Kriging and neural network models for pressure losses across perforated plates

2026-06-28 · Source: Takara TLDR - Daily AI Papers · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Computational Fluid Dynamics · Depth: Expert, quick

Summary

Two novel data-driven models, based on kriging and neural networks (NN), are proposed to accurately predict pressure losses across perforated plates with circular perforations in turbulent flows. Developed using two sets of experimental data, these models consistently outperform widely used empirical formulae for most configurations. The predicted pressure losses show good agreement with experimental measurements, demonstrating the feasibility of data-driven approaches. Furthermore, the models' applicability in numerical simulations is confirmed by implementing them as a source term in the momentum equations for Reynolds-averaged Navier-Stokes (RANS) simulations of two-dimensional channel flows, showing excellent agreement with RANS predictions.

Key takeaway

For Computational Fluid Dynamics (CFD) engineers modeling pressure losses across perforated plates in turbulent flows, you should consider integrating these kriging or neural network models. They offer significantly improved accuracy over traditional empirical formulae and are directly implementable as source terms within Reynolds-averaged Navier-Stokes (RANS) simulations, enhancing the fidelity of your flow predictions. This approach can lead to more reliable design and analysis outcomes.

Key insights

Kriging and neural network models offer superior prediction of pressure losses across perforated plates.

Principles

• Data-driven approaches provide a feasible framework for modeling pressure losses.
• Proposed models consistently outperform existing empirical models.

Method

Models are developed from experimental data and implemented as a source term in momentum equations for RANS simulations.

In practice

• Predict pressure losses in turbulent flows.
• Integrate into RANS computational fluid dynamics applications.

Topics

• Kriging
• Neural Networks
• Pressure Loss
• Perforated Plates
• Turbulent Flow
• Computational Fluid Dynamics
• RANS Simulations

Best for: AI Scientist, Machine Learning Engineer, Research Scientist

Related on AIssential

• Neural Network-Based Parametric Model Reduction for Predicting Turbulent Flow for Different Vehicle Geometries — A VAE-enhanced neural network model reduces computational cost for high-fidelity turbulent flow predictions around diverse vehicle geometries.
• Porosity and permeability prediction from petrographic point-counting data using machine learning — Machine learning can predict reservoir properties from historical petrographic point-counting data.
• Physics-informed convolutional neural networks for fluid flow through porous media — Physics-informed CNNs accurately predict fluid flow in porous media, significantly accelerating traditional LBM simulations.
• FLAME 2023: Diving into the Future of Fluid Dynamics and Machine Learning — AI techniques are transforming simulation by integrating physics-based modeling with data-driven machine learning.
• Mesh Graph Neural Network Framework for Accelerating Finite Element Simulation for Arbitrary Geometries — Mesh Graph Networks effectively generalize finite element analysis predictions across arbitrary structural geometries by encoding relative features.
• A Geometry-Aware Triplane Field Network for Vehicle Aerodynamic Prediction — GTF-Net combines triplane representations with explicit geometric cues for accurate vehicle aerodynamic prediction.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Takara TLDR - Daily AI Papers.