Fast, detailed, accurate simulation of a thermal car-cabin using machine-learning

Brandi Jo Jess, James Brusey, Matteo Maria Rostagno, Alberto Maria Merlo, Elena Gaura, Kojo Sarfo Gyamfi

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)
150 Downloads (Pure)


Car-cabin thermal systems, including heated seats, air-conditioning, and radiant panels, use a large proportion of the energy budget of electric vehicles and thus reduce their effective range. Optimising these systems and their controllers might be possible with computationally efficient simulation. Unfortunately, state-of-the-art simulators are either too slow or provide little resolution of the cabin's thermal environment. In this work, we propose a novel approach to developing a fast simulation by machine learning (ML) from measurements within the car cabin over a number of trials within a climatic wind tunnel. A range of ML approaches are tried and compared. The best-performing ML approach is compared to more traditional 1D simulation in terms of accuracy and speed. The resulting simulation, based on Multivariate Linear Regression, is fast (5 microseconds per simulation second), and yields good accuracy (NRMSE 1.8%), which exceeds the performance of the traditional 1D simulator. Furthermore, the simulation is able to differentially simulate the thermal environment of the footwell versus the head and the driver position versus the front passenger seat, but unlike a traditional 1D model cannot support changes to the physical structure.
This fast method for obtaining computationally efficient simulators of car cabins will accelerate adoption of techniques such as Deep Reinforcement Learning for climate control.
Original languageEnglish
Article number753169
Pages (from-to)753169
Number of pages11
JournalFrontiers of Mechanical Engineering
Publication statusPublished - 10 Mar 2022

Bibliographical note

© 2022 Jess, Brusey, Rostagno, Merlo, Gaura and Gyamfi. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.


  • electric vehicle
  • thermal modeling
  • time series prediction
  • Artificial neural networks (ANN)
  • NARX
  • Heating Ventilation and Air Conditioning Systems (HVAC)


Dive into the research topics of 'Fast, detailed, accurate simulation of a thermal car-cabin using machine-learning'. Together they form a unique fingerprint.

Cite this