Rural water supply network pressure monitoring analysis method and device based on digital twinning

Abstract

The application discloses a pressure monitoring and analysis method and device for a rural water supply network based on digital twinning, and the method comprises the following steps: collecting historical basic data of a predicted area in the countryside; acquiring monitoring data by deploying flow and pressure sensors at nodes of the rural water supply network; uploading data to a server and preprocessing the data by using a data flow processing framework to obtain preprocessed data; constructing a relational database management system to batch process the preprocessed data to obtain batch-processed historical basic data and monitoring data; constructing a rural pipe network water pressure prediction model; constructing a pipe burst detection and water pressure control model; constructing a rural water supply network geometric model based on ArcGIS according to physical data; and constructing a rural water supply network system data model and realizing visualization of a running state of the water supply network. The application fully considers the characteristics of rural water supply and water use, realizes intelligent management and control of the rural water supply system, and effectively guarantees the reliability and safety of rural water supply.

Description

Technical Field

[0001] This invention relates to the field of rural water supply technology, specifically to a method and device for monitoring and analyzing the pressure of rural water supply networks based on digital twins. Background Technology

[0002] Rural water supply is closely related to people's daily production and life. Rural water supply in the hilly areas of southern China is characterized by branching pipe networks, scattered water supply points, and significant elevation changes along the pipeline routes. Water pressure varies considerably in different areas, making it difficult to guarantee the reliability of water supply and the safety of the pipe network.

[0003] Currently, water supply networks in many rural areas still rely on traditional manual management methods, which cannot achieve dynamic monitoring and control of water pressure in the pipelines. This results in low water supply efficiency, slow response, and serious pipeline leakage, which negatively impacts the quality of rural water supply.

[0004] Therefore, it is necessary to develop a method for monitoring and regulating the pressure of rural water supply networks based on digital twins, so as to realize intelligent management and control of water pressure in rural water supply networks. Summary of the Invention

[0005] To this end, the present invention provides a method and device for monitoring and analyzing pressure in rural water supply networks based on digital twins, which fully considers the characteristics of rural water supply and water use, realizes intelligent management and control of rural water supply systems, and effectively ensures the reliability and safety of rural water supply.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for monitoring and analyzing pressure in rural water supply networks based on digital twins, comprising:

[0007] Collect data on the designated rural prediction area to obtain historical baseline data for the rural prediction area;

[0008] Based on the node selection principle, nodes of the rural water supply network are selected; flow and pressure sensors are deployed at the selected nodes, and monitoring data is obtained through the flow and pressure sensors;

[0009] The historical basic data and the monitoring data are uploaded to the server through a data stream processing framework; the historical basic data and the monitoring data are preprocessed by the server to obtain preprocessed data;

[0010] A relational database management system is built based on MySQL; through the relational database management system, Hadoop and Spark tools are used to batch process the preprocessed data to obtain batch-processed historical basic data and monitoring data;

[0011] A rural water pressure prediction model is constructed; the rural water pressure prediction model is trained using the historical basic data to obtain a trained rural water pressure prediction model; the batch-processed historical basic data and monitoring data are input into the trained rural water pressure prediction model to obtain rural water pressure prediction data through prediction;

[0012] A pipe burst detection and water pressure control model is constructed. The batch-processed monitoring data and the predicted water pressure data of the rural pipe network are input into the pipe burst detection and water pressure control model. The model is then processed to detect and output a list of high-risk pipe sections and implement PID control.

[0013] Physical data of rural water supply networks are collected; based on the physical data, a geometric model of the rural water supply network is constructed using ArcGIS.

[0014] Based on the rural water pressure prediction model, the burst pipe detection and water pressure control model, and the rural water supply network geometric model, a data model of the rural water supply network system is constructed.

[0015] The backend program of the rural water supply network system data model was written using Python. The rural water supply network system data model outputs time series curves of real-time data and predicted data, realizing the visualization of the operation status of the water supply network.

[0016] As a preferred solution for the rural water supply network pressure monitoring and analysis method based on digital twins, the set data collected in the rural prediction area includes: historical water supply and actual water consumption hourly data, temperature and humidity data at corresponding time points, data on the week number corresponding to the current day, and numerical data on whether the current day is a holiday.

[0017] As a preferred solution for the pressure monitoring and analysis method of rural water supply network based on digital twins, in the process of selecting nodes of rural water supply network according to the node selection principle, the node selection principle includes: laying at user inlet, network intersection, and at intervals on straight sections of the network.

[0018] As a preferred solution for the rural water supply network pressure monitoring and analysis method based on digital twins, during the preprocessing of the historical basic data and the monitoring data through the server, the historical basic data is stored as a data sequence along with the temperature and humidity data, holiday information and weekday data of the corresponding time node.

[0019] For the monitoring data, the data for that hour and the predicted data obtained from the rural pipeline water pressure prediction model are stored as a data sequence. If there is no predicted data, the default value None is used.

