Machine-learning-based wake prediction and optimization of a circular cylinder with vortex generators using particle swarm optimization and musk ox optimization algorithms
PHYSICS OF FLUIDS, cilt.38, sa.4, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 38 Sayı: 4
- Basım Tarihi: 2026
- Doi Numarası: 10.1063/5.0321303
- Dergi Adı: PHYSICS OF FLUIDS
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Chemical Abstracts Core, Chimica, Compendex, INSPEC, zbMATH, Academic Search Ultimate (EBSCO)
- Yıldız Teknik Üniversitesi Adresli: Evet
Özet
Flow around a circular cylinder is a canonical bluff-body problem for tubular and offshore structures, where separation and vortex shedding govern unsteady loads. Here, experimental particle image velocimetry data at Reynolds number Re = 8 & times; 10(3) were used to train an artificial neural network (ANN) surrogate for the wake of a vortex-generators (VGs)-equipped circular cylinder. The surrogate learned a pointwise mapping from the VGs angles and spatial coordinates (alpha, beta, x, y) to five flow statistics: mean velocities (< u >, < v >), velocity fluctuations ( u(rms)', v(rms)'), and Reynolds shear stress < u ' v '>. A comprehensive search of 1736 ANN candidates identified the best architecture as a multilayer perceptron with a 4-neuron linear projection layer followed by two 65-neuron hidden layers with hyperbolic tangent activation, trained with a mini-batch size of 2; near-unity accuracy was achieved across all five quantities (R-2 approximate to 0.98-0.99) with low errors. SHapley Additive exPlanations (SHAP) and Sobol analyses showed that alpha is the primary control parameter: mean |SHAP| for alpha was 0.004 29 m/s for J(u(rms)'), 0.007 88 m/s for J(v(rms)'), and 3.298 & times; 10(-4) m(2)/s(2) for J(< u ' v '>), exceeding beta by factors of 3.1, 2.9, and 2.6. The ANN was then coupled with Particle Swarm Optimization and Musk Ox Optimization, and both converged to the same optima for each target, yielding distinct (alpha, beta) pairs for J(u(rms)'), J(v(rms)'), and thereby demonstrating clear trade-offs among turbulence metrics.