Scholarlink

<p>In the process of sterilization and disinfection, chemical reagents will react with natural organic matter and inorganic matter in water, and inevitably generate disinfection byproducts. These harmful substances are carcinogenic, teratogenic and mutagenic, and their content is low and difficult to detect. Therefore, in this study, we prepare Fe/CoFe-LDH electrodes by in-situ co-precipitation method, and their special structures and morphologies are used to achieve efficient removal of disinfection byproducts. On this basis, the prediction model of trichloroacetamide removal rate is constructed by using the backpropagation neural network, and the prediction model is used to predict the trichloroacetamide removal rate under different experimental parameters and the experiment is verified. The optimal process conditions are obtained, and the maximum trichloroacetamide removal rate is up to 81.62%. The feasibility of the data analysis and processing method based on machine learning in the prediction of disinfection by-products in drinking water is effectively proved.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Electrocatalytic degradation of trichloroacetamide by Fe/CoFe-LDH electrodes and its optimization via BPNN model

  • 期刊论文

  • 发表日期：

    2025年1月3日

查看全文
  • Zhuwu Jiang,
  • Zhehan Tu,
  • Dongdong Xu,
  • Jinfeng Chen,
  • Jiahan Yang,
  • Fengying Zhang,
  • Weixin Lin,
  • Xue Bai,
  • Hongyu Zhang

摘要

In the process of sterilization and disinfection, chemical reagents will react with natural organic matter and inorganic matter in water, and inevitably generate disinfection byproducts. These harmful substances are carcinogenic, teratogenic and mutagenic, and their content is low and difficult to detect. Therefore, in this study, we prepare Fe/CoFe-LDH electrodes by in-situ co-precipitation method, and their special structures and morphologies are used to achieve efficient removal of disinfection byproducts. On this basis, the prediction model of trichloroacetamide removal rate is constructed by using the backpropagation neural network, and the prediction model is used to predict the trichloroacetamide removal rate under different experimental parameters and the experiment is verified. The optimal process conditions are obtained, and the maximum trichloroacetamide removal rate is up to 81.62%. The feasibility of the data analysis and processing method based on machine learning in the prediction of disinfection by-products in drinking water is effectively proved.