[0020] For abnormal data in the monitoring data, if the abnormality is a missing parameter value, the average of the corresponding data from the six hours before and after that hour is used to fill the gap; if the abnormality is a parameter value that repeats for a long time, the data from the same time period in the same month is used, multiplied by a deviation coefficient, and then used to fill the gap. The deviation coefficient is the average of the divisors of the non-repeating data from the same time period in the same month and the non-repeating data from the repetitive time period; if the abnormality is a parameter value fluctuation error, the average of the data from the same time period in recent days is used to fill the gap.

[0021] As a preferred embodiment of the digital twin-based method for monitoring and analyzing pressure in rural water supply networks, the expression for the rural network water pressure prediction model is as follows:

[0022] pre.=αTime+βSpace+γH+σQ+ε

[0023] In the formula, pre. represents the predicted value of a node; Time represents the time inertia term of the node, including the average water pressure in the previous time period, the average water pressure in the same month and week, the average water pressure in the same year and quarter, and the average water pressure in the same quarter and week of the previous three years; Space represents the spatial inertia term of the node, including the monitored water pressure of upstream nodes in the same time period and the predicted water pressure of upstream nodes in the same time period (this term is not present for the initial calculation node); H represents the baseline term of the node, i.e., the actual monitored water pressure of the node at the same moment; Q represents the water pressure correction term of the node, including the water volume monitoring values ​​of all nodes at the same moment; ε represents the bias term of the node, used to explain possible unconsidered patterns in model learning; α, β, γ, and δ represent the learning rates of various terms in the LSTM model, which are calibrated and corrected by the total hyperparameter lr and model learning.

[0024] As a preferred embodiment of the digital twin-based method for monitoring and analyzing pressure in rural water supply networks, the detection and processing steps of the pipe burst detection and water pressure control model are as follows:

[0025] The batch-processed monitoring data and the predicted water pressure of the rural pipe network are identified using a decision tree model, and the risk of pipe burst is output and marked.

[0026] Optimize low-explosion pipe risk data using fuzzy control strategies;

[0027] The risk data of high-explosive pipes is monitored and processed over time; if the set time is exceeded, the log is automatically uploaded and the monitoring personnel are notified through the set method.

[0028] Analyze abnormal water pressure nodes and the possibility of pipe bursts, output a list of high-risk pipe sections, and implement PID control.

[0029] This invention also provides a rural water supply network pressure monitoring and analysis device based on digital twins, which, based on the above-mentioned rural water supply network pressure monitoring and analysis method based on digital twins, includes:

[0030] The historical basic data collection module is used to collect the set data of the rural prediction area and obtain the historical basic data of the rural prediction area.

[0031] The monitoring data acquisition module is used to select nodes of the rural water supply network according to the node selection principle; deploy flow and pressure sensors at the selected nodes, and acquire monitoring data through the flow and pressure sensors;

[0032] The data preprocessing module is used to upload the historical basic data and the monitoring data to the server through a data stream processing framework; and to preprocess the historical basic data and the monitoring data through the server to obtain preprocessed data.

[0033] The data batch processing module is used to build a relational database management system based on MySQL; through the relational database management system, Hadoop and Spark tools are used to batch process the preprocessed data to obtain batch-processed historical basic data and monitoring data;

[0034] The rural pipeline water pressure prediction model construction and processing module is used to construct a rural pipeline water pressure prediction model; train the rural pipeline water pressure prediction model using the historical basic data to obtain a trained rural pipeline water pressure prediction model; input the batch-processed historical basic data and monitoring data into the trained rural pipeline water pressure prediction model to obtain rural pipeline water pressure prediction data through prediction;

[0035] The burst pipe detection and water pressure control model construction and processing module is used to construct a burst pipe detection and water pressure control model; the batch-processed monitoring data and the predicted water pressure data of the rural pipe network are input into the burst pipe detection and water pressure control model, and the burst pipe detection and water pressure control model is used to detect and process the data, output a list of high-risk pipe sections and perform PID control;

[0036] The rural water supply network geometric model construction module is used to collect physical data of the rural water supply network; and to construct a geometric model of the rural water supply network based on ArcGIS based on the physical data.

[0037] The rural water supply network system data model construction module is used to construct a rural water supply network system data model based on the rural network water pressure prediction model, the pipe burst detection and water pressure control model, and the rural water supply network geometric model.

[0038] The rural water supply network system data model visualization output module is used to write the backend program of the rural water supply network system data model in Python. The rural water supply network system data model outputs time series curves of real-time data and predicted data to realize the visualization of the operation status of the water supply network.

[0039] As a preferred embodiment of the rural water supply network pressure monitoring and analysis device based on digital twins, the historical basic data collection module, in the process of collecting the set data of the rural prediction area, the set data includes: historical water supply and actual water consumption hour data, temperature and humidity data at the corresponding time nodes, data on the number of days of the week corresponding to the current day, and numerical data on whether the current day is a holiday.

[0040] As a preferred embodiment of the rural water supply network pressure monitoring and analysis device based on digital twins, in the process of selecting nodes of the rural water supply network according to the node selection principle in the monitoring data acquisition module, the node selection principle includes: laying at user inlet, network intersection, and at intervals along straight sections of the network.

