1
|
Wang X, Yu Y, Ge SS, Shi K, Zhong S, Cai J. Mode-Mixed Effects Based Intralayer-Dependent Impulsive Synchronization for Multiple Mismatched Multilayer Neural Networks. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024; 35:7697-7711. [PMID: 36427282 DOI: 10.1109/tnnls.2022.3220193] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/16/2023]
Abstract
This article focuses on the intralayer-dependent impulsive synchronization of multiple mismatched multilayer neural networks (NNs) with mode-mixed effects. Initially, a novel multilayer NN model that removes the one-to-one interlayer coupling constraint and introduces nonidentical model parameters is first established to meet diverse modeling requirements in complex applications. To help the multilayer target NNs with mismatched connection coefficients and time delays achieve synchronization, the hybrid controller is designed using intralayer-dependent impulsive control and switched feedback control approaches. Furthermore, the mode-mixed effects caused by the intralayer coupling delays and switched intralayer topologies are incorporated into the novel model and analysis method to ensure that the subsystems operating within the current switching interval can effectively use the topology information of the previous switching intervals. Then, a novel analysis framework including super-Laplacian matrix, augmented matrix, and mode-mixed methods is developed to derive the synchronization results. Finally, the main results are verified via the numerical simulation with secure communication.
Collapse
|
2
|
Liang L, Cheng J, Cao J, Wu ZG, Chen WH. Proportional-Integral Observer-Based State Estimation for Singularly Perturbed Complex Networks With Cyberattacks. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023; 34:9795-9805. [PMID: 35349455 DOI: 10.1109/tnnls.2022.3160627] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
This article investigates the asynchronous proportional-integral observer (PIO) design issue for singularly perturbed complex networks (SPCNs) subject to cyberattacks. The switching topology of SPCNs is regulated by a nonhomogeneous Markov switching process, whose time-varying transition probabilities are polytope structured. Besides, the multiple scalar Winner processes are applied to character the stochastic disturbances of the inner linking strengths. Two mutually independent Bernoulli stochastic variables are exploited to characterize the random occurrences of cyberattacks. In a practical viewpoint, by resorting to the hidden nonhomogeneous Markov model, an asynchronous PIO is formulated. Under such a framework, by applying the Lyapunov theory, sufficient conditions are established such that the augmented dynamic is mean-square exponentially ultimately bounded. Finally, the effectiveness of the theoretical results is verified by two numerical simulations.
Collapse
|
3
|
Zou L, Wang Z, Hu J, Dong H. Partial-Node-Based State Estimation for Delayed Complex Networks Under Intermittent Measurement Outliers: A Multiple-Order-Holder Approach. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023; 34:7181-7195. [PMID: 35038297 DOI: 10.1109/tnnls.2021.3138979] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
This article is concerned with the partial-node-based (PNB) state estimation problem for delayed complex networks (DCNs) subject to intermittent measurement outliers (IMOs). In order to describe the intermittent nature of outliers, several sequences of shifted gate functions are adopted to model the occurrence moments and the disappearing moments of IMOs. Two outlier-related indices, namely, minimum and maximum interval lengths, are employed to parameterize the "occurrence frequency" of IMOs. The norm of the addressed outlier is allowed to be greater than a certain fixed threshold, and this distinguishes the outlier from the extensively studied norm-bounded noise. By adopting the input-output models of the considered complex network, a novel multiple-order-holder (MOH) approach is developed to resist the effects of IMOs by dedicatedly designing a weighted average of certain non-IMO measurements, and then, a PNB state estimator is constructed based on the outputs of the MOHs. Sufficient conditions are proposed to ensure the exponentially ultimate boundedness (EUB) of the resultant estimation error, and the estimator gain matrices are subsequently obtained by solving a constrained optimization problem. Finally, two simulation examples are provided to demonstrate the effectiveness of our developed outlier-resistant PNB state estimation scheme.
