×

A novel interval approximation method for passivity and stability analysis of delayed neural networks. (English) Zbl 1536.93644

Summary: This paper studies passivity analysis and stability analysis for neural networks with time-variant delay. The time-variant delay is presumed to respond in trigonometric form. Firstly, a novel interval approximation method is constructed with adjustable parameters, which can be adjusted to reduce conservatism. According to the feature of time delay in trigonometric form, the specific allowable delay set can be obtained. Secondly, by introducing the delay-product-type parts in Lyapunov-Krasovskii functional (LKF), the emphatically improved passivity criterion and stability criterion with less conservatism are obtained by using the advanced inequalities. Finally, two numerical simulations are listed where our work can obtain larger maximum allowable delay bounds compared with other works, which demonstrate that the results based on the interval approximation method are less conservative.

MSC:

93D05 Lyapunov and other classical stabilities (Lagrange, Poisson, \(L^p, l^p\), etc.) in control theory
93B70 Networked control
93C43 Delay control/observation systems

Software:

YALMIP
Full Text: DOI

References:

[1] Li, X.; Wen, C.; Chen, C., Adaptive formation control of networked robotic systems with bearing-only measurements, IEEE Trans. Cybern., 51, 199-209, (2021)
[2] Yin, R.; Pan, X.; Zhang, L.; Yang, J.; Lu, W., A rule-based deep fuzzy system with nonlinear fuzzy feature transform for data classification, Inf. Sci., 633, 431-452, (2023)
[3] Yang, J.; Zhao, J., A novel parallel merge neural network with streams of spiking neural network and artificial neural network, Inf. Sci., Article 119034 pp., (2023) · Zbl 1536.92012
[4] Li, M.; Huang, P.; Chang, X.; Hu, J.; Yang, Y.; Hauptmann, A., Video pivoting unsupervised multi-modal machine translation, IEEE Trans. Pattern Anal. Mach. Intell., 45, 3918-3932, (2023)
[5] Li, C.; Wang, G.; Wang, B.; Liang, X.; Li, Z.; Chang, X., DS-Net++: dynamic weight slicing for efficient inference in CNNs and vision transformers, IEEE Trans. Pattern Anal. Mach. Intell., 45, 4430-4446, (2023)
[6] Zhang, L.; Chang, X.; Liu, J.; Luo, M.; Li, Z.; Yao, L.; Hauptmann TN-ZSTAD, A., Transferable network for zero-shot temporal activity detection, IEEE Trans. Pattern Anal. Mach. Intell., 45, 3848-3861, (2023)
[7] Mestari, M.; Benzirar, M.; Saber, N.; Khouil, M., Solving nonlinear equality constrained multiobjective optimization problems using neural networks, IEEE Trans. Neural Netw. Learn. Syst., 26, 2500-2520, (2015)
[8] Jaberi, M.; Ravanmehr, R., Human activity recognition via wearable devices using enhanced ternary weight convolutional neural network, Pervasive Mob. Comput., Article 101620 pp., (2022)
[9] Kumar, S. R.; Devakumar, J., Performance evaluation of neural network topologies for online state estimation and fault detection in pressurized water reactor, Ann. Nucl. Energy, 175, Article 109235 pp., (2022)
[10] Yang, Y.; Cao, J., Solving quadratic programming problems by delayed projection neural network, IEEE Trans. Neural Netw., 17, 1630-1634, (2006)
[11] Chu, Y.; Fei, J.; Hou, S., Adaptive global sliding-mode control for dynamic systems using double hidden layer recurrent neural network structure, IEEE Trans. Neural Netw. Learn. Syst., 31, 1297-1309, (2020)
[12] Zhu, S.; Bao, H.; Cao, J., Bipartite synchronization of coupled delayed neural networks with cooperative-competitive interaction via event-triggered control, Phys. A, Stat. Mech. Appl., 600, Article 127586 pp., (2022) · Zbl 07543464
[13] Rakkiyappan, R.; Cao, J.; Velmurugan, G., Existence and uniform stability analysis of fractional-order complex-valued neural networks with time delays, IEEE Trans. Neural Netw. Learn. Syst., 26, 84-97, (2015)
[14] Wang, Z.; Liu, L.; Shan, Q. H.; Zhang, H., Stability criteria for recurrent neural networks with time-varying delay based on secondary delay partitioning method, IEEE Trans. Neural Netw. Learn. Syst., 26, 2589-2595, (2015)
[15] Maharajan, C.; Raja, R.; Cao, J.; Rajchakit, G.; Alsaedi, A., Novel results on passivity and exponential passivity for multiple discrete delayed neutral-type neural networks with leakage and distributed time-delays, Chaos Solitons Fractals, 115, 268-282, (2018) · Zbl 1416.34053
[16] Zhang, X.; Han, Q.; Ge, X.; Zhang, B. L., Delay-variation-dependent criteria on extended dissipativity for discrete-time neural networks with time-varying delay, IEEE Trans. Neural Netw. Learn. Syst., 1-10, (2021)
