H∞ control of memristive neural networks with aperiodic sampling and actuator saturation

The H_∞ control problem for memristive neural networks with aperiodic sampling and actuator saturation is considered in this paper. A novel approach that is combined with the discrete‐time Lyapunov theorem and sampled‐data system is proposed to cope with the aperiodic sampling problem. On the basis of such method and choosing a polyhedral set, sufficient conditions to determine the ellipsoidal region of asymptotic stability and exponential stability for the estimation error system are obtained through a saturating sampled‐data control. Furthermore, H_∞ performance index of memristive neural networks with disturbance is also analyzed, whereas the observer and controller gains are calculated from stability conditions of linear matrix inequalities. Finally, the effectiveness of the theoretical results is illustrated through the numerical examples.     

State estimation for delayed neural networks

In this letter, the state estimation problem is studied for neural networks with time-varying delays. The interconnection matrix and the activation functions are assumed to be norm-bounded. The problem addressed is to estimate the neuron states, through available output measurements, such that for all admissible time-delays, the dynamics of the estimation error is globally exponentially stable. An effective linear matrix inequality approach is developed to solve the neuron state estimation problem. In particular, we derive the conditions for the existence of the desired estimators for the delayed neural networks. We also parameterize the explicit expression of the set of desired estimators in terms of linear matrix inequalities (LMIs). Finally, it is shown that the main results can be easily extended to cope with the traditional stability analysis problem for delayed neural networks. Numerical examples are included to illustrate the applicability of the proposed design method.     

State Estimation for Discrete-Time Neural Networks with Markov-Mode-Dependent Lower and Upper Bounds on the Distributed Delays

This paper is concerned with the state estimation problem for a new class of discrete-time neural networks with Markovian jumping parameters and mixed time-delays. The parameters of the neural networks under consideration switch over time subject to a Markov chain. The networks involve both the discrete-time-varying delay and the mode-dependent distributed time-delay characterized by the upper and lower boundaries dependent on the Markov chain. By constructing novel Lyapunov-Krasovskii functionals, sufficient conditions are firstly established to guarantee the exponential stability in mean square for the addressed discrete-time neural networks with Markovian jumping parameters and mixed time-delays. Then, the state estimation problem is coped with for the same neural network where the goal is to design a desired state estimator such that the estimation error approaches zero exponentially in mean square. The derived conditions for both the stability and the existence of desired estimators are expressed in the form of matrix inequalities that can be solved by the semi-definite programme method. A numerical simulation example is exploited to demonstrate the usefulness of the main results obtained.     

Exponential stability of impulsive high-order Hopfield-type neural networks with delays and reaction–diffusion

The problem of global exponential stability analysis of Impulsive high-order Hopfield-type neural networks with time-varying delays and reaction–diffusion terms has been investigated in this paper. Using the Lyapunov function method and M-matrix theory, we establish the global exponential stability of the neural networks with its estimated exponential convergence rate. As an illustration, a numerical example is given using the results.     

Estimation of rotor angles of synchronous machines using artificial neural networks and local PMU-based quantities

This paper investigates a possibility for estimating rotor angles in the time frame of transient (angle) stability of electric power systems, for use in real-time. The proposed dynamic state estimation technique is based on the use of voltage and current phasors obtained from a phasor measurement unit supposed to be installed on the extra-high voltage side of the substation of a power plant, together with a multilayer perceptron trained off-line from simulations. We demonstrate that an intuitive approach to directly map phasor measurement inputs to the neural network to generator rotor angle does not offer satisfactory results. We found out that a good way to approach the angle estimation problem is to use two neural networks in order to estimate the sin(δ) and cos(δ) of the angle and recover the latter from these values by simple post-processing.Simulation results on a part of the Mexican interconnected system show that the approach could yield satisfactory accuracy for real-time monitoring and control of transient instability.     

Neural networks and the inverse kinematics problem

Inverse kinematics is a fundamental problem in robotics. Past solutions for this problem have been realized through the use of various algebraic or algorithmic procedures. In this paper the use of feedforward neural networks to solve the inverse kinematics problem is examined for three different cases. A closed kinematic linkage is used for mapping input joint angles to output joint angles. A three-degree-of-freedom manipulator in 3D space is used to test mappings from both cartesian and spherical coordinates to manipulator joint coordinates. A majority of the results have average errors which fall below 1% of the robot workspace. The accuracy indicates that neural networks are an alternate method for performing the inverse kinematics estimation, thus introducing the fault-tolerant and high-speed advantages of neural networks to the inverse kinematics problem.This paper also shows the use of a new technique which reduces neural network mapping errors with the use of error compensation networks. The results of the work are put in perspective with a survey of current applications of neural networks in robotics.     

