Physics-based Digital Twins for Autonomous Thermal Food Processing: Efficient, Non-intrusive Reduced-order Modeling
This work addresses the problem of autonomous control in industrial food processing by enabling efficient, non-intrusive modeling, though it is incremental as it builds on existing Digital Twin and ROM concepts with specific optimizations.
The paper tackles the challenge of real-time state estimation in thermal food processing by proposing a physics-based, data-driven Digital Twin framework that uses non-intrusive reduced-order models (ROMs) with minimal computational and data requirements, achieving a mean test error of less than 1 Kelvin and simulation speed-ups of approximately 1.8E4 for on-device model predictive control.
One possible way of making thermal processing controllable is to gather real-time information on the product's current state. Often, sensory equipment cannot capture all relevant information easily or at all. Digital Twins close this gap with virtual probes in real-time simulations, synchronized with the process. This paper proposes a physics-based, data-driven Digital Twin framework for autonomous food processing. We suggest a lean Digital Twin concept that is executable at the device level, entailing minimal computational load, data storage, and sensor data requirements. This study focuses on a parsimonious experimental design for training non-intrusive reduced-order models (ROMs) of a thermal process. A correlation ($R=-0.76$) between a high standard deviation of the surface temperatures in the training data and a low root mean square error in ROM testing enables efficient selection of training data. The mean test root mean square error of the best ROM is less than 1 Kelvin (0.2 % mean average percentage error) on representative test sets. Simulation speed-ups of Sp $\approx$ 1.8E4 allow on-device model predictive control. The proposed Digital Twin framework is designed to be applicable within the industry. Typically, non-intrusive reduced-order modeling is required as soon as the modeling of the process is performed in software, where root-level access to the solver is not provided, such as commercial simulation software. The data-driven training of the reduced-order model is achieved with only one data set, as correlations are utilized to predict the training success a priori.