A5080039247- Hydraulic and Pneumatic Systems
- Cavitation Phenomena in Pumps
- Wind Energy Research and Development
- Model Reduction and Neural Networks
- Oil and Gas Production Techniques
- Turbomachinery Performance and Optimization
- Advanced Multi-Objective Optimization Algorithms
- Fluid Dynamics and Turbulent Flows
- Energy Load and Power Forecasting
- Wind and Air Flow Studies
- Fluid Dynamics and Vibration Analysis
- Fluid Dynamics Simulations and Interactions
Jiangsu University
2023-2025
Jiangsu Industry Technology Research Institute
2024
To investigate the effect of inlet elbow geometry on performance a large low-head pumping system and improve its comprehensive performance, this paper calculated analyzed internal flow fields, external characteristics, entropy production distribution with different parametric combinations via numerical simulations Reynolds averaged Navier Stokes-volume fluids fixed net head method. The energy characteristics were further studied using newly introduced method local change to visualize...
The efficient prediction of system performance is a critical aspect engineering equipment design, with the traditional methods facing limitations such as high computational demands and precise experimental setups. In response to these limitations, neural network models offer promising solution due their lightweight predictive capabilities. this context, evolution deep learning computer vision has significantly influenced design applications, particularly in recognizing intricate...
Obtaining reliable flow data is essential for the fluid mechanics analysis and control, various measurement techniques have been proposed to achieve this goal. However, imperfect can occur in experimental scenarios, particularly particle image velocimetry technique, resulting insufficient accurate analysis. To address issue, a novel machine learning-based multi-scale autoencoder (MS-AE) framework reconstruct missing fields from turbulent flows. The includes two reconstruction strategies:...
This paper explores innovative approaches for reconstructing the wake flow field of yawed wind turbines from sparse data using data-driven and physics-informed machine learning techniques. The estimation (WFE) integrates neural networks with fundamental fluid dynamics equations, providing robust interpretable predictions. method ensures adherence to essential principles, making it suitable reliable in energy applications. In contrast, (DDML-WFE) leverages techniques such as proper orthogonal...
Tidal turbines play a critical role in converting the kinetic energy of water into electricity, contributing significantly to conversion. However, current optimization design these involves computationally intensive simulations, leading higher costs. Additionally, traditional parameterized modeling methods, constrained by predefined parameters, limit exploration innovative designs. In response, this study introduces an data-driven “generative–predictive” approach comprising generative model...
Ventilated cavitation involves complex multiphase flow, phase change, and turbulence, posing challenges for accurate prediction control. This paper investigates the performance of three turbulence models—Large Eddy Simulation (LES), Detached (DES), Shear Stress Transport (SST)—in predicting unsteady characteristics entropy generation mechanisms in ventilated around a hydrofoil. A comparative analysis with experiments reveals each model's strengths limitations capturing at various scales. The...
The high-power consumption and excessive heat generation in data centers present challenges to thermal management. As a critical component of liquid cooling systems, the circulation pump's stability reliability are directly impacted by cavitation air entrainment, which degrade performance. This study investigates effects with entrained under various rotational speeds volume fractions on centrifugal pump performance, pressure pulsation, behavior. Experiments were conducted using closed-loop...
As the demand for ocean energy continues to grow, development of efficient design and optimization methods tidal current turbines is crucial. Traditional approaches, often based on parameterized models, face challenges in fully capturing intricate geometric features turbine blades, limiting space affecting convergence efficiency. In response, this study introduces a novel methodology horizontal axis (HATTs) using variational autoencoder generative adversarial network (VAEGAN) model. This...