Finite-Time State Estimation for Recurrent Delayed Neural Networks With Component-Based Event-Triggering Protocol

Sampled-Data State Estimation for LSTM

This article first introduces a sampled-data state estimator design method for continuous-time long short-term memory (LSTM) neural networks with irregularly sampled output. To this end, the structure of the LSTM is addressed to obtain its dynamic equation. As a result, the LSTM neural network is modeled as a continuous-time linear parameter-varying system that is dependent on the gate units. For this system, the sampled-data Luenberger- and Arcak-type state estimator design methods are presented in terms of linear matrix inequalities (LMIs) by using the properties of the gate units. Lastly, the proposed method not only provides a numerical example for analyzing absolute stability but also demonstrates it in practice by applying a pre-trained behavior generation model of a robot manipulator.

Design, Analysis, and Application of a Discrete Error Redefinition Neural Network for Time-Varying Quadratic Programming

Time-varying quadratic programming (TV-QP) is widely used in artificial intelligence, robotics, and many other fields. To solve this important problem, a novel discrete error redefinition neural network (D-ERNN) is proposed. By redefining the error monitoring function and discretization, the proposed neural network is superior to some traditional neural networks in terms of convergence speed, robustness, and overshoot. Compared with the continuous ERNN, the proposed discrete neural network is more suitable for computer implementation. Unlike continuous neural networks, this article also analyzes and proves how to select the parameters and step size of the proposed neural networks to ensure the reliability of the network. Moreover, how to achieve the discretization of the ERNN is presented and discussed. The convergence of the proposed neural network without disturbance is proven, and bounded time-varying disturbances can be resisted in theory. Furthermore, the comparison results with other related neural networks show that the proposed D-ERNN has a faster convergence speed, better antidisturbance ability, and lower overshoot.

Partial-Neurons-Based Proportional-Integral Observer Design for Artificial Neural Networks: A Multiple Description Encoding Scheme

This article is concerned with a new partial-neurons-based proportional-integral observer (PIO) design problem for a class of artificial neural networks (ANNs) subject to bounded disturbances. For the purpose of improving the reliability of the data transmission, the multiple description encoding mechanisms are exploited to encode the measurement data into two identically important descriptions, and the encoded data are then transmitted to the decoders via two individual communication channels susceptible to packet dropouts, where Bernoulli-distributed stochastic variables are utilized to characterize the random occurrence of the packet dropouts. An explicit relationship is discovered that quantifies the influences of the packet dropouts on the decoding accuracy, and a sufficient condition is provided to assess the boundedness of the estimation error dynamics. Furthermore, the desired PIO parameters are calculated by solving two optimization problems based on two metrics (i.e., the smallest ultimate bound and the fastest decay rate) characterizing the estimation performance. Finally, the applicability and advantage of the proposed PIO design strategy are verified by means of an illustrative example.

Convex Temporal Convolutional Network-Based Distributed Cooperative Learning Control for Multiagent Systems

Due to its great efficiency, scalability, and inclusivity, distributed cooperative learning control has gotten a lot of attention. For complex uncertain multiagent systems, it is challenging to model the uncertainties and exploit the cooperative learning ability of the systems. To address these issues, we proposed a novel convex temporal convolutional network-based distributed cooperative learning control for uncertain discrete-time nonlinear multiagent systems. A new concept of using a convex temporal convolutional network (CTCNet) is proposed for estimating the uncertain agent dynamics in a cooperative way. Unlike previous methods that require adjustment of network weights for different control tasks, the proposed CTCNet can map the high-dimensional input-output space into a deep space spanned by basis features that represent the inherent properties of the system, so it has good robustness for different tasks. Consequently, to improve the control performance, a CTCNet-based distributed cooperative learning control method that shares learned knowledge through the communication topology among adaptive laws of CTCNet is proposed. Furthermore, the asymptotic convergence of system tracking errors to an arbitrarily small neighborhood of the origin is strictly proved. Finally, the simulation results are given to illustrate that our suggested method has higher control accuracy, stronger robustness, and anti-interference ability than the existing methods.