Collapse
|
4
|
Li JY, Wang Z, Lu R, Xu Y. Cluster Synchronization Control for Discrete-Time Complex Dynamical Networks: When Data Transmission Meets Constrained Bit Rate. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023; 34:2554-2568. [PMID: 34495846 DOI: 10.1109/tnnls.2021.3106947] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/04/2023]
Abstract
In this article, the cluster synchronization control problem is studied for discrete-time complex dynamical networks when the data transmission is subject to constrained bit rate. A bit-rate model is presented to quantify the limited network bandwidth, and the effects from the constrained bit rate onto the control performance of the cluster synchronization are evaluated. A sufficient condition is first proposed to guarantee the ultimate boundedness of the error dynamics of the cluster synchronization, and then, a bit-rate condition is established to reveal the fundamental relationship between the bit rate and the certain performance index of the cluster synchronization. Subsequently, two optimization problems are formulated to design the desired synchronization controllers with aim to achieve two distinct synchronization performance indices. The codesign issue for the bit-rate allocation protocol and the controller gains is further discussed to reduce the conservatism by locally minimizing a certain asymptotic upper bound of the synchronization error dynamics. Finally, three illustrative simulation examples are utilized to validate the feasibility and effectiveness of the developed synchronization control scheme.
Collapse
|
5
|
Wang P, He Q, Su H. Stabilization of Discrete-Time Stochastic Delayed Neural Networks by Intermittent Control. IEEE TRANSACTIONS ON CYBERNETICS 2023; 53:2017-2027. [PMID: 34546937 DOI: 10.1109/tcyb.2021.3108574] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/13/2023]
Abstract
This article investigates the stabilization of discrete-time stochastic neural networks with time-varying delay via aperiodically intermittent control (AIC). A comprehensive analysis of the stabilization of discrete-time delayed systems via AIC is provided, where the Lyapunov function method and the Lyapunov-Krasovskii functional method are investigated, respectively. Then, three stabilization criteria are given, which extend previous works from the continuous-time framework to the discrete-time one, and the average activation time ratio (AATR) of AIC is estimated. It is highlighted that for the Lyapunov-Krasovskii functional method, a more flexible estimation for the AATR can be obtained. Finally, the differences and the advantages of the three stabilization criteria are illustrated by numerical simulations.
Collapse
|
6
|
Chen Y, Meng X, Wang Z, Dong H. Event-Triggered Recursive State Estimation for Stochastic Complex Dynamical Networks Under Hybrid Attacks. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023; 34:1465-1477. [PMID: 34464268 DOI: 10.1109/tnnls.2021.3105409] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/13/2023]
Abstract
In this article, the event-based recursive state estimation problem is investigated for a class of stochastic complex dynamical networks under cyberattacks. A hybrid cyberattack model is introduced to take into account both the randomly occurring deception attack and the randomly occurring denial-of-service attack. For the sake of reducing the transmission rate and mitigating the network burden, the event-triggered mechanism is employed under which the measurement output is transmitted to the estimator only when a preset condition is satisfied. An upper bound on the estimation error covariance on each node is first derived through solving two coupled Riccati-like difference equations. Then, the desired estimator gain matrix is recursively acquired that minimizes such an upper bound. Using the stochastic analysis theory, the estimation error is proven to be stochastically bounded with probability 1. Finally, an illustrative example is provided to verify the effectiveness of the developed estimator design method.
