Pipe network water flow prediction method and device and computer readable storage medium

Abstract

The invention discloses a pipe network water flow prediction method and device and a computer readable storage medium. The method comprises the steps: obtaining a sample, training the sample based ona clustering algorithm, and obtaining a final total clustering number and a data set corresponding to each category; inputting the data set corresponding to each category into k long-term and short-term memory network models for training to obtain k types of trained long-term and short-term memory network models for training, wherein k is equal to the final total number of clusters; inputting eachpiece of pipeline data into the trained clustering algorithm through each piece of pipeline data collected in real time; after the category of each pipeline is determined, inputting the category intothe trained long-term and short-term memory network model corresponding to the category to calculate so as to obtain the short-term water flow of each pipeline; and accumulating the short-term waterflow of each pipeline to obtain the total water flow of the pipe network. According to the invention, the problem that a single long-term and short-term memory network model is insufficient in prediction precision in different environments is solved.

Description

technical field [0001] The invention relates to the technical field of pipe network monitoring, in particular to a method, device and computer-readable storage medium for predicting water flow in a pipe network. Background technique [0002] Studying the short-term water flow prediction method of large-scale pipeline networks can enable water companies to better grasp the water flow laws of large-scale pipeline networks, and monitor in advance whether there are pipeline ruptures and water leakage in the pipeline network, and then send personnel to check in advance to prevent serious accidents. A water failure occurs. [0003] At present, the more common method is water flow prediction based on LSTM algorithm. The principle of this method is relatively simple. However, there are great differences in using the same LSTM model in different environments. Using a single LSTM model in the case of environmental changes will lead to The accuracy of the prediction results of the pip...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above problems, an embodiment of the present invention provides a method, device, and computer-readable storage medium for predicting water flow in a pipe network, which can solve the problem of inaccurate prediction results of water flow in a pipe network in the prior art

Images