Solving real-world optimization tasks using physics-informed neural computing
J Seo - Scientific Reports, 2024 - nature.com
Optimization tasks are essential in modern engineering fields such as chip design,
spacecraft trajectory determination, and reactor scenario development. Recently, machine …
spacecraft trajectory determination, and reactor scenario development. Recently, machine …
Past rewinding of fluid dynamics from noisy observation via physics-informed neural computing
J Seo - Physical Review E, 2024 - APS
Reconstructing the past of observed fluids has been known as an ill-posed problem due to
both numerical and physical challenges, especially when observations are distorted by …
both numerical and physical challenges, especially when observations are distorted by …
Highest fusion performance without harmful edge energy bursts in tokamak
The path of tokamak fusion and International thermonuclear experimental reactor (ITER) is
maintaining high-performance plasma to produce sufficient fusion power. This effort is …
maintaining high-performance plasma to produce sufficient fusion power. This effort is …
Applications of Machine Learning in Real-Time Control Systems: A Review
X Zhao, Y Sun, Y Li, N Jia, J Xu - Measurement Science and …, 2024 - iopscience.iop.org
Real-time control systems (RTCS) have become an indispensable part of modern industry,
finding widespread applications in fields such as robotics, intelligent manufacturing and …
finding widespread applications in fields such as robotics, intelligent manufacturing and …
Reinforcement Learning for Sustainable Energy: A Survey
K Ponse, F Kleuker, M Fejér, Á Serra-Gómez… - arXiv preprint arXiv …, 2024 - arxiv.org
The transition to sustainable energy is a key challenge of our time, requiring modifications in
the entire pipeline of energy production, storage, transmission, and consumption. At every …
the entire pipeline of energy production, storage, transmission, and consumption. At every …
Intelligent hydrogen-ammonia combined energy storage system with deep reinforcement learning
P Lan, S Chen, Q Li, K Li, F Wang, Y Zhao - Renewable Energy, 2024 - Elsevier
To achieve carbon neutrality, hydrogen and ammonia are considered promising energy
carriers for renewable energy. Efficient use of these resources has become a critical …
carriers for renewable energy. Efficient use of these resources has become a critical …
Key feature identification of internal kink mode using machine learning
H Ning, S Lou, J Wu, T Zhou - Frontiers in Physics, 2024 - frontiersin.org
The internal kink mode is one of the crucial factors affecting the stability of magnetically
confined fusion devices. This paper explores the key features influencing the growth rate of …
confined fusion devices. This paper explores the key features influencing the growth rate of …
Adapted Swin Transformer-based Real-Time Plasma Shape Detection and Control in HL-3
Q Dong, Z Chen, R Li, Z Yang, F Gao, Y Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
In the field of magnetic confinement plasma control, the accurate feedback of plasma
position and shape primarily relies on calculations derived from magnetic measurements …
position and shape primarily relies on calculations derived from magnetic measurements …
Tokamak edge localized mode onset prediction with deep neural network and pedestal turbulence
A neural network, BES-ELMnet, predicting a quasi-periodic disruptive eruption of the plasma
energy and particles known as edge localized mode (ELM) onset is developed with …
energy and particles known as edge localized mode (ELM) onset is developed with …
Surrogate model of turbulent transport in fusion plasmas using machine learning
H Li, L Wang, YL Fu, ZX Wang, T Wang, J Li - Nuclear Fusion, 2024 - iopscience.iop.org
The advent of machine learning (ML) has revolutionized the research of plasma
confinement, offering new avenues for exploration. It enables the construction of models that …
confinement, offering new avenues for exploration. It enables the construction of models that …