Skip to main content
Springer Nature Link
Log in

Guaranteed performance control for delayed Markov jump neural networks with output quantization and data-injection attacks

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

This paper considers guaranteed performance control for delayed Markov jump neural networks (DMJNNs) under output quantization and data-injection attacks. The objective is to design an asynchronous output-feedback controller (OFC) that takes into account both quantization and attacks to achieve stochastic stability and ensure the boundedness of a predefined performance index. An exponential hidden Markov model is employed to represent the asynchrony between the modes of the OFC and the DMJNN. A sufficient condition for the desired performance is presented using free-weight matrix and Lyapunov–Krasovskii functional methods, integral inequalities, and Dynkin’s formula. Two distinct controller design approaches are proposed, depending on whether the coefficient matrix of the control input is a unit matrix while considering factors related to attacks and quantization. Optimization algorithms are developed based on the proposed controller design approaches, allowing for the determination of the minimum upper bound of the predefined performance index and the accompanying controller gains. Finally, a simulation example is provided to illustrate the applicability and effectiveness of the optimization algorithms developed.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Algorithm 1
Algorithm 2
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data availability

No datasets were generated or analyzed during the current study.

References

  1. Marcus CM, Westervelt RM (1989) Stability of analog neural networks with delay. Phys Rev A 39(1):347

    MathSciNet  MATH  Google Scholar 

  2. Baldi P, Atiya AF (1994) How delays affect neural dynamics and learning. IEEE Trans Neural Netw 5(4):612–621

    MATH  Google Scholar 

  3. Faydasicok O, Arik S (2022) A novel Lyapunov stability analysis of neutral-type Cohen-Grossberg neural networks with multiple delays. Neural Netw 155:330–339

    MATH  Google Scholar 

  4. Wang J, Qin Z, Wu H, Huang T (2019) Passivity and synchronization of coupled uncertain reaction-diffusion neural networks with multiple time delays. IEEE Trans Neural Netw Learn Syst 30(8):2434–2448

    MathSciNet  MATH  Google Scholar 

  5. Song Q, Yu Q, Zhao Z, Liu Y, Alsaadi FE (2018) Boundedness and global robust stability analysis of delayed complex-valued neural networks with interval parameter uncertainties. Neural Netw 103:55–62

    MATH  Google Scholar 

  6. Wang Y, Lu J, Li X, Liang J (2020) Synchronization of coupled neural networks under mixed impulsive effects: a novel delay inequality approach. Neural Netw 127:38–46

    MATH  Google Scholar 

  7. Luo Y, Wang Z, Sheng W, Yue D (2021) State estimation for discrete time-delayed impulsive neural networks under communication constraints: A delay-range-dependent approach. IEEE Trans Neural Netw Learn Syst 34(3):1489–1501

    MathSciNet  MATH  Google Scholar 

  8. Wang Y, Zheng C, Lin M (2023) Robust stability of complex-valued fractional-order neural networks with uncertain parameters based on new integral inequalities. Int J Mach Learn Cybern 14:4377–4391

    MATH  Google Scholar 

  9. Vadivel R, Hammachukiattikul P, Gunasekaran N, Saravanakumar R, Dutta H (2021) Strict dissipativity synchronization for delayed static neural networks: an event-triggered scheme. Chaos Solitons Fract 150:111212

    MathSciNet  MATH  Google Scholar 

  10. Bhuvaneshwari G, Prakash M, Lakshmanan S, Manivannan A (2022) Synchronization of stochastic neural networks using looped-Lyapunov functional and its application to secure communication. IEEE Trans Neural Netw Learn Syst. 35(4):5198–5210

    MathSciNet  MATH  Google Scholar 

  11. Yang J, Chen G, Zhu S, Wen S, Hu J (2023) Fixed/prescribed-time synchronization of BAM memristive neural networks with time-varying delays via convex analysis. Neural Netw 163:53–63

    MATH  Google Scholar 

  12. Yan Z, Huang X, Fan Y, Xia J, Shen H (2021) Threshold-function-dependent quasi-synchronization of delayed memristive neural networks via hybrid event-triggered control. IEEE Trans Syst Man Cybern Syst 51(11):6712–6722

    MATH  Google Scholar 

  13. Dong S, Liu L, Feng G, Liu M , Wu Z, Zheng R (2022) Cooperative output regulation quadratic control for discrete-time heterogeneous multiagent Markov jump systems. IEEE Trans Cybern 52(9):9882–9892

