Chaotic Sech-Tanh dynamic opposition-based learning for metaheuristic optimization. Part II: deep neural network architecture search for two-phase pressure drop prediction
Kerntechnik, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Basım Tarihi: 2026
- Doi Numarası: 10.1515/kern-2026-0065
- Dergi Adı: Kerntechnik
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex
- Anahtar Kelimeler: deep neural network, machine learning, metaheuristic optimization, neural architecture search, two-phase pressure drop
- İstanbul Ticaret Üniversitesi Adresli: Hayır
Özet
Accurate prediction of two-phase pressure drop is essential for the design of the tubular heat-exchange equipment used throughout energy-conversion and thermal-hydraulic systems, yet classical empirical correlations generalize poorly across fluids and operating conditions. This study develops a metaheuristic-driven neural architecture search for predicting the pressure drop due to evaporation and condensation of refrigerants in smooth and micro-fin tubes. Eight state-of-the-art metaheuristic optimizers, each enhanced with the Chaotic Sech–Tanh Dynamic Opposition-based Learning strategy developed in a companion study, were used to optimize the architecture and hyperparameters of a deep neural network trained on an experimental database, comprising 946 measurements (626 evaporation and 320 condensation points). The optimized networks were benchmarked against nine established machine learning regression models. A network with three hidden layers of 50 neurons achieved a mean absolute error (MAE) of 0.157 and a coefficient of determination (R2) of 0.99446 on the evaporation data, with 88.6 % of predictions falling within the 5 % error band. The opposition-enhanced optimizers consistently outperformed their standard counterparts: the improved Marine Predators variant was the most accurate for evaporation (MAE 0.224, R2 0.98977), and the improved Mantis Search variant was the most accurate for condensation (MAE 0.957, R2 0.98347). Among the machine learning models, extreme gradient boosting attained the highest training accuracy (R2 up to 0.99826) but showed signs of overfitting, whereas random forests generalized best.