NUMERICAL OPTIMIZATION OF HELICALLY COILED TUBE HEAT EXCHANGERS USING ARTIFICIAL NEURAL NETWORKS: PREDICTING OPTIMAL PITCH FOR ENHANCED HEAT TRANSFER EFFICIENCY

Helically coiled tube heat exchangers (HCTHEX) are renowned for their compact structure and high convective heat transfer coefficients, making them the subject of extensive experimental and numerical studies. Their efficiency on both the tube and shell sides has led to growing interest in better understanding and optimizing their design. However, previous research has highlighted the complex, irregular behavior of the shell-side fluid dynamics relative to coil geometry, and no conclusive recommendations have been made regarding a specific range of geometrical characteristics, such as tube pitch, for optimal performance. This study aims to address these gaps through a streamlined numerical analysis, building on prior research into shell-side convective behavior. Additionally, Artificial Neural Networks (ANN) are employed to predict the optimum pitch of the helically coiled tubes, allowing for a more precise and efficient design process. The ANN model is trained using both experimental and simulated data, offering a reliable method for determining the ideal pitch that maximizes heat exchanger performance. The validation of the proposed ANN-based approach is demonstrated by comparing the predicted optimal pitch values with the discrete pitch values obtained from previous simulations. This comparison confirms the accuracy of the ANN model, as the predicted pitch falls within the range of optimal values identified in earlier studies. The results indicate a definitive and conclusive optimal pitch range for helically coiled tube heat exchangers, further refining our understanding of their design and offering valuable insights for enhancing heat transfer efficiency.