Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Intelligent control method for adjustable weir of multi-target complex drainage system based on machine learning

A drainage system and machine learning technology, applied in the field of municipal engineering, can solve the problems that the drainage capacity of the shallow system cannot be fully utilized, the inflow weir cannot participate in peak shaving in time, and the municipal pump cannot be fully started, etc., to achieve easy real-time collection, Improve the overall operation level and judge the effect of good effect

Pending Publication Date: 2021-11-12
SHANGHAI MUNICIPAL ENG DESIGN INST GRP
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

According to the model calculation, if the weir drop time is too early, the regulation and storage system may be filled and closed prematurely, and cannot continue to participate in peak shaving, resulting in water accumulation in the system
In addition, the discharge of water in the shallow pipe network into the regulation and storage system before the runoff peak may cause the municipal pumps to fail to fully start, and the drainage capacity of the shallow system cannot be fully utilized. Unable to participate in peak shaving in time
Since the drainage capacity of the municipal pump is not enough to cope with the rain peak, if the shallow pipe network is full at this time and the inflow weir is not lowered in time, the flow through the weir will be insufficient, which will lead to water accumulation in the system

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent control method for adjustable weir of multi-target complex drainage system based on machine learning
  • Intelligent control method for adjustable weir of multi-target complex drainage system based on machine learning
  • Intelligent control method for adjustable weir of multi-target complex drainage system based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0111] In this embodiment, a certain drainage system is taken as an example. The water level value and flow value of the adjustable weir position pipeline of the drainage system, the water level of the forebay of the pumping station in the drainage system, and the product of the most unfavorable point in the area are collected through liquid level meters, flow meters, and cameras. For water conditions, the following variables are selected as the sample matrix (the last data is assumed to be unknown), the operation category is 1, indicating that under the same row of monitoring data, weir operation should be carried out, and the operation category is 0, indicating that under the same row of monitoring data, Weir operations should not be performed.

[0112] Table 1: Truth table of drainage system inflow point flow and weir operation

[0113]

[0114] Since the dimension and order of magnitude of the variables are inconsistent, some are water level and some are flow, the data ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides an intelligent control method for an adjustable weir of a multi-target complex drainage system based on machine learning. The invention relates to a discriminant state element of a control object, a mahalanobis distance of a total and a sample, a prior probability and a posterior probability function structure, and takes a misjudgment rate as an output feedback solver. On the basis of machine learning discriminant analysis calculation, sensitive data of key state factors such as the initial water level of a pipeline, the water level flow of key points, the water level of a forebay of a pump station and the water level of the most unfavorable point are selected, and auxiliary decision making is carried out on key steps of drainage system control through four machine learning discriminant methods including a Bayesian method, linear discrimination, linear diagonal and quadratic discrimination. According to the method, required external data are simple and easy to collect in real time, training samples can be continuously expanded and accumulated, and the closer the training samples are to the whole, the better the judgment effect is. An effective method is provided for improving the intelligent control level of the adjustable weir of the complex drainage system, and the overall operation level of the complex drainage system can be improved.

Description

technical field [0001] The invention belongs to the field of municipal engineering and relates to a control method for a drainage system, in particular to an intelligent control method for an adjustable weir based on a multi-objective complex drainage system. Background technique [0002] In recent years, urban waterlogging prevention and treatment of black and odorous rivers have increasingly become the focus of social attention. The corresponding drainage system upgrades and the construction of river runoff pollution control projects have continued to speed up. Engineering design related to pollution control. The operation control of the drainage system after the transformation is more complicated, and generally involves multiple goals. The first is the flood control goal, which mainly aims to improve the safety of the drainage system, achieve standard improvement and waterlogging prevention; the second is the pollution control goal, mainly to reduce initial rainwater poll...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/27G06N20/00G06F17/16G06F17/18G06F111/08
CPCG06F30/27G06N20/00G06F17/16G06F17/18G06F2111/08
Inventor 李鹏程张辰曹晶徐文征周娟娟汉京超唐文
Owner SHANGHAI MUNICIPAL ENG DESIGN INST GRP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products