RESEARCH ARTICLE
Robust partially mode-dependent H∞ filtering for discrete-time nonhomogeneous Markovian jump neural networks with additive gain perturbations
Dandan Zheng,
Mingang Hua,
Junfeng Chen,
Cunkang Bian,
Weili Dai,
Dandan Zheng
College of Internet of Things Engineering, Hohai University, Changzhou, China
Search for more papers by this authorCorresponding Author
Mingang Hua
College of Internet of Things Engineering, Hohai University, Changzhou, China
Correspondence
Mingang Hua, College of Internet of Things Engineering, Hohai University, Changzhou 213022, China.
Email: [email protected]
Communicated by: Q. Chen
Search for more papers by this authorJunfeng Chen
College of Internet of Things Engineering, Hohai University, Changzhou, China
Search for more papers by this authorCunkang Bian
College of Internet of Things Engineering, Hohai University, Changzhou, China
Search for more papers by this authorWeili Dai
College of Internet of Things Engineering, Hohai University, Changzhou, China
Search for more papers by this authorDandan Zheng,
Mingang Hua,
Junfeng Chen,
Cunkang Bian,
Weili Dai,
Dandan Zheng
College of Internet of Things Engineering, Hohai University, Changzhou, China
Search for more papers by this authorCorresponding Author
Mingang Hua
College of Internet of Things Engineering, Hohai University, Changzhou, China
Correspondence
Mingang Hua, College of Internet of Things Engineering, Hohai University, Changzhou 213022, China.
Email: [email protected]
Communicated by: Q. Chen
Search for more papers by this authorJunfeng Chen
College of Internet of Things Engineering, Hohai University, Changzhou, China
Search for more papers by this authorCunkang Bian
College of Internet of Things Engineering, Hohai University, Changzhou, China
Search for more papers by this authorWeili Dai
College of Internet of Things Engineering, Hohai University, Changzhou, China
Search for more papers by this authorAbstract
This paper studies the robust partially mode-dependent H∞ filtering for nonhomogeneous Markovian jump neural networks with additive gain perturbations. The discrete time-varying jump transition probability matrix is considered to be a polytope set. A partially mode-dependent filter with additive gain perturbations is constructed to increase the robustness of the filter, which is subjects to H∞ performance index. Based on the Lyapunov function approach, sufficient conditions are established such that the filtering error system is robustly stochastically stable. The efficiency of the new technique is illustrated by an illustrative example and a biological network example.
REFERENCES
- 1Ahn CK. An error passivation approach to filtering for switched neural networks with noise disturbance. Neural Comput Appl. 2012; 21(5): 853-861.
- 2Zhu Q, Cao J, Rakkiyappan R. Exponential input-to-state stability of stochastic cohengrossberg neural networks with mixed delays. Nonlinear Dyn. 2015; 79(2): 1085-1098.
- 3Ahn CK. Passive and exponential filter design for fuzzy neural networks. Inf Sci. 2013; 238: 126-137.
- 4Lu CY. A delay-range-dependent approach to design state estimator for discrete-time recurrent neural networks with interval time-varying delay. IEEE Trans Circuits Syst II Express Briefs. 2008; 55(11): 1163-1167.
- 5Shen H, Zhu Y, Zhang L, Park JH. Extended dissipative state estimation for Markov jump neural networks with unreliable links. IEEE Trans Neural Networks Learn Syst. 2017; 28(2): 346-358.
- 6Hua M, Liu X, Deng F, Fei J. New results on robust exponential stability of uncertain stochastic neural networks with mixed time-varying delays. Neural Process Lett. 2010; 32(3): 219-233.
- 7Carpenter GA., Grossberg S, Rosen DB.. Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system. Neural Networks. 1991; 4(6): 759-771.
- 8Herault J, Jutten C. Space or time adaptive signal processing by neural network models. Iie Trans. 1987; 151(1): 206-211.
- 9Carpenter GA. Neural network models for pattern recognition and associative memory. Neural Networks. 1989; 2(4): 243-257.
- 10Fei J, Cheng L. Adaptive sliding mode control of dynamic systems using double loop recurrent neural network structure. IEEE Trans Neural Networks Learn Syst. 2018; 29(4): 1275-1286.
- 11Zhu Q. pth moment exponential stability of impulsive stochastic functional differential equations with Markovian switching. J Franklin Inst. 2014; 351(7): 3965-3986.
- 12Cheng J, Park JH, Zhang L, Zhu Y. An asynchronous operation approach to event-triggered control for fuzzy Markovian jump systems with general switching policies. IEEE Trans Fuzzy Syst. 2018; 26(1): 6-18.
- 13Zhu Q. Razumikhin-type theorem for stochastic functional differential equations with Lévy noise and Markov switching. Int J Control. 2017; 90(8): 1703-1712.
