AIMC Topic: Hydrodynamics

Clear Filters Showing 11 to 20 of 122 articles

Simulating fish autonomous swimming behaviours using deep reinforcement learning based on Kolmogorov-Arnold Networks.

Bioinspiration & biomimetics
The study of fish swimming behaviours and locomotion mechanisms holds significant scientific and engineering value. With the rapid advancements in artificial intelligence, a new method combining deep reinforcement learning (DRL) with computational fl...

A bioinspired fish fin webbing for proprioceptive feedback.

Bioinspiration & biomimetics
The propulsive fins of ray-finned fish are used for large scale locomotion and fine maneuvering, yet also provide sensory feedback regarding hydrodynamic loading and the surrounding environment. This information is gathered via nerve cells in the web...

Theoretical investigations on analysis and optimization of freeze drying of pharmaceutical powder using machine learning modeling of temperature distribution.

Scientific reports
This study investigates the application of various neural network-based models for predicting temperature distribution in freeze drying process of biopharmaceuticals. For heat-sensitive biopharmaceutical products, freeze drying is preferred to preven...

Effects of maximum thickness position on hydrodynamic performance for fish-like swimmers.

Bioinspiration & biomimetics
When designing the internals of robotic fish, variations in the internal arrangements of power and control systems cause differences in external morphological structures, particularly the positions of maximum thickness. These differences considerably...

Optimization of a passive roll absorber for robotic fish based on tune mass damper.

Bioinspiration & biomimetics
The robotic fish utilizes a bio-inspired undulatory propulsion system to achieve high swimming performance. However, significant roll motion has been observed at the head when the tail oscillates at certain frequencies, adversely affecting both perce...

Artificial intelligence neural network and fuzzy modelling of unsteady Sisko trihybrid nanofluids for cancer therapy with entropy insights.

Scientific reports
The main objective of the current endeavor is to monitor hypothetical processes utilizing a Sisko tri-hybrid fluid over a rotating disk with entropy generation suspended in Darcy-Forchheimer porous medium. Electro Magneto Hydro Dynamics (EMHD), non-l...

Predicting coronary artery occlusion risk from noninvasive images by combining CFD-FSI, cGAN and CNN.

Scientific reports
Wall Shear Stress (WSS) is one of the most important parameters used in cardiovascular fluid mechanics, and it provides a lot of information like the risk level caused by any vascular occlusion. Since WSS cannot be measured directly and other availab...

Physical reservoir computing on a soft bio-inspired swimmer.

Neural networks : the official journal of the International Neural Network Society
Bio-inspired Autonomous Underwater Vehicles with soft bodies provide significant performance benefits over conventional propeller-driven vehicles; however, it is difficult to control these vehicles due to their soft underactuated bodies. This study i...

Prediction of directional solidification in freeze casting of biomaterial scaffolds using physics-informed neural networks.

Biomedical physics & engineering express
Freeze casting, a manufacturing technique widely applied in biomedical fields for fabricating biomaterial scaffolds, poses challenges for predicting directional solidification due to its highly nonlinear behavior and complex interplay of process para...

Encoding spatiotemporal asymmetry in artificial cilia with a ctenophore-inspired soft-robotic platform.

Bioinspiration & biomimetics
A remarkable variety of organisms use metachronal coordination (i.e. numerous neighboring appendages beating sequentially with a fixed phase lag) to swim or pump fluid. This coordination strategy is used by microorganisms to break symmetry at small s...