Unlock instant, AI-driven research and patent intelligence for your innovation.

Water supply network leakage positioning method based on deep neural network model

A deep neural network and water supply network technology, applied in the field of water supply network leakage monitoring, can solve the problems of high cost and difficult data processing, and achieve the effect of improving accuracy, strong theoretical and practical significance

Pending Publication Date: 2021-04-06
HEFEI UNIV
View PDF7 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] If each node in the water supply network system is monitored, the cost is too high and the monitored data is not easy to process

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
  • Water supply network leakage positioning method based on deep neural network model
  • Water supply network leakage positioning method based on deep neural network model
  • Water supply network leakage positioning method based on deep neural network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0036] like figure 1 As shown, a water supply network leakage location method based on a deep neural network model includes the following steps:

[0037] S1. Use the EPANET pipe network adjustment software to construct the topological structure diagram of the water supply network to be tested and perform hydraulic simulations under normal conditions to obtain all nodes in the water supply network to be tested in each water use period (peak period, low peak period, general average) Period) the pressure value under the normal state, the present embodiment selects the pressure value as the measuring standard, which is the same as the experimental result of selecting the flow value.

[0038] EPANET pipe network adjustment software is a program developed by the US Environmental Protection Agency-National Risk Management Research Laboratory to ana...

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 a water supply network leakage positioning method based on a deep neural network model. The water supply network leakage positioning method based on the deep neural network model comprises the steps of obtaining pressure values or flow values of all nodes of a water supply network to be measured in normal states of all water use periods through computer pipe network adjustment software; selecting monitoring points by using a fuzzy C-mean clustering fusion algorithm; determining the distance between a simulated leakage point and each monitoring point by using the computer pipe network adjustment software, and obtaining the pressure value or flow value of each monitoring point in the simulated leakage state of each water consumption period; calculating to obtain the pressure or flow change rate of each monitoring point in the simulated leakage state of each water consumption period; constructing a deep neural network model, and training the constructed deep neural network model; and using the trained deep neural network model to locate the leakage point in the water supply network to be measured. According to the water supply network leakage positioning method based on the deep neural network model provided by the invention, accurate positioning of the leakage point can be realized by observing pressure or flow change of the limited monitoring points, and the method has high theoretical and practical significance.

Description

technical field [0001] The invention relates to the technical field of water supply pipe network leakage monitoring, in particular to a water supply pipe network leakage location method based on a deep neural network model. Background technique [0002] In the production and life of contemporary society, the water supply network is one of the important infrastructures of urban construction, and plays a pivotal role in ensuring sustainable economic development and normal life of residents. Because the city's water supply pipe network is buried below the surface, the leakage failure that occurs is hidden. Therefore, it is particularly important to fully grasp the operation status of the water supply network system. [0003] The leakage of the pipeline network is not necessarily caused by a single reason, but may be caused by the joint action of various reasons (pipe quality problems, interface problems, construction problems, pipeline corrosion and external force damage). Th...

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): F17D5/02F17D5/06
CPCF17D5/02F17D5/06
Inventor 吴晓璇王晓峰陈圣兵张琛
Owner HEFEI UNIV