具有脉冲和时滞的四元数神经网络的输入到状态稳定性
Input-to-State Stability of Quaternion-Valued Neural Networks with Impulses and Time Delay
摘要: 本文主要研究具有脉冲和时滞的四元数神经网络(QVNN)的输入到状态稳定(ISS)。首先，由于四元数乘法不适用于交换律，所以我们将四元数神经网络分解为四个实值神经网络来进行分析，然后通过比较原理和平均脉冲间隔方法，以及利用Lyapunov-Krasovskii函数和一些矩阵不等式，提出了一些充分的条件，以确保所考虑的系统是输入到状态稳定(ISS)。最后，我们给出了一个数值模拟例子及其仿真图来证明理论结果的正确性和有效性。
Abstract: In this paper, the input-to-state stability of quaternion-valued neural networks (QVNN) with impulses and time delay is investigated. First of all, in virtue of the quaternion multiplication is not suitable for commutative law, QVNN is resolved into four real-valued neural networks (RVNNs). With the help of the comparison principle and average impulse interval approach, and making use of a Lyapunov function and some inequalities, we obtain sufficient conditions to assure the considered system is ISS. Finally, one numerical example and their simulations are given to show the correctness and effectiveness of our theoretical results.
文章引用：马楠. 具有脉冲和时滞的四元数神经网络的输入到状态稳定性[J]. 理论数学, 2025, 15(4): 381-393. https://doi.org/10.12677/pm.2025.154140

