arXiv:2606.29628v1 Announce Type: cross Abstract: In this paper, two novel data-driven models based on kriging and neural networks (NN) are proposed to predict pressure losses across perforated plates with circular perforations in turbulent flows. The models are developed using two sets of experimental data available in the literature. The predictive performance of the proposed models is assessed and compared against widely used empirical formulae. It is found that the proposed models consistently outperform existing empirical models for most perforated plate configurations contained in the ex
The continuous advancements in AI and machine learning techniques enable new applications in traditional engineering fields, improving predictive capabilities.
Improved predictive models for fluid dynamics and pressure losses can optimize industrial designs, reduce energy consumption, and enhance operational efficiency across various sectors.
Traditional empirical formulae for predicting pressure losses are being supplanted by more accurate and data-driven AI models, leading to better engineering outcomes.
- · Industrial engineering firms
- · Energy sector
- · AI/ML model developers
- · Manufacturing companies
- · Developers of legacy empirical models
- · Companies slow to adopt AI in design
More efficient and cost-effective designs for systems involving fluid flow will emerge.
Reduced operational costs and energy demands in industries relying on fluid dynamics, such as HVAC, aerospace, and chemical processing.
The acceleration of AI adoption within conservative engineering disciplines, further blurring the lines between traditional physics and data science.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG