Jeffrey T. Spooner

Decentralized adaptive control of nonlinear systems using radial basis neural networks

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.

Adaptive fuzzy control: experiments and comparative analyses

Advances in nonlinear control theory have provided the mathematical foundations necessary to establish conditions for stability of several types of adaptive fuzzy controllers. However, very few, if any, of these techniques have been compared to conventional adaptive or nonadaptive nonlinear controllers or tested beyond simulation; therefore, many of them remain as purely theoretical developments whose practical value is difficult to ascertain. In this paper we develop three case studies where we perform a comparative analysis between the adaptive fuzzy techniques in Spooner and Passino (1995,1996) and some conventional adaptive and nonadaptive nonlinear control techniques. In each case, the analysis is performed both in simulation and in implementation, in order to show practical examples of how the performance of these controllers compares to conventional controllers in real systems.

Direct adaptive fuzzy control for a class of discrete-time systems

A direct adaptive control scheme is presented for a class of discrete-time nonlinear systems. The control scheme is based on an online functional approximation approach which modifies a standard or Takai-Sugeno (1985) fuzzy control system. A modified version of the standard key technical lemma which allows for adaptive systems with dead zones is used to guarantee asymptotic convergence of the tracking error to an /spl epsiv/-neighborhood of zero.

Indirect adaptive fuzzy control for a class of discrete-time systems

An indirect adaptive control scheme is presented for a class of discrete-time nonlinear systems. The control scheme is based on an online functional approximation approach which modifies a standard or Takagi-Sugeno fuzzy control system. A modified version of the standard key technical lemma which allows for adaptive systems with dead zones is used to guarantee asymptotic convergence of the tracking error to an /spl epsiv/-neighborhood of zero.

Indirect adaptive fuzzy control for a class of decentralized systems

A stable direct adaptive fuzzy controller is 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 fuzzy systems, 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.

Experimental studies in nonlinear discrete-time adaptive prediction and control

This paper presents implementation results using recently introduced discrete-time adaptive prediction and control techniques using online function approximators. We consider a process control experiment as our test bed, and develop a discrete-time adaptive predictor for liquid volume and a discrete-time adaptive controller for reference volume tracking. We use Takagi-Sugeno (TS) fuzzy systems as our function approximators, and for both prediction and control we investigate the use of a least-squares update of the fuzzy systems parameters

Adaptive prediction using fuzzy systems and neural networks

A collection of adaptive prediction schemes which use the functional approximation properties of fuzzy systems is presented. Both direct and indirect approaches are developed using gradient and least squares update laws. It is proven that the prediction error converges asymptotically to zero for each case provided some minor assumptions hold.

High speed adaptive fuzzy control with quantized errors

A quantized error adaptive fuzzy control scheme is presented for a class of discrete-time nonlinear systems. A quantized error adaptive scheme may be used to improve the update algorithm execution time by reducing the number of required multiplications. It is proven that on average the tracking error will be confined to an /spl epsiv/-neighborhood of zero whose size is dependent upon the quantization function.