Gaussian Process prior models, as used in Bayesian non-parametric statistical models methodology are applied to implement a nonlinear adaptive control law. The expected value of a quadratic cost function is minimised, without ignoring the variance of the model predictions. This leads to implicit regularisation of the control signal (caution) in areas of high uncertainty. As a consequence, the c...

This paper presents a new state-space self-tuning control scheme for adaptive digital control of continuous multivariable nonlinear stochastic hybrid systems with input saturation. Here, the continuous nonlinear stochastic system is assumed to have unknown system parameters, system and measurement noises, and inaccessible system states. The proposed method enables the development of a digitally...

In the paper, a new multivariable self-tuning PID controller design scheme is proposed which has a static matrix precompensator to reduce the interaction terms of the process transfer function matrix adjusted by an online estimator. The p £ p precompensated multivariate system is then controlled via ‘p’ univariate self-tuning PID controllers whose parameters are adjusted by a second identifier ...

Most Active Queue Management (AQM) algorithms based on control theory have difficulty in obtaining desirable performance once the network conditions or the traffic patterns change out of the presumed ones they are designed for. To address these problems, a new self-tuning AQM algorithm called STR is proposed in this paper. STR has the ability of keeping minimum variance between the instantaneou...

This paper presents a new approach for tuning three-term control loops encountered in power station processes. The proposed approach is based on the Pseudo-Derivative Feedback (PDF) control configuration. Simple methods are presented for tuning the PDF controller for dead-time processes. The methods are based on appropriate manipulations of the exponential dead-time term in the denominator of t...