Control of bounded dynamic stochastic distributions using square root models: an applicability study in papermaking systems

Abstract

Following the recent developments on the modelling and control algorithms of the shape of the output probability density function for general dynamic stochastic systems (Wang, 1998a, Proceedings of the IFAC Workshop on AARCT, Cancun, pp. 95-99), this paper presents a square root approximation-based control algorithm, where the B-splines function expansion is used to approximate the square root of the output probability density function in order to guarantee its positiveness. It has been shown that with such an approximation, the system is generally nonlinear. This is true even when the dynamic part of the system is linear. As such, a nonlinear control algorithm has been developed to control the output probability density function of the system. A simulated example is used to demonstrate the use of the algorithm and encouraging results have been obtained.