Hydrodynamic Performance Optimization of AU-Type Propellers Based on BO-BPNN Surrogate Model and CFD Validation

Abstract

This study proposes an intelligent optimization framework integrating Bayesian-optimized Back Propagation Neural Networks (BO-BPNN) with Genetic Algorithm (GA) and Adaptive Monte Carlo (AMC) method for systematic marine propeller design. The methodological innovations include introducing Bayesian Optimization (BO) for adaptive hyperparameter tuning of BPNN and proposing an improved AMC algorithm with hybrid sampling and decaying search radius mechanisms. A data-driven surrogate model is established on 2 552 open-water performance records of AU-type propellers. Compared with conventional BPNN, the BO-BPNN model achieves significant improvements: an 89% reduction in Mean Squared Error (MSE = 0.000 3), a 66% decrease in Mean Absolute Error (MAE = 0.009 7), and a coefficient of determination R² = 0.995 6. Systematic comparative analysis reveals that while both GA and AMC successfully identify identical optimal design parameters (the number of blades Z = 3, pitch ratio P/D = 0.7, disc area ratio A_E/A₀ = 0.36, and advance ratio J = 0.5, yielding maximum open-water efficiency (η₀ = 0.687), GA demonstrates superior convergence reliability despite comparable total computation time. CFD validation using STAR-CCM+ confirms the framework’s reliability with only a 0.6% relative difference. The framework establishes a reusable paradigm that synergistically integrates adaptive surrogate modeling with physics-based validation, significantly reducing computational costs and design cycles while maintaining high accuracy.

Keywords

Marine propeller / Open-water efficiency / Back propagation neural network / Genetic algorithm / Adaptive monte carlo method

References

[1] Abdoos AA, Abdoos H, Kazemitabar J, Mobashsher MM, Khaloo H. An intelligent hybrid method based on Monte Carlo simulation for short-term probabilistic wind power prediction. Energy, 2023, 278: 127914.

[2] Akiba T, Sano S, Yanase T, Ohta T, Koyama M. Optuna: a next-generation hyperparameter optimization framework. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, USA, 20192623-2631

[3] Arapakopoulos A, Polichshuk R, Segizbayev Z, Ospanov S, Ginnis AI, Kostas KV. Parametric models for marine propellers. Ocean Engineering, 2019, 192: 106595.

[4] Bahatmaka A, Kim DJ, Chrismianto D, Setiawan JD, Prabowo AR. Numerical investigation on the performance of ducted propeller. MATEC Web of Conferences, 2017, 138: 07002.

[5] Bergstra J, Bardenet R, Bengio Y, Kégl B. Algorithms for hyper-parameter optimization. Proceedings of the 25th International Conference on Neural Information Processing Systems, Granada, Spain, 20112546-2554

[6] Calcagni D, Salvatore F, Bernardini G, Miozzi M. Automated marine propeller design combining hydrodynamics models and neural networks. Proceedings of the First International Symposium on Fishing Vessel Energy Efficiency, Vigo, Spain, 20101-10

[7] Chen B, Stern F. RANS simulation of marine-propulsor P4119 at design condition. Proceedings of the 22nd ITTC Propulsion Committee Propeller RANS/Panel Method Workshop, Grenoble, France, 1998427-433

[8] Chicco D, Warrens MJ, Jurman G. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Computer Science, 2021, 7: e623.

[9] Gaggero S, Tani G, Villa D, Viviani M, Ausonio P, Travi P, Bizzarri G, Serra F. Efficient and multi-objective cavitating propeller optimization: an application to a high-speed craft. Applied Ocean Research, 2017, 64: 31-57.

[10] Gao N, Chuang Z, Hu A. Propeller hydrodynamic performance optimization based on deep learning. OCEANS 2024-Singapore, 2024

[11] Görmüş T, Ayat B, Aydoğan B. Statistical models for extreme waves: comparison of distributions and Monte Carlo simulation of uncertainty. Ocean Engineering, 2022, 248: 110820.

[12] Guo Z, Han Q, Wei F, Qi W. Wind power prediction based on hybrid deep learning and Monte Carlo simulation. Engineering Applications of Artificial Intelligence, 2025, 161: 112082.

