Scholarlink

<p>Hospital wastewater contains a complex mixture of pollutants, including biological, chemical, and pharmaceutical contaminants, which necessitates effective treatment strategies. This study investigates the efficiency of electrocoagulation for treating hospital wastewater while employing predictive modeling techniques, including feedforward neural networks (FFNN), neural Wiener (NW), neural Hammerstein (NH), and neural Hammerstein–Wiener (NHW) models. The electrocoagulation process was conducted using aluminum and carbon electrodes, with varying voltage levels (5&#xa0;V, 10&#xa0;V, and 15&#xa0;V) and treatment durations (30, 60, 90, and 120&#xa0;min). Key water quality parameters, including turbidity, biochemical oxygen demand (BOD), chemical oxygen demand (COD), <i>Escherichia coli</i>, and coliform bacteria, were analyzed before and after treatment. Results demonstrated that increasing voltage and contact time significantly enhanced pollutant removal, with the highest removal efficiencies observed at 15&#xa0;V and 120&#xa0;min. Electrocoagulation effectively reduced turbidity, BOD, and COD levels while achieving substantial microbial inactivation. The predictive models successfully captured electrocoagulation dynamics, with the neural Hammerstein–Wiener model exhibiting the highest accuracy (root mean square error [RMSE]: 0.0399, weighted mean absolute percentage error [WMAPE]: 0.0665). These findings suggest that electrocoagulation, coupled with advanced modeling techniques, provides a sustainable and efficient hospital wastewater treatment approach. Future research should focus on optimizing operational parameters, integrating hybrid treatment methods, and developing real-time monitoring systems to enhance treatment efficiency and cost-effectiveness.</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

Electrocoagulation for Hospital Wastewater Treatment: Comparing Neural Network Models for Performance Simulation

  • 期刊论文

  • 发表日期：

    2025年5月23日

查看全文
  • Dewi Indira,
  • Fitri Muzayyanah,
  • Rifky Fauzi,
  • Wasinton Simanjuntak,
  • Yandri Yandri,
  • Fakhrony Sholahudin Rohman,
  • Sudibyo Sudibyo,
  • Benadict Rakesh,
  • Anis Tatik Maryani,
  • Yudha Gusti Wibowo

摘要

Hospital wastewater contains a complex mixture of pollutants, including biological, chemical, and pharmaceutical contaminants, which necessitates effective treatment strategies. This study investigates the efficiency of electrocoagulation for treating hospital wastewater while employing predictive modeling techniques, including feedforward neural networks (FFNN), neural Wiener (NW), neural Hammerstein (NH), and neural Hammerstein–Wiener (NHW) models. The electrocoagulation process was conducted using aluminum and carbon electrodes, with varying voltage levels (5 V, 10 V, and 15 V) and treatment durations (30, 60, 90, and 120 min). Key water quality parameters, including turbidity, biochemical oxygen demand (BOD), chemical oxygen demand (COD), Escherichia coli, and coliform bacteria, were analyzed before and after treatment. Results demonstrated that increasing voltage and contact time significantly enhanced pollutant removal, with the highest removal efficiencies observed at 15 V and 120 min. Electrocoagulation effectively reduced turbidity, BOD, and COD levels while achieving substantial microbial inactivation. The predictive models successfully captured electrocoagulation dynamics, with the neural Hammerstein–Wiener model exhibiting the highest accuracy (root mean square error [RMSE]: 0.0399, weighted mean absolute percentage error [WMAPE]: 0.0665). These findings suggest that electrocoagulation, coupled with advanced modeling techniques, provides a sustainable and efficient hospital wastewater treatment approach. Future research should focus on optimizing operational parameters, integrating hybrid treatment methods, and developing real-time monitoring systems to enhance treatment efficiency and cost-effectiveness.