    MATH  Google Scholar 

  14. Guo Y, Ma X, Ma Y, Fu L (2023) Dissipativity-based asynchronous control for time-varying delay T-S fuzzy Markov jump systems with multisource disturbances and input saturation. Int J Mach Learn Cybern 15:1343–1359

    MATH  Google Scholar 

  15. Selvaraj P, Sakthivel R, Kwon OM (2018) Finite-time synchronization of stochastic coupled neural networks subject to Markovian switching and input saturation. Neural Netw 105:154–165

    MATH  Google Scholar 

  16. Manickam I, Ramachandran R, Rajchakit G, Cao J, Huang C (2020) Novel Lagrange sense exponential stability criteria for time-delayed stochastic Cohen-Grossberg neural networks with Markovian jump parameters: a graph-theoretic approach. Nonlinear Anal Model Control 25(5):726–744

    MathSciNet  MATH  Google Scholar 

  17. Zhou J, Liu Y, Xia J, Wang Z, Arik S (2020) Resilient fault-tolerant anti-synchronization for stochastic delayed reaction-diffusion neural networks with semi-Markov jump parameters. Neural Netw 125:194–204

    MATH  Google Scholar 

  18. Song X, Man J, Ahn CK, Song S (2021) Finite-time dissipative synchronization for Markovian jump generalized inertial neural networks with reaction-diffusion terms. IEEE Trans Syst Man Cybern Syst 51(6):3650–3661

    MATH  Google Scholar 

  19. Wang J, Wang Z, Chen X, Qiu J (2021) Synchronization criteria of delayed inertial neural networks with generally Markovian jumping. Neural Netw 139:64–76

    MATH  Google Scholar 

  20. Lin Y, Zhuang G, Xia J, Sun W, Zhao J (2022) Asynchronous \(H_{\infty }\) dynamic output feedback control for Markovian jump neural networks with time-varying delays. Int J Control Autom Syst 20(3):909–923

    MATH  Google Scholar 

  21. Qin X, Dong J, Zhang X, Jiang T, Zhou J (2023) \(H_{\infty }\) control of time-delayed Markov jump systems subject to mismatched modes and interval conditional probabilities. Arab J Sci Eng. 49:7471–7486

    MATH  Google Scholar 

  22. Han X, Wu K, Niu Y (2023) Asynchronous boundary control of Markov jump neural networks with diffusion terms. IEEE Trans Cybern 53(8):4962–4971

    MATH  Google Scholar 

  23. Chang X, Xiong J, Li Z, Park JH (2018) Quantized static output feedback control for discrete-time systems. IEEE Trans Industr Inf 14(8):3426–3435

    MATH  Google Scholar 

  24. Song S, Park JH, Zhang B, Song X (2022) Composite adaptive fuzzy finite-time quantized control for full state-constrained nonlinear systems and its application. IEEE Trans Syst Man Cybern Syst 52(4):2479–2490

    MATH  Google Scholar 

  25. Zhou J, Dong J, Xu S (2023) Asynchronous dissipative control of discrete-time fuzzy Markov jump systems with dynamic state and input quantization. IEEE Trans Fuzzy Syst 31(11):3906–3920

    MATH  Google Scholar 

  26. Qiu H, Liu H, Zhang X (2023) Composite adaptive fuzzy backstepping control of uncertain fractional-order nonlinear systems with quantized input. Int J Mach Learn Cybern 14(3):833–847

    MATH  Google Scholar 

  27. Xiong L, Cai L, Cao J, Wu T, Zhang H (2023) Stochastic quantized control for memristive neural networks with mixed semi-Markov jump and sampled-data communications using a novel approach. Knowl-Based Syst 277:110751

    MATH  Google Scholar 

  28. Yang X, Song Q, Cao J, Lu J (2019) Synchronization of coupled Markovian reaction-diffusion neural networks with proportional delays via quantized control. IEEE Trans Neural Netw Learn Syst 30(3):951–958

    MathSciNet  MATH  Google Scholar 

  29. Qi W, Park JH, Zong G, Cao J, Cheng J (2021) Synchronization for quantized semi-Markov switching neural networks in a finite time. IEEE Trans Neural Netw Learn Syst 32(3):1264–1275