Adaptive Neural Event-Triggered Control of Networked Markov Jump Systems Under Hybrid Cyberattacks

This article is concerned with the neural network (NN)-based event-triggered control problem for discrete-time networked Markov jump systems with hybrid cyberattacks and unmeasured states. The event-triggered mechanism (ETM) is used to reduce the communication load, and a Luenberger observer is introduced to estimate the unmeasured states. Two kinds of cyberattacks, denial-of-service (DoS) attacks and deception attacks, are investigated due to the vulnerability of cyberlayer. For the sake of mitigating the impact of these two types of cyberattacks on system performance, the ETM under DoS jamming attacks is discussed first, and a new estimation of such mechanism is given. Then, the NN technique is applied to approximate the injected false information. Some sufficient conditions are derived to guarantee the boundedness of the closed-loop system, and the observer and controller gains are presented by solving a set of matrix inequalities. The effectiveness of the presented control method is demonstrated by a numerical example.

Quasisynchronization of Delayed Neural Networks With Discontinuous Activation Functions on Time Scales via Event-Triggered Control

Almost all event-triggered control (ETC) strategies were designed for discrete-time or continuous-time systems. In order to unify these existing theoretical results of ETC and develop ETC strategies for nonlinear systems, whose state variables evolve steadily at one time and change intermittently at another time, this article investigates quasisynchronization of delayed neural networks (NNs) on time scales with discontinuous activation functions via ETC approaches. First, the existence of the Filippov solutions is proved for discontinuous NNs with finite discontinuities. Second, two static event-triggered conditions and two dynamic event-triggered conditions are established to avoid continuous communication between the master-slave systems under algebraic/matrix inequality criteria. Third, under static/dynamic event-triggered conditions, a positive lower bound of event-triggered intervals is demonstrated to be greater than a positive number for each event-based controller, which shows that the Zeno behavior will not occur. Finally, two numerical simulations are carried out to show the effectiveness of the presented theoretical results in this article.

Multiloop Decentralized H∞ Fuzzy PID-Like Control for Discrete Time-Delayed Fuzzy Systems Under Dynamical Event-Triggered Schemes

This article is concerned with the multiloop decentralized H_∞ fuzzy proportional-integral-derivative-like (PID-like) control problem for discrete-time Takagi-Sugeno fuzzy systems with time-varying delays under dynamical event-triggered mechanisms (ETMs). The sensors of the plant are grouped into several nodes according to their physical distribution. For resource-saving purposes, the signal transmission between each sensor node and the controller is implemented based on the dynamical ETM. Taking the node-based idea into account, a general multiloop decentralized fuzzy PID-like controller is designed with fixed integral windows to reduce the potential accumulation error. The overall decentralized fuzzy PID-like control scheme involves multiple single-loop controllers, each of which is designed to generate the local control law based on the measurements of the corresponding sensor node. These kinds of local controllers are convenient to apply in practice. Sufficient conditions are obtained under which the controlled system is exponentially stable with the prescribed H_∞ performance index. The desired controller gains are then characterized by solving an iterative optimization problem. Finally, a simulation example is presented to demonstrate the correctness and effectiveness of the proposed design procedure.

New Event Based H ∞ State Estimation for Discrete-Time Recurrent Delayed Semi-Markov Jump Neural Networks Via a Novel Summation Inequality

This paper investigates the event-based state estimation for discrete-time recurrent delayed semi-Markovian neural networks. An event-triggering protocol is introduced to find measurement output with a specific triggering condition so as to lower the burden of the data communication. A novel summation inequality is established for the existence of asymptotic stability of the estimation error system. The problem addressed here is to construct an H ∞ state estimation that guarantees the asymptotic stability with the novel summation inequality, characterized by event-triggered transmission. By the Lyapunov functional technique, the explicit expressions for the gain are established. Finally, two examples are exploited numerically to illustrate the usefulness of the new methodology.

