A5047562320- Geophysical Methods and Applications
- Geophysical and Geoelectrical Methods
- Cavitation Phenomena in Pumps
- Seismic Imaging and Inversion Techniques
- Heat Transfer and Optimization
- Vibration and Dynamic Analysis
- Power Systems and Renewable Energy
- Soil Moisture and Remote Sensing
- Hydraulic and Pneumatic Systems
Jiangxi College of Applied Technology
2023-2025
Ministry of Natural Resources
2023
The conventional magnetotelluric inversion method is subject to the influence of initial model, which leads an unstable process and a tendency get trapped at local optimal solutions. In contrast, deep learning technology relies on its powerful non-linear fitting capability can construct complex mappings directly from observation data (input) model (output). recent years, it has received extensive attention researchers. Due difficulties in creating sufficiently large dataset performing neural...
Traditional gradient-based inversion methods usually suffer from the problems of falling into local minima and relying heavily on initial guesses. Deep-learning have received increasing attention due to their excellent nonlinear fitting ability. However, given recent application deep-learning in field magnetotelluric (MT) inversion, there are currently challenges associated with achieving high resolution extracting sufficient features. We develop a neural network model (called MT2DInv-Unet)...
Abstract To address the issue of excessive temperature rises within field electronic device cooling, this study adopts a multi-parameter optimization method. The primary objective is to explore and realize design shell structure high-voltage control box, aiming effectively mitigate rise in internal components enhance their thermal management efficacy without altering fan performance, environmental conditions, or spatial layout. Initially, employs computational fluid dynamics methods...