Scientific Machine Learning-assisted Model Discovery from Telemetry Data
This addresses the challenge of model calibration in engineering design, particularly for HVAC and thermal systems, offering an incremental AI-assisted workflow.
The paper tackles the problem of calibrating dynamic models for digital twins when simplifying assumptions cause missing physics, by proposing Dyad Model Discovery to augment physical equations with symbolic expressions from data, resulting in improved predictive performance for a transportation refrigeration unit digital twin.
Calibration of dynamic models to data is an important step in building building digital twins of HVAC equipment, thermal loads and control systems. Sometimes, when a model fails to calibrate to data, a possible cause is that the model has made too many sim- plifying assumptions and is missing physics. In this paper we propose a semi-automated approach, called Dyad Model Discovery, that can augment the physical equations of the model with symbolic expressions discovered from the data. We demonstrate this method on a digital twin of a transportation refrigeration unit to improve its predictive performance, trained using telemetry data. An engineer-in-the-loop workflow is proposed, which provides suggestions to the user which can then be accepted or rejected. This is the first AI-assisted engineering design workflow to our knowledge.