Stable adaptive control using fuzzy systems and neural networks

Spooner, J.T.; Passino, K.M.

doi:10.1109/91.531775

Cited by 524 publications

(167 citation statements)

References 31 publications

Supporting

Mentioning

165

Contrasting

Unclassified

Order By: Relevance

“…The update law (11) is used to estimate the dynamics of the subsystem under control, while the update laws (12) and (13) are used to stabilize the subsystem by estimating the effects of the interconnections. Both (12) and (13) increase monotonically and we require that a (0); a (0) 0 so a projection algorithm may be required to ensure that they do not become unnecessarily large.…”

Section: Direct Adaptive Controlmentioning

confidence: 99%

Section: Radial Basis Neural Networkmentioning

confidence: 99%

“…On-line function approximation approaches have been successfully applied to a wide variety of control problems, in particular in the area of nonlinear adaptive control of SISO systems (see [9]- [13] for examples). On-line function approximation approaches adjust parameters within a universal approximator (such as a fuzzy system or neural network) to estimate unknown nonlinearities which may describe plant dynamics or a desired control law.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Decentralized adaptive control of nonlinear systems using radial basis neural networks

Spooner

Passino

1999

IEEE Trans. Automat. Contr.

Self Cite

273

120

View full text Add to dashboard Cite

Abstract-Stable direct and indirect decentralized adaptive radial basis neural network controllers are presented for a class of interconnected nonlinear systems. The feedback and adaptation mechanisms for each subsystem depend only upon local measurements to provide asymptotic tracking of a reference trajectory. Due to the functional approximation capabilities of radial basis neural networks, the dynamics for each subsystem are not required to be linear in a set of unknown coefficients as is typically required in decentralized adaptive schemes. In addition, each subsystem is able to adaptively compensate for disturbances and interconnections with unknown bounds.

show abstract

Section: Direct Adaptive Controlmentioning

confidence: 99%

Section: Radial Basis Neural Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Decentralized adaptive control of nonlinear systems using radial basis neural networks

Spooner

Passino

1999

IEEE Trans. Automat. Contr.

Self Cite

273

120

View full text Add to dashboard Cite

show abstract

“…This neural network based ILC algorithm can be applied to a nonlinear system with state dependent input gain. Compared with works dealing with the same case of state dependent input gain (for example, [17,20] for the adaptive tracking control problem or [21] for the adaptive iterative learning control problem), we only require a known lower bound of the input gain before the controller is designed. It is shown that the tracking error vector asymptotically converges to zero as the iteration goes to infinity, and that all adjustable parameters as well as the internal signals remain bounded.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, Gaussian neural networks and fuzzy logic systems have also become popular tools for adaptive control of nonlinear systems since they can be expressed as series expansion of basis functions. Adaptive tracking control architectures have been presented in [17][18][19][20] for Gaussian or fuzzy networks for which explicit linear parameterization of the nonlinearity is either unknown or impossible. For the iterative learning control problem, for example, an adaptive nonlinear compensation ILC using a fuzzy approximation technique can be found in [21].…”

Section: Introductionmentioning

confidence: 99%

The sampled-data iterative learning control for nonlinear systems

Chien

Proceedings of the 36th IEEE Conference on Decision and Control

View full text Add to dashboard Cite

In this paper, a feedforward neural network with sigmoid hidden units is used to design a neural network based iterative learning controller for nonlinear systems with state dependent input gains. No prior offline training phase is necessary, and only a single neural network is employed. All the weights of the neurons are tuned during the iteration process in order to achieve the desired learning performance. The adaptive laws for the weights of neurons and the analysis of learning performance are determined via Lyapunov-like analysis. A projection learning algorithm is used to prevent drifting of weights. It is shown that the tracking error vector will asymptotically converges to zero as the iteration goes to infinity, and the all adjustable parameters as well as internal signals remain bounded.

show abstract