logo

SCIENTIA SINICA Informationis, Volume 51 , Issue 4 : 618(2021) https://doi.org/10.1360/SSI-2019-0198

Adaptive neural network fault-tolerant control for MIMO systems with dead zone inputs

More info
  • ReceivedNov 19, 2019
  • AcceptedMar 7, 2020
  • PublishedFeb 23, 2021

Abstract


Funded by

国家自然科学基金(61973091)

广东省自然科学基金研究团队项目(2018B030312006)

广州市科技计划项目(201904020006)


References

[1] Ge S S, Wang C. Adaptive NN control of uncertain nonlinear pure-feedback systems. Automatica, 2002, 38: 671-682 CrossRef Google Scholar

[2] Chen C L P, Wen G X, Liu Y J. Observer-Based Adaptive Backstepping Consensus Tracking Control for High-Order Nonlinear Semi-Strict-Feedback Multiagent Systems. IEEE Trans Cybern, 2016, 46: 1591-1601 CrossRef Google Scholar

[3] Wang F, Chen W, Dai H. Backstepping control of a quadrotor unmanned aerial vehicle based on multi-rate sampling. Sci China Inf Sci, 2019, 62: 19203 CrossRef Google Scholar

[4] Liu Y J, Tong S. Barrier Lyapunov functions for Nussbaum gain adaptive control of full state constrained nonlinear systems. Automatica, 2017, 76: 143-152 CrossRef Google Scholar

[5] Chen B, Liu X, Liu K. Direct adaptive fuzzy control of nonlinear strict-feedback systems. Automatica, 2009, 45: 1530-1535 CrossRef Google Scholar

[6] Shao-Cheng Tong , Yong-Ming Li , Gang Feng . Observer-Based Adaptive Fuzzy Backstepping Dynamic Surface Control for a Class of MIMO Nonlinear Systems. IEEE Trans Syst Man Cybern B, 2011, 41: 1124-1135 CrossRef Google Scholar

[7] Mou Chen , Shuzhi Sam Ge , How B. Robust Adaptive Neural Network Control for a Class of Uncertain MIMO Nonlinear Systems With Input Nonlinearities. IEEE Trans Neural Netw, 2010, 21: 796-812 CrossRef Google Scholar

[8] Zhou Q, Shi P, Tian Y. Approximation-Based Adaptive Tracking Control for MIMO Nonlinear Systems With Input Saturation. IEEE Trans Cybern, 2015, 45: 2119-2128 CrossRef Google Scholar

[9] Zheng H, Wang P, Zou T. A framework for multi-variable, semi-adaptive predictive control system. Sci Sin-Inf, 2019, 49: 57-73 CrossRef Google Scholar

[10] Bing Chen , Liu X P, Ge S S. Adaptive Fuzzy Control of a Class of Nonlinear Systems by Fuzzy Approximation Approach. IEEE Trans Fuzzy Syst, 2012, 20: 1012-1021 CrossRef Google Scholar

[11] Wang H Q, Chen B, Lin C. Approximation-based adaptive fuzzy control for a class of non-strict-feedback stochastic nonlinear systems. Sci China Inf Sci, 2014, 57: 1-16 CrossRef Google Scholar

[12] Li Y, Tong S. Command-Filtered-Based Fuzzy Adaptive Control Design for MIMO-Switched Nonstrict-Feedback Nonlinear Systems. IEEE Trans Fuzzy Syst, 2017, 25: 668-681 CrossRef Google Scholar

[13] Ma H, Zhou Q, Bai L. Observer-Based Adaptive Fuzzy Fault-Tolerant Control for Stochastic Nonstrict-Feedback Nonlinear Systems With Input Quantization. IEEE Trans Syst Man Cybern Syst, 2019, 49: 287-298 CrossRef Google Scholar

[14] Wang F, Chen B, Lin C. Distributed Adaptive Neural Control for Stochastic Nonlinear Multiagent Systems. IEEE Trans Cybern, 2017, 47: 1795-1803 CrossRef Google Scholar

[15] Sun Y, Chen B, Lin C. Finite-Time Adaptive Control for a Class of Nonlinear Systems With Nonstrict Feedback Structure. IEEE Trans Cybern, 2018, 48: 2774-2782 CrossRef Google Scholar

[16] Chai T. Industrial process control systems: research status and development direction. Sci Sin-Inf, 2016, 46: 1003-1015 CrossRef Google Scholar

