An efficient parallel dynamic component tracking model of gas networks by decoupling hydraulic, thermal, and convection-diffusion processes

Energy, Journal Year: 2025, Volume and Issue: unknown, P. 135203 - 135203

Published: Feb. 1, 2025

Language: Английский

Research on turbine blade temperature field reconstruction by coupling proper orthogonal decomposition and artificial neural network methods

Physics of Fluids, Journal Year: 2025, Volume and Issue: 37(3)

Published: March 1, 2025

The temperature of turbine blades is a critical factor influencing their performance and lifespan. However, high cost required for the traditional experimental computational fluid dynamics (CFD) methods to obtain an accurate field blades. In this paper, effective reconstruction method that combines proper orthogonal decomposition (POD) with artificial neural network (ANN) proposed. Initially, POD employed reduce dimensionality blade data by extracting dominant spatial modes corresponding mode coefficients, thereby significantly reducing complexity. Subsequently, ANN feedforward as its core developed predict facilitating rapid field. Comparative results indicate POD-ANN approach not only maintains prediction accuracy—with maximum relative error 2.61% solid fields 0.10% domain—but also dramatically reduces computation time, achieving speedup 793 223.2 conventional CFD methods. This study, therefore, presents robust feasible technical optimization fields.

Language: Английский

Rapid modeling of transient processes in hydrogen-blended natural gas pipelines featuring injection and withdrawal points

International Journal of Hydrogen Energy, Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Language: Английский