Optimization of thermophysical properties of CuO-MWCNT/ethylene glycol–water hybrid nanofluid using SVR-SA models for heat-exchanger systems


Salman D. S., Alattar S. A., Makki D. S., Taher G. N., TANER M., Salahshour S., ...Daha Fazla

Energy Conversion and Management: X, cilt.31, 2026 (ESCI, Scopus)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 31
  • Basım Tarihi: 2026
  • Doi Numarası: 10.1016/j.ecmx.2026.102185
  • Dergi Adı: Energy Conversion and Management: X
  • Derginin Tarandığı İndeksler: Emerging Sources Citation Index (ESCI), Scopus
  • Anahtar Kelimeler: Multi-objective optimization, Nanofluid, NSGA-II, Pareto-optimal solution, Support vector regression, Thermal conductivity, Viscosity
  • İstanbul Gelişim Üniversitesi Adresli: Evet

Özet

This study proposes a novel hybrid framework combining Support Vector Regression optimized by Simulated Annealing (SVR-SA) and the NSGA-II algorithm to optimize the thermophysical properties of CuO-MWCNT/ethylene glycol–water nanofluids for heat-exchanger systems. Two high-fidelity SVR-SA models were developed, achieving exceptional accuracy (correlation coefficients exceeding 0.997; MSEs of 8.36 × 10−5 for μnf and 3.67 × 10−4 for thermal conductivity (TC)). To ensure model robustness and generalization capability, a rigorous 10-fold cross-validation procedure was implemented, yielding consistently low Coefficient of Variation of Errors (CV) values (ranging from 0.0043 to 0.0987). This analysis further highlighted a strong interaction between temperature and concentration, particularly at lower temperatures for viscosity and higher concentrations for thermal conductivity. The results demonstrate that the synergy between SVR-SA-NSGA-II and a comprehensive sensitivity analysis provides a computationally efficient and reliable tool for designing nanofluids with tailored properties, significantly advancing the current state of nanofluid engineering.