Gis-based digital pipe network control system

Abstract

The application relates to a GIS-based digital pipe network control system, which comprises a collection module, a data analysis module, a defect detection module, a prediction module and a terminal module. The collection module comprises sensor units arranged in nodes of the pipe network, and the sensor units are used for collecting monitoring data of the nodes of the pipe network. The data analysis module is used for importing the monitoring data of the nodes into a GIS server to obtain a pipe network distribution map of the nodes, inputting the monitoring data of the nodes into an abnormality prediction model to obtain load abnormal nodes, and highlighting the load abnormal nodes in the pipe network distribution map. The defect detection module detects the load abnormal nodes to obtain defect detection data. The prediction module is used for inputting the monitoring data of the load abnormal nodes and the defect detection data of the load abnormal nodes into a risk prediction model to obtain risk values of the load abnormal nodes and highlight the risk values in the pipe network distribution map, and the existing risks of the pipe network are analyzed and early warned, so that the control precision is improved.

Description

Technical Field

[0001] This invention relates to the field of digital pipeline networks, and in particular to a GIS-based digital pipeline network control system. Background Technology

[0002] Urban pipeline networks are a crucial component of urban infrastructure, responsible for transmitting information, energy, and other media. They are the material foundation upon which cities survive and develop, often referred to as the "lifeline" of a city. Currently, pipeline networks are typically controlled through experience-based judgment and simple reasoning calculations, lacking effective management and scientific evaluation of pipeline data. Each functional component within the network operates independently, resulting in a lack of effective coordination throughout the entire process. Summary of the Invention

[0003] To achieve the above objectives, the present invention adopts the following technical solution:

[0004] This invention provides a GIS-based digital pipeline network control system, comprising a data acquisition module, a data analysis module, a defect detection module, a prediction module, and a terminal module. The data acquisition module includes sensor units installed at each node of the pipeline network, which collect monitoring data from each node. The data analysis module imports the monitoring data from each node into a GIS server to obtain a pipeline network distribution map, and inputs the monitoring data from each node into an anomaly prediction model to identify load anomaly nodes, highlighting these nodes on the pipeline network distribution map. The defect detection module detects load anomaly nodes to obtain defect detection data. The prediction module inputs the monitoring data and defect detection data of the load anomaly nodes into a risk prediction model to obtain a risk value for the load anomaly nodes, which is then highlighted on the pipeline network distribution map. The terminal module displays the pipeline network distribution map and issues an alarm based on the risk value.

[0005] In a preferred embodiment, the sensor unit includes a flow meter, a level gauge, a combustible gas monitor, or a rainfall monitor.

[0006] In a preferred embodiment, the defect detection module includes a camera, a sonar detector, or a periscope detector, used to detect functional or structural defects within abnormal nodes.

[0007] As a preferred implementation, the monitoring data of each node is input into the anomaly prediction model to obtain load anomaly nodes, including: performing dimensionality reduction analysis on the monitoring data of each node and determining the correlation factors of each monitoring data; inputting the monitoring data and correlation factors of each node into the anomaly prediction model to obtain the correlation index of the correlation factors with the load; if the correlation index is greater than or equal to a preset index, it is confirmed as a load anomaly node, otherwise it is not a load anomaly node.

[0008] As a preferred embodiment, the anomaly prediction model is obtained by: acquiring historical monitoring data of nodes under normal conditions and historical monitoring data of nodes when pipeline network failure occurs, extracting feature factors from the historical monitoring data, generating an anomaly index based on the feature factors, and associating the anomaly index with the historical monitoring data to generate an anomaly prediction model.

[0009] In a preferred embodiment, the defect detection module detects load anomaly nodes to obtain defect detection data, including: acquiring historical data of normal nodes and historical data of load anomaly nodes, and extracting features from the historical data to obtain a feature map including the historical data; classifying the feature map using a defect detection model to obtain the classification result and classification loss value of the historical data; optimizing the parameters of the object defect detection model to obtain a trained defect detection model; and inputting the detection data of load anomaly nodes into the trained defect detection model to obtain defect detection data.