Collapse
|
7
|
Chen Y, Zhang N, Yang J. A survey of recent advances on stability analysis, state estimation and synchronization control for neural networks. Neurocomputing 2023. [DOI: 10.1016/j.neucom.2022.10.020] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
|
8
|
Zhu K, Wang Z, Han QL, Wei G. Distributed Set-Membership Fusion Filtering for Nonlinear 2-D Systems Over Sensor Networks: An Encoding-Decoding Scheme. IEEE TRANSACTIONS ON CYBERNETICS 2023; 53:416-427. [PMID: 34546940 DOI: 10.1109/tcyb.2021.3110587] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/13/2023]
Abstract
In this article, the distributed set-membership fusion filtering problem is investigated for a class of nonlinear 2-D shift-varying systems subject to unknown-but-bounded noises over sensor networks. The sensors are communicated with their neighbors according to a given topology through wireless networks of limited bandwidth. With the purpose of relieving the communication burden as well as enhancing the transmission security, a logarithmic-type encoding-decoding mechanism is introduced for each sensor node so as to encode the transmitted data with a finite number of bits. A distributed set-membership filter is designed to determine the local ellipsoidal set that contains the system state by only utilizing the data from the local sensor node and its neighbors, where the proposed filter scheme is truly distributed with desirable scalability. Then, a new ellipsoid-based fusion rule is developed for the designed set-membership filters in order to form the fused ellipsoidal set that has a globally smaller volume than all local ellipsoidal sets. With the aid of the mathematical induction technique, the set theory, and the convex optimization approach, sufficient conditions are derived for the existence of the desired distributed set-membership filters and the fusion weights. Then, the filter parameters and the fusion weights are acquired by solving a set of constrained optimization problems. Finally, an illustrative example is given to demonstrate the effectiveness of the proposed fusion filtering algorithm.
Collapse
|
9
|
Song Q, Yang L, Liu Y, Alsaadi FE. Stability of quaternion-valued neutral-type neural networks with leakage delay and proportional delays. Neurocomputing 2022. [DOI: 10.1016/j.neucom.2022.12.009] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/13/2022]
|
10
|
Synchronization Control for Chaotic Neural Networks with Mixed Delays Under Input Saturations. Neural Process Lett 2021. [DOI: 10.1007/s11063-021-10577-9] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|
11
|
Yao D, Dou C, Zhao N, Zhang T. Practical fixed-time adaptive consensus control for a class of multi-agent systems with full state constraints and input delay. Neurocomputing 2021. [DOI: 10.1016/j.neucom.2021.03.032] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
|
12
|
Liu H, Wang Z, Fei W, Li J. H ∞ and l 2-l ∞ state estimation for delayed memristive neural networks on finite horizon: The Round-Robin protocol. Neural Netw 2020; 132:121-130. [PMID: 32871337 DOI: 10.1016/j.neunet.2020.08.006] [Citation(s) in RCA: 13] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/20/2020] [Revised: 07/19/2020] [Accepted: 08/10/2020] [Indexed: 11/26/2022]
Abstract
In this paper, a protocol-based finite-horizon H∞ and l2-l∞ estimation approach is put forward to solve the state estimation problem for discrete-time memristive neural networks (MNNs) subject to time-varying delays and energy-bounded disturbances. The Round-Robin protocol is utilized to mitigate unnecessary network congestion occurring in the sensor-to-estimator communication channel. For the delayed MNNs, our aim is to devise an estimator that not only ensures a prescribed disturbance attenuation level over a finite time-horizon, but also keeps the peak value of the estimation error within a given range. By resorting to the Lyapunov-Krasovskii functional method, the delay-dependent criteria are formulated that guarantee the existence of the desired estimator. Subsequently, the estimator gains are obtained via figuring out a bank of convex optimization problems. The validity of our estimator is finally shown via a numerical example.
Collapse
Affiliation(s)
- Hongjian Liu
- Key Laboratory of Advanced Perception and Intelligent Control of High-end Equipment, Ministry of Education, Anhui Polytechnic University, Wuhu 241000, China; Artificial Intelligence Energy Research Institute, Northeast Petroleum University, Daqing 163318, China.
| | - Zidong Wang
- College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, China; Department of Computer Science, Brunel University London, Uxbridge, Middlesex, UB8 3PH, United Kingdom.
| | - Weiyin Fei
- Key Laboratory of Advanced Perception and Intelligent Control of High-end Equipment, Ministry of Education, Anhui Polytechnic University, Wuhu 241000, China; School of Mathematics and Physics, Anhui Polytechnic University, Wuhu 241000, China.
| | - Jiahui Li
- Artificial Intelligence Energy Research Institute, Northeast Petroleum University, Daqing 163318, China; Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control, Northeast Petroleum University, Daqing 163318, China.
| |
Collapse
|