Finite-Time H∞ Estimator Design for Switched Discrete-Time Delayed Neural Networks With Event-Triggered Strategy

This article is concerned with the event-triggered finite-time H_∞ estimator design for a class of discrete-time switched neural networks (SNNs) with mixed time delays and packet dropouts. To further reduce the data transmission, both the measured information of system outputs and switching signal of the SNNs are only allowed to be accessible for the constructed estimator at the certain triggering time instants. Under this consideration, the simultaneous presence of the switching and triggering actions also leads to the asynchronism between the indices of the SNNs and the designed estimator. Unlike the existing event-triggered strategies for the general switched linear systems, the proposed event-triggered mechanism not only allows the occurrence of multiple switches in one triggering interval but also removes the minimum dwell-time constraint on the switched signal. In light of the piecewise Lyapunov-Krasovskii functional theory, sufficient conditions are developed for the estimation error system to be stochastically finite-time bounded with a finite-time specified H_∞ performance. Finally, the effectiveness and applicability of the theoretical results are verified by a switched Hopfield neural network.

Nonfragile H∞ State Estimation for Recurrent Neural Networks With Time-Varying Delays: On Proportional-Integral Observer Design

In this article, a novel proportional-integral observer (PIO) design approach is proposed for the nonfragile H_∞ state estimation problem for a class of discrete-time recurrent neural networks with time-varying delays. The developed PIO is equipped with more design freedom leading to better steady-state accuracy compared with the conventional Luenberger observer. The phenomena of randomly occurring gain variations, which are characterized by the Bernoulli distributed random variables with certain probabilities, are taken into consideration in the implementation of the addressed PIO. Attention is focused on the design of a nonfragile PIO such that the error dynamics of the state estimation is exponentially stable in a mean-square sense, and the prescribed H_∞ performance index is also achieved. Sufficient conditions for the existence of the desired PIO are established by virtue of the Lyapunov-Krasovskii functional approach and the matrix inequality technique. Finally, a simulation example is provided to demonstrate the effectiveness of the proposed PIO design scheme.

Multistability of delayed fractional-order competitive neural networks

This paper is concerned with the multistability of fractional-order competitive neural networks (FCNNs) with time-varying delays. Based on the division of state space, the equilibrium points (EPs) of FCNNs are given. Several sufficient conditions and criteria are proposed to ascertain the multiple O(t^-α)-stability of delayed FCNNs. The O(t^-α)-stability is the extension of Mittag-Leffler stability of fractional-order neural networks, which contains monostability and multistability. Moreover, the attraction basins of the stable EPs of FCNNs are estimated, which shows the attraction basins of the stable EPs can be larger than the divided subsets. These conditions and criteria supplement and improve the previous results. Finally, the results are illustrated by the simulation examples.

Proportional-Integral Observer Design for Multidelayed Sensor-Saturated Recurrent Neural Networks: A Dynamic Event-Triggered Protocol

In this article, the design problem of the proportional-integral observer (PIO) is investigated for a class of discrete-time multidelayed recurrent neural networks (RNNs). In the addressed RNN model, the delays occurring in the information interconnections are allowed to be different, and the phenomenon of sensor saturation is taken into consideration in the measurement model. A novel dynamic event-triggered protocol is employed in the data transmission from sensors to the observer with hope to improve the efficiency of resource utilization, where the threshold parameters are adaptive to the dynamical environment. By virtue of the Lyapunov-like approach, a general framework is established for examining the boundedness of the estimation errors in mean-square sense, and the ultimate bound of the error dynamics is also acquired. Subsequently, the explicit expression of the desired PIO is parameterized by using the matrix inequality techniques. Finally, a simulation example is utilized to verify the effectiveness and superiority of the proposed PIO design scheme.

Dynamic event-based state estimation for delayed artificial neural networks with multiplicative noises: A gain-scheduled approach

This study is concerned with the state estimation issue for a kind of delayed artificial neural networks with multiplicative noises. The occurrence of the time delay is in a random way that is modeled by a Bernoulli distributed stochastic variable whose occurrence probability is time-varying and confined within a given interval. A gain-scheduled approach is proposed for the estimator design to accommodate the time-varying nature of the occurrence probability. For the sake of utilizing the communication resource as efficiently as possible, a dynamic event triggering mechanism is put forward to orchestrate the data delivery from the sensor to the estimator. Sufficient conditions are established to ensure that, in the simultaneous presence of the external noises, the randomly occurring time delays with time-varying occurrence probability as well as the dynamic event triggering communication protocol, the estimation error is exponentially ultimately bounded in the mean square. Moreover, the estimator gain matrices are explicitly calculated in terms of the solution to certain easy-to-solve matrix inequalities. Simulation examples are provided to show the validity of the proposed state estimation method.

