# Adaptive Digital Twin Modeling with Control: Integration of Extended Kalman Filter-Based Recursive Sparse Nonlinear Identification with Model Predictive Control

## TL;DR

This paper introduces a new framework for digital twin modeling that improves accuracy and control by combining advanced identification and real-time updates.

## Contribution

A novel digital twin framework integrating sparse nonlinear identification, extended Kalman filter updates, and model predictive control.

## Key findings

- Sparse identification reduces development time while maintaining model accuracy.
- Extended Kalman filter updates help maintain model accuracy over time.
- Model predictive control improves interactive capabilities of digital twins.

## Abstract

The adoption of digital twins has revolutionized industrial process simulation, monitoring, and control effectiveness. However, practical implementations of digital twins are hindered by substantial challenges, including extended development time, diminishing model accuracy, and restricted interactive capabilities. Addressing these critical issues, this paper proposes a comprehensive digital twin development framework that integrates digital twin identification, real-time model updating, and advanced process control. The proposed approach first identifies the offline digital twin model through the sparse identification of a nonlinear dynamics algorithm, reducing the digital twin development time while maintaining model fidelity. Then, the identified model is updated by the extended Kalman filter to mitigate the problem of diminishing accuracy. Finally, incorporating the latest updated model into the model predictive control facilitates the control inputs optimization and enhances the interactive capacity of digital twins. Through one industrial case study and two simulation examples, the advantages of the proposed algorithm are demonstrated.