Adaptive neural network control of nonlinear systems with unknown time delays

Ge, Shuzhi Sam; Fan, Hong; Lee, T.H.

doi:10.1109/acc.2003.1240554

Cited by 70 publications

(115 citation statements)

References 22 publications

Supporting

Mentioning

114

Contrasting

Order By: Relevance

“…But limited by computation algorithms, a proper selection of Gamma and Sigma is necessary for identification and control. Similar work can be found in some papers, such as Ge, Hong, and Lee (2003).…”

supporting

confidence: 59%

“…Accordingly its derivative is derived as below (Ge et al 2003), the error induced in using the neural network to approximate this class of systems is uniformly ultimately bounded. The boundary 2 is a function of the ideal weights of the neural network and in (6).…”

Section: T T T T T T T T T T V V E T Cy T E T Af Y T E T Bf Y T T K Ementioning

confidence: 99%

“…A notable contribution by Ge et al (2003Ge et al ( , 2005 is the construction of an integral Lyapunov function which is proved to be the key for the success of the approach. A function approximator has been used to describe the unknown nonlinear functions.…”

Section: Introductionmentioning

confidence: 99%

“…A function approximator has been used to describe the unknown nonlinear functions. Two types of artificial neural networks, the linearly parameterized neural networks (Ge et al, 2002(Ge et al, , 2003(Ge et al, , 2005 and the multilayer neural networks (Lewis, 1996), Huang, 2002, andZhang, et al, 1999), have been predominantly used for approximating a wide range of unknown nonlinear functions in control system design.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A generalized procedure in designing recurrent neural network identification and control of time-varying-delayed nonlinear dynamic systems

Zhang

Zhu

2010

Neurocomputing

View full text Add to dashboard Cite

supporting

confidence: 59%

Section: T T T T T T T T T T V V E T Cy T E T Af Y T E T Bf Y T T K Ementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A generalized procedure in designing recurrent neural network identification and control of time-varying-delayed nonlinear dynamic systems

Zhang

Zhu

2010

Neurocomputing

View full text Add to dashboard Cite

“…The delay(s) may appear in the system state, control input and/or output. Delays occur frequently in incubation periods, mechanics, viscoelasticity, physics, physiology, population dynamics, communication, information technologies, stability of networked control systems, maturation times, age structure, blood transfusions, biological, chemical, electronic and transportation systems [1][2][3]. Therefore the control of time-delay systems has been interested by many engineers and scientists, due to its variety presence in realistic models of phenomena.…”

Section: Introductionmentioning

confidence: 99%

Optimal Control of Time Delay Systems via Hybrid of Block-Pulse Functions and Orthonormal Taylor Series

Dadkhah

Farahi

2015

Int. J. Appl. Comput. Math

View full text Add to dashboard Cite

A new method to find the optimal control of time delay systems with quadratic performance index is discussed. The method is based on hybrid functions. The properties of the hybrid functions which consists of block-pulse functions and orthonormal Taylor series are presented. The operational matrices of integration, delay, dual and product are used to reduce the solution of optimal control time delay system to the solution of algebraic equations. Numerical examples are included to illustrate the effectiveness and validity of the technique.

show abstract

Decentralized adaptive control of nonlinear large‐scale pure‐feedback interconnected systems with time‐varying delays

Zhang

2013

Adaptive Control & Signal

View full text Add to dashboard Cite

In this paper, an adaptive decentralized neural control problem is addressed for a class of pure-feedback interconnected system with unknown time-varying delays in outputs interconnections. By taking advantage of implicit function theorem and the mean-value theorem, the difficulty from the pure-feedback form is overcome. Under a wild assumption that the nonlinear interconnections are assumed to be bounded by unknown nonlinear functions with outputs, the difficulties from unknown interconnections are dealt with, by introducing continuous packaged functions and hyperbolic tangent functions, and the time-varying delays in interconnections are compensated by Lyapunov-Krasovskii functional. Radial basis function neural network is used to approximate the unknown nonlinearities. Dynamic surface control is successfully extended to eliminate 'the explosion of complexity' problem in backstepping procedure. To reduce the computational burden, minimal learning parameters technique is successfully incorporated into this novel control design. A delay-independent decentralized control scheme is proposed. With the adaptive neural decentralized control, only one estimated parameter need to be updated online for each subsystem. Therefore, the controller is more simplified than the existing results. Also, semiglobal uniform ultimate boundedness of all of the signals in the closed-loop system is guaranteed. Finally, simulation studies are given to demonstrate the effectiveness of the proposed design scheme. DECENTRALIZED ADAPTIVE CONTROL 25 models be known exactly or the unknown nonlinear functions can be linearly parameterized. These control methods will be invalid, if the knowledge on nonlinear dynamics is not available.Recently, to overcome this limitation, many fuzzy logic systems (FLSs) or neural networks (NNs) control strategies for nonlinear systems have been proposed (see [10][11][12][13][14][15][16][17][18][19] with time delays or not), based on the reason that FLSs or NNs are universal approximators and have the ability to approximate the nonlinear functions. Although these approaches do not require nonlinear dynamic model to be known exactly or the unknown nonlinear functions to be linearly parameterized and still can achieve a good control performance, they are applied only to a relatively simple class of single nonlinear system. For large-scale systems, as is well known, because of the difficulties to deal with interconnections and the difficulties inherent in nonlinear subsystems, the decentralized control scheme designing with FLSs or NNs is still a challenging problem. Inspired by this challenge, many adaptive decentralized NN or fuzzy backstepping control approaches have been investigated for uncertain nonlinear systems [20][21][22][23][24][25][26].Although the approximation-based adaptive decentralized backstepping control approaches can overcome the difficulties that nonlinear systems do not satisfy the matching conditions and unknown nonlinear functions cannot be linearly parameterized, the backstepping design re...

show abstract

Adaptive neural network control of nonlinear systems with unknown time delays

Cited by 70 publications

References 22 publications

A generalized procedure in designing recurrent neural network identification and control of time-varying-delayed nonlinear dynamic systems

A generalized procedure in designing recurrent neural network identification and control of time-varying-delayed nonlinear dynamic systems

Optimal Control of Time Delay Systems via Hybrid of Block-Pulse Functions and Orthonormal Taylor Series

Decentralized adaptive control of nonlinear large‐scale pure‐feedback interconnected systems with time‐varying delays

Contact Info

Product

Resources

About