首页> 中文期刊> 《工程(英文)》 >基于可控参数的前馈神经网络出水总氮预测模型研究

基于可控参数的前馈神经网络出水总氮预测模型研究

         

摘要

当前,出水总氮(TN)稳定达标是我国城镇污水处理厂面临的关键问题.本文基于我国城镇污水处理厂主流工艺——序批式活性污泥工艺(SBR),构建了一种基于可控参数的前馈神经网络(FFNN)出水总氮预测模型.与已有预测模型相比,本模型具备以下两个特点:①采用可控参数(表面气速与缺氧段时长)代替溶解氧作为模型主要输入参数,明显提高模型可用可控性;②采用算法优化的前馈神经网络构建模型,显著提高模型预测精准度.研究结果表明:量化共轭梯度法优化的FFNN模型预测精准,其拟合相关系数(R)明显高于其他相关模型;优化后的FFNN模型可根据进水与关键控制参数实现出水TN精准预测,有望实现城镇污水处理厂总氮稳定去除、系统节能降耗,助力国家"3060"碳目标实现.

著录项

  • 来源
    《工程(英文)》 |2021年第002期|195-202中插71-中插78|共16页
  • 作者单位

    Institution of Environment Pollution Control and Treatment Department of Environmental Engineering Zhejiang University Hangzhou 310058 China;

    Institution of Environment Pollution Control and Treatment Department of Environmental Engineering Zhejiang University Hangzhou 310058 China;

    Institution of Environment Pollution Control and Treatment Department of Environmental Engineering Zhejiang University Hangzhou 310058 China;

    Institution of Environment Pollution Control and Treatment Department of Environmental Engineering Zhejiang University Hangzhou 310058 China;

    Institution of Environment Pollution Control and Treatment Department of Environmental Engineering Zhejiang University Hangzhou 310058 China;

    Haining Water Investment Group Co. Ltd Haining 314400 China;

    Haining Capital Water Co. Ltd Haining 31440 China;

    Institution of Environment Pollution Control and Treatment Department of Environmental Engineering Zhejiang University Hangzhou 310058 China;

    Zhejiang Province Key Laboratory for Water Pollution Control and Environmental Safety Hangzhou 310058 China;

    Zhejiang Provincial Engineering Laboratory of Water Pollution Control Hangzhou 310058 China;

  • 原文格式 PDF
  • 正文语种 chi
  • 中图分类
  • 关键词

    前馈神经网络(FFNN); 算法; 可控参数; 序批式活性污泥工艺; 总氮;

    机译:前馈神经网络(FFNN);算法;可控参数;序批式活性污泥工艺;总氮;
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号