Modeling the Energy Consumption of R600a Gas in a Refrigeration System with New Explainable Artificial Intelligence...

Area of Science:

• Thermodynamics and Refrigeration Engineering
• Artificial Intelligence and Machine Learning

Background:

• Refrigerant gases are critical for cooling systems, with selection based on thermophysical properties and energy efficiency.
• Modeling refrigerant properties, including compressor energy consumption, using AI is a growing research area.
• Low global warming potential and energy consumption are key factors in choosing refrigerants.

Purpose of the Study:

• To develop explainable, interpretable, and transparent AI models for compressor energy consumption in R600a vapor compression refrigeration systems.
• To identify optimal operating conditions for minimizing energy consumption using a hybrid-optimization-based AI classification method.
• To apply a novel AI methodology for refrigerant gas energy consumption modeling.

Main Methods:

• Implementation of a hybrid-optimization-based artificial intelligence classification method.
• Development of models to predict R600a refrigerant gas energy consumption based on operating parameters.
• Analysis of system energy consumption relative to evaporator and condenser temperatures and pressures.

Main Results:

• The AI models accurately determine R600a energy consumption based on operating parameters.
• The method automatically reveals operating conditions that result in the lowest energy consumption.
• The developed models achieved an 84.4% accuracy when compared to experimental data.

Conclusions:

• The applied explainable AI method provides transparent and interpretable models for refrigerant energy consumption.
• This innovative approach enables the determination of optimal operating conditions for minimum energy consumption across different refrigerant gases.
• The study demonstrates the potential of AI in optimizing refrigeration system efficiency and environmental impact.