[0010] As a preferred implementation, the risk prediction model is obtained by: obtaining historical monitoring data and historical defect detection data of load anomaly nodes, generating a fusion map based on the number, location, and size of pipeline defects, labeling the fusion map, and generating a sample dataset; generating an initial risk prediction model based on a neural network, and training the initial risk prediction model based on the sample dataset to determine the model parameters; and generating a risk prediction model based on the model parameters and the initial defect diagnosis model.

[0011] In a preferred embodiment, the prediction module is used to input monitoring data and defect detection data of load anomaly nodes into a risk prediction model to obtain the risk value of the load anomaly node, including: obtaining the predicted value of the pipeline fault according to the risk prediction model, determining the weight corresponding to the pipeline fault using the entropy method; and obtaining the risk value of the load anomaly node according to the predicted value of the pipeline fault and the weight corresponding to the pipeline fault.

[0012] In a preferred embodiment, the terminal module triggers an alarm based on the risk value, including: determining the risk level based on the risk value, and determining the alarm level based on the risk level.

[0013] As a preferred implementation, the geographical coordinates of each node and the monitoring data of each node are imported into the GIS server to obtain the pipeline distribution map of each node. Then, the risk values ​​of nodes with abnormal loads are superimposed and highlighted on the pipeline distribution map.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0015] This invention collects monitoring data from various nodes in a pipeline network using sensor units. A data analysis module imports this data into a GIS server to obtain a network distribution map. The monitoring data is then input into an anomaly prediction model to identify nodes with abnormal loads. A defect detection module then detects these nodes to obtain defect detection data. The prediction module inputs both the monitoring data and the defect detection data into a risk prediction model to determine the risk value of each node. This integration of sensor unit and defect detection methods allows for the analysis and early warning of potential risks in the pipeline network, significantly improving control accuracy. Multi-point monitoring assists in pipeline network operation and maintenance, enabling the development of operation and maintenance plans, scheduling control, and inspection and maintenance. Online monitoring data is used to analyze pipeline network risks and safety hazards, providing a basis for upgrades. Liquid level and flow monitoring is implemented at historical waterlogging points and flood-prone areas, providing real-time early warnings and alarms. This improves pipeline network operational safety and reduces flood control and drainage costs. It also verifies whether existing drainage facilities meet construction standards. Pipeline inspection, emergency repair and maintenance, pipeline monitoring, liquid level monitoring, water quality monitoring, zoned metering, pipeline scheduling, source tracing analysis, and rainwater pipeline network. Attached Figure Description

[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a flowchart of the GIS-based digital pipeline control method of the present invention. Detailed Implementation

[0018] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0020] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0021] This invention provides a GIS-based digital pipeline network control system, including a data acquisition module, a data analysis module, a defect detection module, a prediction module, and a terminal module. The data acquisition module includes sensor units installed at each node of the pipeline network, which are used to collect monitoring data from each node. The data analysis module imports the monitoring data from each node into a GIS server to obtain a pipeline network distribution map of each node, and inputs the monitoring data from each node into an anomaly prediction model to obtain load anomaly nodes, which are then highlighted on the pipeline network distribution map. The defect detection module detects load anomaly nodes to obtain defect detection data. The prediction module inputs the monitoring data and defect detection data of load anomaly nodes into a risk prediction model to obtain a risk value for the load anomaly nodes, which is then highlighted on the pipeline network distribution map. The terminal module displays the pipeline network distribution map and issues an alarm based on the risk value.