[0041] As a preferred embodiment of the rural water supply network pressure monitoring and analysis device based on digital twins, in the data preprocessing module, during the preprocessing of the historical basic data and the monitoring data through the server, the historical basic data is stored as a data sequence along with the hourly data, temperature and humidity data, holiday information, and weekday data at the corresponding time points.

[0042] For the monitoring data, the data for that hour and the predicted data obtained from the rural pipeline water pressure prediction model are stored as a data sequence. If there is no predicted data, the default value None is used.

[0043] For abnormal data in the monitoring data, if the abnormality is a missing parameter value, the average of the corresponding data from the six hours before and after that hour is used to fill the gap; if the abnormality is a parameter value that repeats for a long time, the data from the same time period in the same month is used, multiplied by a deviation coefficient, and then used to fill the gap. The deviation coefficient is the average of the divisors of the non-repeating data from the same time period in the same month and the non-repeating data from the repetitive time period; if the abnormality is a parameter value fluctuation error, the average of the data from the same time period in recent days is used to fill the gap.

[0044] As a preferred embodiment of the rural water supply network pressure monitoring and analysis device based on digital twins, the expression of the rural water supply network pressure prediction model in the rural water supply network water pressure prediction model construction and processing module is as follows:

[0045] pre.=αTime+βSpace+γH+σQ+ε

[0046] In the formula, pre. represents the predicted value of a node; Time represents the time inertia term of the node, including the average water pressure in the previous time period, the average water pressure in the same month and week, the average water pressure in the same year and quarter, and the average water pressure in the same quarter and week of the previous three years; Space represents the spatial inertia term of the node, including the monitored water pressure of upstream nodes in the same time period and the predicted water pressure of upstream nodes in the same time period (this term is not present for the initial calculation node); H represents the baseline term of the node, i.e., the actual monitored water pressure of the node at the same moment; Q represents the water pressure correction term of the node, including the water volume monitoring values ​​of all nodes at the same moment; ε represents the bias term of the node, used to explain possible unconsidered patterns in model learning; α, β, γ, and δ represent the learning rates of various terms in the LSTM model, which are calibrated and corrected by the total hyperparameter lr and model learning.

[0047] As a preferred embodiment of a digital twin-based rural water supply network pressure monitoring and analysis device, the detection and evaluation sub-module within the burst pipe detection and water pressure control model construction and processing module includes:

[0048] The data identification and labeling submodule is used to identify the batch-processed monitoring data and the rural pipeline water pressure prediction data through a decision tree model, output the risk of pipe burst, and label the risk of pipe burst.

[0049] The low-explosion tube risk data optimization submodule is used to optimize the low-explosion tube risk data through fuzzy control strategies;

[0050] The high-explosive pipe risk data processing submodule is used to monitor and process high-explosive pipe risk data over time; if the set time is exceeded, the log will be automatically uploaded and the monitoring personnel will be notified through the set method.

[0051] The probability analysis submodule is used to analyze the probability of abnormal water pressure nodes and pipe bursts, output a list of high-risk pipe sections and perform PID control.

[0052] This invention has the following advantages: It collects data on a designated rural prediction area to obtain historical baseline data; selects nodes in the rural water supply network according to node selection principles; deploys flow and pressure sensors at the selected nodes to acquire monitoring data; uploads the historical baseline data and monitoring data to a server using a data stream processing framework; preprocesses the historical baseline data and monitoring data on the server to obtain preprocessed data; constructs a relational database management system based on MySQL; uses Hadoop and Spark tools to batch process the preprocessed data using the relational database management system to obtain batch-processed historical baseline data and monitoring data; constructs a rural water supply network water pressure prediction model; trains the rural water supply network water pressure prediction model using the historical baseline data to obtain a trained rural water supply network water pressure prediction model; and then processes the batch-processed historical baseline data and monitoring data. Basic data and monitoring data are input into the trained rural water supply network water pressure prediction model to obtain rural water supply network water pressure prediction data; a pipe burst detection and water pressure control model is constructed; batch-processed monitoring data and the rural water supply network water pressure prediction data are input into the pipe burst detection and water pressure control model, which detects and processes the data, outputs a list of high-risk pipe sections, and performs PID control; physical data of the rural water supply network is collected; based on the physical data, a geometric model of the rural water supply network is constructed using ArcGIS; based on the rural water supply network water pressure prediction model, the pipe burst detection and water pressure control model, and the rural water supply network geometric model, a rural water supply network system data model is constructed; the backend program of the rural water supply network system data model is written using Python, and the rural water supply network system data model outputs time series curves of real-time data and predicted data to visualize the operating status of the water supply network. This invention analyzes historical data, mines data features, and constructs a digital twin-based water pressure prediction model to achieve accurate monitoring and early warning of water pressure across the entire water supply network, ensuring water supply safety. This invention fully considers the characteristics of rural water supply and water usage, enabling intelligent management and control of rural water supply systems and effectively guaranteeing the reliability and safety of rural water supply. Attached Figure Description

[0053] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0054] The structures, proportions, sizes, etc. illustrated in this specification are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed herein, and are not intended to limit the conditions under which the present invention can be implemented. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportions, or adjustments to the size, without affecting the effects and objectives that the present invention can produce, should still fall within the scope of the technical content disclosed in the present invention.

