Data monitoring and early warning maintenance system of intelligent water service pipe network based on digital twinning

Abstract

The invention discloses a data monitoring, early warning and maintenance system of an intelligent water affair pipe network based on digital twinning, which comprises a data acquisition module, a digital twinning model construction module, a data monitoring and analysis module, an early warning and maintenance decision module, a visual display interface and an execution unit, and relates to the technical field of intelligent water affair. According to the data monitoring and early warning maintenance system of the intelligent water service pipe network based on the digital twinning, the data monitoring and analysis module is arranged, historical conductivity data is extracted to obtain the ion concentration in a pipeline, and the corrosion speed is obtained through calculation; various data at the initial end of the one-way pipeline are extracted to predict a pressure value at the tail end of the one-way pipeline for analysis, and a corresponding abnormal result is generated and transmitted when data abnormity is generated in the analysis process, so that the corrosion condition and the pressure condition in the pipeline are predicted in time, and simulation early warning can be performed in real time; therefore, the safety of a water service pipe network and the timeliness of early warning maintenance are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of smart water affairs, specifically a data monitoring and early warning maintenance system for a smart water affairs pipe network based on digital twinning. BACKGROUND

[0002] With the development of cities, water affairs pipe network systems are becoming increasingly complex, and traditional monitoring and maintenance methods cannot meet the needs of efficient management. The advent of digital twinning technology provides new ideas and methods for solving these problems. By constructing a virtual model of the water affairs pipe network, real-time monitoring, simulation analysis, and precise management of the actual pipe network can be achieved.

[0003] Referring to the patent entitled "Data acquisition, monitoring, early warning, and maintenance method for a smart water affairs pipe network" (patent publication number CN113176758A, patent publication date July 27, 2021), step a: Obtain the location information of the user's mobile terminal, as well as the user's water fee payment records and historical water usage period data through a cloud server; step b: Real-time monitoring of the intelligent water meter to obtain the flow information of the intelligent water meter; step c: When the intelligent water meter detects water flow information, determine whether the mobile terminal is within the preset location, and output alarm information to the mobile terminal according to the determination result. The user's location is determined by the location of the mobile terminal, and the water flow in the user's home is monitored according to the user's location. According to the historical water usage, it is determined whether there is a water leakage in the user's home, so as to timely alarm the user and timely cut off the pipeline, thereby effectively detecting and alarming water leakage in the user's home to reduce the loss caused by water leakage for the user and avoid waste of water resources.

[0004] Based on the above-mentioned document, the existing water affairs pipe network is wide in scope and complex, and monitoring of the water affairs pipe network is crucial. However, current regulatory operations often only provide early warning after problems occur, and during the monitoring process, the abnormal conditions of the pipeline are not predicted or judged in a timely manner, resulting in potential problems or damage to the subsequent pipeline. Therefore, the present application provides a data monitoring and early warning maintenance system for a smart water affairs pipe network based on digital twinning. SUMMARY

[0005] In view of the deficiencies of the prior art, the present application provides a data monitoring and early warning maintenance system for a smart water affairs pipe network based on digital twinning, which solves the problem that the existing water affairs pipe network is wide in scope and complex, and monitoring of the water affairs pipe network is crucial. However, current regulatory operations often only provide early warning after problems occur, and during the monitoring process, the abnormal conditions of the pipeline are not predicted or judged in a timely manner, resulting in potential problems or damage to the subsequent pipeline.

[0006] In order to achieve the above object, the present application is realized by the following technical scheme: the data monitoring and early warning maintenance system of the intelligent water affairs pipe network based on digital twinning includes:

[0007] The data acquisition module is used for real-time acquisition of the operation data of the pipe network.

[0008] The digital twinning model construction module is used for constructing the digital twinning model corresponding to the real water affairs pipe network by using the collected actual data.

[0009] The data monitoring and analysis module is used for realizing the classification processing of the data based on the digital twinning model, extracting the historical conductivity data to obtain the ion concentration in the pipe and calculating the corrosion speed, extracting the data of the initial end of the one-way pipe to predict the pressure value at the end of the one-way pipe for analysis, and generating the corresponding abnormal result for transmission when the data is abnormal in the analysis process.