[17] Saravanakumar, R.; Rajchakit, G.; Ahn, C. K.; Karimi, H. R., Exponential stability, passivity, and dissipativity analysis of generalized neural networks with mixed time-varying delays, IEEE Trans. Syst. Man Cybern. Syst., 49, 395-405, (2019)
[18] Ye, Y.; Xiong, L.; Zhang, H.; Liu, Y., Passivity analysis of delayed neural networks via novel integral inequality, Proc. Comput. Sci., 199, 1292-1299, (2022)
[19] Zhang, X. M.; Han, Q. L.; Ge, X.; Zhang, B. L., Passivity analysis of delayed neural networks based on Lyapunov-Krasovskii functionals with delay-dependent matrices, IEEE Trans. Cybern., 50, 946-956, (2020)
[20] Ge, C.; Park, J. H.; Hua, C.; Shi, C., Robust passivity analysis for uncertain neural networks with discrete and distributed time-varying delays, Neurocomputing, 364, 330-337, (2019)
[21] Michiels, W.; Van Assche, V.; Niculescu, S. I., Stabilization of time-delay systems with a controlled time-varying delay and applications, IEEE Trans. Autom. Control, 50, 493-504, (2005) · Zbl 1365.93411
[22] Lee, T. H.; Park, J. H., Improved stability conditions of time-varying delay systems based on new Lyapunov functionals, J. Franklin Inst., 355, 1176-1191, (2018) · Zbl 1393.93097
[23] Li, S.; Xiang, Z. R., Positivity, exponential stability and disturbance attenuation performance for singular switched positive systems with time-varying distributed delays, Appl. Math. Comput., 372, 1-20, (2020) · Zbl 1433.93083
[24] Pan, X. J.; Yang, B.; Cao, J. J.; Zhao, X. D., Improved stability analysis of Takagi-Sugeno fuzzy systems with time-varying delays via an extended delay-dependent reciprocally convex inequality, Inf. Sci., 571, 24-37, (2021) · Zbl 1535.93017
[25] Zhang, X. M.; Han, Q. L.; Seuret, A.; Gouaisbaut, F.; He, Y., Overview of recent advances in stability of linear systems with time-varying delays, IET Control Theory Appl., 13, 1-16, (2019) · Zbl 1434.93034
[26] Lozano, R.; Brogliato, B.; Egeland, O.; Maschke, B., Dissipative Systems Analysis and Control: Theory and Applications, (2013), Springer Science & Business Media
[27] Gu, V. L.; Kharitonov, K.; Chen, J., Stability of Time-Delay Systems, (2003), Birkhauser · Zbl 1039.34067
[28] Seuret, A.; Gouaisbaut, F., Wirtinger-based integral inequality: application to time-delay systems, Automatica, 49, 2860-2866, (2013) · Zbl 1364.93740
[29] Zhang, X. M.; Han, Q. L., State estimation for static neural networks with time-varying delays based on an improved reciprocally convex inequality, IEEE Trans. Neural Netw. Learn. Syst., 29, 1376-1381, (2018)
[30] Seuret, A.; Gouaisbaut, F., Stability of linear systems with time-varying delays using Bessel-Legendre inequalities, IEEE Trans. Autom. Control, 63, 225-232, (2018) · Zbl 1390.34213
[31] Zeng, H. B.; He, Y.; Teo, K. L., Monotone-delay-interval-based Lyapunov functionals for stability analysis of systems with a periodically varying delay, Automatica, 138, Article 110030 pp., (2022) · Zbl 1489.93093
[32] Zhang, X. M.; Han, Q. L.; Ge, X. H., Novel stability criteria for linear time-delay systems using Lyapunov-Krasovskii functionals with a cubic polynomial on time-varying delay, IEEE/CAA J. Autom. Sin., 8, 77-85, (2021)
[33] J. Lofberg, YALMIP: a toolbox for modeling and optimization in MATLAB, 2004, pp. 284-289.
[34] Zeng, H. B.; Park, J. H.; Shen, H., Robust passivity analysis of neural networks with discrete and distributed delays, Neurocomputing, 149, 1092-1097, (2015)
[35] Zhang, X. M.; Han, Q. L., Global asymptotic stability for a class of generalized neural networks with interval time-varying delays, IEEE Trans. Neural Netw., 22, 1180-1192, (2011)
[36] Thuan, M.; Trinh, H.; Hien, L., New inequality-based approach to passivity analysis of neural networks with interval time-varying delay, Neurocomputing, 194, 301-307, (2016)
[37] Lee, T. H.; Trinh, H. M.; Park, J. H., Stability analysis of neural networks with time-varying delay by constructing novel Lyapunov functionals, IEEE Trans. Neural Netw. Learn. Syst., 29, 4238-4247, (2018)
[38] Long, F.; Zhang, C. K.; He, Y.; Wang, Q. G.; Wu, M., Stability analysis for delayed neural networks via a novel negative-definiteness determination method, IEEE Trans. Cybern., 1-11, (2020)
[39] Lin, H. C.; Zeng, H. B.; Zhang, X. M.; Wang, W., Stability analysis for delayed neural networks via a generalized reciprocally convex inequality, IEEE Trans. Neural Netw. Learn. Syst., 1-9, (2022)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.