[0055] Figure 1 This is a schematic diagram of the process for monitoring and analyzing pressure in a rural water supply network based on digital twins, as provided in Embodiment 1 of the present invention.

[0056] Figure 2 This is a schematic diagram illustrating the specific implementation process of the rural water supply network pressure monitoring and analysis method based on digital twin provided in Embodiment 1 of the present invention;

[0057] Figure 3 This is a schematic diagram of the implementation process of the pipe burst detection and water pressure control model in the rural water supply network pressure monitoring and analysis method based on digital twin provided in Embodiment 1 of the present invention;

[0058] Figure 4 This is a schematic diagram of the anomaly detection probability in the rural water supply network pressure monitoring and analysis method based on digital twins provided in Embodiment 1 of the present invention;

[0059] Figure 5 This is a schematic diagram of water pressure monitoring data in the rural water supply network pressure monitoring and analysis method based on digital twin provided in Embodiment 1 of the present invention;

[0060] Figure 6 This is a schematic diagram of the predicted water pressure data in the rural water supply network pressure monitoring and analysis method based on digital twin provided in Embodiment 1 of the present invention;

[0061] Figure 7 This is a schematic diagram comparing water pressure monitoring data and predicted data in the rural water supply network pressure monitoring and analysis method based on digital twins provided in Embodiment 1 of the present invention;

[0062] Figure 8 This is a schematic diagram of the fuzzy control process in the rural water supply network pressure monitoring and analysis method based on digital twin provided in Embodiment 1 of the present invention;

[0063] Figure 9 This is a schematic diagram illustrating the error accumulation elimination in the rural water supply network pressure monitoring and analysis method based on digital twins provided in Embodiment 1 of the present invention.

[0064] Figure 10 This is a schematic diagram of the architecture of the rural water supply network pressure monitoring and analysis device based on digital twin provided in Embodiment 2 of the present invention. Detailed Implementation

[0065] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. 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.

[0066] Example 1

[0067] See Figure 1 and Figure 2 Embodiment 1 of the present invention provides a method for monitoring and analyzing the pressure of rural water supply networks based on digital twins, comprising the following steps:

[0068] S1. Collect the data for setting up the rural prediction area and obtain the historical basic data of the rural prediction area;

[0069] S2. Based on the node selection principle, select nodes of the rural water supply network; deploy flow and pressure sensors at the selected nodes, and acquire monitoring data through the flow and pressure sensors;

[0070] S3. Upload the historical basic data and the monitoring data to the server through the data stream processing framework; preprocess the historical basic data and the monitoring data through the server to obtain preprocessed data;

[0071] S4. Build a relational database management system based on MySQL; use Hadoop and Spark tools to batch process the preprocessed data through the relational database management system to obtain batch-processed historical basic data and monitoring data;

[0072] S5. Construct a rural pipeline water pressure prediction model; train the rural pipeline water pressure prediction model using the historical basic data to obtain a trained rural pipeline water pressure prediction model; input the batch-processed historical basic data and monitoring data into the trained rural pipeline water pressure prediction model to obtain rural pipeline water pressure prediction data through prediction;

[0073] S6. Construct a pipe burst detection and water pressure control model; input the batch-processed monitoring data and the predicted water pressure data of the rural pipe network into the pipe burst detection and water pressure control model, process the data through the pipe burst detection and water pressure control model, output a list of high-risk pipe sections and perform PID control;

[0074] S7. Collect physical data of rural water supply network; based on the physical data, construct a geometric model of rural water supply network using ArcGIS;

[0075] S8. Construct a data model for the rural water supply network system based on the rural pipe network water pressure prediction model, the pipe burst detection and water pressure control model, and the rural water supply network geometric model.

[0076] S9. The backend program of the rural water supply network system data model is written using Python. The rural water supply network system data model outputs time series curves of real-time data and predicted data to visualize the operation status of the water supply network.

[0077] In this embodiment, in step S1, the set data of the rural prediction area is collected to obtain the historical basic data of the rural prediction area;

[0078] The set data includes: historical water supply and actual water usage hour data, temperature and humidity data at corresponding time points, data on the week number corresponding to the current day, and numerical data on whether the current day is a holiday.

[0079] Specifically, the date corresponds to the week number, assuming the date data is in Gregorian calendar format. The Zeller formula is used for calculation:

[0080]

[0081] In the formula, h is the day of the week, 0 represents Saturday, 1 represents Sunday, 2 represents Monday, and so on; q is the day of the week (1 to 31); m is the month (3 represents March, 4 represents April, ..., 12 represents December; 1 and 2 represent the 13th and 14th months of the previous year, i.e. January and February); K is the last two digits of the year; J is the first two digits of the year.