[13] Herath MT, Natarajan S, Prusty BG, John NS. Isogeometric analysis and genetic algorithm for shape-adaptive composite marine propellers. Computer Methods in Applied Mechanics and Engineering, 2015, 284: 835-860.

[14] Kim Y, Lee Y, Son M, Kim T, Suh J. Generating cutter paths for marine propellers without interference and gouging. Journal of Marine Science and Technology, 2009, 14(3): 275-284.

[15] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521(7553): 436-444.

[16] Lee C, Lee J. Geometric modeling and tool path generation of model propellers with a single setup change. The International Journal of Advanced Manufacturing Technology, 2010, 50(1): 253-263.

[17] Li L, Chen Y, Qiang Y, Zhou B, Chen W. Construction and application of numerical diagram for high-skew propeller based on machine learning. Ocean Engineering, 2023, 278: 114480.

[18] Li L, Chen Y, Xie S, Xiao Y, Fang T, Wang C. Comprehensive feature-based machine learning for fast prediction of marine propeller’s open-water performance. Applied Ocean Research, 2025, 154: 104310.

[19] Li X, Cai W, Ren N, Sun S. The effect of the fillets on submarine wake field and propeller unsteady bearing force. Journal of Marine Science and Engineering, 2023, 11(12): 2287

[20] Lin Y, Hasan AD. The CFD simulation of E1619 propeller open-water tests validated by the EFD in the NCKU towing tank. Journal of Mechanics, 2023, 39: 416-430.

[21] Liu Y, Gong Q. Numerical investigation on the flow characteristics and hydrodynamic performance of tandem propeller. Applied Ocean Research, 2020, 101: 102292.

[22] Lu L, Pan G, Sahoo PK. CFD prediction and simulation of a pumpjet propulsor. International Journal of Naval Architecture and Ocean Engineering, 2016, 8(1): 110-116.

[23] Lu Y, Sun L, Zhang X, Kang J, Zhang Q, Yu B. Analysis of FPSO dropped objects combining Monte Carlo simulation and neural network-genetic approach. Ocean Engineering, 2018, 149: 183-193.

[24] Mahmoodi K, Böling J, Vettor R. Evaluating the influence of marine weather parameters uncertainties on the ship fuel consumption with Monte Carlo analysis. Ocean Engineering, 2025, 341: 122531.

[25] Nouri NM, Mohammadi S, Zarezadeh M. Optimization of a marine contra-rotating propellers set. Ocean Engineering, 2018, 167: 397-404.

[26] Portillo Juan N, Negro Valdecantos V. A novel model for the study of future maritime climate using artificial neural networks and Monte Carlo simulations under the context of climate change. Ocean Modelling, 2024, 190: 102384.

[27] Scrucca L. GA: a package for genetic algorithms in R. Journal of Statistical Software, 2013, 53(4): 1-37.

[28] Shanker M, Hu MY, Hung MS. Effect of data standardization on neural network training. Omega-International Journal of Management Science, 1996, 24(4): 385-397.

[29] Sheng Z. Principles of ships, 2019. Shanghai, Shanghai Jiao Tong University Press. (in Chinese).

[30] Snoek J, Larochelle H, Adams RP. Practical Bayesian optimization of machine learning algorithms. Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012, Lake Tahoe, Nevada, USA, 20122951-2959

[31] Stern F, Wilson RV, Coleman HW, Paterson EG. Comprehensive approach to verification and validation of CFD simulations—Part 1: methodology and procedures. Journal of Fluids Engineering, 2001, 123(4): 793-802.

[32] Sun Z, Li Y, Li Y, Su L, He W. Investigation on compressive strength of coral aggregate concrete: hybrid machine learning models and experimental validation. Journal of Building Engineering, 2024, 82: 108220.

[33] Tadros M, Boulougouris E. Performance assessment of B-series marine propellers with cupping and face camber ratio using machine learning techniques. Journal of Marine Science and Engineering, 2025, 13(7): 1345.

[34] Tadros M, Shi W, Xu Y, Song Y. A unified cross-series marine propeller design method based on machine learning. Ocean Engineering, 2024, 314: 119691.

