New results on adaptive fixed-time control for convex-delayed neural networks

Area of Science:

• Neural network dynamics
• Control theory
• Synchronization

Background:

• Neural networks often exhibit state delays impacting performance.
• Existing models may not fully capture complex delay components like switching communication.

Purpose of the Study:

• To investigate adaptive fixed-time synchronization for neural networks with convex delays.
• To develop a control strategy that accounts for multiple delay factors.
• To establish theoretical criteria for fixed-time stability.

Main Methods:

• Introduction of convex delay to model complex state delays.
• Development of a novel adaptive fixed-time control method with a unified update law.
• Application of Lyapunov stability theorem to derive stability conditions.

Main Results:

• Sufficient criteria for fixed-time stability of delayed neural networks were established.
• The proposed adaptive control method successfully determined control gains.
• Simulated examples confirmed the effectiveness of the theoretical results.

Conclusions:

• The proposed adaptive fixed-time control strategy ensures stability for convex-delayed neural networks.
• The method effectively handles multiple delay components, enhancing synchronization.
• The findings provide a robust framework for analyzing and controlling complex neural network systems.