To achieve rapid and uniform mixing requirements for fluid agitation tanks in industrial processes, this study takes a fluid agitation tank used in wastewater treatment as the research object and conducts numerical simulation research on its internal flow field using the flow field analysis software Fluent. A three-dimensional geometric model of the agitation tank is established using SOLIDWORKS software. Meshing is performed in Fluent with local refinement applied to the blade region, and simulation analysis is carried out using Fluent software. The research results indicate that the density distribution of the mixture within the agitation tank gradually becomes uniform over time, reaching a dynamic equilibrium. The Fluent simulation method effectively overcomes the shortcomings of traditional theoretical calculations and physical experiments, offering advantages such as shorter cycles, lower costs, and higher safety, thus providing a reliable technical basis for the structural design and process optimization of agitation tanks.
Zhen Wei, Ning Liu, Peng Du et al.· Journal of Physics, Conferen...· 0 citations
Current mainstream deep learning techniques exhibit an over-reliance on extensive training data and a lack of adaptability to the dynamic world, marking a considerable disparity from human intelligence. To bridge this gap, Few-Shot Class-Incremental Learning(FSCIL) has emerged, focusing on continuous learning of new categories with limited samples without forgetting old knowledge. Existing FSCIL studies typically use a single model to learn knowledge across all sessions, inevitably leading to the stability–plasticity dilemma. Unlike machines that usually consolidate all categories into a single parameter space, cortical memory organization suggests that different types of knowledge can be distributed and organized across specialized cortical regions. Inspired by this organization principle, our paper aims to develop a method that learns independent models for each session. It can inherently prevent catastrophic forgetting. During the testing stage, our method integrates Uncertainty Quantification (UQ) for model deployment. Our method provides a fresh viewpoint for FSCIL and demonstrates the state-of-the-art performance on CIFAR-100 and mini-ImageNet datasets.
Renye Zhang, Yi Yin, Jinghua Zhang· Entropy· 0 citations