[0010] The early warning and maintenance decision module is used for triggering the early warning mechanism immediately when the abnormal data result is received, sending the early warning information to the relevant management personnel according to the severity and type of the abnormality, and processing the operation by tracing the historical maintenance strategy.

[0011] The visual display interface is used for displaying the data and reflecting the conditions of the water affairs pipe network in real time.

[0012] The execution unit is used for realizing the opening and closing of the water supply pipe by the control valve according to the instruction.

[0013] Preferably, the data acquisition module is used for deploying various sensors at the water supply pipe of the water affairs pipe network, and the operation is as follows:

[0014] One monitoring node is covered at every two hundred meters of the water affairs pipe network, and the frequency of data collection is greater than once per minute.

[0015] The sensors include: the conductivity sensor continuously records the conductivity value, the temperature sensor records the water temperature in the pipe, the pressure sensor is used for collecting the pressure transmitted in the pipe, the flow sensor is used for collecting the water flow size in the pipe, and the water quality sensor is used for determining the water quality parameter of the pipe.

[0016] The data collected by the sensors is transmitted to the control terminal for storage and processing.

[0017] Preferably, the digital twinning model construction module is used for constructing the digital twinning model corresponding to the real water affairs pipe network, and the operation is as follows:

[0018] The GIS geographic information data is fused based on the distribution map data of the initial water affairs pipe network to realize the establishment of the basic digital model.

[0019] Extract the pipe network topology and corresponding monitoring node data and introduce them into the basic digital model for setting up and establishing the digital twin model. Subsequent newly created data is introduced into the digital twin model in real time to implement update operations.

[0020] The parameter data and collected data are then extracted and introduced into the digital twin model to realize the mapping simulation of the actual water pipe network operation.

[0021] Preferably, the operations for implementing data classification processing in the data monitoring and analysis module are:

[0022] The monitoring nodes are sequentially labeled as the first category labels;

[0023] Based on the main classification node set under the monitoring node, the data category collected by the corresponding sensor is the main classification node, and then based on the main classification node set under the secondary classification node, the collection timestamp under the corresponding data category is the secondary classification node, and the corresponding data result is located after the secondary classification node;

[0024] In the indexing stage, the data values ​​are extracted using the architecture of first-category label + primary classification node + secondary classification node.

[0025] Preferably, the operation of extracting the conductivity data in the data monitoring and analysis module to obtain the ion concentration in the pipeline and calculate the corrosion rate is:

[0026] Extract historical conductivity data within multiple equal-period time periods, establish the horizontal axis with the conductivity data of the timestamp data, and establish the vertical axis with the ion concentration data. After the data is introduced into the coordinate axis where the horizontal and vertical axes intersect, a conductivity-ion concentration relationship curve is established.

[0027] By determining the fluctuation rate of the change curve, the number of conductivity intervals in each cycle time is determined, and the number of conductivity intervals in each cycle time is averaged to obtain the number of conductivity intervals for subsequent setting;

[0028] The interval width is obtained based on the change in ion concentration and the number of conductivity intervals. The corrosion rate in the current pipeline is calculated by determining the ion concentration and combining various parameters.

[0029] Preferably, the calculation formula for the interval width is:

[0030] △J=(D max -D min ) / N;

[0031] △J is the width of the dynamically changing interval, D max D is the maximum conductivity value within the one-way pipeline cycle time. min is the minimum conductivity value within the one-way pipeline cycle time, and N is the number of conductivity intervals set;

[0032] Determine the conductivity value interval in the current pipeline based on the interval width, determine the ion concentration in the corresponding interval based on the real-time conductivity value, and calculate the corrosion rate in the current pipeline through the ion concentration;

[0033] And the corrosion rate calculation formula is: ;

[0034] V f That is the current corrosion rate in the pipeline, C b is the iron ion concentration in the current corroded medium, C0 is the iron ion concentration in the initial pipeline, V r is the volume of the solution in the pipeline, s is the contact surface area between the pipeline and the medium, and t is the corrosion time;

[0035] The safety threshold based on historical data is compared with the corrosion rate. If the corrosion rate exceeds the safety threshold within the same cycle time, a data anomaly is generated and a corrosion anomaly result is generated.