[0082] The numerical data on whether a day is a holiday or not is mapped according to the following function H(x):

[0083]

[0084] In this embodiment, in step S2, nodes of the rural water supply network are selected according to the node selection principle; flow and pressure sensors are deployed at the selected nodes, and monitoring data is obtained through the flow and pressure sensors;

[0085] The node selection principles include: laying at user entry points, pipeline intersections, and at intervals along straight sections of the pipeline network.

[0086] Specifically, based on the node selection principle, important nodes of the rural water supply network are selected and flow and pressure sensors are deployed; the sensors upload and interact with data based on HTTP / HTTPS and TCP protocols.

[0087] In this embodiment, in step S3, the historical basic data and the monitoring data are uploaded to the server through a data stream processing framework; the server preprocesses the historical basic data and the monitoring data to obtain preprocessed data.

[0088] Specifically, data stream processing frameworks such as Kafka are used to collect the historical basic data and the monitoring data and upload them to the deployed server. The data is then preprocessed as follows:

[0089] For the aforementioned historical basic data, the data for that hour, along with the temperature and humidity data, holiday information, and weekday data for the corresponding time points, are stored as a data sequence.

[0090] For the monitoring data, the data for that hour and the predicted data obtained from the rural pipeline water pressure prediction model are stored as a data sequence. If there is no predicted data, the default value None is used.

[0091] For abnormal data in the monitoring data, if the abnormality is a missing parameter value, the average of the corresponding data from the six hours before and after that hour is used to fill the gap; if the abnormality is a parameter value that repeats for a long time, the data from the same time period in the same month is used, multiplied by a deviation coefficient, and then used to fill the gap. The deviation coefficient is the average of the divisors of the non-repeating data from the same time period in the same month and the non-repeating data from the repetitive time period; if the abnormality is a parameter value fluctuation error, the average of the data from the same time period in recent days is used to fill the gap.

[0092] In this embodiment, in step S4, a relational database management system is built based on MySQL; through the relational database management system, Hadoop and Spark tools are used to batch process the preprocessed data to obtain batch-processed historical basic data and monitoring data.

[0093] In this embodiment, in step S5, a rural pipeline water pressure prediction model is constructed; the rural pipeline water pressure prediction model is trained using the historical basic data to obtain a trained rural pipeline water pressure prediction model; the batch-processed historical basic data and monitoring data are input into the trained rural pipeline water pressure prediction model to obtain rural pipeline water pressure prediction data through prediction.

[0094] Specifically, for each calculation unit, the expression of the rural pipeline water pressure prediction model is:

[0095] pre.=αTime+βSpace+γH+σQ+ε

[0096] In the formula, pre. represents the predicted value of a node; Time represents the time inertia term of the node, including the average water pressure in the previous time period, the average water pressure in the same month and week, the average water pressure in the same year and quarter, and the average water pressure in the same quarter and week of the previous three years; Space represents the spatial inertia term of the node, including the monitored water pressure of upstream nodes in the same time period and the predicted water pressure of upstream nodes in the same time period (this term is not present for the initial calculation node); H represents the baseline term of the node, i.e., the actual monitored water pressure of the node at the same moment; Q represents the water pressure correction term of the node, including the water volume monitoring values ​​of all nodes at the same moment; ε represents the bias term of the node, used to explain possible unconsidered patterns in model learning; α, β, γ, and δ represent the learning rates of various terms in the LSTM model, which are calibrated and corrected by the total hyperparameter lr and model learning.

[0097] Based on historical data, the dataset is constructed by taking the data from each hour, the data from the previous 6 hours, and the data from the same week of the current month as input, and the data from the next hour as output labels. Two-thirds of the dataset size is randomly used as the training set, and the remaining one-third is used as the validation set. Each independent dataset contains at least one month's worth of data from continuous operation.

[0098] The rural water pressure prediction model is trained using a training set; the robustness and accuracy of the model are validated using a validation set. After validation, the trained rural water pressure prediction model is obtained. Batch-processed historical baseline data and monitoring data are then input into the trained model to obtain predicted rural water pressure data.

[0099] In this embodiment, in step S6, a pipe burst detection and water pressure control model is constructed; the batch-processed monitoring data and the rural pipe network water pressure prediction data are input into the pipe burst detection and water pressure control model, and the model is processed to output a list of high-risk pipe sections and perform PID control.

[0100] like Figure 3 As shown, the detection and processing steps of the pipe burst detection and water pressure control model are as follows:

[0101] S61. The batch-processed monitoring data and the rural pipeline water pressure prediction data are identified using a decision tree model, the risk of pipe burst is output, and the risk of pipe burst is marked.