An ISS-modular approach for adaptive neural control of pure-feedback systems

Controlling non-affine non-linear systems is a challenging problem in control theory. In this paper, we consider adaptive neural control of a completely non-affine pure-feedback system using radial basis function (RBF) neural networks (NN). An ISS-modular approach is presented by combining adaptive neural design with the backstepping method, input-to-state stability (ISS) analysis and the small-gain theorem. The difficulty in controlling the non-affine pure-feedback system is overcome by achieving the so-called “ISS-modularity” of the controller-estimator. Specifically, a neural controller is designed to achieve ISS for the state error subsystem with respect to the neural weight estimation errors, and a neural weight estimator is designed to achieve ISS for the weight estimation subsystem with respect to the system state errors. The stability of the entire closed-loop system is guaranteed by the small-gain theorem. The ISS-modular approach provides an effective way for controlling non-affine non-linear systems. Simulation studies are included to demonstrate the effectiveness of the proposed approach.     

Global asymptotic stability of delay BAM neural networks with impulses via nonsmooth analysis

In this paper, we study global asymptotic stability of delay bi-directional associative memory (BAM) neural networks with impulses. We obtain a sufficient condition of ensuring existence and uniqueness of equilibrium point for delay BAM neural networks with impulses basing on nonsmooth analysis. And we give a criteria of global asymptotic stability of the unique equilibrium point for delay BAM neural networks with impulses using Lyapunov method. At last, we present examples to illustrate that our results are feasible.     

Robust Control of Uncertain Stochastic Recurrent Neural Networks with Time-varying Delay

In this paper, robust control of uncertain stochastic recurrent neural networks with time-varying delay is considered. A novel control method is given by using the Lyapunov functional method and linear matrix inequality (LMI) approach. Several delay-independent and delay-dependent sufficient conditions are then further derived to ensure the global asymptotical stability in mean square for the uncertain stochastic recurrent neural networks, and the estimation gains can also be obtained. Numerical examples are constructed to verify the theoretical analysis in this paper.     

Hopfield Neural Networks for Parametric Identification of Dynamical Systems

In this work, a novel method, based upon Hopfield neural networks, is proposed for parameter estimation, in the context of system identification. The equation of the neural estimator stems from the applicability of Hopfield networks to optimization problems, but the weights and the biases of the resulting network are time-varying, since the target function also varies with time. Hence the stability of the method cannot be taken for granted. In order to compare the novel technique and the classical gradient method, simulations have been carried out for a linearly parameterized system, and results show that the Hopfield network is more efficient than the gradient estimator, obtaining lower error and less oscillations. Thus the neural method is validated as an on-line estimator of the time-varying parameters appearing in the model of a nonlinear physical system.     

Dealing with missing values in neural network-based diagnostic systems

Backpropagation neural networks have been applied to prediction and classification problems in many real world situations. However, a drawback of this type of neural network is that it requires a full set of input data, and real world data is seldom complete. We have investigated two ways of dealing with incomplete data — network reduction using multiple neural network classifiers, and value substitution using estimated values from predictor networks — and compared their performance with an induction method. On a thyroid disease database collected in a clinical situation, we found that the network reduction method was superior. We conclude that network reduction can be a useful method for dealing with missing values in diagnostic systems based on backpropagation neural networks.     

Pruning recurrent neural networks for improved generalizationperformance

Determining the architecture of a neural network is an important issue for any learning task. For recurrent neural networks no general methods exist that permit the estimation of the number of layers of hidden neurons, the size of layers or the number of weights. We present a simple pruning heuristic that significantly improves the generalization performance of trained recurrent networks. We illustrate this heuristic by training a fully recurrent neural network on positive and negative strings of a regular grammar. We also show that rules extracted from networks trained with this pruning heuristic are more consistent with the rules to be learned. This performance improvement is obtained by pruning and retraining the networks. Simulations are shown for training and pruning a recurrent neural net on strings generated by two regular grammars, a randomly-generated 10-state grammar and an 8-state, triple-parity grammar. Further simulations indicate that this pruning method can have generalization performance superior to that obtained by training with weight decay.     

Estimate of exponential convergence rate and exponential stabilityfor neural networks

Estimates of exponential convergence rate and exponential stability are studied for a class of neural networks which includes Hopfield neural networks and cellular neural networks. Both local and global exponential convergence are discussed. Theorems for estimation of the exponential convergence rate are established and the bounds on the rate of convergence are given. The domains of attraction in the case of local exponential convergence are obtained. Simple conditions are presented for checking exponential stability of the neural networks.     

Decentralised adaptive neural connectively finite-time control for a class of p-normal form large-scale nonlinear systems

ABSTRACT

This paper focuses on the decentralised adaptive finite-time connective stabilisation problem for a class of p-normal form large-scale nonlinear systems at the first. By combining the adding a power integrator technique, the neural network technique and the finite-time Lyapunov stability theory, the decentralised adaptive neural finite-time controllers are designed, which can guarantee the large-scale system is finite-time connectively stable. In order to avoid the effect of neural network estimation error on satisfying the finite-time criteria, the combination vectors are composed by the weights and the estimation errors of the neural networks. The maximal upper bounds of the combination vector norms are taken as the adaptive parameters. Because of employing neural networks, the restriction of the unknown nonlinear terms in some literature about finite-time control is relaxed. Two simulation examples are provided to prove the effectiveness and advantage of the proposed control method.     

