Future trends: AI models tackle complex particle drag coefficients

Accurately modeling the movement of particles in fluids is critical in fields ranging from chemical engineering to aerospace. Drag coefficients, which affect how particles settle and move within a fluid environment, are a core element of these calculations. Although the behavior of spherical particles is well understood, predicting the drag coefficient of irregularly shaped particles has long been a challenge. These complexities highlight the need for more sophisticated approaches to modeling particle-fluid interactions, especially for non-spherical particles.

A team from Nanjing University of Science and Technology and West Lake University addressed this problem by integrating machine learning and advanced numerical methods. Their study, published in the International Journal of Mechanical System Dynamics, combines the discrete element method (DEM) and the lattice Boltzmann method (LBM) to create a highly accurate dataset. This data was used to develop four machine learning models aimed at predicting the drag coefficient of polygonal particles, with one model achieving a prediction error of less than 5%, representing a major advance in fluid mechanics research. Ta.

This study addresses the long-standing challenge of predicting the drag coefficient of irregularly shaped particles. Traditionally, a single shape factor has not been sufficient to capture the complex details that influence particle behavior. By using DEM and LBM simulations, the researchers generated accurate datasets on which multiple machine learning models can be developed. The genetic algorithm-artificial neural network (GA-ANN) model performed better than other models, reducing the prediction error to less than 5%. This breakthrough demonstrates the effectiveness of machine learning in improving the accuracy of particle-fluid interaction models.

Professor Cheng Cheng, one of the lead researchers, said: “This study shows the immense potential of machine learning to solve complex fluid dynamics problems. Leveraging numerical simulation and artificial intelligence (AI) By doing so, we achieved an unprecedented level of precision.” Predicting the drag coefficient of polygonal particles can have far-reaching implications in both academic and industrial settings. ”

This ability to predict drag coefficients with such accuracy has wide applications across industries such as chemical processing, environmental engineering, and aerospace technology. Enhanced drag prediction models improve processes such as sedimentation, filtration, and propulsion to increase system efficiency. The results of this research are expected to lead to advances in fluid-particle interaction design and provide a wide range of possibilities for optimizing various industrial systems.