[17] Lu R, Yu W, Lu J. Synchronization on Complex Networks of Networks. IEEE Trans Neural Netw Learning Syst, 2014, 25: 2110-2118 CrossRef Google Scholar

[18] Chai Y, Mao W B, Ren H, et al. Research on operational safety assessment for spacecraft launch system: progress and challenges. Act Autom Sin, 2019, 45: 1829--1845. Google Scholar

[19] Zhang K, Zhou D H, Chai Y. Review of multiple fault diagnosis methods. Control Theory Appl, 2015, 32: 1143--1157. Google Scholar

[20] Shaker M S, Patton R J. Active sensor fault tolerant output feedback tracking control for wind turbine systems via T-S model. Eng Appl Artificial Intelligence, 2014, 34: 1-12 CrossRef Google Scholar

[21] Li H, Gao Y, Shi P. Observer-Based Fault Detection for Nonlinear Systems With Sensor Fault and Limited Communication Capacity. IEEE Trans Automat Contr, 2016, 61: 2745-2751 CrossRef Google Scholar

[22] Zhai D, An L, Li X. Adaptive Fault-Tolerant Control for Nonlinear Systems With Multiple Sensor Faults and Unknown Control Directions. IEEE Trans Neural Netw Learning Syst, 2018, 29: 4436-4446 CrossRef Google Scholar

[23] Lu R, Xu Y, Xue A. Networked Control With State Reset and Quantized Measurements: Observer-Based Case. IEEE Trans Ind Electron, 2013, 60: 5206-5213 CrossRef Google Scholar

[24] Yan X G, Edwards C. Nonlinear robust fault reconstruction and estimation using a sliding mode observer. Automatica, 2007, 43: 1605-1614 CrossRef Google Scholar

[25] Khebbache H, Tadjine M, Labiod S. Adaptive sensor-fault tolerant control for a class of MIMO uncertain nonlinear systems: Adaptive nonlinear filter-based dynamic surface control. J Franklin Institute, 2016, 353: 1313-1338 CrossRef Google Scholar

[26] Bounemeur A, Chemachema M, Essounbouli N. Indirect adaptive fuzzy fault-tolerant tracking control for MIMO nonlinear systems with actuator and sensor failures. ISA Trans, 2018, 79: 45-61 CrossRef Google Scholar

[27] Zhang L, Yang G H. Observer-Based Fuzzy Adaptive Sensor Fault Compensation for Uncertain Nonlinear Strict-Feedback Systems. IEEE Trans Fuzzy Syst, 2018, 26: 2301-2310 CrossRef Google Scholar

[28] Wang W, Xie B, Zuo Z. Adaptive Backstepping Control of Uncertain Gear Transmission Servosystems With Asymmetric Dead-Zone Nonlinearity. IEEE Trans Ind Electron, 2019, 66: 3752-3762 CrossRef Google Scholar

[29] Yu J, Shi P, Dong W. Adaptive Fuzzy Control of Nonlinear Systems With Unknown Dead Zones Based on Command Filtering. IEEE Trans Fuzzy Syst, 2018, 26: 46-55 CrossRef Google Scholar

[30] Li H, Zhao S, He W. Adaptive finite-time tracking control of full state constrained nonlinear systems with dead-zone. Automatica, 2019, 100: 99-107 CrossRef Google Scholar

[31] Li Y, Tong S, Li T. Observer-Based Adaptive Fuzzy Tracking Control of MIMO Stochastic Nonlinear Systems With Unknown Control Directions and Unknown Dead Zones. IEEE Trans Fuzzy Syst, 2015, 23: 1228-1241 CrossRef Google Scholar

[32] Guan X, Luo X, Wu X. Adaptive backstepping fault-tolerant control for unmatched non-linear systems against actuator dead-zone. IET Control Theor Appl, 2010, 4: 879-888 CrossRef Google Scholar

[33] Chen M, Tao G. Adaptive Fault-Tolerant Control of Uncertain Nonlinear Large-Scale Systems With Unknown Dead Zone. IEEE Trans Cybern, 2016, 46: 1851-1862 CrossRef Google Scholar

[34] Zhang T P, Ge S S. Adaptive dynamic surface control of nonlinear systems with unknown dead zone in pure feedback form. Automatica, 2008, 44: 1895-1903 CrossRef Google Scholar