参考文献

[1] 张守武, 王恒, 陈鹏, 等. 神经网络在无人驾驶车辆运动控制中的应用综述[J]. 工程科学学报, 2022, 44(2): 235-243.
[2] Mohareri, O., Dhaouadi, R. and Rad, A.B. (2012) Indirect Adaptive Tracking Control of a Nonholonomic Mobile Robot via Neural Networks. Neurocomputing, 88, 54-66. [Google Scholar] [CrossRef] 
[3] Shitong, W. and Min, W. (2006) A New Detection Algorithm (NDA) Based on Fuzzy Cellular Neural Networks for White Blood Cell Detection. IEEE Transactions on Information Technology in Biomedicine, 10, 5-10. [Google Scholar] [CrossRef] [PubMed]
[4] Cao, J.D. (2001) Global Stability Conditions for Delayed CNNs. IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications, 48, 1330-1333. [Google Scholar] [CrossRef] 
[5] Xiang, M., Scalzo Dees, B. and Mandic, D.P. (2019) Multiple-Model Adaptive Estimation for 3-D and 4-D Signals: A Widely Linear Quaternion Approach. IEEE Transactions on Neural Networks and Learning Systems, 30, 72-84. [Google Scholar] [CrossRef] [PubMed]
[6] Ayrulu, B. and Barshan, B. (2001) Neural Networks for Improved Target Differentiation and Localization with Sonar. Neural Networks, 14, 355-373. [Google Scholar] [CrossRef] [PubMed]
[7] Zou, C., Kou, K.I. and Wang, Y. (2016) Quaternion Collaborative and Sparse Representation with Application to Color Face Recognition. IEEE Transactions on Image Processing, 25, 3287-3302. [Google Scholar] [CrossRef] [PubMed]
[8] Rajchakit, G., Chanthorn, P., Niezabitowski, M., Raja, R., Baleanu, D. and Pratap, A. (2020) Impulsive Effects on Stability and Passivity Analysis of Memristor-Based Fractional-Order Competitive Neural Networks. Neurocomputing, 417, 290-301. [Google Scholar] [CrossRef] 
[9] Isokawa, T., Kusakabe, T., Matsui, N. and Peper, F. (2003) Quaternion Neural Network and Its Application. Knowledge-Based Intelligent Information and Engineering Systems: 7th International Conference, KES 2003, Oxford, September 2003, 318-324. [Google Scholar] [CrossRef] 
[10] Kusamichi, H., Isokawa, T., Matsui, N., et al. (2004) A New Scheme for Color Night Vision by Quaternion Neural Network. Proceedings of the 2nd International Conference on Autonomous Robots and Agents, New Orleans, 26 April-1 May 2004, 1315.
[11] Pei, S.-C. and Cheng, C.-M. (1997) A Novel Block Truncation Coding of Color Images Using a Quaternion-Moment-Preserving Principle. IEEE Transactions on Communications, 45, 583-595. [Google Scholar] [CrossRef] 
[12] Shu, H., Song, Q., Liu, Y., Zhao, Z. and Alsaadi, F.E. (2017) Global μ-Stability of Quaternion-Valued Neural Networks with Non-Differentiable Time-Varying Delays. Neurocomputing, 247, 202-212. [Google Scholar] [CrossRef] 
[13] Zhang, D., Kou, K.I., Liu, Y. and Cao, J. (2017) Decomposition Approach to the Stability of Recurrent Neural Networks with Asynchronous Time Delays in Quaternion Field. Neural Networks, 94, 55-66. [Google Scholar] [CrossRef] [PubMed]
[14] Qi, X., Bao, H. and Cao, J. (2019) Exponential Input-to-State Stability of Quaternion-Valued Neural Networks with Time Delay. Applied Mathematics and Computation, 358, 382-393. [Google Scholar] [CrossRef] 
[15] Zhu, J. and Sun, J. (2018) Stability of Quaternion-Valued Impulsive Delay Difference Systems and Its Application to Neural Networks. Neurocomputing, 284, 63-69. [Google Scholar] [CrossRef] 
[16] Yang, X., Li, C., Song, Q., Li, H. and Huang, J. (2019) Effects of State-Dependent Impulses on Robust Exponential Stability of Quaternion-Valued Neural Networks under Parametric Uncertainty. IEEE Transactions on Neural Networks and Learning Systems, 30, 2197-2211. [Google Scholar] [CrossRef] [PubMed]
[17] Popa, C. and Kaslik, E. (2018) Multistability and Multiperiodicity in Impulsive Hybrid Quaternion-Valued Neural Networks with Mixed Delays. Neural Networks, 99, 1-18. [Google Scholar] [CrossRef] [PubMed]
[18] Zhong, S. and Liu, X. (2007) Exponential Stability and Periodicity of Cellular Neural Networks with Time Delay. Mathematical and Computer Modelling, 45, 1231-1240. [Google Scholar] [CrossRef] 
[19] Yunquan, K. and Chunfang, M. (2012) Stability and Existence of Periodic Solutions in Inertial BAM Neural Networks with Time Delay. Neural Computing and Applications, 23, 1089-1099. [Google Scholar] [CrossRef] 
[20] Liu, Y., Zhang, D. and Lu, J. (2016) Global Exponential Stability for Quaternion-Valued Recurrent Neural Networks with Time-Varying Delays. Nonlinear Dynamics, 87, 553-565. [Google Scholar] [CrossRef] 
[21] Li, H., Jiang, H. and Cao, J. (2020) Global Synchronization of Fractional-Order Quaternion-Valued Neural Networks with Leakage and Discrete Delays. Neurocomputing, 385, 211-219. [Google Scholar] [CrossRef] 
[22] Tu, Z., Yang, X., Wang, L. and Ding, N. (2019) Stability and Stabilization of Quaternion-Valued Neural Networks with Uncertain Time-Delayed Impulses: Direct Quaternion Method. Physica A: Statistical Mechanics and Its Applications, 535, Article ID: 122358. [Google Scholar] [CrossRef] 
[23] Jiang, Z. and Wang, Y. (2001) Input-to-State Stability for Discrete-Time Nonlinear Systems. Automatica, 37, 857-869. [Google Scholar] [CrossRef] 
[24] Wang, Y., Sun, X. and Wu, B. (2015) Lyapunov-Krasovskii Functionals for Input‐to‐State Stability of Switched Non‐linear Systems with Time‐Varying Input Delay. IET Control Theory & Applications, 9, 1717-1722. [Google Scholar] [CrossRef] 
[25] Angeli, D., Sontag, E.D. and Wang, Y. (2000) A Characterization of Integral Input-to-State Stability. IEEE Transactions on Automatic Control, 45, 1082-1097. [Google Scholar] [CrossRef] 
[26] Wu, X., Tang, Y. and Zhang, W. (2016) Input-to-State Stability of Impulsive Stochastic Delayed Systems under Linear Assumptions. Automatica, 66, 195-204. [Google Scholar] [CrossRef] 
[27] Wang, Y., Li, X. and Song, S. (2022) Input-to-State Stabilization of Nonlinear Impulsive Delayed Systems: An Observer-Based Control Approach. IEEE/CAA Journal of Automatica Sinica, 9, 1273-1283. [Google Scholar] [CrossRef] 
[28] Yang, Z., Zhou, W. and Huang, T. (2013) Exponential Input-to-State Stability of Recurrent Neural Networks with Multiple Time-Varying Delays. Cognitive Neurodynamics, 8, 47-54. [Google Scholar] [CrossRef] [PubMed]
[29] Hespanha, J.P., Liberzon, D. and Teel, A.R. (2008) Lyapunov Conditions for Input-to-State Stability of Impulsive Systems. Automatica, 44, 2735-2744. [Google Scholar] [CrossRef] 
[30] Chen, X., Li, Z., Song, Q., Hu, J. and Tan, Y. (2017) Robust Stability Analysis of Quaternion-Valued Neural Networks with Time Delays and Parameter Uncertainties. Neural Networks, 91, 55-65. [Google Scholar] [CrossRef] [PubMed]
[31] Boyd, S., El Ghaoui, L., Feron, E. and Balakrishnan, V. (1994) Linear Matrix Inequalities in System and Control Theory. Society for Industrial and Applied Mathematics. [Google Scholar] [CrossRef] 

为你推荐