[0102] Among them, the PyTorch library based on the Python language is used to define, train, and validate the decision tree model;

[0103] Specifically, data is obtained from batch-processed monitoring data and the predicted water pressure in the rural pipe network. A decision tree model is trained based on historical abnormal pipe burst data to identify pipe burst risks. Input features include water pressure, flow rate, and historical abnormal patterns. The output value is a floating-point number between 0 and 1, representing the pipe burst risk value. Confusion matrices and classification reports are used to evaluate the model's performance, focusing on precision, recall, and F1 score. If a pipe burst risk is detected, the data is marked as "risk" and uploaded to monitoring personnel via logs; if no risk is detected, the data is marked as "safe."

[0104] S62. Optimize low-explosion pipe risk data through fuzzy control strategy;

[0105] Specifically,

[0106] (1) Determine the input and output:

[0107] Input variables: water pressure error (the difference between the current water pressure and the target water pressure), rate of change of water pressure error (the speed at which the error changes);

[0108] Output variable: Head adjustment amount.

[0109] (2) Define fuzzy sets:

[0110] Water pressure error:

[0111] Negative large (NB), negative small (NS), zero (ZE), positive small (PS), positive large (PB);

[0112] Water pressure error change rate:

[0113] Negative large (NB), negative small (NS), zero (ZE), positive small (PS), positive large (PB);

[0114] Head adjustment amount:

[0115] Decrease large (RD), decrease small (RS), remain unchanged (ZE), increase small (IS), increase large (ID).

[0116] (3) Fuzzy control rules:

[0117] If the water pressure error is positive (PB) and the rate of change is positive (PS), then the head adjustment amount is increased (ID).

[0118] If the water pressure error is negative small (NS) and the rate of change is negative large (NB), then the head adjustment amount is reduced small (RS);

[0119] If the water pressure error is positive (PB) and the rate of change is zero (ZE), then the head adjustment amount is increased (ID).

[0120] If the water pressure error is positive small (PS) and the rate of change is positive small (PS), then the head adjustment amount is increased small (IS);

[0121] If the water pressure error is negative large (NB) and the rate of change is negative small (NS), then the head adjustment amount is reduced large (RD);

[0122] If the water pressure error is zero (ZE) and the rate of change is zero (ZE), then the head adjustment amount remains unchanged (ZE).

[0123] If the water pressure error is negative (NS) and the rate of change is zero (ZE), then the head adjustment amount is reduced (RS).

[0124] If the water pressure error is positive small (PS) and the rate of change is zero (ZE), then the head adjustment amount is increased small (IS).

[0125] (4) Membership function:

[0126] Membership is defined using the Sigmoid function:

[0127]

[0128] Adjust parameters a and b according to requirements.

[0129] (5) Fuzzy reasoning:

[0130] The activation degree of a rule is calculated using the minimum value method (Min): For each rule, the membership degree of the input condition is calculated, and the minimum value is taken as the activation degree of the rule.

[0131] (6) Defuzzification:

[0132] The mean method is used to defuzzify:

[0133] Z = ∑μi*∑(μi·zi)

[0134] In the formula, μi represents the activation level of each rule, and zi represents the output value of the rule.

[0135] S63. Perform time-based monitoring and processing of high-explosion pipe risk data; if the set time is exceeded, automatically upload the log and notify the monitoring personnel through the set method;

[0136] Specifically, for high-risk data related to burst pipes, if the duration exceeds 5 minutes, logs will be automatically uploaded, and monitoring personnel will be notified via SMS or other means.

[0137] S64. Analyze abnormal water pressure nodes and the possibility of pipe bursts, output a list of high-risk pipe sections and perform PID control.

[0138] Specifically,

[0139] (1) Data preparation:

[0140] Obtain the risk level of each node (from 0 to 1, with the risk level increasing as the number increases). Obtain the topological structure between nodes (directed edge weighted graph).

[0141] (2) Abnormal node identification:

[0142] A risk threshold (0.4) is set, and risk nodes exceeding this threshold are identified and marked as anomalous nodes. Specifically, data with a risk threshold higher than 0.7 are marked as high-risk data.

[0143] (3) Pipeline segment assessment:

[0144] For each anomalous node, obtain all its connected upstream and downstream nodes. Calculate the risk probability of adjacent pipe segments: if the risk levels of both upstream and downstream nodes are high, the risk of pipe bursting in that segment is high. Consider historical fault records of the pipe segment (if any) and increase their weight.

[0145] (4) Assessment of the probability of pipe burst:

[0146] Calculate a burst probability score for each pipe segment: the score can be based on the average or maximum risk level of the nodes. Incorporate historical failure weights (if applicable). Identify the segments with the highest scores as high-risk segments.

[0147] (5) Output of results:

[0148] The list of identified high-risk pipe sections is uploaded to the log system. The output format includes information such as pipe section identifier, connection nodes, and pipe burst probability score.

[0149] (6) Decision support:

[0150] Provide maintenance personnel with information on high-risk pipeline sections for priority inspection and maintenance.

[0151] In this embodiment, in step S7, physical data of the rural water supply network is collected; based on the physical data, a geometric model of the rural water supply network is constructed using ArcGIS.