Some extensions of a new method to analyze complete stability of neural networks

In a recent work, a new method has been introduced to analyze complete stability of the standard symmetric cellular neural networks (CNNs), which are characterized by local interconnections and neuron activations modeled by a three-segment piecewise-linear (PWL) function. By complete stability it is meant that each trajectory of the neural network converges toward an equilibrium point. The goal of this paper is to extend that method in order to address complete stability of the much wider class of symmetric neural networks with an additive interconnecting structure where the neuron activations are general PWL functions with an arbitrary number of straight segments. The main result obtained is that complete stability holds for any choice of the parameters within the class of symmetric additive neural networks with PWL neuron activations, i.e., such a class of neural networks enjoys the important property of absolute stability of global pattern formation. It is worth pointing out that complete stability is proved for generic situations where the neural network has finitely many (isolated) equilibrium points, as well as for degenerate situations where there are infinite (nonisolated) equilibrium points. The extension in this paper is of practical importance since it includes neural networks useful to solve significant signal processing tasks (e.g., neural networks with multilevel neuron activations). It is of theoretical interest too, due to the possibility of approximating any continuous function (e.g., a sigmoidal function), using PWL functions. The results in this paper confirm the advantages of the method of Forti and Tesi, with respect to LaSalle approach, to address complete stability of PWL neural networks.     

Stochastic stability of uncertain fuzzy recurrent neural networks with Markovian jumping parameters

In this paper, the global robust stability of uncertain recurrent neural networks with Markovian jumping parameters which are represented by the Takagi–Sugeno fuzzy model is considered. A novel linear matrix inequality-based stability criterion is obtained by using Lyapunov functional theory to guarantee the asymptotic stability of uncertain fuzzy recurrent neural networks with Markovian jumping parameters. Finally, numerical examples are given to demonstrate the correctness of the theoretical results. Our results are also compared with results discussed in Arik [On the global asymptotic stability of delayed cellular neural networks, IEEE Trans. Circ. Syst. I 47 (2000), pp. 571–574], Cao [Global stability conditions for delayed CNNs, IEEE Trans. Circ. Syst. I 48 (2001), pp. 1330–1333] and Lou and Cui [Delay-dependent stochastic stability of delayed Hopfield neural networks with Markovian jump parameters, J. Math. Anal. Appl. 328 (2007), pp. 316–326] to show the effectiveness and conservativeness.     

A supervised Actor–Critic approach for adaptive cruise control

A novel supervised Actor–Critic (SAC) approach for adaptive cruise control (ACC) problem is proposed in this paper. The key elements required by the SAC algorithm namely Actor and Critic, are approximated by feed-forward neural networks respectively. The output of Actor and the state are input to Critic to approximate the performance index function. A Lyapunov stability analysis approach has been presented to prove the uniformly ultimate bounded property of the estimation errors of the neural networks. Moreover, we use the supervisory controller to pre-train Actor to achieve a basic control policy, which can improve the training convergence and success rate. We apply this method to learn an approximate optimal control policy for the ACC problem. Experimental results in several driving scenarios demonstrate that the SAC algorithm performs well, so it is feasible and effective for the ACC problem.     

Robust Stability in Cohen–Grossberg Neural Network with both Time-Varying and Distributed Delays

In this article, the global exponential robust stability is investigated for Cohen–Grossberg neural network with both time-varying and distributed delays. The parameter uncertainties are assumed to be time-invariant and bounded, and belong to given compact sets. Applying the idea of vector Lyapunov function, M-matrix theory and analysis techniques, several sufficient conditions are obtained to ensure the existence, uniqueness, and global exponential robust stability of the equilibrium point for the neural network. The methodology developed in this article is shown to be simple and effective for the exponential robust stability analysis of neural networks with time-varying delays and distributed delays. The results obtained in this article extend and improve a few recently known results and remove some restrictions on the neural networks. Three examples are given to show the usefulness of the obtained results that are less restrictive than recently known criteria.      

Guided Neural Network Learning Using a Fuzzy Controller,with Applications to Textile Spinning

We apply neural networks to build a metamodel of the relation between key input parameters and output performance measures of a simulated textile spinning plant. We investigate two different neural network estimation algorithms, namely back-propagation and an algorithm incorporating a fuzzy controller for the learning rate. According to our experience, both algorithms are capable of providing high-quality predictions. In addition, results obtained using a fuzzy controller for the learning rate suggest a significant potential for speeding up the training process.     

Globally Exponential Stability for Delayed Neural Networks Under Impulsive Control

In this paper, the dynamic behaviors of a class of neural networks with time-varying delays are investigated. Some less weak sufficient conditions based on p-norm and ∞-norm are obtained to guarantee the existence, uniqueness of the equilibrium point for the addressed neural networks without impulsive control by applying homeomorphism theory. And then, by utilizing inequality technique, Lyapunov functional method and the analysis method, some new and useful criteria of the globally exponential stability with respect to the equilibrium point under impulsive control we assumed are derived based on p-norm and ∞-norm, respectively. Finally, an example with simulation is given to show the effectiveness of the obtained results.