New delay-dependent stability criteria for neural networks with two additive time-varying delay components

Area of Science:

• Control Theory
• Computational Neuroscience
• Systems Engineering

Background:

• Neural networks are crucial in various applications, but their stability analysis is complicated by time-varying delays.
• Ensuring the stability of neural networks with multiple time delays is a significant challenge in control theory.

Purpose of the Study:

• To develop novel delay-dependent stability criteria for neural networks with two additive time-varying delays.
• To reduce the conservatism of existing stability analysis methods for neural networks.

Main Methods:

• Construction of a new Lyapunov functional tailored for systems with multiple time-varying delays.
• Application of the convex polyhedron method to accurately estimate the derivative of the Lyapunov functional.
• Derivation of new stability criteria based on the developed Lyapunov functional and estimation method.

Main Results:

• The proposed stability criteria are demonstrated to be less conservative than existing criteria.
• A specific example illustrates the reduced conservatism and improved efficacy of the new stability results.
• The derived criteria provide a more accurate assessment of neural network stability under time-varying delays.

Conclusions:

• The novel approach offers enhanced stability analysis for neural networks with complex delay structures.
• The findings contribute to the design and reliable operation of neural network-based systems.
• This work provides a valuable tool for researchers and engineers dealing with stability in time-delay systems.