Development of a neural network model for an automated HVAC system based on collected data
DOI:
https://doi.org/10.15587/2706-5448.2025.326909Keywords:
microclimate control, HVAC automation, machine learning, energy efficiency, neural networksAbstract
The object of research is ventilation and air conditioning systems, which act as the object of data collection for the development of a neural network model based on them. The main attention is paid to the choice of algorithm, data collection for training a neural network model based on the MATLAB software package, to simplify the model development process.
The main problem that was considered in the study is the complexity of building mathematical models for ventilation and air conditioning systems. Traditional approaches require significant computing resources and in-depth analysis of physical processes, which complicates their development and practical use.
The research results show one of the approaches to creating a model of ventilation and air conditioning systems using neural networks. The proposed approach provides fast training of the model based on real data, which in further studies will allow adapting the system to changing operating conditions and increasing its efficiency.
The obtained results are explained by the fact that, unlike classical mathematical models that require precise formulation of all dependencies and parameters. Neural networks are able to approximate complex nonlinear functions without the need for a complete understanding of physical processes.
The proposed approach can be used for ventilation and air conditioning systems provided that there is a sufficient amount of data for training the neural network. Also important is the integration of such a system with controllers and SCADA systems that provide operational collection of parameters from the environment. The use of neural network models is especially effective in smart buildings, industrial facilities and energy-saving systems, where it is important to optimize energy consumption and provide comfortable conditions for users. In addition, such models can be implemented in cloud platforms for centralized management of climatic parameters in various buildings or production complexes.
References
- Asamoah, P. B., Shittu, E. (2025). Evaluating the performance of machine learning models for energy load prediction in residential HVAC systems. Energy and Buildings, 334, 115517. https://doi.org/10.1016/j.enbuild.2025.115517
- Bundo, J., Tola, S., Daci, A. (2024). HVAC/R Systems Modelling: Assessing Mathematical Model for Gas Compressor. Mathematical Modelling of Engineering Problems, 11 (9), 2285–2292. https://doi.org/10.18280/mmep.110901
- Yan, L., Chang, X., Wang, N., Zhang, L., Liu, W., Deng, X. (2024). Comparison of Machine Learning and Classic Methods on Aerodynamic Modeling and Control Law Design for a Pitching Airfoil. International Journal of Aerospace Engineering, 2024 (1). https://doi.org/10.1155/2024/5535800
- Guo, W., Liang, S., He, Y., Li, W., Xiong, B., Wen, H. (2022). Combining EnergyPlus and CFD to predict and optimize the passive ventilation mode of medium-sized gymnasium in subtropical regions. Building and Environment, 207, 108420. https://doi.org/10.1016/j.buildenv.2021.108420
- García Vázquez, C. A., Cotfas, D. T., González Santos, A. I., Cotfas, P. A., León Ávila, B. Y. (2024). Reduction of electricity consumption in an AHU using mathematical modelling for controller tuning. Energy, 293, 130619. https://doi.org/10.1016/j.energy.2024.130619
- Chaudhary, G., Johra, H., Georges, L., Austbø, B. (2025). Transfer learning in building dynamics prediction. Energy and Buildings, 330, 115384. https://doi.org/10.1016/j.enbuild.2025.115384
- Afram, A., Janabi-Sharifi, F., Fung, A. S., Raahemifar, K. (2017). Artificial neural network (ANN) based model predictive control (MPC) and optimization of HVAC systems: A state of the art review and case study of a residential HVAC system. Energy and Buildings, 141, 96–113. https://doi.org/10.1016/j.enbuild.2017.02.012
- Zheng, G., Jia, R., Yi, W., Yue, X. (2025). Multi-step fusion model for predicting indoor temperature in residential buildings based on attention mechanism and neural network. Journal of Building Engineering, 102, 112057. https://doi.org/10.1016/j.jobe.2025.112057
- Lopatko, O., Mykytyn, I. (2016). Neural networks as a tool for the temperature value prediction using transition process. Measuring Equipment and Metrology, 77, 65–70. https://doi.org/10.23939/istcmtm2016.77.065
- ROZROBKA MODELI SYSTEMY VENTYLYATSIYI TA KONDYTSIONUVANNYA DLYA REHULYUVANNYA TEMPERATURY TA VOLOHOSTI ZA DOPOMOHOYU NEYRONNYKH MEREZH NA OSNOVI ZIBRANYKH DANYKH DLYA PROTSESU AVTOMATYZATSIYI KERUVANNYA MIKROKLIMATOM. Available at: https://drive.google.com/drive/folders/1avfqXfqOSdkn6ZrbnP97oymGjdkCd_Hd?usp=sharing Last accessed: 14.04.2025
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Illia Velychko, Viktor Sidletskyi
This work is licensed under a Creative Commons Attribution 4.0 International License.
The consolidation and conditions for the transfer of copyright (identification of authorship) is carried out in the License Agreement. In particular, the authors reserve the right to the authorship of their manuscript and transfer the first publication of this work to the journal under the terms of the Creative Commons CC BY license. At the same time, they have the right to conclude on their own additional agreements concerning the non-exclusive distribution of the work in the form in which it was published by this journal, but provided that the link to the first publication of the article in this journal is preserved.
