Title: Data driven optimal control for stochastic systems with non-Gaussian disturbances

Authors: Lanlan Lai; Liping Yin; Yue Hong; Tao Li

Addresses: School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, China ' School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, China ' School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, China ' School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, China

Abstract: In this paper, a data-based algorithm is applied to optimise the performance index and search for a global solution for non-Gaussian systems. The control objective is to track a desired probability density function (PDF). The control law is obtained through optimising the performance index. The well-known kernel density estimation (KDE) technique is employed to estimate the output PDFs because the output PDFs are immeasurable for many industrial processes, and the performance index function is established based on the stochastic distribution control theory. The established performance index function is optimised by using an intelligent optimisation algorithm with a simpler formulation and less computation load than existing results. Furthermore, a new global optimal control strategy can be obtained through a data-based control algorithm. Two numerical examples are given to demonstrate the effectiveness of the control algorithm.

Keywords: kernel density estimation; KDE; performance index function; stochastic distribution control; SDC; probability density functions.

DOI: 10.1504/IJMIC.2021.123493

International Journal of Modelling, Identification and Control, 2021 Vol.39 No.3, pp.245 - 256

Received: 02 Mar 2021
Accepted: 25 Jun 2021

Published online: 23 Jun 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article