Adaptive optimal controller design for a class of LDI-based neural network systems with input time-delays

2020 ◽  
Vol 385 ◽  
pp. 292-299 ◽  
Author(s):  
Chenglong Wang ◽  
Haiyang Fang ◽  
Shuping He
2003 ◽  
Vol 13 (03) ◽  
pp. 193-204 ◽  
Author(s):  
Wenlian Lu ◽  
Libin Rong ◽  
Tianping Chen

In this paper, without assuming the boundedness, strict monotonicity and differentiability of the activation functions, we utilize a new Lyapunov function to analyze the global convergence of a class of neural networks models with time delays. A new sufficient condition guaranteeing the existence, uniqueness and global exponential stability of the equilibrium point is derived. This stability criterion imposes constraints on the feedback matrices independently of the delay parameters. The result is compared with some previous works. Furthermore, the condition may be less restrictive in the case that the activation functions are hyperbolic tangent.


2014 ◽  
Vol 351 (3) ◽  
pp. 1205-1225 ◽  
Author(s):  
Xianlin Zeng ◽  
Qing Hui ◽  
Wassim M. Haddad ◽  
Tomohisa Hayakawa ◽  
James M. Bailey

2017 ◽  
Vol 40 (7) ◽  
pp. 2408-2415 ◽  
Author(s):  
Liang Liu ◽  
Shengyuan Xu ◽  
Xuejun Xie ◽  
Bing Xiao

Based on stochastic time-delay system stability criterion and a homogeneous domination approach, the output-feedback stabilization problem for a class of more general stochastic upper-triangular systems with state and input time-delays has been solved in this paper. Firstly, the initial system is changed into an equivalent one with a designed scalar by introducing a set of coordinate transformations. After that, by designing an implementable homogeneous reduced-order observer, and tactfully selecting a suitable Lyapunov–Krasoviskii functional and a low gain scale, a delay-independent output-feedback controller is explicitly constructed. Finally, the globally asymptotically stability in probability of the closed-loop system is ensured by rigorous proof. The simulation results demonstrate the efficiency of the proposed design scheme.


Sign in / Sign up

Export Citation Format

Share Document