Recursive Learning-Based Bilinear Subspace Identification for Online Modeling and Predictive Control of a Complicated Industrial Process

Ping Zhou,Peng Dai,Shuai Zhang

doi:10.1109/access.2020.2984319

Abstract

In this paper, a recursive learning based bilinear subspace identification (R-B-SI) algorithm is proposed for online modeling and data-driven predictive control of blast furnace (BF) ironmaking process with strong nonlinear time-varying dynamics. Different from the existing linear SI algorithms, the R-B-SI algorithm can make full use of the process data information by adding the Kronecker product term of input data and the Kronecker product term between input and output data into the data block Hankel matrices. Moreover, the parameters of the R-B-SI model can be updated online with the latest data using recursive learning. In order to adjust the sensitivity of the algorithm to the data at different sampling times, the forgetting factor is introduced into the involved recursive learning as well. Therefore, the nonlinear time-varying dynamics of process can be well captured and described by the R-B-SI model. As a result, the data-driven predictive controller designed by the R-B-SI prediction model with parameter adaption is always capable of achieving satisfactory control performances regardless of the variation in various process operating conditions. Data experiments using actual industrial data have verified the practicability and superiority of the proposed methods.

Highlights

As an indispensable and important resource in modern society, steel plays an extremely key role in national economy, and blast furnace (BF) ironmaking process is one of the most important links in steelmaking production [1]–[3]
The molten iron quality (MIQ) is characterized by the Si content ([Si]) and the molten iron temperature (MIT) [5]
Focusing on the above mentioned practical challenge, a novel recursive learning based bilinear subspace identification (R-bilinear SI (B-SI)) algorithm is proposed for online modeling and data-driven predictive control of blast furnace (BF) ironmaking process, and the main contributions of this paper are as follows

Summary

INTRODUCTION

As an indispensable and important resource in modern society, steel plays an extremely key role in national economy, and blast furnace (BF) ironmaking process is one of the most important links in steelmaking production [1]–[3]. Focusing on the above mentioned practical challenge, a novel recursive learning based bilinear subspace identification (R-B-SI) algorithm is proposed for online modeling and data-driven predictive control of blast furnace (BF) ironmaking process, and the main contributions of this paper are as follows. It is noticed that the bilinear system models (1) and (23) obtained by the LS algorithm cannot update the model parameters with the latest data online, cannot characterize the nonlinear time-varying dynamics of complex industrial process To this end, the recursive learning algorithm is further proposed to solve the above optimization problem so that the subspace matrices Lp, Lu and Lv or the system matrices A, B, C, D and N can be renewed by the latest data online. Satisfactory control performance of the data-driven predictive controller based on the R-B-SI predictor can be guaranteed

DATA-DRIVEN PREDICTIVE CONTROLLER DESIGN WITH

CONCLUSION