Scientific Machine Learning-assisted Model Discovery from Telemetry Data

Read full text Summarise with VIRAT
Authors: Sebastian Micluţa-Câmpeanu, Avinash Subramanian, Anas Abdelrehim, Ranjan Anantharaman, Rohit Dhumane, Brad Carman, Christopher Rackauckas
Cited by: 0
References: 11

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

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.

Fields of Study & Subjects

Model Reduction and Neural Networks Building Energy and Comfort Optimization Control Systems and Identification

Publication details

Journal / source
arXiv (Cornell University)
Publication date
16 March 2026
Language
EN
Document type
Preprint