[0022] This invention collects monitoring data from various nodes in a pipeline network using sensor units. A data analysis module imports this data into a GIS server to obtain a network distribution map. The monitoring data is then input into an anomaly prediction model to identify nodes with abnormal loads. A defect detection module then detects these nodes to obtain defect detection data. The prediction module inputs both the monitoring data and the defect detection data into a risk prediction model to determine the risk value of each node. This integration of sensor unit and defect detection methods allows for the analysis and early warning of potential risks in the pipeline network, significantly improving control accuracy. Multi-point monitoring assists in pipeline network operation and maintenance, enabling the development of operation and maintenance plans, scheduling control, and inspection and maintenance. Online monitoring data is used to analyze pipeline network risks and safety hazards, providing a basis for upgrades. Liquid level and flow monitoring is implemented at historical waterlogging points and flood-prone areas, providing real-time early warnings and alarms. This improves pipeline network operational safety and reduces flood control and drainage costs. It also verifies whether existing drainage facilities meet construction standards. Pipeline inspection, emergency repair and maintenance, pipeline monitoring, liquid level monitoring, water quality monitoring, zoned metering, pipeline scheduling, source tracing analysis, and rainwater pipeline network.

[0023] Geographic Information System (GIS) is a comprehensive technical system for collecting, storing, managing, analyzing, and displaying information about geographic phenomena. It is characterized by spatial distribution, large data volume, diverse information carriers, and temporal sequence. Its data types are vector data and grid data, and its basic data elements include geographic coordinates, planar coordinates, and vertical coordinates.

[0024] The sensor unit includes a flow meter, a level gauge, a combustible gas detector, or a rainfall monitor. The defect detection module includes a camera, a sonar detector, or a periscope detector, used to detect functional or structural defects within abnormal nodes.

[0025] Submersible level gauges or flow meters mounted on L-shaped brackets can be used during installation. Determine the type, location, and quantity of pipeline defects. Structural defects include disconnections, ruptures, errors, and foreign object intrusion; functional defects include sludge or mud deposits within the pipeline.

[0026] In a preferred embodiment, monitoring data from each node is input into an anomaly prediction model to obtain load anomaly nodes. This includes: performing dimensionality reduction analysis on the monitoring data of each node and determining the correlation factors for each monitoring data point; inputting the monitoring data and correlation factors of each node into the anomaly prediction model to obtain the correlation index of the correlation factors with the load; if the correlation index is greater than or equal to a preset index, the node is confirmed as a load anomaly node; otherwise, it is not a load anomaly node. The anomaly prediction model is obtained by: acquiring historical monitoring data of nodes under normal conditions and historical monitoring data of nodes when pipeline network failures occur, extracting feature factors from the historical monitoring data, generating an anomaly index based on the feature factors, and correlating the anomaly index with the historical monitoring data to generate the anomaly prediction model.

[0027] Among them, load anomaly nodes can be nodes in the pipeline network with abnormal data such as flow rate, and can be set based on empirical values. The anomaly prediction model can be trained using a BP neural network model.

[0028] The defect detection module detects nodes with abnormal loads to obtain defect detection data, including: acquiring historical data of normal nodes and historical data of nodes with abnormal loads, and extracting features from the historical data to obtain a feature map including the historical data; classifying the feature map using a defect detection model to obtain the classification result and classification loss value of the historical data; optimizing the parameters of the object defect detection model to obtain a trained defect detection model; and inputting the detection data of nodes with abnormal loads into the trained defect detection model to obtain defect detection data. Defects mainly include structural defects and functional defects. Structural defects include disconnection, rupture, error, and foreign object intrusion, while functional defects include sludge or mud deposition in the pipeline.

[0029] This method allows for the acquisition of defect detection data, including defect location and type. Defects can affect pipeline network operation and even lead to malfunctions. This invention provides a method to predict pipeline network malfunctions by combining defect detection data with a risk prediction model.