[0036] Preferably, the operation of extracting various data at the initial end of the one-way pipeline and predicting the pressure value at the end of the one-way pipeline for analysis in the data monitoring and analysis module is:

[0037] The plane where the current monitoring node is located is the horizontal plane, and then a coordinate system is established with the water inlet of the one-way pipe as the starting point and parallel to the horizontal plane. The X-axis is established toward the location of the one-way pipe, and the Y-axis is established in the horizontal plane perpendicular to the X-axis, and the Z-axis is established vertically downward from the starting point;

[0038] The coordinates of the water inlet are (0, 0, 0), and the pressure value at the end of the one-way pipe is calculated by combining the parameters obtained at the monitoring node;

[0039] The pressure safety value of the pipeline in the historical data is extracted and compared with the pressure value at the end of the one-way pipeline. If the pressure safety value is less than the pressure value at the end of the one-way pipeline, a data anomaly is generated and a pressure anomaly result is generated.

[0040] Preferably, the pressure value calculation formula at the end of the one-way pipe is:

[0041] ;

[0042] P2 is the pressure value at the end of the one-way pipe, P1 is the pressure value at the water inlet of the one-way pipe, ρ is the water density, g is the acceleration of gravity, h is the height difference between the water inlet and the end of the one-way pipe, v1 is the flow velocity at the water inlet, v2 is the flow velocity at the end of the pipe, f is the friction coefficient affecting the water flow, L is the length between the water inlet and the end of the one-way pipe, d is the current diameter of the one-way pipe, and v3 is the flow velocity in the pipe process;

[0043] The calculation formula for the height difference h between the outlet and the end of a one-way pipe is:

[0044] h = L × Sinθ;

[0045] θ is the angle between the extension direction of the unidirectional pipeline and the horizontal plane.

[0046] Preferably, the operation of sending warning information to relevant management personnel according to the severity and type of the abnormality in the warning and maintenance decision module is:

[0047] After receiving the abnormal result, a maintenance instruction is initiated from the monitoring node position according to the monitoring node position generated by the abnormal result;

[0048] The distance between the personnel and the monitoring node is determined by GPS positioning of the personnel's mobile phone terminal, and the number of personnel required is confirmed according to the severity of the anomaly. The personnel are then arranged in order of distance from shortest to longest.

[0049] Preferably, the operation of processing the maintenance strategy of the traceability history in the early warning and maintenance decision module is:

[0050] Determine the control valves that can be closed based on abnormal conditions to deactivate the current pipeline and have personnel perform maintenance;

[0051] The specific number of control valves to be closed must meet the conditions of completely shutting down the currently abnormal pipeline and having the least impact on the number of households;

[0052] By sorting the number of households affected by each control valve, and combining the control valves in order from the least to the most affected households, the abnormal pipeline can be deactivated. In this way, multiple control schemes are generated, and the scheme with the least total number of affected households is compared as the maintenance strategy.

[0053] The present invention provides a data monitoring, early warning and maintenance system for smart water pipe networks based on digital twins. Compared with existing technologies, it has the following advantages:

[0054] 1. The data monitoring, early warning and maintenance system for the smart water pipe network based on digital twins is equipped with a data monitoring and analysis module. It extracts historical conductivity data to obtain the ion concentration in the pipe and calculates the corrosion rate. It extracts various data at the initial end of the one-way pipe to predict the pressure value at the end of the one-way pipe for analysis. When data anomalies occur during the analysis process, corresponding abnormal results are generated and transmitted. In this way, the corrosion and pressure conditions in the pipe can be predicted in a timely manner, and simulated early warnings can be performed in real time, thereby improving the safety of the water pipe network and the timeliness of early warning maintenance.