    MathSciNet  MATH  Google Scholar 

  30. Zhou J, Xu D, Tai W, Ahn CK (2023) Switched event-triggered \(H_{\infty }\) security control for networked systems vulnerable to aperiodic DoS attacks. IEEE Trans Netw Sci Eng 10(4):2109–2123

    MathSciNet  MATH  Google Scholar 

  31. Qi Y, Yuan S, Niu B (2021) Asynchronous control for switched T-S fuzzy systems subject to data injection attacks via adaptive event-triggering schemes. IEEE Trans Syst Man Cybern Syst 52(7):4658–4670

    MATH  Google Scholar 

  32. Luo Y, Wang Z, Hu J, Dong H, Yue D (2023) Security-guaranteed fuzzy networked state estimation for 2-D systems with multiple sensor arrays subject to deception attacks. IEEE Trans Fuzzy Syst 31(10):3624–3638

    MATH  Google Scholar 

  33. Franze G, Tedesco F, Lucia W (2019) Resilient control for cyber-physical systems subject to replay attacks. IEEE Control Syst Lett 3(4):984–989

    MathSciNet  MATH  Google Scholar 

  34. Sakthivel R, Kwon O-M, Choi S-G, Sakthivel R (2023) Observer-based state estimation for discrete-time semi-Markovian jump neural networks with round-robin protocol against cyber attacks. Neural Netw 165:611–624

    MATH  Google Scholar 

  35. Yao L, Huang X (2023) Memory-based adaptive event-triggered secure control of Markovian jumping neural networks suffering from deception attacks. Sci China Technol Sci 66(2):468–480

    MATH  Google Scholar 

  36. Liu K, Seuret A, Xia Y (2017) Stability analysis of systems with time-varying delays via the second-order Bessel-Legendre inequality. Automatica 76:138–142

    MathSciNet  MATH  Google Scholar 

  37. Han J, Zhang Z, Zhang X, Zhou J (2020) Design of passive filters for time-delay neural networks with quantized output. Chin Phys B 29(11):110201

    MATH  Google Scholar 

  38. Peixoto MLC, Coutinho PHS, Lacerda MJ, Palhares RM (2022) Guaranteed region of attraction estimation for time-delayed fuzzy systems via static output-feedback control. Automatica 143:110438

    MathSciNet  MATH  Google Scholar 

  39. Aktas E, Faydasicok O, Arik S (2023) Robust stability of dynamical neural networks with multiple time delays: a review and new results. Artif Intell Rev 26:1647–1684

    MATH  Google Scholar 

  40. Wang Z, Liu L, Shan Q, Zhang H (2015) Stability criteria for recurrent neural networks with time-varying delay based on secondary delay partitioning method. IEEE Trans Neural Netw Learn Syst 26(10):2589–2595

    MathSciNet  MATH  Google Scholar 

  41. Fu M, Xie L (2005) The sector bound approach to quantized feedback control. IEEE Trans Autom Control 50(11):1698–1711

    MathSciNet  MATH  Google Scholar 

  42. Luo Y, Wang Z, Chen Y, Yi X (2021) \(H_{\infty }\) state estimation for coupled stochastic complex networks with periodical communication protocol and intermittent nonlinearity switching. IEEE Trans Netw Sci Eng 8(2):1414–1425

    MathSciNet  MATH  Google Scholar 

  43. Kazemy A, Lam J, Zhang X (2022) Event-triggered output feedback synchronization of master-slave neural networks under deception attacks. IEEE Trans Neural Netw Learn Syst 33(3):952–961

    MathSciNet  MATH  Google Scholar 

  44. Stadtmann F, Costa OLV (2018) Exponential hidden Markov models for \(H_{\infty }\) control of jumping systems. IEEE Control Syst Lett 2(4):845–850

    MathSciNet  MATH  Google Scholar 

  45. Song Y (1995) Guaranteed performance control of nonlinear systems with application to flexible space structure. J Guid Control Dyn 18(1):143–150

    MATH  Google Scholar 

  46. Nguyen NT (2018) Model-reference adaptive control. Springer, Cham, Switzerland

    MATH  Google Scholar 

  47. Cao Y, Lam J (2000) Robust \(H_{\infty }\) control of uncertain Markovian jump systems with time-delay. IEEE Trans Autom Control 45:77–83

    MathSciNet  MATH  Google Scholar 

  48. Seuret A, Gouaisbaut F (2015) Hierarchy of LMI conditions for the stability analysis of time-delay systems. Syst Control Lett 81:1–7