[0030] As a preferred implementation, the risk prediction model is obtained by: obtaining historical monitoring data and historical defect detection data of load anomaly nodes, generating a fusion map based on the number, location, and size of pipeline defects, labeling the fusion map, and generating a sample dataset; generating an initial risk prediction model based on a neural network, and training the initial risk prediction model based on the sample dataset to determine the model parameters; and generating a risk prediction model based on the model parameters and the initial defect diagnosis model.

[0031] The prediction module is used to input monitoring data and defect detection data of load anomaly nodes into the risk prediction model to obtain the risk value of the load anomaly nodes, including: obtaining the predicted value of pipeline faults according to the risk prediction model, determining the weight corresponding to the pipeline faults using the entropy method; and obtaining the risk value of the load anomaly nodes according to the predicted value of the pipeline faults and the weight corresponding to the pipeline faults.

[0032] The terminal module issues an alarm based on the risk value, including: determining the risk level based on the risk value, and determining the alarm level based on the risk level. The geographical coordinates of each node and the monitoring data of each node are imported into the GIS server to obtain a pipeline network distribution map of each node. Then, the risk values ​​of nodes with abnormal loads are overlaid and highlighted on the pipeline network distribution map.

[0033] like Figure 1 As shown, the present invention also provides a GIS-based digital pipeline network control method, comprising the following steps: setting up a data acquisition module, wherein the data acquisition module includes sensor units installed in each node of the pipeline network, and using the sensor units to acquire monitoring data of each node of the pipeline network;

[0034] The monitoring data of each node is imported into the GIS server using the data analysis module to obtain the pipeline distribution map of each node. The monitoring data of each node is then input into the anomaly prediction model to obtain the load anomaly nodes, and the load anomaly nodes are highlighted in the pipeline distribution map.

[0035] The defect detection module is used to detect load abnormal nodes to obtain defect detection data. The prediction module is used to input the monitoring data and defect detection data of the load abnormal nodes into the risk prediction model to obtain the risk value of the load abnormal nodes and highlight it in the pipeline distribution map.

[0036] The terminal module is used to display the pipeline network distribution map and to issue alarms based on the risk values.

[0037] The above method imports monitoring data from each node into a GIS server to obtain a network distribution map of each node, and inputs the monitoring data of each node into an anomaly prediction model to identify load anomaly nodes. Then, it detects the load anomaly nodes to obtain defect detection data. The prediction module inputs the monitoring data and defect detection data of the load anomaly nodes into a risk prediction model to obtain the risk value of the load anomaly nodes. This integrates the sensor unit and defect detection module to analyze and warn of potential risks in the network, thus greatly improving control accuracy. Multi-point monitoring assists in network operation and maintenance, enabling the development of operation and maintenance plans, scheduling control, and inspection and maintenance. Online monitoring data is used to analyze network risks and safety hazards, providing a basis for renovation. Liquid level and flow monitoring is implemented at historical waterlogging points and flood-prone areas, providing real-time early warning and alarms. This improves network operation safety and reduces flood control and drainage costs. It verifies whether existing drainage facilities meet construction standards. The methods include network inspection, emergency repair and maintenance, network monitoring, liquid level monitoring, water quality monitoring, zoned metering, network scheduling, source tracing analysis, and rainwater network management.

[0038] Geographic Information System (GIS) is a comprehensive technical system for collecting, storing, managing, analyzing, and displaying information about geographic phenomena. It is characterized by spatial distribution, large data volume, diverse information carriers, and temporal sequence. Its data types are vector data and grid data, and its basic data elements include geographic coordinates, planar coordinates, and vertical coordinates.

[0039] The sensor unit includes a flow meter, a level gauge, a combustible gas detector, or a rainfall monitor. The defect detection module includes a camera, a sonar detector, or a periscope detector, used to detect functional or structural defects within abnormal nodes.

[0040] Submersible level gauges or flow meters mounted on L-shaped brackets can be used during installation. Determine the type, location, and quantity of pipeline defects. Structural defects include disconnections, ruptures, errors, and foreign object intrusion; functional defects include sludge or mud deposits within the pipeline.