[0055] 2、The data monitoring and early warning maintenance system of the intelligent water management pipe network based on digital twinning, by setting the digital twinning model construction module, based on the initial water management pipe network distribution map data fusion GIS geographic information data to realize the establishment of the basic digital model, extract the pipe network topology structure and the corresponding monitoring node data to introduce the basic digital model to realize the establishment of the digital twinning model, break through the limitation of traditional static model, realize the dynamic simulation of the whole life cycle of the pipe network, and based on the digital twinning model, the influence of the fault is preplayed, the maintenance strategy is formulated in advance, the multi-dimensional data such as flow, pressure, water quality and equipment state are integrated, the early warning accuracy is improved, and at the same time, a complete chain is formed from data collection to maintenance execution, and the demand for manual intervention is reduced.

[0056] 3、The data monitoring and early warning maintenance system of the intelligent water management pipe network based on digital twinning, by setting the early warning and maintenance decision module, the distance between the personnel mobile terminal GPS positioning and the monitoring node position is determined, the number of personnel required is confirmed according to the severity of the abnormality, then the personnel are arranged in order from short to long distance, the maintenance is realized by meeting the conditions of shutting down the current abnormal pipe and minimizing the number of households, a complete process from abnormal detection to maintenance dispatch is formed, and the least affected and fastest processing mode in the operation of maintenance is realized, and the repair and maintenance of the water management pipe network are effectively realized. BRIEF DESCRIPTION OF DRAWINGS

[0057] Figure 1 It is the principle diagram of the data monitoring and early warning maintenance system of the application;

[0058] Figure 2 It is the operation flow chart of the digital twinning model construction module of the application;

[0059] Figure 3 It is the operation flow chart of the data monitoring and analysis module for corrosion speed analysis of the application;

[0060] Figure 4 It is the operation flow chart of the early warning and maintenance decision module of the application. DETAILED DESCRIPTION

[0061] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, not all. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor belong to the scope of protection of the application.

[0062] Please refer to Figures 1-4 The application provides two technical solutions:

[0063] Embodiment one, the data monitoring and early warning maintenance system of the intelligent water management pipe network based on digital twinning, comprising:

[0064] a data acquisition module, which is located at a water supply pipeline of a water service network in a region and is provided with various sensors for acquiring operation data of the pipeline in real time;

[0065] a digital twin model construction module, which constructs a digital twin model corresponding to the actual water service network by using the acquired data;

[0066] a data monitoring and analysis module, which classifies and processes the data based on the digital twin model, extracts historical conductivity data to obtain ion concentration in the pipeline and calculates corrosion speed, extracts various data at the initial end of the one-way pipeline to predict pressure values at the end of the one-way pipeline for analysis, and generates corresponding abnormal results for transmission when data anomalies occur during the analysis;

[0067] an early warning and maintenance decision module, which triggers an early warning mechanism immediately when receiving abnormal data results, sends early warning information to relevant management personnel according to the severity and type of the anomaly, and traces historical maintenance strategies for processing operations;

[0068] a visual display interface, which displays the data and reflects various conditions of the water service network in real time;

[0069] an execution unit, which opens and closes the water supply pipeline according to the instructions through a control valve.

[0070] The execution unit controls electrical components such as electric control valves according to the instructions of the system to realize control operations matching the instructions.

[0071] The data monitoring and analysis module extracts historical conductivity data to obtain ion concentration in the pipeline and calculates corrosion speed, extracts various data at the initial end of the one-way pipeline to predict pressure values at the end of the one-way pipeline for analysis, and generates corresponding abnormal results for transmission when data anomalies occur during the analysis, so as to timely predict the corrosion and pressure conditions in the pipeline and realize real-time simulation warning, thereby improving the safety of the water service network and the timeliness of early warning and maintenance.

[0072] In the embodiment of the application, the data acquisition module is located at the water supply pipeline of the water service network and is provided with various sensors to operate as follows:

[0073] A monitoring node is covered at every 200-meter pipeline of the water service network, and the frequency of data acquisition is maintained to be greater than once per minute;

[0074] The sensors include: a conductivity sensor continuously recording conductivity values, a temperature sensor recording water temperature in the pipeline, a pressure sensor for acquiring pressure transmitted in the pipeline, a flow sensor for acquiring water flow size in the pipeline, and a water quality sensor for determining water quality parameters of the pipeline.

