Predictive Digital Twin for Condition Monitoring Using Thermal Imaging

TL;DR

This work presents a comprehensive approach to integrating Proper Orthogonal Decomposition (POD), Robust Principal Component Analysis (RPCA), and Dynamic Mode Decomposition (DMD) to establish a robust predictive digital twin framework.

Abstract

This paper explores the development and practical application of a predictive digital twin specifically designed for condition monitoring, using advanced mathematical models and thermal imaging techniques. Our work presents a comprehensive approach to integrating Proper Orthogonal Decomposition (POD), Robust Principal Component Analysis (RPCA), and Dynamic Mode Decomposition (DMD) to establish a robust predictive digital twin framework. We employ these methods in a real-time experimental setup involving a heated plate monitored through thermal imaging. This system effectively demonstrates the digital twin's capabilities in real-time predictions, condition monitoring, and anomaly detection. Additionally, we introduce the use of a human-machine interface that includes virtual reality, enhancing user interaction and system understanding. The primary contributions of our research lie in the demonstration of these advanced techniques in a tangible setup, showcasing the potential of digital twins to transform industry practices by enabling more proactive and strategic asset management.

Figures (18)

• Figure 1: Concept of a digital twin and digital sibling. The physical asset is shown in the top right. Data from the asset is collected and enhanced with models (middle) to instill physical realism into the digital twin (middle left). The digital twin can be used for decision-making and public engagement (top left) and for optimal control (top middle). By devising and modeling hypothetical scenarios, risk assessment, what-if analysis, uncertainty quantification, and process optimization can be performed. This is often referred to as a digital sibling. Green arrows represent real-time actions and information flow, while grey arrows and boxes may be executed offline.
• Figure 2: Description of capability levels of a digital twin.
• Figure 3: Setup: A back heated aluminum plate observed using a thermal camera
• Figure 4: The data flowchart for physical setup and digital twin. All components can be monitored and controlled remotely through a dashboard and a virtual reality application.
• Figure 5: Temperature distribution of the training data ranging from [10]V to [120]V.