[35] Shen Q, Jiang B, Cocquempot V. Adaptive Fuzzy Observer-Based Active Fault-Tolerant Dynamic Surface Control for a Class of Nonlinear Systems With Actuator Faults. IEEE Trans Fuzzy Syst, 2014, 22: 338-349 CrossRef Google Scholar

[36] Li H, Wang L, Du H. Adaptive Fuzzy Backstepping Tracking Control for Strict-Feedback Systems With Input Delay. IEEE Trans Fuzzy Syst, 2017, 25: 642-652 CrossRef Google Scholar

  • Figure 1

    Types of sensor faults

  • Figure 2

    Nonsymmetric dead-zone nonlinearity

  • Figure 3

    (Color online) (a) Output $y_1$ and reference signal $y_{d1}$; (b) output $y_2$ and reference signal $y_{d2}$ in simulation 1.

  • Figure 4

    (Color online) Adaptive parameters (a) $\hat{\theta}_1$ and (b) $\hat{\theta}_2$ in simulation 1.

  • Figure 5

    (Color online) Dead zone input $\varpi_1$ and dead zone output $u_1$ in simulation 1.

  • Figure 6

    (Color online) Dead zone input $\varpi_2$ and dead zone output $u_2$ in simulation 1.

  • Figure 7

    (Color online) (a) Output $y_1$ and reference signal $y_{d1}$; (b) output $y_2$ and reference signal $y_{d2}$ in simulation 2.

  • Figure 8

    (Color online) Adaptive parameters (a) $\hat{\theta}_1$ and (b) $\hat{\theta}_2$ in simulation 2.

  • Figure 9

    (Color online) Dead zone input $\varpi_1$ and dead zone output $u_1$ in simulation 2.

  • Figure 10

    (Color online) Dead zone input $\varpi_2$ and dead zone output $u_2$ in simulation 2.

  •   

    Algorithm 1

    Step 1.Determine the number of neural network nodes $\iota$, and design the Gaussian function $S_j(\zeta)$.

    Step 2.Based on Step 1, define the neural network $W^{\rm T}S(\zeta)$ to identify the nonlinear functions of the MIMO systems (1).

    Step 3.Select appropriate design parameters $k_{j,1}>0$, $c_{j,1}>0$, $c_{psj}>0$, $\beta_j>0$, $d_j>0$, and design virtual control signal $\alpha_{j,1}$ (10), adaptive law $\dot{\hat{\Theta}}_j$ (11) and first-order filter (20), where $j=1, 2, \ldots, n$.

    Step 4.Provide approximate design parameters $k_{j,i}>0$, $c_{j,i}>0$, and design virtual control signals $\alpha_{j,i}$ (12) and first-order filter (23), where $i=2, 3, \ldots, m-1$.

    Step 5.Choose appropriate design parameters $k_{j,m}>0, c_{j,m}>0, r_{j}>0, b_j>0$, and determine the actual control signal $\varpi_j(t)$ (13) and adaptive law $\dot{\hat{\theta}}_j$ (14) for the MIMO nonlinear systems (1).

  •   

    Algorithm 1

    Step 1.Determine the number of neural network nodes $\iota$, and design the Gaussian function $S_j(\zeta)$.

    Step 2.Based on Step 1, define the neural network $W^{\rm T}S(\zeta)$ to identify the nonlinear functions of the MIMO systems (1).

    Step 3.Select appropriate design parameters $k_{j,1}>0$, $c_{j,1}>0$, $c_{psj}>0$, $\beta_j>0$, $d_j>0$, and design virtual control signal $\alpha_{j,1}$ (10), adaptive law $\dot{\hat{\Theta}}_j$ (11) and first-order filter (20), where $j=1, 2, \ldots, n$.

    Step 4.Provide approximate design parameters $k_{j,i}>0$, $c_{j,i}>0$, and design virtual control signals $\alpha_{j,i}$ (12) and first-order filter (23), where $i=2, 3, \ldots, m-1$.

    Step 5.Choose appropriate design parameters $k_{j,m}>0, c_{j,m}>0, r_{j}>0, b_j>0$, and determine the actual control signal $\varpi_j(t)$ (13) and adaptive law $\dot{\hat{\theta}}_j$ (14) for the MIMO nonlinear systems (1).

qqqq

Contact and support