[35] Tadros M, Ventura M, Guedes Soares C. Design of propeller series optimizing fuel consumption and propeller efficiency. Journal of Marine Science and Engineering, 2021, 9(11): 1226.

[36] Takekoshi Y, Kawamura T, Yamaguchi H, Maeda M, Ishii N, Kimura K, Taketani T, Fujii A. Study on the design of propeller blade sections using the optimization algorithm. Journal of Marine Science and Technology, 2005, 10(2): 70-81.

[37] Tang DH, Chen JD, Zhou WX. Comparative calculations of propeller performance by RANS/PANEL method. Proceedings of the 22nd ITTC Propulsion Committee Propeller RANS/PANEL Method Workshop, Grenoble, France, 1998

[38] Uto S. RANS simulation of turbulent flow around DTMB4119 propeller. Proceedings of the 22nd ITTC Propulsion Committee Propeller RANS/PANEL Method Workshop, Grenoble, France, 1998

[39] Vázquez-Santos A, Camacho-Zamora N, Hernández-Hernández J, Herrera-May AL, Santos-Cortes LD, Tejeda-del-Cueto ME. Numerical analysis and validation of an optimized Bseries marine propeller based on NSGA-II constrained by cavitation. Journal of Marine Science and Engineering, 2024, 12(2): 205.

[40] Vickers GW. Computer-aided manufacture of marine propellers. Computer-Aided Design, 1977, 9(4): 267-274.

[41] Wang S, Karniadakis GE. GMC-PINNs: a new general Monte Carlo PINNs method for solving fractional partial differential equations on irregular domains. Computer Methods in Applied Mechanics and Engineering, 2024, 429: 117189.

[42] Xie G. Optimal preliminary propeller design based on multi-objective optimization approach. Procedia Engineering, 2011, 16: 278-283.

[43] Xue Y, Yang C, Dong X, Li W, Noblesse F. Design of marine propellers with prescribed and optimal spanwise circulation distributions based on genetic algorithms and neural network. Applied Ocean Research, 2022, 127: 103318.

[44] Yang RY, Shen HC, Yao HZ. Uncertain analysis of CFD simulation on the open-water performance of the propeller. Chuan Bo Li Xue/Journal of Ship Mechanics, 2010, 14: 472-480. (in Chinese).

[45] Ye J, Zhang D, Zheng Z, Yang W, Ke L. Numerical analysis of wake field and unsteady forces on submarine propeller with twisted rudders. Ocean Engineering, 2023, 287: 115798.

[46] Ye X, Jackson TR, Patrikalakis NM. Geometric design of functional surfaces. Computer-Aided Design, 1996, 28(9): 741-752.

[47] Yousaf MZ, Guerrero JM, Sadiq MT. Optimizing machine learning algorithms for fault classification in rolling bearings: A Bayesian optimization approach. Engineering Applications of Artificial Intelligence, 2025, 150: 110597.

[48] Zeng Z, Kuiper G. Blade section design of marine propellers with maximum cavitation inception speed. Journal of Hydrodynamics, Ser. B, 2012, 24(1): 65-75.

[49] Zeng ZB, Ding EB, Tang DH. Ship propeller design optimization based on BP neural network and genetic algorithm. Journal of Ship Mechanics, 2010, 14(10): 1100-1109. (in Chinese).

[50] Zhang H, Hu Y, Li X, Du K, Zeng T, Li C. Application of support vector machines and genetic algorithms to fluid identification in offshore granitic subduction hill reservoirs. Geoenergy Science and Engineering, 2024, 240: 213013.

[51] Zhang L, Wang F, Sun T, Xu B. A constrained optimization method based on BP neural network. Neural Computing and Applications, 2018, 29(2): 413-421.

[52] Zuo H, Zhao Y, Jia J. Bayesian-optimized BP neural network for marine propeller design optimization with improved NSGA-III. Ocean Engineering, 2025, 340: 122375.

RIGHTS & PERMISSIONS

Harbin Engineering University and Springer-Verlag GmbH Germany, part of Springer Nature