Partial-Neurons-Based Passivity-Guaranteed State Estimation for Neural Networks With Randomly Occurring Time Delays

In this brief, the partial-neurons-based passivity-guaranteed state estimation (SE) problem is examined for a class of discrete-time artificial neural networks with randomly occurring time delays. The measurement outputs available utilized for the SE are allowed to be available only at a fraction of neurons in the networks. A Bernoulli-distributed random variable is employed to characterize the random nature of the occurrence of time delays. By resorting to the Lyapunov-Krasovskii functional method as well as the stochastic analysis technique, sufficient criteria are provided for the existence of the desired state estimators ensuring the estimation error dynamics to achieve the asymptotic stability in the mean square with a guaranteed passivity performance level. In addition, the parameterization of the estimator gain is acquired by solving a convex optimization problem. Finally, the validity of the obtained theoretical results is illustrated via a numerical simulation example.

Observer-Based Fuzzy Output-Feedback Control for Discrete-Time Strict-Feedback Nonlinear Systems With Stochastic Noises

This paper focuses on the observer-based output-feedback control (OBOFC) problem for a class of discrete-time strict-feedback nonlinear systems (DTSFNSs) with both multiplicative process noises and additive measurement noises. A state observer is first designed to estimate immeasurable system states, and then a novel observer-based backstepping control framework is proposed for DTSFNSs with known model information. To be specific, virtual control laws and the actual control law are derived using a variable substitution method that gets rid of the repeated accumulation of measurement noises in the recursive process. Furthermore, for technical derivation, the multiplicative noise is successively bounded by state estimation errors and controlled errors. Stability conditions are obtained to guarantee the exponential mean-square boundedness of the closed-loop system. Moreover, the nonlinear modeling uncertainties are taken into account to better reflect engineering practices. In virtue of the universal approximation property of fuzzy-logic systems, a fuzzy observer and the corresponding fuzzy output-feedback controller are simultaneously constructed to derive the stability criteria by using novel weight updated laws. Simulation studies are performed to test the validity of the proposed OBOFC scheme.

Finite-Horizon H∞ State Estimation for Periodic Neural Networks Over Fading Channels

The problem of finite-horizon H_∞ state estimator design for periodic neural networks over multiple fading channels is studied in this paper. To characterize the measurement signals transmitted through different channels experiencing channel fading, a multiple fading channels model is considered. For investigating the situation of correlated fading channels, a set of correlated random variables is introduced. Specifically, the channel coefficients are described by white noise processes and are assumed to be correlated. Two sufficient criteria are provided, by utilizing a stochastic analysis approach, to guarantee that the estimation error system is stochastically stable and achieves the prescribed H_∞ performance. Then, the parameters of the estimator are derived by solving recursive linear matrix inequalities. Finally, some simulation results are shown to illustrate the effectiveness of the proposed method.

Event-Based Dissipative Analysis for Discrete Time-Delay Singular Jump Neural Networks

This paper investigates the event-triggered dissipative filtering issue for discrete-time singular neural networks with time-varying delays and Markovian jump parameters. Via event-triggered communication technique, a singular jump neural network (SJNN) model of network-induced delays is first given, and sufficient criteria are then provided to guarantee that the resulting augmented SJNN is stochastically admissible and strictly stochastically dissipative (SASSD) with respect to (X_ι,Y_ι,Z_ι,δ) by using slack matrix scheme. Furthermore, employing filter equivalent technique, codesigned filter gains, and event-triggered matrices are derived to make sure that the augmented SJNN model is SASSD with respect to (X_ι,Y_ι,Z_ι,δ) . An example is also given to illustrate the effectiveness of the proposed method.

l2-l∞ state estimation for delayed artificial neural networks under high-rate communication channels with Round-Robin protocol

