Multi-cavitation states diagnosis of the vortex pump using a combined DT-CWT-VMD and BO-LW-KNN based on motor current signals

IEEE Sensors Journal, Journal Year: 2024, Volume and Issue: 24(19), P. 30690 - 30705

Published: Aug. 26, 2024

Language: Английский

---

Analyzing magnetic dipole impact in fluid flow with endothermic/exothermic reactions: neural network simulation

Physica Scripta, Journal Year: 2024, Volume and Issue: 99(6), P. 065215 - 065215

Published: April 18, 2024

Abstract The consequence of exothermic/endothermic chemical reactions and Arrhenius activation on the heat mass transport liquid flow past a cylinder in incidence magnetic dipole is considered current investigation. Magnetic dipoles are used medical applications such as magnotherapy spectroscopy, to produce static fields. Scientists engineers can improve effectiveness or transfer operations by analyzing impact building systems with optimized flows. modelled equations converted into non-dimensional ordinary differential (ODEs) using similarity variables. resultant solved employing physics-informed neural network (PINN) technique. Additionally, comparison PINN numerical method Runge–Kutta Fehlberg’s fourth-fifth order (RKF-45) studied. effects different parameters temperature, concentration, velocity profiles for endothermic/exothermic instances shown graphically. thermal, velocity, concentration get stronger curvature parameter values increase both endothermic exothermic cases. influence energy parameters, reaction thermal also depicted.

Language: Английский

---

Physics-informed neural networks for two-phase film boiling heat transfer

International Journal of Heat and Mass Transfer, Journal Year: 2025, Volume and Issue: 241, P. 126680 - 126680

Published: Jan. 10, 2025

Language: Английский

---

Application of machine learning in adsorption energy storage using metal organic frameworks: A review

Journal of Energy Storage, Journal Year: 2025, Volume and Issue: 111, P. 115363 - 115363

Published: Jan. 13, 2025

Language: Английский

---

On the Preprocessing of Physics-informed Neural Networks: How to Better Utilize Data in Fluid Mechanics

Journal of Computational Physics, Journal Year: 2025, Volume and Issue: unknown, P. 113837 - 113837

Published: Feb. 1, 2025

Language: Английский

---

Can Artificial Intelligence Accelerate Fluid Mechanics Research?

Fluids, Journal Year: 2023, Volume and Issue: 8(7), P. 212 - 212

Published: July 19, 2023

The significant growth of artificial intelligence (AI) methods in machine learning (ML) and deep (DL) has opened opportunities for fluid dynamics its applications science, engineering medicine. Developing AI encompass different challenges than with massive data, such as the Internet Things. For many scientific, biomedical problems, data are not massive, which poses limitations algorithmic challenges. This paper reviews ML DL research dynamics, presents discusses potential future directions.

Language: Английский

---

Physics-Informed Machine Learning for Data Anomaly Detection, Classification, Localization, and Mitigation: A Review, Challenges, and Path Forward

IEEE Access, Journal Year: 2023, Volume and Issue: 12, P. 4597 - 4617

Published: Dec. 28, 2023

Advancements in digital automation for smart grids have led to the installation of measurement devices like phasor units (PMUs), micro-PMUs (μ-PMUs), and meters. However, large amount data collected by these bring several challenges as control room operators need use this with models make confident decisions reliable resilient operation cyber-power systems. Machine-learning (ML) based tools can provide a interpretation deluge obtained from field. For decision-makers ensure network under all operating conditions, identify solutions that are feasible satisfy system constraints, while being efficient, trustworthy interpretable. This resulted increasing popularity physics-informed machine learning (PIML) approaches, methods overcome model-based or data-driven ML face silos. work aims at following: a) review existing strategies techniques incorporating underlying physical principles power grid into different types approaches (supervised/semi-supervised learning, unsupervised reinforcement (RL)); b) explore works on PIML anomaly detection, classification, localization, mitigation transmission distribution systems, c) discuss improvements through consideration potential also addressing limitations them suitable real-world applications.

Language: Английский

---

The Application of Physics-Informed Machine Learning in Multiphysics Modeling in Chemical Engineering

Industrial & Engineering Chemistry Research, Journal Year: 2023, Volume and Issue: 62(44), P. 18178 - 18204

Published: Oct. 26, 2023

Physics-Informed Machine Learning (PIML) is an emerging computing paradigm that offers a new approach to tackle multiphysics modeling problems prevalent in the field of chemical engineering. These often involve complex transport processes, nonlinear reaction kinetics, and coupling. This Review provides detailed account main contributions PIML with specific emphasis on momentum transfer, heat mass reactions. The progress method development (e.g., algorithm architecture), software libraries, applications coupling surrogate modeling) are detailed. On this basis, future challenges highlight importance developing more practical solutions strategies for PIML, including turbulence models, domain decomposition, training acceleration, modeling, hybrid geometry module creation.

Language: Английский

---

Understanding Physics-Informed Neural Networks: Techniques, Applications, Trends, and Challenges

AI, Journal Year: 2024, Volume and Issue: 5(3), P. 1534 - 1557

Published: Aug. 29, 2024

Physics-informed neural networks (PINNs) represent a significant advancement at the intersection of machine learning and physical sciences, offering powerful framework for solving complex problems governed by laws. This survey provides comprehensive review current state research on PINNs, highlighting their unique methodologies, applications, challenges, future directions. We begin introducing fundamental concepts underlying motivation integrating physics-based constraints. then explore various PINN architectures techniques incorporating laws into network training, including approaches to partial differential equations (PDEs) ordinary (ODEs). Additionally, we discuss primary challenges faced in developing applying such as computational complexity, data scarcity, integration Finally, identify promising Overall, this seeks provide foundational understanding PINNs within rapidly evolving field.

Language: Английский

---

Physics-informed neural networks for transonic flow around a cylinder with high Reynolds number

Physics of Fluids, Journal Year: 2024, Volume and Issue: 36(3)

Published: March 1, 2024

The physics-informed neural network (PINN) method is extended to learn and predict compressible steady-state aerodynamic flows with a high Reynolds number. To better the thin boundary layer, sampling distance function hard condition are explicitly introduced into input output layers of deep network, respectively. A gradient weight factor considered in loss implement PINN methods based on averaged Navier–Stokes (RANS) Euler equations, respectively, denoted as PINN–RANS PINN–Euler. Taking transonic flow around cylinder an example, these first verified for ability complex then applied global part physical data. When predicting velocity data local key regions, can always accurately field including layer wake, while PINN–Euler inviscid region. subsonic under different freestream Mach numbers (Ma∞= 0.3–0.7), fields predicted by both avoid inconsistency real phenomena pure data-driven method. insufficient shock identification capabilities. Since does not need second derivative, training time only 1/3 times that at same point network.

Language: Английский

---