It is demonstrated that neural networks can be used effectively for the identification and control of nonlinear dynamical systems. The emphasis is on models for both identification and control. Static and dynamic backpropagation methods for the adjustment of parameters are discussed. In the models that are introduced, multilayer and recurrent networks are interconnected in novel configurations, and hence there is a real need to study them in a unified fashion. Simulation results reveal that the identification and adaptive control schemes suggested are practically feasible. Basic concepts and definitions are introduced throughout, and theoretical questions that have to be addressed are also described. >

Identification and control of dynamical systems using neural networks

Networked control systems (NCSs) are spatially distributed systems for which the communication between sensors, actuators, and controllers is supported by a shared communication network. We review several recent results on estimation, analysis, and controller synthesis for NCSs. The results surveyed address channel limitations in terms of packet-rates, sampling, network delay, and packet dropouts. The results are presented in a tutorial fashion, comparing alternative methodologies

/pdf/a-survey-of-recent-results-in-networked-control-systems-2vqnhq8czm.pdf

A Survey of Recent Results in Networked Control Systems

By a switched system, we mean a hybrid dynamical system consisting of a family of continuous-time subsystems and a rule that orchestrates the switching between them. The article surveys developments in three basic problems regarding stability and design of switched systems. These problems are: stability for arbitrary switching sequences, stability for certain useful classes of switching sequences, and construction of stabilizing switching sequences. We also provide motivation for studying these problems by discussing how they arise in connection with various questions of interest in control theory and applications.

Basic problems in stability and design of switched systems

关于Semigroups of Linear Operators and Applications to Partial Differential Equations的两个注解

During the past several years, there have been increasing research activities in the field of stability analysis and switching stabilization for switched systems. This paper aims to briefly survey recent results in this field. First, the stability analysis for switched systems is reviewed. We focus on the stability analysis for switched linear systems under arbitrary switching, and we highlight necessary and sufficient conditions for asymptotic stability. After a brief review of the stability analysis under restricted switching and the multiple Lyapunov function theory, the switching stabilization problem is studied, and a variety of switching stabilization methods found in the literature are outlined. Then the switching stabilizability problem is investigated, that is under what condition it is possible to stabilize a switched system by properly designing switching control laws. Note that the switching stabilizability problem has been one of the most elusive problems in the switched systems literature. A necessary and sufficient condition for asymptotic stabilizability of switched linear systems is described here.

Stability and Stabilizability of Switched Linear Systems: A Survey of Recent Results

An investigation was conducted of the qualitative properties of a class of neural networks described by a system of first-order linear ordinary differential equations which are defined on a closed hypercube of the state space with solutions extended to the boundary of the hypercube. When solutions are located on the boundary of the hypercube, the system is said to be in a saturated mode. The class of systems considered retains the basic structure of the Hopfield model but is easier to analyze, synthesize, and implement. An efficient analysis method is developed which can be used to completely determine the set of asymptotically stable equilibrium points and the set of unstable equilibrium points. The latter set can be used to estimate the domains of attraction for the elements of the former set. A synthesis procedure that was developed previously by the authors is modified and applied to the present class of neural networks. The class of systems considered herein can easily be implemented in analog integrated circuits. >

Analysis and synthesis of a class of neuron networks: linear systems operating in saturated modes

An artificial-neural-network-based drug interaction warning system was developed for use with a computerized real-time entry medical records system. The goal of the study was to provide physicians and nurses with timely warnings of potential drug interactions as therapies were prescribed. In a dialysis unit, physicians and clinical pharmacists defined rules of proper drug therapy, then trained a neural network with those rules. When the network was used to review the therapies of this patient population, a number of inconsistencies were discovered, and medication orders were changed on several patients. Real-time implementation of this monitoring system could provide messages to assure that drug therapy is consistent and proper, according to rules created by the providers of healthcare, thus preventing occasional mistakes in drug therapy.

The training and use of an artificial neural network to monitor use of medication in treatment of complex patients.

In the implementation of artificial neural networks, several limitations are encountered which may affect their qualitative behavior and performance. These include delays, parameter perturbations and interconnection constraints. Depending on the particular type of implementation, more than one of these limitations will usually be encountered simultaneously. In the present paper, we address these issues.

Recurrent neural networks: overview and perspectives

First considers a family of nonlinear time-delay systems with uncertainties and establishes sufficient conditions for the asymptotic stability of an equilibrium for this family. The authors then apply these results to the stability analysis of a class of artificial neural networks with transmission delays. These results require the verification of the definiteness of a certain matrix or the verification of a certain inequality. The authors' results provide also a method of estimating the domain of attraction of an asymptotically stable equilibrium of the time-delay neural networks.

https://ieeexplore.ieee.org/iel3/3920/11353/00532354.pdf

Stability of nonlinear time-delay systems with parameter uncertainties with an application to neural networks

We apply the stability theory of dynamical systems presented in Chapters 3 and 4 in the analysis of an important class of discrete-event systems. We show that these discrete-event systems determine dynamical systems. We establish necessary and sufficient conditions for the uniform stability and the uniform asymptotic stability of invariant sets with respect to the class of discrete-event systems considered. We apply these results in the analysis of two specific examples, a manufacturing system and a load balancing problem in a computer network.

Anthony N. Michel

Papers

Analysis and synthesis of a class of neuron networks: linear systems operating in saturated modes

The training and use of an artificial neural network to monitor use of medication in treatment of complex patients.

Recurrent neural networks: overview and perspectives

Stability of nonlinear time-delay systems with parameter uncertainties with an application to neural networks

Applications to a Class of Discrete-Event Systems