期刊
CHEMOSPHERE
卷 303, 期 -, 页码 -出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.chemosphere.2022.134929
关键词
Nanoparticles; Genetic algorithm; Artificial neural network; Diffusion limitation; Immobilization; Magnetite
The presence of urea in runoff from fertilized soil could contribute to the growth of dangerous blooms. Integrating enzymatic urea hydrolysis with nanotechnology can significantly reduce diffusion barriers. A model developed using a Genetic Algorithm and an Artificial Neural Network showed that the system's diffusion restrictions were reduced. Additionally, a neural network with one hidden layer and 20 neurons demonstrated the highest output and least mean square error.
The presence of urea in runoff from fertilized soil could be contributing to the growth of dangerous blooms. Enzymatic urea hydrolysis is a well-known outstanding process that, when integrated with nanotechnology, would be much more efficient. This research provides a novel perspective on magnetic nanobiocatalysts that reduce diffusion barriers in effective urea hydrolysis. Surprisingly, the model developed with the use of a Genetic Algorithm (GA) and an Artificial Neural Network (ANN) demonstrated that the system's diffusion restrictions were reduced. In order to forecast accurate outputs using artificial intelligence (AI), a neural network with one hidden layer and 20 neurons was built utilizing multilayer feed-forward network and showed highest output (diffusion co-efficient) with least mean square error (MSE). The diffusion coefficients of free urease, urease immobilized onto porous MNs (U-aMNs), and nanobiocatalyst, i.e. urease immobilized onto surface modified MNs (U-MN beta), were 1.9 x 10(-17), 12.62 x 10(-16), and 15.48 x 10(-16) cm(2)/min, respectively. These results revealed that the addition of Chitosan to the surface of MNs had a considerable impact on enzyme dispersion. The decrease in Damkohler number (Da) from 2.37 +/- 0.26 for U-aMNs to 2.19 +/- 0.11 for U-MN beta suggested a beneficial effect in overcoming diffusion constraints. Pseudo-first order and pseudo-second order models were
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据