CN-121977768-A - GIS intelligent positioning monitoring system of intelligent well lid for railway station rain and sewage

CN121977768ACN 121977768 ACN121977768 ACN 121977768ACN-121977768-A

Abstract

The invention relates to the technical field of pipe network monitoring, in particular to a GIS intelligent positioning monitoring system of a railway station rain and sewage intelligent well lid. The system is used for collecting flow data and pressure data corresponding to a pipeline, uploading the flow data and the pressure data to a management platform, determining a first significant coefficient according to the flow data, determining a second significant coefficient according to the pressure data, determining a comprehensive abnormal significant value based on the first significant coefficient and the second significant coefficient, determining a real-time first characteristic value according to the comprehensive abnormal significant value, determining a pipeline running state based on the real-time first characteristic value and a leakage fault threshold value, monitoring the pipeline running state in real time, and outputting position information, leakage alarm information and pipeline running state report of an intelligent well lid corresponding to a leakage pipeline under the condition that the pipeline running state is the leakage state. The GIS intelligent positioning and monitoring accuracy of the intelligent well lid of the railway station rain and sewage is improved.

Inventors

QI FAN
XIN SIYUAN
DING HAO
QIAO XIAODONG
WANG GUANGYUAN

Assignees

中国铁路设计集团有限公司

Dates

Publication Date: 20260505
Application Date: 20260409

Claims (10)

1. GIS intelligent positioning monitoring system of dirty wisdom well lid of railway website rain, its characterized in that, the system includes: the data acquisition module is used for acquiring flow data and pressure data corresponding to the pipeline and uploading the flow data and the pressure data to the management platform; the system comprises an operation state analysis module, a comprehensive abnormal significant value, a real-time first characteristic value, a pipeline operation state and a leakage fault threshold, wherein the operation state analysis module is used for determining a first significant coefficient according to flow data, a second significant coefficient according to pressure data, the comprehensive abnormal significant value is determined based on the first significant coefficient and the second significant coefficient, the real-time first characteristic value is determined according to the comprehensive abnormal significant value, the pipeline operation state is determined based on the real-time first characteristic value and the leakage fault threshold, the first significant coefficient is used for representing abnormal fluctuation and spatial distribution deviation degree of pipeline flow, the second significant coefficient is used for representing pulse mutation and high-frequency fluctuation abnormality degree of pipeline pressure, the comprehensive abnormal significant value is used for representing comprehensive abnormality degree of pipeline overall operation, and the leakage fault threshold is used for defining critical judgment standard of pipeline leakage; And the GIS intelligent monitoring module is used for monitoring the pipeline running state in real time and outputting the position information, the leakage alarm information and the pipeline running state report of the intelligent well lid corresponding to the leakage pipeline under the condition that the pipeline running state is the leakage state.
2. The intelligent positioning and monitoring system for a GIS of a smart well cover for a railway station according to claim 1, wherein the determining a first significant coefficient according to the flow data comprises: Determining a flow rate fluctuation abnormal value and a flow gradient deviation coefficient based on the flow data in a preset monitoring window; And determining a first significant coefficient according to the abnormal value of the flow rate fluctuation and the flow gradient deviation coefficient.
3. The intelligent positioning and monitoring system for a GIS of a railway station rain and sewage intelligent manhole cover according to claim 2, wherein the determining a flow rate fluctuation outlier and a flow gradient deviation coefficient based on the flow data comprises: curve fitting is carried out on the flow data in the preset monitoring window, normalization processing is carried out on slopes corresponding to points on a fitted curve, and flow rate fluctuation abnormal values are determined according to the normalized slopes; And determining a flow gradient deviation coefficient according to the flow average value corresponding to each monitoring position in the preset monitoring window, the absolute value of the flow average value difference between each monitoring position and the adjacent monitoring position and the variation coefficient, wherein the variation coefficient is used for representing the relative discrete degree of the flow average value of different monitoring positions.
4. The intelligent positioning and monitoring system for a GIS of a smart well cover for a railway station according to claim 1, wherein the determining a second significant coefficient from the pressure data comprises: determining pulse salient factors and high-frequency salient coefficients based on the pressure data within a preset monitoring window; and determining a second significant coefficient according to the pulse protrusion factor and the high-frequency significant coefficient.
5. The intelligent positioning and monitoring system for a GIS of a smart well cover for a railway station according to claim 4, wherein the determining the pulse protrusion factor and the high frequency saliency coefficient based on the pressure data comprises: determining a pulse salient factor according to the ratio of the maximum value of the pressure data to the square root amplitude of the pressure data in the preset monitoring window; Performing complementary set empirical mode decomposition on the pressure data to obtain at least two modal components, wherein the modal components comprise a high-frequency modal component and a medium-low frequency modal component; and determining a high-frequency significant coefficient according to the ratio of the energy sum of the high-frequency modal components to the energy sum of all modal components.
6. The GIS intelligent positioning monitoring system of a railway station rain and sewage intelligent manhole cover according to claim 1, wherein the determining an integrated anomaly significant value based on the first significant coefficient and the second significant coefficient comprises: normalizing the first significant coefficient and the second significant coefficient; And determining the comprehensive abnormal significant value according to the normalized first significant coefficient, the normalized second significant coefficient and the preset weight parameter.
7. The intelligent positioning and monitoring system for a GIS of a smart well cover for a railway station according to claim 1, wherein the determining the pipeline running state based on the real-time first characteristic value and the leakage fault threshold value comprises: Determining that the pipeline operating state is the leakage state under the condition that the real-time first characteristic value is greater than or equal to the leakage fault threshold value; And under the condition that the real-time first characteristic value is smaller than the leakage fault threshold value, determining that the pipeline running state is a normal state.
8. The intelligent positioning and monitoring system for a GIS of a smart well cover for a railway station according to claim 1, wherein the determining the real-time first characteristic value according to the comprehensive abnormal significant value comprises: Respectively calculating difference values of the comprehensive abnormal significant values corresponding to the preset monitoring windows and the comprehensive abnormal significant values corresponding to the previous preset number of adjacent history windows; All positive differences are summed to determine a real-time first characteristic value.
9. The GIS intelligent positioning monitoring system of a railway station rain and sewage intelligent manhole cover of claim 1, wherein the operational state analysis module is further configured to: Determining a first characteristic value corresponding to each history monitoring window based on flow data and pressure data in the history normal operation period; And determining the leakage fault threshold according to the mean value and the standard deviation of the first characteristic values corresponding to all the history monitoring windows.
10. The intelligent positioning and monitoring system for a GIS of a smart well lid for a railway station according to claim 1, wherein the operation state analysis module comprises: The first significant coefficient determining module is used for determining a flow rate fluctuation abnormal value and a flow gradient deviation coefficient based on the flow data in a preset monitoring window, and determining the first significant coefficient according to the flow rate fluctuation abnormal value and the flow gradient deviation coefficient.