[0075] And the data collected by the sensor is transmitted to the control terminal to realize storage and processing.

[0076] In the embodiment of the application, the operation of constructing a digital twin model corresponding to the real water management pipe network in the digital twin model construction module is:

[0077] Based on the initial water management pipe network distribution map data, GIS geographic information data is fused to realize the establishment of the basic digital model;

[0078] The pipe network topology and corresponding monitoring node data are extracted and introduced into the basic digital model to realize the setting of the digital twin model, and the subsequent newly built data is introduced into the digital twin model to realize the updating operation;

[0079] The parameter data and the collected data are extracted and introduced into the digital twin model to realize the mapping simulation of the operation of the real water management pipe network.

[0080] Among them, by setting the digital twin model construction module, based on the initial water management pipe network distribution map data, GIS geographic information data is fused to realize the establishment of the basic digital model, the pipe network topology and the corresponding monitoring node data are extracted and introduced into the basic digital model to realize the setting of the digital twin model, which breaks through the limitation of the traditional static model, realizes the dynamic simulation of the whole life cycle of the pipe network, and based on the digital twin model, the influence of the fault is preplayed, the maintenance strategy is formulated in advance, the multi-dimensional data such as flow, pressure, water quality and equipment state are integrated, the early warning accuracy is improved, at the same time, a complete chain is formed from data collection to maintenance execution, and the demand for manual intervention is reduced.

[0081] In the embodiment of the application, the operation of the data monitoring and analysis module for classifying and processing data is:

[0082] The monitoring nodes are sequentially labeled as the first type of label;

[0083] Based on the main classification node set under the monitoring node, the data category collected by the sensor is the main classification node, and then based on the sub-classification node set under the main classification node, the collection time stamp under the data category is the sub-classification node, and the data result corresponds to the sub-classification node.

[0084] The index stage realizes the extraction of data values based on the architecture of the first type of label+main classification node+sub-classification node.

[0085] In the embodiment of the application, the operation of the data monitoring and analysis module for extracting conductivity data to obtain ion concentration in the pipeline and calculating corrosion speed is:

[0086] Extracting historical conductivity data in multiple equal period time, establishing horizontal axis with time stamp data conductivity data, establishing vertical axis with ion concentration data, and establishing conductivity-ion concentration relation curve after data introduction into coordinate axis crossing horizontal axis and vertical axis;

[0087] Determine fluctuation rate of change curve, determine conductivity interval number in each period time, and calculate average value of conductivity interval number in each period time to obtain conductivity interval number of subsequent setting division;

[0088] Obtain interval width according to ion concentration change and conductivity interval number, and calculate current pipeline corrosion speed by determining ion concentration and each parameter.

[0089] In the embodiment of the application, the calculation formula of the interval width is:

[0090] △J= (D max -D min ) / N;

[0091] △J is a dynamic change interval width, D max is the maximum conductivity value in the period time of the one-way pipeline, D min is the minimum conductivity value in the period time of the one-way pipeline, and N is the set conductivity interval number;

[0092] Determine the conductivity value interval in the current pipeline according to the interval width, determine the ion concentration in the corresponding interval according to the real-time conductivity value, and calculate the corrosion speed in the current pipeline through the ion concentration;

[0093] And the corrosion speed calculation formula is: ;

[0094] V f is the corrosion speed in the current pipeline, C b is the iron ion concentration in the medium after the current corrosion, C0 is the initial iron ion concentration in the pipeline, V r is the solution volume in the pipeline, s is the pipeline and medium contact surface area, and t is the corrosion time;

[0095] Compare the safety threshold value based on the historical data with the corrosion speed, if the corrosion speed exceeds the safety threshold value in the same period time, data anomaly corrosion anomaly result is generated.