[0152] Specifically, information such as rural pipeline network layout, pipe materials, pipe diameter, pipe length, and nodes is collected; based on the collected physical information of the rural pipeline network, a geometric model of the pipeline network is established using ArcGIS.

[0153] Store relevant information in a CSV file format, including node ID, X coordinate, and Y coordinate. Import the CSV file into the project using the "Add Data" function. Right-click the imported table and select "Display XY Data". Specify the coordinate columns corresponding to the X and Y fields and set the coordinate system (usually WGS 84 or a projection suitable for the local area). Use the "Point to Line" tool (requires ArcGIS Pro or ArcMap Advanced License). Specify the point layer as input and generate lines according to the node connection order. If there is no connection order, edit manually or create it based on topology information. Use the "Edit" tool to manually adjust pipeline connections to ensure they conform to the actual pipeline topology. You can add attribute fields, such as pipe diameter and pipe material. Use the "Topology" tool to check and correct topology errors, such as dangling nodes and overlapping line segments. Set line symbols as needed. Add labels to display node or pipe segment information.

[0154] In this embodiment, in step S8, a data model of the rural water supply network system is constructed based on the rural pipe network water pressure prediction model, the pipe burst detection and water pressure control model, and the rural water supply network geometric model.

[0155] Specifically, based on the rural water pressure prediction model, the burst pipe detection and water pressure control model, and the rural water supply network geometric model, the collected historical data and real-time monitored operational data are integrated into the rural water supply network geometric model to construct a rural water supply network system data model.

[0156] In this embodiment, in step S9, the backend program of the rural water supply network system data model is written using Python. The rural water supply network system data model outputs time series curves of real-time data and predicted data, thereby realizing the visualization of the water supply network operation status.

[0157] Specifically, a backend program is written in Python to generate time series curves for real-time and predicted data, display the trend of data changes over time, provide a user interface for viewing and analyzing data, and visualize the operating status of the water supply network.

[0158] Generating time series curves of real-time data, capable of, for example Figure 4 As shown, it displays abnormal situations; it can be as follows Figure 5 As shown, this illustrates the change in actual water pressure over time; Figure 6 As shown, this illustrates the predicted change in water pressure over time; Figure 7 As shown, a visual interface is used to compare real-time and predicted data, helping users analyze and make decisions. Figure 8As shown, this displays the changes in control parameters over time, providing a visual interface for users to monitor the fuzzy control process; for example... Figure 9 As shown, this illustrates the process of eliminating abnormal water pressure in the pipeline network.

[0159] In summary, this invention collects data on the rural prediction area to obtain historical baseline data; selects nodes of the rural water supply network according to node selection principles; deploys flow and pressure sensors at the selected nodes to acquire monitoring data; uploads the historical baseline data and the monitoring data to a server using a data stream processing framework; preprocesses the historical baseline data and the monitoring data on the server to obtain preprocessed data; constructs a relational database management system based on MySQL; uses Hadoop and Spark tools to batch process the preprocessed data using the relational database management system to obtain batch-processed historical baseline data and monitoring data; constructs a rural water supply network water pressure prediction model; trains the rural water supply network water pressure prediction model using the historical baseline data to obtain a trained rural water supply network water pressure prediction model; and then uploads the batch-processed historical baseline data to the server. Basic data and monitoring data are input into the trained rural water supply network water pressure prediction model to obtain rural water supply network water pressure prediction data; a pipe burst detection and water pressure control model is constructed; batch-processed monitoring data and the rural water supply network water pressure prediction data are input into the pipe burst detection and water pressure control model, which detects and processes the data, outputs a list of high-risk pipe sections, and performs PID control; physical data of the rural water supply network is collected; based on the physical data, a geometric model of the rural water supply network is constructed using ArcGIS; based on the rural water supply network water pressure prediction model, the pipe burst detection and water pressure control model, and the rural water supply network geometric model, a rural water supply network system data model is constructed; the backend program of the rural water supply network system data model is written using Python, and the rural water supply network system data model outputs time series curves of real-time data and predicted data to visualize the operating status of the water supply network. This invention analyzes historical data, mines data features, and constructs a digital twin-based water pressure prediction model to achieve accurate monitoring and early warning of water pressure across the entire water supply network, ensuring water supply safety. This invention fully considers the characteristics of rural water supply and water usage, enabling intelligent management and control of rural water supply systems and effectively guaranteeing the reliability and safety of rural water supply.

[0160] It should be noted that the method of this disclosure embodiment can be executed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of this disclosure embodiment, and the multiple devices will interact with each other to complete the method described.

[0161] It should be noted that the above description describes some embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0162] Example 2

[0163] See Figure 10 Embodiment 2 of the present invention also provides a rural water supply network pressure monitoring and analysis device based on digital twins, comprising:

[0164] The historical basic data collection module 001 is used to collect the set data of the rural prediction area and obtain the historical basic data of the rural prediction area.

