Machine learning regression modeling of liquid jet impingement cooling: Based on computational fluid dynamics (CFD)

A comprehensive CFD and Machine Learning Regression Models (MLRM) investigation optimized circular Jet Impingement cooling. Jet impingement, influenced by several parameters, is widely studied in industry. This study used a design of experiments based on the Taguchi Method (TM) to determine the efficient number of CFD simulations. Numerical simulations generated a dataset to analyze nozzle diameter, nozzle height, flow rate, and different fluids (water, nanofluids, and Microencapsulated PCM), validated with experimental data. Data is cleaned and split into training, validation, and test sets. Validation and training data are augmented, while test data remained unchanged. After feature selection, 6 singular and 6 ensemble RMs are trained to identify the best models, followed by developing a novel hybrid model. The hybrid model achieved a total R² = 0.90 and test R² = 0.84. Applicability and sensitivity analysis validated the hybrid model, followed by a TM-based analysis of variance. Results revealed that flow rate is the most crucial factor (51.5%) followed by the fluid type (45.8%). Finally, several optimization methods are applied, with the Nelder-Mead method predicting the optimum case (with total error = 10%): Re = 5961.6 to result in an h_average = 4.6 (W/cm² °C) given a heat flux of 64 W/cm².