[0041] The above embodiments are merely preferred embodiments of the present invention and should not be construed as limiting the scope of protection of the present invention. Any non-substantial changes and substitutions made by those skilled in the art based on the present invention shall fall within the scope of protection claimed by the present invention.

Claims

1. A GIS-based digital pipe network control system, characterized by, The system comprises a collection module, a data analysis module, a defect detection module, a prediction module and a terminal module, the collection module comprises sensor units arranged in each node of the pipe network, the sensor units are used to collect monitoring data of each node of the pipe network, the data analysis module is used to import the monitoring data of each node into a GIS server to obtain a pipe network distribution map of each node, and import the monitoring data of each node into an abnormality prediction model to obtain a load abnormal node, and highlight the load abnormal node in the pipe network distribution map, the defect detection module detects the load abnormal node to obtain defect detection data, the prediction module is used to input the monitoring data of the load abnormal node and the defect detection data of the load abnormal node into a risk prediction model to obtain a risk value of the load abnormal node and highlight the risk value in the pipe network distribution map, the terminal module is used to display the pipe network distribution map and alarm according to the risk value, the defect detection module is used to detect functional defects or structural defects in the load abnormal node, the defect detection data comprises types, positions and quantities of defects, The monitoring data of each node is input into an abnormality prediction model to obtain a load abnormal node, comprising: performing dimensionality reduction analysis on the monitoring data of each node, determining correlation factors of each monitoring data, inputting the monitoring data of each node and the correlation factors into the abnormality prediction model, obtaining a correlation index of the correlation factors on the load, and confirming the load abnormal node if the correlation index is greater than or equal to a preset index, otherwise not a load abnormal node, The defect detection module detects the load abnormal node to obtain defect detection data, comprising: obtaining historical data of normal nodes and historical data of the load abnormal node, performing feature extraction on the historical data to obtain a feature map comprising the historical data, classifying the feature map by a defect detection model to obtain a classification result and a classification loss value of the historical data, optimizing parameters of the object defect detection model to obtain a trained defect detection model, and inputting the detection data of the load abnormal node into the trained defect detection model to obtain the defect detection data.

2. The GIS-based digital pipe network control system of claim 1, wherein, The sensor unit comprises a flow meter, a liquid level meter, a combustible gas monitor or a rain gauge monitor.

3. The GIS-based digital pipe network control system of claim 1, wherein, The defect detection module comprises a camera, a sonar detector or a periscope detector, and is used to detect functional defects or structural defects in the abnormal node.

4. The GIS-based digital pipe network control system of claim 1, wherein, The abnormality prediction model is obtained by: obtaining historical monitoring data of nodes in normal conditions and historical monitoring data of nodes in pipe network failure, extracting feature factors of the historical monitoring data, generating an abnormality index according to the feature factors, and correlating the abnormality index and the historical monitoring data to generate the abnormality prediction model.

5. The GIS-based digital pipe network control system of claim 1, wherein, The prediction module is configured to input the monitoring data of the load abnormal node and the load abnormal node defect detection data into a risk prediction model to obtain a risk value of the load abnormal node, including: obtaining a prediction value of a pipe network fault according to the risk prediction model, determining a weight corresponding to the pipe network fault by using an entropy value method; and obtaining the risk value of the load abnormal node according to the prediction value of the pipe network fault and the weight corresponding to the pipe network fault.

6. The GIS-based digital pipe network control system of claim 5, wherein, The terminal module alarms according to the risk value, including: judging a risk level according to the risk value, and determining an alarm level according to the risk level.

7. The GIS-based digital pipe network control system of claim 1, wherein, The geographic coordinates of each node and the monitoring data of each node are input into the GIS server to obtain a pipe network distribution map of each node, and the risk value of the load abnormal node is superimposed and highlighted on the pipe network distribution map.

Images