Leakage Recognition Method Based on Long Short-term Memory Neural Network Model

Abstract

The disclosure provides a pipeline network leakage identification method based on a long-short-term memory neural network model, including the following steps: S1, obtaining DMA entry data; S2, cleaning the obtained DMA entry data, and constructing a multi-scale time Data set; S3, establishing a long-short-term memory neural network model; S4, identifying abnormal traffic points based on the constructed multi-scale time data set and the established long-short-term memory neural network model; S5, based on the identified abnormal traffic points Identify leaks in the pipeline network. The leakage identification method of the disclosed pipeline network reduces the false alarm rate of accidents and increases the accuracy of leakage identification.

Description

technical field [0001] The present disclosure relates to the field of neural networks, in particular to a leakage identification method based on a long-short-term memory neural network model. Background technique [0002] In recent years, sudden and high-uncertainty water supply network leakage accidents have occurred frequently, which has attracted widespread attention from the society. Leakage accidents will not only cause waste of water energy and economic losses, but also cause serious water pollution in the pipeline network. , endangering public health. However, because the water supply pipeline network is buried deep underground, the system is huge, and there are many environmental interference factors, the status of the pipeline network is not easy to monitor, which greatly increases the difficulty of pipeline network leakage detection. [0003] In recent years, the global water supply industry has vigorously promoted and practiced the District Metering Area (DMA) to...

AI Technical Summary

Problems solved by technology

[0005] The traditional model can successfully identify some leakage accidents with large flows, but under the background of the increasing frequency of online monitoring of the pipeline network, more intensive data collection, and uneven data quality, it cannot process a large amount of flow data quickly and with high precision , low fault tolerance

Application No. 201410507513.1 proposes a water pipe leakage detection method based on wavelet singularity analysis and ARMA model, and judges whether there is a slow leakage phenomenon of water pipe leakage through two-step prediction data analysis, successfully solving the problem of slow leakage judgment, but the two-stage prediction of this method is too It is cumbersome, and the single-point alarm cannot continuously judge the leakage of the pipe network, and there are problems such as high false alarm rate

Application number 201710998436.8 obtains the predicted water volume through the prediction of the neural network model of the gated cyclic unit, and compares the threshold value with the measured water volume through the method of cosine angle to realize the identification of pipe network leakage; but these methods do not consider the correction of water volume feedback and input, it is impossible to continuously identify pipe network bursts in real time, and a single threshold alarm will cause a large misjudgment, causing unnecessary manpower and material resources loss for the water supply company, and the reliability of the method is low in actual operation

Images