An Interpretable Digital Twin for Self-Aware Industrial Machines

Abstract

This paper presents a proposed three-step methodology designed to enhance the performance and efficiency of industrial systems by integrating Digital Twins with particle swarm optimization (PSO) algorithms while prioritizing interpretability. Digital Twins are becoming increasingly prevalent due to their capability to offer a comprehensive virtual representation of physical systems, thus facilitating detailed simulations and optimizations. Concurrently, PSO has demonstrated its effectiveness for real-time parameter estimation, especially in identifying both standard and unknown components that influence the dynamics of a system. Our methodology, as exemplified through DC Motor and Hydraulic Actuator simulations, underscores the potential of Digital Twins to augment the self-awareness of industrial machines. The results indicate that our approach can proficiently optimize system parameters in real-time and unveil previously unknown components, thereby enhancing the adaptive capacities of the Digital Twin. While the reliance on accurate data to develop Digital Twin models is a notable consideration, the proposed methodology serves as a promising framework for advancing the efficiency of industrial applications. It further extends its relevance to fault detection and system control. Central to our approach is the emphasis on interpretability, ensuring a more transparent understanding and effective usability of such systems.