Small leakage detection method based on exponential weighted moving average algorithm

Abstract

The invention discloses a small leakage detection method based on an exponential weighted moving average algorithm, which comprises the following steps of: collecting flow data of a water consumptionstable period, estimating a reference water consumption range of the water consumption stable period through frequency statistics, and verifying the reasonability of the estimated reference water consumption range through setting confidence coefficient, eliminating interference of large low-value fluctuation of flow data according to the reference water consumption range, and finally detecting small leakage in the DMA pipe network through an EWMA algorithm. The flow change trend is analyzed through the EWMA algorithm, the discovery time of small leakage events is greatly shortened, a manager can make a quick response and guide leakage detection personnel to optimize the priority of leakage detection, targeted and important leakage detection is achieved, and the method has high applicationand economic value and is suitable for popularization and application. The method can be used as an effective auxiliary means for implementing DMA pipe network active leakage control.

Description

technical field [0001] The invention relates to a water supply pipe network leakage detection method, in particular to a small leakage detection method based on an exponentially weighted moving average algorithm. Background technique [0002] Pipe network leakage is a common problem in urban water supply systems at home and abroad, which will bring adverse effects on economy, environment and other aspects. On the one hand, the loss of water resources will not only lead to a greater loss of economic benefits for water supply companies, but also cause waste of energy and water resources, which is inconsistent with the current concept of sustainable development advocated by the country. Therefore, reducing the leakage rate of the pipe network is of great significance for improving the utilization efficiency of urban water resources and maintaining the sustainability of the economy. [0003] The methods of pipeline network leakage detection can be divided into two categories: m...

AI Technical Summary

Problems solved by technology

However, most of the existing methods based on software analysis focus on the detection of larger leaks (the loss of water is greater than or equal to 5% of the average flow in the same time period), and for small leaks (the loss of water is less than 5% of the average flow in the same time period). %) is poorly detected

Images