Design of An Arcak-Type Generalized $$H_2$$ H 2 Filter for Delayed Static Neural Networks

Hu, Dongming; Huang, He; Huang, Tingwen

doi:10.1007/s00034-014-9814-5

Cited by 9 publications

(10 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This completes the proof. [8][9][10][12][13][14][15], we solve the filtering problem based on an Arcak-type filter, in which there are two gain matrices to be determined. Compared with the widely used Luenbergertype filter, it contains an additional gain matrix 1 included in the activation function.…”

Section: Mathematical Problems In Engineeringmentioning

confidence: 99%

“…By using the double Jensen inequality to estimate the double integral terms and using the free-matrix-based integral inequality to estimate the single integral term, the derivation of the triple term is accomplished without ignoring any terms. It should be pointed out that this technique is more effective than the ones used in [10], in which the derived double integral term − ∫ −ℎ ∫̇( )( ) is estimated in its entirety.…”

Section: Remarkmentioning

confidence: 99%

“…This example has been studied in [10,16], and we take these literatures for comparison study. To verify the advantages of our proposed approach, we calculate the optimal 2 performance bounds index min for various ℎ, , and such that filtering error system (5) is globally asymptotically stable with generalized 2 performance.…”

Section: Numerical Examplesmentioning

confidence: 99%

“…In [9], the delay-dependent 2 filter of the Luenberger form was derived for delayed switched Hopfield NNs. Considering that there is only one gain matrix in the Luenberger-type filter to be determined, which may introduce some restrictions to certain extent, [10] further studied the 2 filtering problem of delayed static NNs based on an Arcak-type filter. Since it contains two gain matrices, the Arcak-type filter is regarded as an extension of the Luenberger-type filter.…”

Section: Introductionmentioning

confidence: 99%

“…In early years, the simple LKFs combined with the Jensen inequality is considered to be the most popular method for the filtering problems of delayed NNs [8]. In order to consider more information about time delays, some triple integral terms were introduced into the LKF in [10]. In [12], the delay-decomposition idea was used to derive the delaydependent condition such that the filtering error system is globally asymptotically stable with a guaranteed ∞ performance.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Improved GeneralizedH2Filtering for Static Neural Networks with Time-Varying Delay via Free-Matrix-Based Integral Inequality

2018

Mathematical Problems in Engineering

View full text Add to dashboard Cite

This paper focuses on the generalized 2 filtering of static neural networks with a time-varying delay. The aim of this problem is to design a full-order filter such that the filtering error system is globally asymptotically stable with guaranteed 2 performance index. By constructing an augmented Lyapunov-Krasovskii functional and applying the free-matrix-based integral inequality to estimate its derivative, an improved delay-dependent condition for the generalized 2 filtering problem is established in terms of LMIs. Finally, a numerical example is presented to show the effectiveness of the proposed method.

show abstract

Section: Mathematical Problems In Engineeringmentioning

confidence: 99%

Section: Remarkmentioning

confidence: 99%

Section: Numerical Examplesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Improved GeneralizedH2Filtering for Static Neural Networks with Time-Varying Delay via Free-Matrix-Based Integral Inequality

2018

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

Damage identification of a large cable-stayed bridge with novel cointegrated Kalman filter method under changing environments

Huang

et al. 2018

Struct Control Health Monit

View full text Add to dashboard Cite

Damage identification is an indispensable part for successive applications of structural health monitoring. In practical applications, however, time-varying environmental and operational conditions, such as temperature and external loadings, often overwhelm the subtle structural changes caused by damage. It is therefore of great significance to remove those structural changes (damage features) caused by external influences from actual structural damage. In this paper, a new damage identification method based on Kalman filter and cointegration (KFC) is developed, and the environmental effects on damage indicator are removed by the cointegration process of the Kalman filtered coefficients. The cointegration relationship between structural frequencies is first established with augmented Dickey-Fuller test and Johansen procedure. The cointegration coefficients are then used to constitute the Kalman filter (KF) state vector, and the recursive KF process is intrigued to on-line estimate the change of structure states. To enhance the importance of incoming new observations in the KF, we introduce an adaptive fading factor into the conventional KF. Numerical simulation of a truss bridge is used to validate the effectiveness of the proposed KFC method for damage identification under varying temperature, even with 10% noise. Finally, the KFC method is applied to a cable-stayed bridge built in China (Tianjin Yonghe Bridge), and two structural damage scenarios are successfully identified. The advantages of the proposed KFC method are its ability to eliminate ambient temperature influences and identify structural damage on-line.

show abstract

Generalized Lag Synchronization of Neural Networks with Discontinuous Activations and Bounded Perturbations

Yang

2015

Circuits Syst Signal Process

View full text Add to dashboard Cite

Design of An Arcak-Type Generalized $$H_2$$ H 2 Filter for Delayed Static Neural Networks

Cited by 9 publications

References 40 publications

Improved GeneralizedH2Filtering for Static Neural Networks with Time-Varying Delay via Free-Matrix-Based Integral Inequality

Improved GeneralizedH2Filtering for Static Neural Networks with Time-Varying Delay via Free-Matrix-Based Integral Inequality

Damage identification of a large cable-stayed bridge with novel cointegrated Kalman filter method under changing environments

Generalized Lag Synchronization of Neural Networks with Discontinuous Activations and Bounded Perturbations

Contact Info

Product

Resources

About