Premium
Finite‐time reliable dissipative control of neutral‐type switched artificial neural networks with non‐linear fault inputs and randomly occurring uncertainties
Author(s) -
Saravanakumar Thangavel,
Nirmala Veerappan Jayakannu,
Raja Ramachandran,
Cao Jinde,
Lu Guoping
Publication year - 2020
Publication title -
asian journal of control
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.769
H-Index - 53
eISSN - 1934-6093
pISSN - 1561-8625
DOI - 10.1002/asjc.2252
Subject(s) - dissipative system , control theory (sociology) , artificial neural network , mathematics , bernoulli distribution , linear matrix inequality , dwell time , lyapunov stability , matlab , stability (learning theory) , actuator , computer science , mathematical optimization , control (management) , random variable , physics , artificial intelligence , medicine , clinical psychology , statistics , quantum mechanics , machine learning , operating system
This work reports the result of finite‐time reliable dissipative control for switched neutral‐type based neural networks subject to input nonlinearities, time‐delay and randomly occurring perturbations. In particular, a novel control model consist of both linear and non‐linear fault inputs is designed for reliable control. In addition, randomly occurring uncertainty caused by stochastic variables satisfying the Bernoulli distribution is considered. Based on Lyapunov stability theory, Jensen's integral inequality technique and average dwell time method, sufficient criteria for finite‐time boundedness of resulting neural networks are obtained. Furthermore, the obtained boundedness theory are enhanced to solve the finite‐time dissipative problem of the considered systems through reliable control against mixed actuator failures. The obtained sufficient conditions are constructed in the form of linear matrix inequalities, which can be facilitated by using some standard numerical Matlab packages. At last, numerical simulations are presented to demonstrate the effectiveness of the considered theory.