Can Artificial Intelligence Accelerate Fluid Mechanics Research?

Drikakis, Dimitris; Sofos, Filippos

doi:10.3390/fluids8070212

Cited by 16 publications

(6 citation statements)

References 195 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CFD allows for the simulation of fluid flow in and around medical devices, providing insights that are difficult to obtain through experimental methods alone. This is particularly important in the design of devices where the flow of fluids is a critical factor affecting their performance (Drikakis & Sofos, 2023).…”

Section: The Significance Of Fluid Mechanics In Biomedical Engineeringmentioning

confidence: 99%

“…AI and machine learning techniques can be used to analyze complex fluid dynamics data, predict fluid flow patterns, and optimize device designs. This integration is particularly promising in personalized medicine, where patient-specific models can be developed to predict how a particular device or treatment will perform for an individual patient (Drikakis & Sofos, 2023).…”

Section: The Significance Of Fluid Mechanics In Biomedical Engineeringmentioning

confidence: 99%

See 1 more Smart Citation

Nzubechukwu Chukwudum Ohalete

Oluwatoyin Ayo-Farai,

Chinyere Onwumere,

Chinedu Paschal Maduka

et al. 2024

World J. Adv. Res. Rev.

View full text Add to dashboard Cite

This paper delves into the critical role of Navier-Stokes equations in biomedical engineering, with a specific focus on their application in the development of medical devices across the United States and Africa. The study aims to elucidate the integration of fluid dynamics principles in medical device innovation, assess the influence of cultural and economic factors on device design, and explore the regulatory landscape shaping this domain. Employing a methodical approach, the study analyzes Navier-Stokes applications in diverse geographical contexts, utilizing case studies to underscore the relevance and methodological rigor in biomedical engineering. The findings reveal that Navier-Stokes equations are pivotal in modeling biological fluid flows, essential for the design and analysis of cardiovascular and respiratory devices. The advancement of computational fluid dynamics (CFD) has significantly enhanced these applications, enabling more precise and patient-specific analyses. However, challenges in computational resources and simulating physiological conditions are identified as key limitations. The study highlights the profound impact of cultural and economic considerations on medical device design and functionality. It emphasizes the necessity of creating devices that are not only innovative and effective but also culturally appropriate and economically viable. Additionally, the evolving regulatory frameworks, particularly in the wake of global health crises, are examined for their impact on device safety and efficacy. In conclusion, the study recommends continued research and development to address the identified challenges and limitations, advocating for a multidisciplinary approach that integrates engineering, computational modeling, and medical expertise. It also calls for the consideration of cultural, economic, and regulatory factors in the design and development of medical devices, ensuring their global applicability and effectiveness in improving healthcare outcomes.

show abstract

Section: The Significance Of Fluid Mechanics In Biomedical Engineeringmentioning

confidence: 99%

Section: The Significance Of Fluid Mechanics In Biomedical Engineeringmentioning

confidence: 99%

Nzubechukwu Chukwudum Ohalete

Oluwatoyin Ayo-Farai,

Chinyere Onwumere,

Chinedu Paschal Maduka

et al. 2024

World J. Adv. Res. Rev.

View full text Add to dashboard Cite

show abstract

“…Nevertheless, the increased computational effort inherent in DNS and other numerical formulations, both in terms of time and hardware needs, has opened the way to adopt novel computational techniques stemming from machine learning (ML) [16]. Aerodynamic coefficient prediction, turbulence modeling, transitional flow modeling, and flow reconstruction are just a few fields of application [17,18].…”

Section: Introductionmentioning

confidence: 99%

From Sparse to Dense Representations in Open Channel Flow Images with Convolutional Neural Networks

Sofos,

Sofiadis,

Chatzoglou

et al. 2024

Inventions

Self Cite

View full text Add to dashboard Cite

Convolutional neural networks (CNN) have been widely adopted in fluid dynamics investigations over the past few years due to their ability to extract and process fluid flow field characteristics. Both in sparse-grid simulations and sensor-based experimental data, the establishment of a dense flow field that embeds all spatial and temporal flow information is an open question, especially in the case of turbulent flows. In this paper, a deep learning (DL) method based on computational CNN layers is presented, focusing on reconstructing turbulent open channel flow fields of various resolutions. Starting from couples of images with low/high resolution, we train our DL model to efficiently reconstruct the velocity field of consecutive low-resolution data, which comes from a sparse-grid Direct Numerical Simulation (DNS), and focus on obtaining the accuracy of a respective dense-grid DNS. The reconstruction is assessed on the peak signal-to-noise ratio (PSNR), which is found to be high even in cases where the ground truth input is scaled down to 25 times.

show abstract

“…The significant growth of AI methods in machine learning has opened additional opportunities for fluid dynamics and its applications in science and engineering. However, experts note that AI methods should be deeply immersed in interpretability, with detailed explanations of cause-and-effect relationships [55]. The potential impact of AI will be high only if the output obeys physical laws.…”

Section: Introductionmentioning

confidence: 99%

“…Nevertheless, its applicability should be thoroughly tested and verified. In addition, researchers should be allowed to publish not only their successes but also their unsuccessful attempts at using AI [55].…”

Section: Introductionmentioning

confidence: 99%

Solving Innovative Problems of Thrust Vector Control Based on Euler's Scientific Legacy

Sazonov,

Mokhov,

Gryaznova

et al. 2023

Civ Eng J

View full text Add to dashboard Cite

This study aims to develop an interdisciplinary approach to solving innovative thrust vector control problems. The methodology involves the development of a working hypothesis about the ejection process when using a controlled nozzle to deflect the thrust vector (velocity vector) in any direction within a complete geometric sphere. When developing the working hypothesis, a multilateral analysis of individual facts and scientific and technical information is performed using tools in the "big data" area, assessing opportunities to apply the "Foresight" methodology for predicting the development of fluidics. The authors propose new mathematical models to describe the thrust vector in the distribution of the mass flow rate of the fluid medium between flow channels. Patents for inventions support the novelty of scientific results that reveal new opportunities for more active development of fluidics as applied to simple and complex jet systems with low and extremely high energy density in flows. The proposed methodology rests on a modern computer base and is a logical continuation and development of well-known Euler’s works. The computer simulation of multiflow jet devices mainly focuses on power engineering, production, and processing of hydrocarbons. Some results of this research work, including patented design developments and calculation methods, also apply to developing robotics, unmanned vehicles, and programable jet systems. The authors attribute further development of the interdisciplinary approach for solving inventive problems to the use of different AI options. Doi: 10.28991/CEJ-2023-09-11-017 Full Text: PDF

show abstract

Can Artificial Intelligence Accelerate Fluid Mechanics Research?

Cited by 16 publications

References 195 publications

Nzubechukwu Chukwudum Ohalete

Nzubechukwu Chukwudum Ohalete

From Sparse to Dense Representations in Open Channel Flow Images with Convolutional Neural Networks

Solving Innovative Problems of Thrust Vector Control Based on Euler's Scientific Legacy

Contact Info

Product

Resources

About