Establishment method for pipe network leakage prediction model based on EPR evolution polynomial regression

Abstract

The invention provides an establishment method for a pipe network leakage prediction model based on EPR evolution polynomial regression, and belongs to the field of an urban water supply network. The method comprises: processing original data of modeling, determining pipe diameters, pipe lengths, and pipe age as influence factors; then respectively modeling five kinds of pipes, grouping each kind of pipes according to pipe diameters, pipe lengths, average weighted pipe age, and leakage frequency per year, establishing a leakage prediction model with pipe diameter, pipe length, and pipe age as independent variables, and leakage frequency per year as a dependent variable, using fitting degree of a CoD determination model; using actual leakage data to verify the leakage prediction model, using predictive ability of a RMSE judging model; finally, summing the leakage frequency per year which is predicted according to the leakage prediction models respectively established for the five kinds of pipes, to obtain final leakage frequency total amount of the pipe network in a region. Through the establishment of the model and determination of the leakage number of the region, the pipes which have leakage risks can be found out as early as possible in daily management, so as to reduce probability of accidents and reduce economical loss.

Description

technical field [0001] The invention relates to a method for establishing a pipe network leakage prediction model based on EPR evolutionary polynomial regression, and belongs to the field of urban water supply pipe networks. Background technique [0002] The water supply network is the "lifeline" of the city, responsible for delivering fresh "blood" to the city, and is the prerequisite for ensuring the stable rotation of the city. The occurrence of water supply network leakage will bring huge social impact and economic loss. Therefore, it is of great significance to judge the high-risk pipelines with leakage in advance, predict the leakage status of the water supply network, and reduce the possibility of leakage. [0003] At present, there are two main types of models commonly used in water supply network leakage prediction: one is a physical research model based on laboratory experiments, and the other is a data analysis model based on computer simulation. The research on...

AI Technical Summary

Problems solved by technology

The research of the first type of model needs to have a clear understanding of the relationship between the various influencing factors that cause pipeline leakage, but the actual relationship between the various influencing factors is complex

The second type of model mainly includes two contents. One is a physical model based on the aging mechanism. The construction of this model requires time tracking of a specific research pipeline. It is difficult to obtain data and consumes a lot of time and effort; the other is based on historical leakage. Statistical model of data, the study of this model can obtain a clear mathematical relationship between the number of omissions and various influencing factors, which is a hot spot in current research

[0004] my country's urban water supply network has a large amount of basic data, and the records of leakage data are not perfect. There are many reasons for pipeline leakage and the relationship is complex and non-linear.

Existing high-precision models have the problem of lack of clear model formulas, while the accuracy of models with clear formulas needs to be improved, the formula structure needs to be simplified, and the efficiency of formula acquisition needs to be improved

At the same time, there is no clear theoretical method to evaluate the prediction effect after the model is established, and to correct the error effect

Images