[0096] In the embodiment of the application, the operation of extracting each data of the initial end of the one-way pipeline in the data monitoring and analysis module to predict the pressure value at the end of the one-way pipeline for analysis is:

[0097] The face where the current monitoring node is located is taken as a horizontal plane, then a coordinate system is established from the water inlet of the one-way pipeline as a starting point and parallel to the horizontal plane, an X axis is established towards the position where the one-way pipeline is located, a Y axis is established vertically downwards from the starting point and located in the horizontal plane and perpendicular to the X axis, and a Z axis is established vertically downwards from the starting point;

[0098] The coordinate of the water inlet is (0, 0, 0), and the pressure value at the end of the one-way pipeline is calculated in combination with the parameters obtained at the monitoring node;

[0099] The pressure safety value of the pipeline in the historical data is extracted and compared with the pressure value at the end of the one-way pipeline, and if the pressure safety value is less than the pressure value at the end of the one-way pipeline, a pressure abnormality result is generated.

[0100] In the embodiment of the application, the pressure value calculation formula at the end of the one-way pipeline is:

[0101] ;

[0102] P2 is the pressure value at the end of the one-way pipeline, P1 is the pressure value at the water inlet of the one-way pipeline, p is the water density, g is the gravitational acceleration, h is the height difference between the water inlet and the end of the one-way pipeline, v1 is the flow rate at the water inlet, v2 is the flow rate at the end of the pipeline, f is the friction coefficient affecting the water flow, L is the length between the water inlet and the end of the one-way pipeline, d is the pipe diameter of the current one-way pipeline, and v3 is the flow rate in the pipeline process.

[0103] The calculation formula of the height difference h between the water inlet and the end of the one-way pipeline is:

[0104] h = L x Sin theta;

[0105] Theta is the included angle between the extension direction of the one-way pipeline and the horizontal plane.

[0106] In the embodiment of the application, the operation of the early warning and maintenance decision module for sending early warning information to relevant management personnel according to the severity and type of the abnormality is:

[0107] After receiving the abnormality result, a maintenance instruction is initiated from the monitoring node position where the abnormality result is generated;

[0108] The distance between the personnel mobile terminal GPS positioning and the monitoring node position is determined, the required number of personnel is confirmed according to the severity of the abnormality, and then the personnel are arranged in order from short to long distance.

[0109] In the embodiment of the application, the operation of the early warning and maintenance decision module for processing the maintenance strategy of the historical traceability is:

[0110] Determine the control valves that can be closed based on abnormal conditions to deactivate the current pipeline and have personnel perform maintenance;

[0111] The specific number of control valves to be closed must meet the conditions of completely shutting down the currently abnormal pipeline and having the least impact on the number of households;

[0112] By sorting the number of households affected by each control valve, and combining the control valves in order from the least to the most affected households, the abnormal pipeline can be deactivated. In this way, multiple control schemes are generated, and the scheme with the least total number of affected households is compared as the maintenance strategy.

[0113] Among them, by setting up an early warning and maintenance decision-making module, the distance between the personnel and the monitoring node location is determined by the GPS positioning of the personnel's mobile phone terminal, and the required number of personnel is confirmed according to the severity of the abnormality. The personnel are arranged by sorting the distance from short to long, and maintenance is achieved by satisfying the conditions of completing the deactivation of the current abnormal pipeline and the least impact on the number of households. A complete process from abnormality detection to maintenance dispatch is formed, and the maintenance operation is achieved with the least impact and the fastest processing method, effectively realizing the repair and maintenance of the water pipe network.

[0114] The difference between Example 2 and Example 1 is that: a location with a large number of abnormal situations in the historical data is selected, and the existing water pipe network data monitoring system and the water pipe network data monitoring and early warning maintenance system of the present invention are used to perform monitoring and early warning operations in this area, and the abnormal monitoring results and the time of completion of maintenance and repair are recorded. The specific results are shown in Table 1:

[0115] Table 1 Result record table

[0116]

[0117] To sum up, in the process of monitoring achieved by the data monitoring and early warning maintenance system of the water pipe network of the present invention, the number of abnormalities that can be identified is more accurate, and the time to complete maintenance and repair is shorter, so it can be better applied in actual operations.

