2 July 2024 in Computers and Electronics in Agriculture
22 August 2013 in Chemical Engineering & Technology
Chemical looping combustion (CLC) is a promising technology for CO2 capture, with inherent CO2 separation and low energy consumption. In this study, the reactive multiphase model is incorporated into a computational fluid dynamics code to simulate the reactive fluid dynamics in the CLC reactor with a two‐fluid model. The solid friction stress is used to account for the interaction of individual particles with their neighbors through sustained contact at high particle concentrations and the kinetic theory of granular flow is used for closure. Gas‐solid flow characteristics and chemical reactions in interconnected fluidized beds using a Cu‐based oxygen carrier are simulated. The distributions of solid concentration and gas composition are obtained. The predicted gas compositions at the outlet agree with experimental results. The effects of the operating velocity and the temperature on the combustion efficiencies are also shown. The results demonstrate that a higher bed temperature at a lower operating velocity could enhance the CLC performance.
3 July 2025 in IEEE Transactions on Neural Networks and Learning Systems
In the domain of deep learning for visual tasks, ensemble models combine several less accurate models to form a more precise composite model, improving overall performance. Traditionally, majority voting and average probabilities have been the main decision-making techniques in ensemble learning, focusing only on the TOP1 Class of base models, hence overlooking other significant information. This article introduces a new algorithm, TOP2 hybrid decision (TOP2 HD), which enhances the TOP1 accuracy of the ensemble model. TOP2 HD categorizes base models into hierarchies based on their TOP1 Class and uses the TOP2 Class for ranking, leading to better performance. Extensive experiments across various models and datasets demonstrate that TOP2 HD not only surpasses traditional ensemble methods, such as majority voting, average probabilities, and stacking, but also exceeds many of the latest ensemble strategies in the image domain. In addition, our experiments revealed a functional relationship between the test accuracy of the ensemble model and the number of base models. This enables us to predict the upper limit of the ensemble model’s performance using only a fraction of the models, providing a crucial reference for the performance after the deployment of the ensemble model.