A new approach to non-fragile state estimation for continuous neural networks with time-delays

Neurocomputing

Volumn 197, Issue , 2016, Pages 205-211

  Yang, Fan ^a   Dong, Hongli ^a   Wang, Zidong ^b,c   Ren, Weijian ^a   Alsaadi, Fuad E ^c  

^a NORTHEAST PETROLEUM UNIVERSITY   (China)

^b BRUNEL UNIVERSITY   (United Kingdom)

^c KING ABDULAZIZ UNIVERSITY   (Saudi Arabia)

Author keywords

Lyapunov functional; Matrix inequality; Non fragility; Recurrent neural networks; State estimation; Time delays

Indexed keywords

CLOSED LOOP SYSTEMS; ESTIMATION; LINEAR MATRIX INEQUALITIES; LYAPUNOV FUNCTIONS; MATRIX ALGEBRA; NEURAL NETWORKS; RECURRENT NEURAL NETWORKS; ROBUSTNESS (CONTROL SYSTEMS); STATE ESTIMATION; TIME DELAY;

ADMISSIBLE PARAMETERS; CONTINUOUS NEURAL NETWORKS; DELAYED NEURAL NETWORKS; LYAPUNOV FUNCTIONALS; MATRIX INEQUALITY; MULTIPLICATIVE PARAMETERS; NON-FRAGILITY; NONLINEAR PERTURBATIONS;

PARAMETER ESTIMATION;

ANALOG DIGITAL CONVERTER; ARTICLE; ARTIFICIAL NEURAL NETWORK; COMPUTER; FUZZY SYSTEM; KAPLAN MEIER METHOD; MARKOV CHAIN; PARAMETERS; PRIORITY JOURNAL; QUANTITATIVE STUDY; RECURRENT NEURAL NETWORK; SIMULATION; TIME DELAY; TIME PERCEPTION; TIME SERIES ANALYSIS;

EID: 84965176668     PISSN: 09252312     EISSN: 18728286     Source Type: Journal    
DOI: 10.1016/j.neucom.2016.02.062     Document Type: Article

References (38)

