Maximizing efficiency in solar ammonia-water absorption refrigeration cycles: Exergy analysis, concentration impact, and advanced optimization with GBRT machine learning and FHO optimizer

A detailed analysis of energy and exergy is conducted on a single-effect solar ammonia-water (NH3-H2O) absorption refrigeration cycle (ARC) using TRNSYS and EES software. Considering the physical and chemical exergies, the exergy destruction rate ((E) over dot(D)) in each component of the system is calculated, highlighting its contribution to the overall (E) over dot(D). The study explores the effects of varying refrigerant mass flow rate ((m) over dot(r)) and ammonia concentration in strong and weak solutions (X-s and X-w) on key performance parameters, including coefficient of performance (COP), exergy efficiency ((E) over dot(D)), and overall E. D across a range of generator temperatures (T-g). In this study, a gradient boosting regression tree (GBRT) is employed as a supervised machine-learning technique for classification and regression problems, utilizing boosting to enhance conventional decision tree predictions. The Fire Hawk Optimizer (FHO) approach is also utilized to optimize performance parameters, maximizing COP and eta(eta E) while minimizing T-g and (E) over dot(D). The GBRT models are developed using available experimental and simulation data, revealing relationships between variables ((m) over dot(r), X-s, X-w, and T-g) and outcomes (COP, (E) over dot(D), and overall (E) over dot(D)). The results revealed that the generator exhibits considerable E. D regardless of operating conditions, underscoring its pivotal role in the ARC. It emerges as the primary (E) over dot(D) contributor (50 %), followed by the evaporator (17 %) and the absorber (15 %). However, E. D associated with the recooler, pump, and expansion valves is negligible in comparison. Optimization results reveal that, when minimizing Tg and (E) over dot(D), the highest COP and (E) over dot(D) at T-g of 373.15 K reach 0.8081 and 0.46, respectively.