    MathSciNet  MATH  Google Scholar 

  49. Zeng H, He Y, Wu M, She J (2015) New results on stability analysis for systems with discrete distributed delay. Automatica 60:189–192

    MathSciNet  MATH  Google Scholar 

  50. Park PG, Ko JW, Jeong C (2011) Reciprocally convex approach to stability of systems with time-varying delays. Automatica 47(1):235–238

    MathSciNet  MATH  Google Scholar 

  51. Khalil IS, Doyle JC, Glover K (1996) Robust and optimal control. Prentice hall, New York

    MATH  Google Scholar 

  52. Stephen B, Laurent EG, Eric F, Venkataramanan B (1994) Linear Matrix Inequalities in System and Control Theory. SIAM

  53. Zhou J, Park JH, Shen H (2016) Non-fragile reduced-order dynamic output feedback \(H_{\infty }\) control for switched systems with average dwell-time switching. Int J Control 89(2):281–296

    MathSciNet  MATH  Google Scholar 

  54. Nallappan Gunasekaran M, Ali S, Sabri Arik HI, Ghaffar A, Zaki AA (2022) Finite-time and sampled-data synchronization of complex dynamical networks subject to average dwell-time switching signal. Neural Netw 149:137–145

    MATH  Google Scholar 

  55. Li W, Xie Y, Li Y, Geng K, Nguyen AT, Zhu X (2023) Robust lateral motion control of distributed drive vehicle considering long input delays. Int J Robust Nonlinear Control 33(5):3185–3209

    MATH  Google Scholar 

  56. Min W, He Y, She J (2010) Stability analysis and robust control of time-delay systems. Springer, New York

    MATH  Google Scholar 

  57. Castelan EB, Tarbouriech S, Queinnec I (2008) Control design for a class of nonlinear continuous-time systems. Automatica 44(8):2034–2039

    MathSciNet  MATH  Google Scholar 

  58. Lu H (2002) Chaotic attractors in delayed neural networks. Phys Lett A 298(2–3):109–116

    MATH  Google Scholar 

  59. Luo Y, Wang Z, Dong H, Mao J, Alsaadi FE (2023) A novel sequential switching quadratic particle swarm optimization scheme with applications to fast tuning of PID controllers. Inf Sci 633:305–320

    Google Scholar 

  60. Xie Z, Wu Z (2023) Event-triggered consensus control for DC microgrids based on MKELM and state observer against false data injection attacks. Int J Mach Learn Cybern 15:775–793

    MATH  Google Scholar 

  61. Chang M, Wu Y (2022) Speed control of electric vehicle by using type-2 fuzzy neural network. Int J Mach Learn Cybern 13:1647–1660

    MATH  Google Scholar 

  62. Nguyen AT, Sentouh C, Zhang H, Popieul JC (2020) Fuzzy static output feedback control for path following of autonomous vehicles with transient performance improvements. IEEE Trans Intell Transp Syst 21(7):3069–3079

    MATH  Google Scholar 

  63. You L, Li C, Han Y (2020) Consensus of nonlinear multi-agent systems with fuzzy modelling uncertainties via state-constraint hybrid impulsive protocols. Int J Mach Learn Cybern 11(12):2653–2664

    MATH  Google Scholar 

  64. Lamrabet O, Tissir EH, El Haoussi F (2019) Anti-windup compensator synthesis for sampled-data delay systems. Circ Syst Signal Process 38(5):2055–2071

    MathSciNet  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, Anhui University of Technology, Ma’anshan, 243032, Anhui, China

    Lanlan He, Xiaoqing Zhang & Taiping Jiang

  2. College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, 211106, Jiangsu, China

    Chaoying Tang

Authors
  1. Lanlan He
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Xiaoqing Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Taiping Jiang
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Chaoying Tang
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

Lanlan He: investigation, software, writing. Xiaoqing Zhang: investigation, validation. Taiping Jiang: conceptualization, methodology. Chaoying Tang: methodology, supervision.

Corresponding author

Correspondence to Taiping Jiang.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

He, L., Zhang, X., Jiang, T. et al. Guaranteed performance control for delayed Markov jump neural networks with output quantization and data-injection attacks. Int. J. Mach. Learn. & Cyber. 16, 173–188 (2025). https://doi.org/10.1007/s13042-024-02195-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-024-02195-3

Keywords