Estimation of energy and exergy efficiency of the trilateral cycle using machine learning algorithms

Abstract Trilateral cycles, widely employed in thermal systems for energy transformations, are recognized for their complex structures. In this study, thermodynamic analyses were conducted using R290 refrigerant, resulting in an energy efficiency of 11.15% and an exergy efficiency of 22.6%. Subsequently, the study aimed to estimate energy and exergy efficiencies in trilateral cycles using machine learning algorithms. Data collected during the process were processed using various machine learning algorithms, and the results determined the degree of alignment between prediction models and actual data. Utilizing the Python programming language, estimation values of 95% for exergy and 93% for energy efficiency were obtained. This research endeavors to underscore the potential of machine learning in estimating the energy and exergy efficiency of trilateral cycles, with the ultimate goal of contributing to the efficient design and operation of thermal systems.