Optimization-Based Correction of Turbulence Models for Flow Prediction in Control Valves

The conventional Shear Stress Transport (SST) k–ω turbulence model often exhibits substantial inaccuracies when applied to the prediction of flow behavior in complex regions within axial flow control valves. To enhance its predictive fidelity for internal flow fields, this study introduces a novel calibration framework that integrates an artificial neural network (ANN) surrogate model with a particle swarm optimization (PSO) algorithm. In particular, an optimal Latin hypercube sampling strategy was employed to generate representative sample points across the empirical parameter space. For each sample, numerical simulations using ANSYS Fluent were conducted to evaluate the flow characteristics, with empirical turbulence model parameters as inputs and flow rate as the target output. These data were used to construct the high-fidelity ANN surrogate model. The PSO algorithm was then applied to this surrogate to identify the optimal set of empirical parameters tailored specifically to axial flow control valve configurations. A revealed by the presented results, the calibrated SST k–ω model significantly improves prediction accuracy: deviations from large eddy simulation (LES) benchmarks at small valve openings were reduced from 7.6% to under 3%. Furthermore, the refined model maintains the computational efficiency characteristic of Reynolds-averaged Navier-Stokes (RANS) simulations while substantially enhancing the accuracy of both pressure and velocity field predictions. Overall, the proposed methodology effectively reconciles the trade-off between computational cost and predictive accuracy, offering a robust and scalable approach for turbulence model calibration in complex internal flow scenarios.