State estimation with guaranteed performance for switching-type fuzzy neural networks in presence of sensor nonlinearities

Xu, Yanghui; Zhang, Dan

doi:10.1016/j.cnsns.2013.11.014

Cited by 5 publications

(3 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Theorem 2 gives the less conservative LMI conditions on strictly stochastic (X l , S l , R l )-α-dissipativity of the augmented fuzzy DMJNNs (4). It can be seen from the proof of Theorem 1 that, when ω(k) ≡ 0, we can deduce from (29) that that E{∆V (k)} < 0 holds, which imply that there exists a scalar > 0 such that…”

Section: Resultsmentioning

confidence: 97%

“…Much work has been investigated for the state estimation of the neural networks, see the references [25,26]. It should noted that state estimation problems were also studied for continuoustime T-S fuzzy neural networks in [27][28][29]. Therefore, as an analogue of the continuous-time case, it is essential to deal with state estimation of discrete-time T-S fuzzy neural networks due to both theoretical and practical importance to study the dynamics of discrete-time neural networks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dissipativity Analysis for Discrete Time-Delay Fuzzy Neural Networks With Markovian Jumps

Zhang

Shi

Agarwal

et al. 2016

IEEE Trans. Fuzzy Syst.

View full text Add to dashboard Cite

Abstract-This paper is concerned with the dissipativity analysis and design of discrete Markovian jumping neural networks with sector-bounded nonlinear activation functions and timevarying delays represented by Takagi-Sugeno fuzzy model. The augmented fuzzy neural networks with Markovian jumps are firstly constructed based on estimator of Luenberger observer type. Then, applying piecewise Lyapunov-Krasovskii functional approach and stochastic analysis technique, a sufficient condition is provided to guarantee that the augmented fuzzy jump neural networks are stochastically dissipative. Moreover, a less conservative criterion is established to solve the dissipative state estimation problem by using matrix decomposition approach. Furthermore, to reduce the computational complexity of the algorithm, a dissipative estimator is designed to ensure stochastic dissipativity of the error fuzzy jump neural networks. As a special case, we have also considered the mixed H∞ and passive analysis of fuzzy jump neural networks. All criteria can be formulated in terms of linear matrix inequalities. Finally, two examples are given to show the effectiveness and potential of the new design techniques.

show abstract

Section: Resultsmentioning

confidence: 97%

Section: Introductionmentioning

confidence: 99%

Dissipativity Analysis for Discrete Time-Delay Fuzzy Neural Networks With Markovian Jumps

Zhang

Shi

Agarwal

et al. 2016

IEEE Trans. Fuzzy Syst.

View full text Add to dashboard Cite

show abstract

“…Remark 7: Recently, some new results on filter design have been reported [23], [37], [39], [42], [44] for various kinds of NNs. These studies have focused on filtering problems with multiple missing measurements, switching regularities, and sensor nonlinearities.…”

Section: Exponential L 2 -L ∞ Filter Designmentioning

confidence: 99%

Filtering of Discrete-Time Switched Neural Networks Ensuring Exponential Dissipative and $l_{2}$ – $l_{\infty }$ Performances

Choi

Ahn

Karimi

et al. 2017

IEEE Trans. Cybern.

View full text Add to dashboard Cite

This paper studies delay-dependent exponential dissipative and l - l filtering problems for discrete-time switched neural networks (DSNNs) including time-delayed states. By introducing a novel discrete-time inequality, which is a discrete-time version of the continuous-time Wirtinger-type inequality, we establish new sets of linear matrix inequality (LMI) criteria such that discrete-time filtering error systems are exponentially stable with guaranteed performances in the exponential dissipative and l - l senses. The design of the desired exponential dissipative and l - l filters for DSNNs can be achieved by solving the proposed sets of LMI conditions. Via numerical simulation results, we show the validity of the desired discrete-time filter design approach.

show abstract

Adaptive event‐triggered H∞ state estimation of semi‐Markovian jump neural networks with randomly occurred sensor nonlinearity

Song

et al. 2022

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

This article mainly discusses the problem for adaptive event-triggered H∞ state estimation of semi-Markovian jump neural networks (s-MJNNs) subject to random sensor nonlinearity. To reduce the communication load, adaptive event-triggered scheme (AETS) is introduced to decide whether to transmit sampled data or not. Also, considering the possible sensor nonlinearity, a new estimation error model is established under the framework of AETS. An appropriate Lyapunov-Krasovskii functional (LKF) containing the proposed adaptive event trigger condition is constructed, and sufficient conditions are obtained to guarantee the asymptotic stability of the estimation error system. Then, through a set of feasible linear matrix inequalities (LMIs), the co-design method of estimator and AETS is proposed. Finally, the feasibility of this paper is proved by three numerical examples.

show abstract

State estimation with guaranteed performance for switching-type fuzzy neural networks in presence of sensor nonlinearities

Cited by 5 publications

References 52 publications

Dissipativity Analysis for Discrete Time-Delay Fuzzy Neural Networks With Markovian Jumps

Dissipativity Analysis for Discrete Time-Delay Fuzzy Neural Networks With Markovian Jumps

Filtering of Discrete-Time Switched Neural Networks Ensuring Exponential Dissipative and $l_{2}$ – $l_{\infty }$ Performances

Adaptive event‐triggered H∞ state estimation of semi‐Markovian jump neural networks with randomly occurred sensor nonlinearity

Contact Info

Product

Resources

About