- 14Zhang L, Zhu Y, Zheng WX. Energy-to-peak state estimation for Markov jump RNNs with time-varying delays via nonsynchronous filter with nonstationary mode transitions. IEEE Trans Neural Networks Learn Syst. 2015; 26(10): 2346-2356.
- 15Tan H, Hua M, Chen J, Fei J. Stability analysis of stochastic Markovian switching static neural networks with asynchronous mode-dependent delays. Neurocomputing. 2015; 151(151): 864-872.
- 16Zhu Q, Cao J. Stability analysis of Markovian jump stochastic BAM neural networks with impulse control and mixed time delays. IEEE Trans Neural Networks Learn Syst. 2012; 23(3): 467-479.
- 17Zhang Y, Lou K, Ge Y, Zhang CK. Improved state estimation for Markovian jumping systems with time delay and partial information on transition probabilities. Optimal Control Appl Methods. 2016; 38(1): 75-87.
- 18Ma Q, Xu S, Zou Y. Stability and synchronization for Markovian jump neural networks with partly unknown transition probabilities. Neurocomputing. 2011; 74(17): 3404-3411.
- 19Chandrasekar A, Rakkiyappan R, Rihan FA, Lakshmanan S. Exponential synchronization of Markovian jumping neural networks with partly unknown transition probabilities via stochastic sampled-data control. Neurocomputing. 2014; 133(10): 385-398.
- 20Lu Y, Ren W, Yi S, Zuo Y. Stability analysis for discrete delayed Markovian jumping neural networks with partly unknown transition probabilities. Neurocomputing. 2011; 74(18): 3768-3772.
- 21Ali MS, Saravanakumar R, Arik S. Novel H∞ state estimation of static neural networks with interval time-varying delays via augmented Lyapunov-Krasovskii functional. Neurocomputing. 2016; 171: 949-954.
- 22Shen M, Nguang SK, Ahn CK. Quantized H∞ output control of linear markov jump systems in finite frequency domain. IEEE Trans Syst Man CybernSyst. 2018. In press, https://doi.org/10.1109/TSMC.2018.2798159
10.1109/TSMC.2018.2798159 Google Scholar
- 23Cheng J, Ahn CK, Karimi HR, Cao J, Qi W. An event-based asynchronous approach to Markov jump systems with hidden mode detections and missing measurements. IEEE Trans Syst Man Cybern Syst. 2018. In press, https://doi.org/10.1109/TSMC.2018.2798159
- 24Hua M, Tan H, Chen J, Fei J. Robust delay-range-dependent non-fragile H∞ filtering for uncertain neutral stochastic systems with markovian switching and mode-dependent time delays. J Franklin Inst. 2015; 352(3): 1318-1341.
- 25Arunkumar A, Sakthivel R, Mathiyalagan K. Robust reliable H∞ control for stochastic neural networks with randomly occurring delays. Neurocomputing. 2015; 149: 1524-1534.
- 26Mousavi SM, Majd VJ. Robust filtering of extended stochastic genetic regulatory networks with parameter uncertainties, disturbances, and time-varying delays. Neurocomputing. 2011; 74(12): 2123-2134.
- 27Mathiyalagan K, Su H, Shi P, Sakthivel R. Exponential H∞ filtering for discrete-time switched neural networks with random delays. IEEE Trans Cybern. 2015; 45(4): 676-687.
- 28Shen Y, Wu ZG., Shi P, Su H, Huang T. Asynchronous filtering for Markov jump neural networks with quantized outputs. IEEE Trans Syst Man Cybern Syst. 2017. In press, https://doi.org/10.1109/TSMC.2017.2789180
- 29Shen H, Huo S, Cao J, Huang T. Generalized state estimation for Markovian coupled networks under round-robin protocol and redundant channels. IEEE Trans Cybern. 2018. In press, https://doi.org/10.1109/TCYB.2018.2799929
10.1109/TCYB.2018.2799929 Google Scholar
- 30Cheng J, Park JH, Karimi HR, Shen H. A flexible terminal approach to sampled-data exponentially synchronization of Markovian neural networks with time-varying delayed signals. IEEE Trans Cybern. 2018; 48(8): 2232-2244
- 31Shen H, Xing M, Huo S, Wu ZG., H PJ. Finite-time H∞ asynchronous state estimation for discrete-time fuzzy Markov jump neural networks with uncertain measurements. Fuzzy Sets Syst. 2018. In press, https://doi.org/10.1016/j.fss.2018.01.017
- 32Song J, Niu Y. Resilient finite-time stabilization of fuzzy stochastic systems with randomly occurring uncertainties and randomly occurring gain fluctuations. Neurocomputing. 2016; 171: 444-451.
