Yedilkhan D. Zhakiyev N. Mohammadzadeh A.
2025Institute of Electrical and Electronics Engineers Inc.

IEEE Access
2025#13180218 - 180231 pp.

The stabilization of chaotic systems remains a critical research topic in control and systems theory, particularly due to the challenges introduced by model uncertainties. This study proposes a novel approach that integrates computational intelligence with the L1 adaptive control framework to effectively address these challenges. Conventional L1 adaptive control methods typically require accurate knowledge of specific parameters, which may be difficult or impractical to obtain. Furthermore, some parameters vary dynamically with system behavior, and treating them as constant can result in degraded performance. To overcome this limitation, a type-2 fuzzy neural network is employed to compute the low-pass filter parameters online and in real time. The stability of the proposed method is rigorously established through Lyapunov-based analysis. Simulation results demonstrate that the approach achieves effective and robust stabilization of chaotic systems under uncertain conditions.

adaptive control , chaotic system , estimation , stabilization , Type-2 fuzzy system

Text of the article Перейти на текст статьи

Guangdong University of Science and Technology, School of Management, Dongguan, 523083, China
Astana IT University, Smart City Research Center, Astana, 010000, Kazakhstan
Astana IT University, Department of Science and Innovation, Astana, 010000, Kazakhstan
Harvard University, Davis Center for Russian and Eurasian Studies, Cambridge, 02138, MA, United States
Astana IT University, Department of Computational and Data Science, Astana, 010000, Kazakhstan

Guangdong University of Science and Technology
Astana IT University
Astana IT University
Harvard University
Astana IT University

10 лет помогаем публиковать статьи Международный издатель

Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026