In this paper, the l₂-l_∞ state estimation problem is addressed for a class of delayed artificial neural networks under high-rate communication channels with Round-Robin (RR) protocol. To estimate the state of the artificial neural networks, numerous sensors are deployed to measure the artificial neural networks. The sensors communicate with the remote state estimator through a shared high-rate communication channel. In the high-rate communication channel, the RR protocol is utilized to schedule the transmission sequence of the numerous sensors. The aim of this paper is to design an estimator such that, under the high-rate communication channel and the RR protocol, the exponential stability of the estimation error dynamics as well as the l₂-l_∞ performance constraint are ensured. First, sufficient conditions are given which guarantee the existence of the desired l₂-l_∞ state estimator. Then, the estimator gains are obtained by solving two sets of matrix inequalities. Finally, numerical examples are provided to verify the effectiveness of the developed l₂-l_∞ state estimation scheme.

Synchronization control of quaternion-valued memristive neural networks with and without event-triggered scheme

In this paper, the real-valued memristive neural networks (MNNs) are extended to quaternion field, a new class of neural networks named quaternion-valued memristive neural networks (QVMNNs) is then established. The problem of master-slave synchronization of this type of networks is investigated in this paper. Two types of controllers are designed: the traditional feedback controller and the event-triggered controller. Corresponding synchronization criteria are then derived based on Lyapunov method. Moreover, it is demonstrated that Zeno behavior can be avoided in case of the event-triggered strategy proposed in this work. Finally, corresponding simulation examples are proposed to demonstrate the correctness of the proposed results derived in this work.

Observer-Based Event-Triggered Control for Nonlinear Systems With Mixed Delays and Disturbances: The Input-to-State Stability

In this paper, the input-to-state stabilization problem is investigated for a class of nonlinear delayed systems with exogenous disturbances. The model under consideration is general that covers for both mixed time-delays and Lipschitz-type nonlinearities. An observer-based controller is designed such that the closed-loop system is stable under an event-triggered mechanism. Two separate event-triggered strategies are proposed in sensor-to-observer (S/O) and controller-to-actuator (C/A) channels, respectively, in order to reduce the updating frequencies of the sensor and the controller with guaranteed performance requirements. The notion of input-to-state practical stability is introduced to characterize the performance of the controlled system that caters for the influence from both disturbances and event-triggered schemes. The estimates of the upper bounds of the delayed states and two measurement errors are employed to analyze and further exclude the Zeno behavior resulting from the proposed event-triggered schemes in S/O and C/A channels. The controller gain matrices and the event-trigger parameters are co-designed in terms of the feasibility of certain matrix inequalities. A numerical simulation example is provided to illustrate the effectiveness of theoretical results.

Exponential Synchronization for Delayed Dynamical Networks via Intermittent Control: Dealing With Actuator Saturations

Over the past two decades, the synchronization problem for dynamical networks has drawn significant attention due to its clear practical insight in biological systems, social networks, and neuroscience. In the case where a dynamical network cannot achieve the synchronization by itself, the feedback controller should be added to drive the network toward a desired orbit. On the other hand, the time delays may often occur in the nodes or the couplings of a dynamical network, and the existence of time delays may induce some undesirable dynamics or even instability. Moreover, in the course of implementing a feedback controller, the inevitable actuator limitations could downgrade the system performance and, in the worst case, destabilize the closed-loop dynamics. The main purpose of this paper is to consider the synchronization problem for a class of delayed dynamical networks with actuator saturations. Each node of the dynamical network is described by a nonlinear system with a time-varying delay and the intermittent control strategy is proposed. By using a combination of novel sector conditions, piecewise Lyapunov-like functionals and the switched system approach, delay-dependent sufficient conditions are first obtained under which the dynamical network is locally exponentially synchronized. Then, the explicit characterization of the controller gains is established by means of the feasibility of certain matrix inequalities. Furthermore, optimization problems are formulated in order to acquire a larger estimate of the set of initial conditions for the evolution of the error dynamics when designing the intermittent controller. Finally, two examples are given to show the benefits and effectiveness of the developed theoretical results.