首页> 外国专利> APPARATUS AND METHOD FOR PREDICTING THE PRODUCTION OF DISINFECTION BY-PRODUCT USING A ARTIFICIAL NEURAL NETWORK

APPARATUS AND METHOD FOR PREDICTING THE PRODUCTION OF DISINFECTION BY-PRODUCT USING A ARTIFICIAL NEURAL NETWORK

机译:使用人工神经网络预测消毒副产物产量的装置和方法

摘要

The invention of disinfection by-products produced using artificial neural network forecasting device and as a result of the method, an integer disinfection by-products in the processing system by selecting the optimal neural network model according to a nonlinear form, depending on the comparison result of the error and the threshold value for the predicted value and the actual value of (for example, trihaloalkyl such as methane) production of disinfection by-products result (for example, For example, generating density, to provide a readable recording medium amount, etc.) to estimate beforehand, the generation of disinfection by-products result using artificial neural network prediction apparatus and a program for realizing that method, and the method by recording computer . and ; To this end, the present invention is a data collection unit for collecting process water quality factors, and factors for disinfecting process; Receiving the process parameters and the quality factor, the artificial neural network model in a predetermined unit for applying at least one artificial neural network model having any one of a target in the artificial neural network model; And selecting an optimal neural network model based on the comparison result of the error and the threshold value set based on 'the actual value of the actual check disinfection by-products in the water treatment system' 'predicted values of disinfection by-products outputted through the neural network model, and After performing the feedback includes a feedback for the generation result of the prediction for disinfection by-products.
机译:使用人工神经网络预测装置产生的消毒副产物的发明,作为该方法的结果,根据比较结果,通过根据非线性形式选择最佳神经网络模型,在处理系统中获得整数消毒副产物产生的消毒副产物(例如,产生密度)的误差和阈值(例如,甲烷等三卤代烷基)的预测值和实际值(例如,产生密度),等)进行预先估算,然后使用人工神经网络预测设备,用于实现该方法的程序以及通过记录计算机的方法来估算消毒副产物的生成结果。和;为此,本发明是一种数据收集单元,用于收集过程水水质因子和消毒过程的因子。接收过程参数和品质因数,在预定单元中应用神经网络模型,以应用至少一个具有该神经网络模型中的任意一个目标的神经网络模型;并根据误差的比较结果和基于“水处理系统中实际检查消毒副产物的实际值”“通过输出的消毒副产物的预测值设置的阈值”选择最佳的神经网络模型。神经网络模型,并且在执行反馈之后包括对消毒副产物的预测的生成结果的反馈。

著录项

  • 公开/公告号KR101099703B1

    专利类型

  • 公开/公告日2011-12-28

    原文格式PDF

  • 申请/专利权人

    申请/专利号KR20090043561

  • 申请日2009-05-19

  • 分类号G01N33/18;G06N3/02;C02F1/00;

  • 国家 KR

  • 入库时间 2022-08-21 17:10:52

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

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