[0118] Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0119] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0120] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. The data monitoring, early warning and maintenance system for smart water pipe networks based on digital twins is characterized by: include: The data acquisition module deploys multiple sensors on the water supply pipes of the regional water supply network to collect real-time operation data of the pipe network; The digital twin model construction module uses the collected actual data to build a digital twin model corresponding to the real water pipe network; The data monitoring and analysis module, based on the digital twin model, classifies and processes data, extracts historical conductivity data to derive the ion concentration in the pipeline and calculates the corrosion rate. It also extracts various data at the initial end of the one-way pipeline to predict the pressure value at the end of the one-way pipeline for analysis. If data anomalies occur during the analysis process, the corresponding abnormal results are generated and transmitted; The early warning and maintenance decision module immediately triggers the early warning mechanism when receiving abnormal data results. It sends early warning information to relevant management personnel based on the severity and type of the abnormality and takes action based on historical maintenance strategies. The visual display interface displays data and reflects the various conditions of the water pipe network in real time; The execution unit opens and closes the water supply pipeline through the control valve according to the instructions.

2. The data monitoring, early warning and maintenance system for the smart water pipe network based on digital twin according to claim 1 is characterized by: The data acquisition module is located in the water supply pipe of the water supply network and deploys multiple sensors to operate as follows: A monitoring node is located every 200 meters of the water pipe network, and the frequency of data collection is maintained at more than once per minute; The sensors include: conductivity sensor to continuously record the conductivity value, temperature sensor to record the temperature of the water in the pipeline, pressure sensor to collect the pressure transmitted in the pipeline, flow sensor to collect the water flow in the pipeline, and water quality sensor to determine the water quality parameters of the pipeline; The data collected by the sensor is transmitted to the control terminal for storage and processing.

3. The data monitoring, early warning and maintenance system for the smart water pipe network based on digital twin according to claim 1 is characterized by: The operations for constructing a digital twin model corresponding to the real water pipe network in the digital twin model construction module are as follows: The basic digital model is established based on the initial water pipe network distribution map data and GIS geographic information data; Extract the pipe network topology and corresponding monitoring node data and introduce them into the basic digital model for setting up and establishing the digital twin model. Subsequent newly created data is introduced into the digital twin model in real time to implement update operations. The parameter data and collected data are then extracted and introduced into the digital twin model to realize the mapping simulation of the actual water pipe network operation.

4. The data monitoring, early warning and maintenance system for the smart water pipe network based on digital twin according to claim 2 is characterized by: The operations for classifying data in the data monitoring and analysis module are as follows: The monitoring nodes are sequentially labeled as the first category labels; Based on the main classification node set under the monitoring node, the data category collected by the corresponding sensor is the main classification node, and then based on the main classification node set under the secondary classification node, the collection timestamp under the corresponding data category is the secondary classification node, and the corresponding data result is located after the secondary classification node; In the indexing stage, the data values ​​are extracted using the architecture of first-category label + primary classification node + secondary classification node.

5. The data monitoring, early warning and maintenance system for the smart water pipe network based on digital twin according to claim 1 is characterized by: The data monitoring and analysis module extracts the conductivity data to obtain the ion concentration in the pipeline and calculates the corrosion rate as follows: Extract historical conductivity data within multiple equal-period time periods, establish the horizontal axis with the conductivity data of the timestamp data, and establish the vertical axis with the ion concentration data. After the data is introduced into the coordinate axis where the horizontal and vertical axes intersect, a conductivity-ion concentration relationship curve is established. By determining the fluctuation rate of the change curve, the number of conductivity intervals in each cycle time is determined, and the number of conductivity intervals in each cycle time is averaged to obtain the number of conductivity intervals for subsequent setting; The interval width is obtained based on the change in ion concentration and the number of conductivity intervals. The corrosion rate in the current pipeline is calculated by determining the ion concentration and combining various parameters.

