首页> 外国专利> Al-based control system and method for treating sewage / wastewater using a neural network and a back-propagation algorithm

Al-based control system and method for treating sewage / wastewater using a neural network and a back-propagation algorithm

机译:基于神经网络和反向传播算法的基于Al的污水/废水控制系统和方法

摘要

An AI (artificial intelligence) control system for controlling automatically variable factors, such as DO (dissolved oxygen), SRT (solids retention time) and the like depending upon properties of the inflow water, the internal condition of the reaction tank and the target treated water quality, particularly the AI control system wherein a retention time is applied in consideration of each volume of the reaction tank and the sedimentation tank, and thereby, each SP (set point), such as each DO and SRT of the 1st story and the 2nd story of the exhalation tank, is obtained from the data collected by measuring automatically BOD (biological oxygen demand), an incoming stream flow and a water temperature, control automatically a control valve for controlling the supply air and a pump for drawing sludge by means of each PV (present value), and then a learning method, an algorithm for controlling the surplus sludge and the like are used by letting AI (corresponding to the neural network controller) learn through the use of the knowledge-base, setting a concentration of DO in response to any change in a temperature and a concentration and calculating an appropriate SRT. IMAGE
机译:AI(人工智能)控制系统,可根据流入水的性质,反应罐的内部条件和处理的目标自动控制可变因素,例如DO(溶解氧),SRT(固体保留时间)等水质,尤其是AI控制系统,其中考虑到反应池和沉淀池的每个容积,并因此考虑每个SP(设定点),例如第一级的每个DO和SRT,都要应用保留时间通过自动测量BOD(生物需氧量),进水流量和水温,从收集到的数据中获得呼气罐的第二层和第二层。通过每个PV(当前值)抽取污泥的泵,然后通过让AI(对应于神经网络co)使用学习方法,控制剩余污泥的算法等ntroller)通过使用知识库进行学习,根据温度和浓度的任何变化设置DO的浓度,并计算适当的SRT。 <图像>

著录项

  • 公开/公告号DK1376276T3

    专利类型

  • 公开/公告日2006-10-23

    原文格式PDF

  • 申请/专利权人 H2L CO. LTD;

    申请/专利号DK20020258239T

  • 发明设计人 YANG IK-BAE;

    申请日2002-11-29

  • 分类号C02F3/12;G05B13/02;C02F1;C02F3;C02F3/02;G06F17/17;G06N3;

  • 国家 DK

  • 入库时间 2022-08-21 21:39:44

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