Description

GIS intelligent positioning monitoring system of intelligent well lid for railway station rain and sewage Technical Field The invention relates to the technical field of pipe network monitoring, in particular to a GIS intelligent positioning monitoring system of a railway station rain and sewage intelligent well lid. Background The three-dimensional underground pipe network modeling and monitoring technology of the geographic information system (Geographic Information System, GIS) can help the city to manage underground pipe network facilities more efficiently, check the hidden trouble of facilities in time, avoid various accidents caused by pipeline breakage, ensure the living safety of residents, and is an important component in the construction of modern smart cities. The GIS model can integrate monitoring data acquired by the sensors of the Internet of things, realize real-time monitoring and intelligent early warning of running states such as pipeline pressure, flow, leakage and the like, and further help operation and maintenance personnel to quickly locate the rain and sewage well lid corresponding to the fault pipeline and carry out timely maintenance. However, the rain sewage pipeline is easy to leak in the long-term operation process, the problems are usually carried out by means of signal acquisition, the water flow working condition in the pipeline is complex, the impurity flows such as rain and sewage converging and sediments can generate strong noise interference, the extraction and identification of leakage abnormal signals are seriously influenced, meanwhile, the topological structure of the underground pipe network is intricate and complex, the operation working condition of the underground pipe network can also change in real time along with factors such as rainfall and pump station scheduling, and the like, and the existing GIS intelligent monitoring mode has the defects of low reliability of monitoring results and difficulty in realizing accurate and timely positioning of the leakage pipeline. That is, the intelligent well lid of the railway station rain and sewage in the prior art has lower accuracy in GIS intelligent positioning monitoring for the leakage of the rain and sewage pipeline. Disclosure of Invention The invention aims to provide a GIS intelligent positioning monitoring system for a railway station rain and sewage intelligent well lid, which is used for solving the technical problem of low accuracy of GIS intelligent positioning monitoring results in the prior art. In a first aspect, an embodiment of the present invention provides a GIS intelligent positioning and monitoring system for a smart manhole cover of a railway station, the system comprising: The data acquisition module is used for acquiring flow data and pressure data corresponding to the pipeline and uploading the flow data and the pressure data to the management platform; The system comprises an operation state analysis module, a comprehensive abnormal significant value, a real-time first characteristic value, a pipeline operation state and a leakage fault threshold, wherein the operation state analysis module is used for determining a first significant coefficient according to flow data, determining a second significant coefficient according to pressure data, determining a comprehensive abnormal significant value based on the first significant coefficient and the second significant coefficient, determining a real-time first characteristic value according to the comprehensive abnormal significant value and determining the pipeline operation state based on the real-time first characteristic value and the leakage fault threshold; And the GIS intelligent monitoring module is used for monitoring the pipeline running state in real time and outputting the position information, the leakage alarm information and the pipeline running state report of the intelligent well lid corresponding to the leakage pipeline under the condition that the pipeline running state is the leakage state. In some embodiments, determining the first significant coefficient from the traffic data includes: Determining a flow rate fluctuation abnormal value and a flow gradient deviation coefficient based on flow data in a preset monitoring window; and determining a first significant coefficient according to the abnormal flow rate fluctuation value and the flow gradient deviation coefficient. In some embodiments, determining a flow rate fluctuation anomaly value and a flow gradient deviation coefficient based on the flow data comprises: curve fitting is carried out on flow data in a preset monitoring window, normalization processing is carried out on slopes corresponding to each point on a fitted curve, and a flow rate fluctuation abnormal value is determined according to the normalized slopes; and determining a flow gradient deviation coefficient according to the flow average value corresponding to each monitoring position in the preset monitoring