ART.I.CO. (ARTificial Intelligence for COoling): An innovative method for optimizing the control of refrigeration systems based on Artificial Neural Networks

Angelo Maiorino, Manuel Gesù Del Duca and Ciro Aprea

Applied Energy, 2022, vol. 306, issue PB, No S0306261921013593

Abstract: Advanced control methods proved they effectiveness in reducing energy consumption of refrigeration systems equipped with a variable-speed compressor, but they could not be suitable for fixed-speed compressors, which are usually controlled by a simple ON/OFF logic with a mechanical thermostat, which does not allow to optimize the performance of such devices. Hence, a novel control method based on the use of Artificial Neural Networks to optimize the operations of refrigeration systems equipped with a fixed-speed compressor is proposed. This technique uses an Artificial Neural Network, which stem from a three-step process, able to provide the ON/OFF control loop with the optimal hysteresis value accordingly to the requirement of the user, in terms of set-point temperature and optimization priority, and the ambient temperature. The proposed control method was encoded in a microcontroller to test its effectiveness with a refrigeration system. The results of the experimental tests demonstrated the great potential of this approach showing a reduction of energy consumption of 6.8% and 2.2% with no stored material and ambient temperatures of 25 °C and 32 °C, respectively. Then, the introduction of 45 kg of stored material led to energy savings up to 13.4% and 6.6% with ambient temperatures of 25 °C and 32 °C, respectively. Furthermore, it was evidenced that door openings and pick-and-place operations can reduce the positive effect of this approach, reducing the energy saving to 3.7%. The results show that Artificial Neural Networks can be successfully applied to optimize the ON/OFF control loop of refrigeration systems, considering both plug-in and built-in solutions.

Keywords: Optimization; Refrigeration; Vapour-compression; Control; Artificial Neural Network; Energy saving (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (4)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0306261921013593
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:appene:v:306:y:2022:i:pb:s0306261921013593

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2021.118072

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().