1. Boyd S., Ghaoui L.E., Feron E., Balakrishnan V. Linear Matrix Inequalities in System and Control Theory 1994, SIAM, Philadelphia, PA.
2. P. Dorato, Non-fragile controller design: an overview, in: Proceedings of American Control Conference, Philadelphia, Pennsylvania, 1998, pp. 2829-2831.
3. Elanayar V.T.S., Shin Y.C. Approximation and estimation of nonlinear stochastic dynamic systems using radial basis function neural networks. IEEE Trans. Neural Netw. 1994, 5(4):594-603.
4. Fang M., Park J.H. Non-fragile synchronization of neural networks with time-varying delay and randomly occurring controller gain fluctuation. Appl. Math. Comput. 2013, 219(15):8009-8017.
5. R. Habtom, L. Litz, Estimation of unmeasured inputs using recurrent neural networks and the extended Kalman filter, in: International Conference on Neural Networks, Houston, Texas, USA, vol. 4, 1997, pp. 2067-2071.
6. He Y., Wang Q., Wu M., Lin C. Delay-dependent state estimation for delayed neural networks. IEEE Trans. Neural Netw. 2006, 17(4):1077-1081.
7. Hua C., Guan X. Output feedback stabilization for time-delay nonlinear interconnected systems using neural networks. IEEE Trans. Neural Netw. 2008, 19(4):673-688.
8. Hua C., Guan X., Shi P. Robust output feedback tracking control for time-delay nonlinear systems using neural network. IEEE Trans. Neural Netw. 2007, 18(2):495-505.
9. Huang H., Feng G., Cao J. An LMI approach to delay-dependent state estimation for delayed neural networks. Neurocomputing 2008, 71(13-15):2857-2867.
10. Keel L., Bhattacharyya S. Robust, fragile, or optimal. IEEE Trans. Autom. Control 1997, 42:1098-1105.
11. Lien C.H., Cheng W.C., Tsai C.H., Yu K.W. Non-fragile observer-based controls of linear system via LMI approach. Chaos Solitons Fractals 2007, 32(4):1530-1537.
12. Jian J., Zhao Z. Global stability in Lagrange sense for BAM-type Cohen-Grossberg neural networks with time-varying delays. Syst. Sci. Control Eng.: Open Access J. 2015, 3(1):1-7.
13. Liu Y., Wang Z., Liu X. Global exponential stability of generalized recurrent neural networks with discrete and distributed delays. Neural Netw. 2006, 19:667-675.
14. Wu L., Ho D.W.C. Fuzzy filter design for Ito stochastic systems with application to sensor fault detection. IEEE Trans. Fuzzy Syst. 2009, 17(1):233-242.
15. X. Luo, Q. Ye, B. Cui, Observer-based control for state estimation of uncertain fuzzy neural networks with time-varying delay, in: Proceedings of the 33rd Chinese Control Conference, Nanjing, China, 2014, pp. 5096-5101.
16. ∞ and passivity state estimation of memristive neural networks with random gain fluctuations. Neurocomputing 2015, 168(November):1111-1120.
17. Kermania M., Sakly A. Stability analysis for a class of switched nonlinear time-delay systems. Syst. Sci. Control Eng.: Open Access J. 2014, 2(1):80-89.
18. ∞ control for a class of nonlinear Markovian jump systems with probabilistic sensor failures. Int. J. Control 2011, 84(11):1847-1857.
19. Dong H., Wang Z., Alsaadi F.E., Ahmad B. Event-triggered robust distributed state estimation for sensor networks with state-dependent noises. Int. J. Gen. Syst. 2015, 44(2):254-266.
20. F.M. Salam, J. Zhang, Adaptive neural observer with forward co-state propagation, in: International Joint Conference on Neural Networks, Washington, D.C., vol. 1, 2001, pp. 675-680.
21. Dong H., Wang Z., Ding S.X., Gao H. Finite-horizon estimation of randomly occurring faults for a class of nonlinear time-varying systems. Automatica 2014, 50(12):3182-3189.
22. 2 fault detection for Markovian jumping two-dimensional systems. Automatica 2012, 48(8):1741-1750.
23. Vembarasan V., Balasubramaniam P., Chan C.S. Non-fragile state observer design for neural networks with Markovian jumping parameters and time-delays. Nonlinear Anal.-Hybrid Syst. 2014, 14(November):61-73.
24. Dong H., Wang Z., Ding S.X., Gao H. Finite-horizon reliable control with randomly occurring uncertainties and nonlinearities subject to output quantization. Automatica 2015, 52:355-362.
25. Wang Z., Ho D.W.C., Liu X. State estimation for delayed neural networks. IEEE Trans. Neural Netw. 2005, 16(1):279-284.
26. Wu S.L., Li K.L., Huang T.Z. Exponential stability of static neural networks with time delay and impulses. IET Control Theory Appl. 2011, 5:943-951.
27. Wu Z., Su H., Chu J. State estimation for discrete Markovian jumping neural networks with time delay. Neurocomputing 2010, 73:2247-2254.
28. ∞ control for nonlinear stochastic Ito^ systems using neural network. Int. J. Control Autom. Syst. 2012, 10(5):873-882.
29. ∞ state estimation with fading measurements, randomly varying nonlinearities and probabilistic distributed delays. Int. J. Robust Nonlinear Control 2015, 25(13):2180-2195.
30. ∞ control for discrete time-varying systems with randomly occurring nonlinearities and fading measurements. IEEE Trans. Autom. Control 2015, 60(9):2488-2493.
31. Ding S.X., Shen B., Wang Z., Zhong M. A fault detection scheme for linear discrete-time systems with an integrated online performance evaluation. Automatica 2014, 87(12):2511-2552.
32. ∞ filtering with fading measurements and randomly occurring nonlinearities. the finite horizon case. Automatica 2015, 55:37-45.
33. S. Zhang, H. Liu, D. Gao, W. Wang, Determing the input time delay τ of a neural network for nonlinear time series prediction, in: Proceedings of the 2nd International Conference on Machine Learning and Cybernetics, Xi[U+05F3]an, China, 2003, pp. 1255-1258.
34. Shen B., Wang Z., Huang T. Stabilization for sampled-data systems under noisy sampling interval. Automatica 2016, 63(1):162-166.
35. Zhou Q., Shi P., Xu S., Li H. Observer-based adaptive neural network control for nonlinear stochastic systems with time delay. IEEE Trans. Neural Netw. Learn. Syst. 2012, 24(1):71-80.
36. ∞ state estimation for complex networks with uncertain inner coupling and incomplete measurements. IEEE Trans. Neural Netw. Learn. Syst. 2013, 24(12):2027-2037.
37. S. Zhang, Z. Wang, D. Ding, H. Dong, F. Alsaadi, T. Hayat, Non-fragile H∞ fuzzy filtering with randomly occurring gain variations and channel fadings, IEEE Trans. Fuzzy Syst., 2015, doi:10.1109/TFUZZ.2015.2446509.
38. Wei G., Liu S., Song Y., Liu Y. Probability-guaranteed set-membership filtering for systems with incomplete measurements. Automatica 2015, 24(60):12-16.