- 33Ren W, Hou N, Wang Q, Lu Y, Liu X. Non-fragile H∞ filtering for nonlinear systems with randomly occurring gain variations and channel fadings. Neurocomputing. 2015; 156: 176-185.
- 34Zhang S, Wang Z, Ding D, Dong H. Nonfragile H∞ fuzzy filtering with randomly occurring gain variations and channel fadings. IEEE Trans Fuzzy Syst. 2016; 24(3): 505-518.
- 35Li X, Ahn CK, Lu D, Guo S. Robust simultaneous fault estimation and nonfragile output feedback fault-tolerant control for Markovian jump systems. IEEE Trans Syst Man Cybern Syst. 2018. In press, https://doi.org/10.1109/TSMC.2018.2828123
- 36Zhang L, Zhu Y, Shi P, Zhao Y. Resilient asynchronous H∞ filtering for Markov jump neural networks with unideal measurements and multiplicative noises. IEEE Trans Cybern. 2015; 45(12): 2840-2852.
- 37Chen M, Zhang L, Shen H. Resilient H∞ filtering for discrete-time uncertain Markov jump neural networks over a finite-time interval. Neurocomputing. 2015; 185: 212-219.
- 38Xu Y, Lu R, Tao J, Peng H, Xie K. Nonfragile L2 − L∞ state estimation for discrete-time neural networks with jumping saturations. Neurocomputing. 2016; 207: 15-21.
- 39Wang G, Zhang Q, Sreeram V. Partially mode-dependent H∞ filtering for discrete-time Markovian jump systems with partly unknown transition probabilities. Signal Process. 2010; 90(2): 548-556.
- 40Wang G. Partially mode-dependent design of H∞ filter for stochastic Markovian jump systems with mode-dependent time delays. J Math Anal Appl. 2011; 383(2): 573-584.
- 41Han K, Feng J, Chang X. Reduced-order partially mode-dependent energy-to-peak filter design for discrete-time Markov jump systems subject to quantizer faults and state-dependent noises. Circuits, Syst Signal Process. 2015; 34(1): 77-103.
- 42Chen M, Shen H, Li F. On dissipative filtering over unreliable communication links for stochastic jumping neural networks based on a unified design method. J Franklin Inst. 2016; 353(17): 4583-4601.
- 43Aberkane S. Stochastic stabilization of a class of nonhomogeneous Markovian jump linear systems. Syst Control Lett. 2011; 60(3): 156-160.
- 44Yin Y, Shi P, Liu F, Teo KL.. Filtering for discrete-time nonhomogeneous Markov jump systems with uncertainties. Inf Sci. 2014; 259(3): 118-127.
- 45Yin Y, Shi P, Liu F, Teo KL. Robust l2 − l∞ filtering for a class of dynamical systems with nonhomogeneous Markov jump process. Int J Syst Sci. 2015; 46(4): 599-608.
- 46Hua M, Zheng D, Deng F. Partially mode-dependent l2 − l∞ filtering for discrete-time nonhomogeneous Markov jump systems with repeated scalar nonlinearities. Inf Sci. 2018; 451–452: 223-239.
- 47Wang B, Cheng J, Zhan J. A sojourn probability approach to fuzzy-model-based reliable control for switched systems with mode-dependent time-varying delays. Nonlinear Anal Hybrid Syst. 2017; 26: 239-253.
- 48Zhang Y, Mu J, Shi Y, Zhang J. Finite-time filtering for T-S fuzzy jump neural networks with sector-bounded activation functions. Neurocomputing. 2016; 186: 97-106.
- 49Guo XG, Yang GH. Reliable H∞ filter design for discrete-time systems with sector-bounded nonlinearities: An LMI optimization approach. Acta Autom Sin. 2009; 35(10): 1347-1351.
10.3724/SP.J.1004.2009.01347 Google Scholar
- 50Chen Y, Zheng WX. Stochastic state estimation for neural networks with distributed delays and Markovian jump. Neural Netw. 2012; 25(1): 14-20.
- 51Hua M, Cai Y, Ni J, Fei J. Delay-dependent H∞ filtering for discrete-time fuzzy stochastic systems with mixed delays and sector-bounded nonlinearity. J Franklin Inst. 2015; 352(8): 3069-3097.
- 52Wang Z, Liu Y, Yu L, Liu X. Exponential stability of delayed recurrent neural networks with Markovian jumping parameters. Phys Lett A. 2006; 356(4): 346-352.
- 53Zhang H, Wang Y. Stability analysis of Markovian jumping stochastic cohen-grossberg neural networks with mixed time delays. IEEE Trans Neural Netw. 2008; 19(2): 366-370.
- 54Wang Y, Xie L, de Souza CE. Robust control of a class of uncertain nonlinear systems. Syst Control Lett. 1992; 19(2): 139-149.
