Particle Swarm Optimization-Based Deep Neural Network vs Whale Optimization Algorithm-Based Deep Convolutional Neural Networks for Critical Heat Flux Prediction

Critical heat flux (CHF) denotes the thermal limit at which a phase change occurs during heating, that causes a significant decline in heat transfer efficiency and eventual localized overheating of the heating surface. This study applies two hybrid deep learning models: a Deep Convolutional Neural Network (CNN) optimized with the Whale Optimization Algorithm and a Deep Neural Network (DNN) optimized with Particle Swarm Optimization, to predict Critical Heat Flux (CHF). The results show that the latter model outperforms the former in terms of performance, simplicity, and computation efficiency in the CHF prediction task.