Scientific Machine Learning-assisted Model Discovery from Telemetry Data
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915868227665920 |
|---|---|
| author | Micluta-Campeanu, Sebastian Subramanian, Avinash Abdelrehim, Anas Anantharaman, Ranjan Dhumane, Rohit Carman, Brad Rackauckas, Chris |
| author_facet | Micluta-Campeanu, Sebastian Subramanian, Avinash Abdelrehim, Anas Anantharaman, Ranjan Dhumane, Rohit Carman, Brad Rackauckas, Chris |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_15943 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Scientific Machine Learning-assisted Model Discovery from Telemetry Data Micluta-Campeanu, Sebastian Subramanian, Avinash Abdelrehim, Anas Anantharaman, Ranjan Dhumane, Rohit Carman, Brad Rackauckas, Chris Computational Engineering, Finance, and Science 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. |
| title | Scientific Machine Learning-assisted Model Discovery from Telemetry Data |
| topic | Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2603.15943 |