Stability analysis of time-varying delay neural networks based on new integral inequalities

Abstract This paper is concerned with the stability analysis of time-varying delay neural networks. By introducing some new delay integral terms and relaxation matrix, an augmented Lyapunov–Krasovskii functional (LKF) is constructed. In dealing with the inequality relations, a new method is proposed to deal with the integral term, which makes the inequality contain more neural network information and delay information. By solving the convergence of inequalities, the conservatism of the stability condition is improved and a more larger admissible maximum upper bounds (AMUBs) is obtained. Finally, some numerical examples are given to prove the effectiveness of the proposed method.