Feedback Control of Dynamic Artificial Neural Networks Using Linear Matrix Inequalities

2020 ◽  
Author(s):  
Anastasia Nikolakopoulou ◽  
Moo Sun Hong ◽  
Richard D. Braatz
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Feedback Control ◽  
Linear Matrix Inequalities ◽  
Linear Matrix ◽  
Matrix Inequalities ◽  
Artificial Neural

AUTOASSOCIATIVE MEMORY DESIGN USING INTERCONNECTED GENERALIZED BRAIN-STATE-IN-A-BOX NEURAL NETWORKS

2005 ◽  
Vol 15 (03) ◽  
pp. 181-196 ◽  
Author(s):  
CHEOLHWAN OH ◽  
STANISLAW H. ŻAK ◽  
GUISHENG ZHAI
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Linear Matrix Inequalities ◽  
Linear Matrix ◽  
Brain State ◽  
Stability Conditions ◽  
Network Architectures ◽  
Associative Memories ◽  
Matrix Inequalities ◽  
Memory Design

A class of interconnected neural networks composed of generalized Brain-State-in-a-Box (gBSB) neural subnetworks is considered. Interconnected gBSB neural network architectures are proposed along with their stability conditions. The design of the interconnected neural networks is reduced to the problem of solving linear matrix inequalities (LMIs) to determine the interconnection parameters. A method for solving LMIs is devised generating the solutions that, in general, are further away from zero than the corresponding solutions obtained using MATLAB's LMI toolbox, thus resulting in stronger interconnections between the subnetworks. The proposed architectures are then used to construct neural associative memories. Simulations are performed to illustrate the results obtained.

Synchronization of delayed neural networks with hybrid coupling via impulsive control

2019 ◽  
Vol 41 (13) ◽  
pp. 3714-3724 ◽  
Author(s):  
Tianhu Yu ◽  
Huamin Wang ◽  
Dengqing Cao
Keyword(s):  
Neural Networks ◽  
Linear Matrix Inequalities ◽  
Upper Bound ◽  
Hybrid Control ◽  
Impulsive Control ◽  
Distributed Delay ◽  
Linear Matrix ◽  
Matrix Inequalities ◽  
Delayed Neural Networks ◽  
Coupled Neural Networks

The synchronization problem of coupled neural networks via impulsive control is investigated in the present paper. Based on a time varying Lyapunov functional associated with the impulsive time sequence, the delay-dependent criteria in terms of linear matrix inequalities are derived to guarantee the synchronization of the coupled neural networks. The obtained criteria are closely related to both the lower and the upper bound of the adjacent impulsive instant difference. By solving the corresponding linear matrix inequalities, the synchronization criteria can be used to estimate the upper bound of both transmission delay and distributed-delay. The low-dimensional criteria also are obtained for the coupled neural networks with identical nodes. Finally, two examples are given to illustrate the validity of the proposed hybrid control.

Stability Analyses of Neural Networks with Unbounded Time-Varying Delays and Nonlinear Perturbations

2013 ◽  
Vol 278-280 ◽  
pp. 1247-1250 ◽  
Author(s):  
Li Zi Yin
Keyword(s):  
Neural Networks ◽  
Linear Matrix Inequalities ◽  
Functional Method ◽  
Neural Systems ◽  
Linear Matrix ◽  
Time Varying ◽  
Nonlinear Perturbations ◽  
Matrix Inequalities ◽  
Stability Analyses

In this paper, we consider the problem of mu-stability of unbounded time-varying delays neural systems with nonlinear perturbations. Some mu-stability criterias are derived by using Lyapunov- Krasovski functional method . Those criteria are expressed in the form of linear matrix inequalities (LMIs).

Continuous-Time Feedback Control With Finite-Time Boundedness and H∞ Performance Criteria

2015 ◽  
Author(s):  
Jacob D. Hostettler ◽  
Xin Wang
Keyword(s):  
Feedback Control ◽  
Linear Matrix Inequalities ◽  
Finite Time ◽  
Control Method ◽  
Sufficient Conditions ◽  
State Feedback Control ◽  
Performance Criteria ◽  
Linear Matrix ◽  
Matrix Inequalities ◽  
Finite Time Boundedness

For advanced control applications, research into the use of linear matrix inequalities has yielded a notable amount of work in the area of nonlinear systems. Linear Matrix Inequalities can be formed through the application of desired performance criteria to a general system. By proper selection of a Lyapunov energy function, sufficient conditions to satisfy the performance objectives can be realized. The performance criteria, typically chosen for the application, define the objectives associated with the control. This work presents a control method for discrete-time systems with finite-time boundedness and H∞ performance criteria. The design of the controller corresponds to a system existing with bounded model uncertainties, and in the presence of L2 type external disturbances. Through the use of a linear state feedback control, sufficient conditions which guarantee the finite-time stability and H∞ performance objectives are achieved via the solution of a Linear Matrix Inequality. MATLAB application and simulation is carried out using the field oriented control of a permanent magnet synchronous generator in order to effectively demonstrate the effectiveness of this control strategy in the wind energy conversion system application.

Artificial neural networks for feedback control of a human elbow hydraulic prosthesis

2014 ◽  
Vol 137 ◽  
pp. 3-11 ◽  
Author(s):  
Vitoantonio Bevilacqua ◽  
Mariagrazia Dotoli ◽  
Mario Massimo Foglia ◽  
Francesco Acciani ◽  
Giacomo Tattoli ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Feedback Control ◽  
Artificial Neural

scholarly journals New Results on Passivity for Discrete-Time Stochastic Neural Networks with Time-Varying Delays

2015 ◽  
Vol 2015 ◽  
pp. 1-10
Author(s):  
Wei Kang ◽  
Jun Cheng ◽  
Xiangyang Cheng
Keyword(s):  
Neural Networks ◽  
Linear Matrix Inequalities ◽  
Discrete Time ◽  
Linear Matrix ◽  
Stochastic Neural Networks ◽  
Time Varying ◽  
Matrix Inequalities ◽  
Numerical Examples ◽  
Passivity Analysis ◽  
Delay Dependent

The problem of passivity analysis for discrete-time stochastic neural networks with time-varying delays is investigated in this paper. New delay-dependent passivity conditions are obtained in terms of linear matrix inequalities. Less conservative conditions are obtained by using integral inequalities to aid in the achievement of criteria ensuring the positiveness of the Lyapunov-Krasovskii functional. At last, numerical examples are given to show the effectiveness of the proposed method.

Sign in / Sign up

Export Citation Format

Share Document