6. The data monitoring, early warning and maintenance system for the smart water pipe network based on digital twin according to claim 5 is characterized by: The calculation formula for the interval width is: △J=(D max -D min ) / N; △J is the width of the dynamically changing interval, D max D is the maximum conductivity value within the one-way pipeline cycle time. min is the minimum conductivity value within the one-way pipeline cycle time, and N is the number of conductivity intervals set; Determine the conductivity value interval in the current pipeline based on the interval width, determine the ion concentration in the corresponding interval based on the real-time conductivity value, and calculate the corrosion rate in the current pipeline through the ion concentration; And the corrosion rate calculation formula is: ; V f That is the current corrosion rate in the pipeline, C b is the iron ion concentration in the current corroded medium, C0 is the iron ion concentration in the initial pipeline, V r is the volume of the solution in the pipeline, s is the contact surface area between the pipeline and the medium, and t is the corrosion time; The safety threshold based on historical data is compared with the corrosion rate. If the corrosion rate exceeds the safety threshold within the same cycle time, a data anomaly is generated and a corrosion anomaly result is generated.

7. The data monitoring, early warning and maintenance system for the smart water pipe network based on digital twin according to claim 2 is characterized by: The operation of extracting various data at the initial end of the one-way pipeline and predicting the pressure value at the end of the one-way pipeline for analysis in the data monitoring and analysis module is as follows: The plane where the current monitoring node is located is the horizontal plane, and then a coordinate system is established with the water inlet of the one-way pipe as the starting point and parallel to the horizontal plane. The X-axis is established toward the location of the one-way pipe, and the Y-axis is established in the horizontal plane perpendicular to the X-axis, and the Z-axis is established vertically downward from the starting point; The coordinates of the water inlet are (0, 0, 0), and the pressure value at the end of the one-way pipe is calculated by combining the parameters obtained at the monitoring node; The pressure safety value of the pipeline in the historical data is extracted and compared with the pressure value at the end of the one-way pipeline. If the pressure safety value is less than the pressure value at the end of the one-way pipeline, a data anomaly is generated and a pressure anomaly result is generated.

8. The data monitoring, early warning and maintenance system for the smart water pipe network based on digital twin according to claim 7 is characterized by: The formula for calculating the pressure at the end of the one-way pipe is: ； P2 is the pressure value at the end of the one-way pipe, P1 is the pressure value at the water inlet of the one-way pipe, ρ is the water density, g is the acceleration of gravity, h is the height difference between the water inlet and the end of the one-way pipe, v1 is the flow velocity at the water inlet, v2 is the flow velocity at the end of the pipe, f is the friction coefficient affecting the water flow, L is the length between the water inlet and the end of the one-way pipe, d is the current diameter of the one-way pipe, and v3 is the flow velocity in the pipe process; The calculation formula for the height difference h between the outlet and the end of a one-way pipe is: h = L × Sinθ; θ is the angle between the extension direction of the unidirectional pipeline and the horizontal plane.

9. The data monitoring, early warning and maintenance system for the smart water pipe network based on digital twin according to claim 1 is characterized by: The operation of sending warning information to relevant management personnel according to the severity and type of abnormality in the warning and maintenance decision module is: After receiving the abnormal result, a maintenance instruction is initiated from the monitoring node position according to the monitoring node position generated by the abnormal result; The distance between the personnel and the monitoring node is determined by GPS positioning of the personnel's mobile phone terminal, and the number of personnel required is confirmed according to the severity of the anomaly. The personnel are then arranged in order of distance from shortest to longest.

10. The data monitoring, early warning and maintenance system for the smart water pipe network based on digital twin according to claim 1 is characterized by: The operations for processing the maintenance strategy of the traceability history in the early warning and maintenance decision module are: Determine the control valves that can be closed based on abnormal conditions to deactivate the current pipeline and have personnel perform maintenance; The specific number of control valves to be closed must meet the conditions of completely shutting down the currently abnormal pipeline and having the least impact on the number of households; By sorting the number of households affected by each control valve, and combining the control valves in order from the least to the most affected households, the abnormal pipeline can be deactivated. In this way, multiple control schemes are generated, and the scheme with the least total number of affected households is compared as the maintenance strategy.

Images