[0165] The monitoring data acquisition module 002 is used to select nodes of the rural water supply network according to the node selection principle; deploy flow and pressure sensors at the selected nodes, and acquire monitoring data through the flow and pressure sensors;

[0166] The data preprocessing module 003 is used to upload the historical basic data and the monitoring data to the server through the data stream processing framework; and to preprocess the historical basic data and the monitoring data through the server to obtain preprocessed data.

[0167] Data batch processing module 004 is used to build a relational database management system based on MySQL; through the relational database management system, Hadoop and Spark tools are used to batch process the preprocessed data to obtain batch-processed historical basic data and monitoring data;

[0168] The rural pipeline water pressure prediction model construction and processing module 005 is used to construct a rural pipeline water pressure prediction model; train the rural pipeline water pressure prediction model using the historical basic data to obtain a trained rural pipeline water pressure prediction model; input the batch-processed historical basic data and monitoring data into the trained rural pipeline water pressure prediction model to obtain rural pipeline water pressure prediction data through prediction;

[0169] The burst pipe detection and water pressure control model construction and processing module 006 is used to construct a burst pipe detection and water pressure control model; the batch-processed monitoring data and the rural pipe network water pressure prediction data are input into the burst pipe detection and water pressure control model, and the burst pipe detection and water pressure control model is used to detect and process the data, output a list of high-risk pipe sections and perform PID control;

[0170] The rural water supply network geometric model construction module 007 is used to collect physical data of the rural water supply network; and to construct a geometric model of the rural water supply network based on ArcGIS based on the physical data.

[0171] The rural water supply network system data model construction module 008 is used to construct a rural water supply network system data model based on the rural network water pressure prediction model, the pipe burst detection and water pressure control model, and the rural water supply network geometric model.

[0172] The rural water supply network system data model visualization output module 009 is used to write the backend program of the rural water supply network system data model in Python. The rural water supply network system data model outputs time series curves of real-time data and predicted data to realize the visualization of the operation status of the water supply network.

[0173] In this embodiment, the historical basic data collection module 001 collects the set data for the rural prediction area. The set data includes: historical water supply and actual water usage hour data, temperature and humidity data at corresponding time points, the number of days of the week corresponding to the current day, and numerical data on whether the current day is a holiday.

[0174] In this embodiment, in the process of selecting nodes of the rural water supply network according to the node selection principle in the monitoring data acquisition module 002, the node selection principle includes: laying at user inlet, pipeline intersection, and at intervals along straight sections of the pipeline.

[0175] In this embodiment, in the data preprocessing module 003, during the process of preprocessing the historical basic data and the monitoring data through the server, the historical basic data is stored as a data sequence along with the temperature and humidity data of the corresponding time node, holiday information and week number data for that hour.

[0176] For the monitoring data, the data for that hour and the predicted data obtained from the rural pipeline water pressure prediction model are stored as a data sequence. If there is no predicted data, the default value None is used.

[0177] For abnormal data in the monitoring data, if the abnormality is a missing parameter value, the average of the corresponding data from the six hours before and after that hour is used to fill the gap; if the abnormality is a parameter value that repeats for a long time, the data from the same time period in the same month is used, multiplied by a deviation coefficient, and then used to fill the gap. The deviation coefficient is the average of the divisors of the non-repeating data from the same time period in the same month and the non-repeating data from the repetitive time period; if the abnormality is a parameter value fluctuation error, the average of the data from the same time period in recent days is used to fill the gap.

[0178] In this embodiment, in the rural pipeline water pressure prediction model construction and processing module 005, the expression of the rural pipeline water pressure prediction model is:

[0179] pre.=αTime+βSpace+γH+σQ+ε

[0180] In the formula, pre. represents the predicted value of a node; Time represents the time inertia term of the node, including the average water pressure in the previous time period, the average water pressure in the same month and week, the average water pressure in the same year and quarter, and the average water pressure in the same quarter and week of the previous three years; Space represents the spatial inertia term of the node, including the monitored water pressure of upstream nodes in the same time period and the predicted water pressure of upstream nodes in the same time period (this term is not present for the initial calculation node); H represents the baseline term of the node, i.e., the actual monitored water pressure of the node at the same moment; Q represents the water pressure correction term of the node, including the water volume monitoring values ​​of all nodes at the same moment; ε represents the bias term of the node, used to explain possible unconsidered patterns in model learning; α, β, γ, and δ represent the learning rates of various terms in the LSTM model, which are calibrated and corrected by the total hyperparameter lr and model learning.

[0181] In this embodiment, the detection and evaluation sub-module in the pipe burst detection and water pressure control model construction and processing module 006 includes:

[0182] The data identification and labeling submodule 061 is used to identify the batch-processed monitoring data and the rural pipeline water pressure prediction data through a decision tree model, output the risk of pipe burst, and label the risk of pipe burst.

[0183] The low-explosion tube risk data optimization submodule 062 is used to optimize the low-explosion tube risk data through a fuzzy control strategy.

[0184] The high-explosive pipe risk data processing submodule 063 is used to perform time monitoring and processing of high-explosive pipe risk data; if the set time is exceeded, the log will be automatically uploaded and the monitoring personnel will be notified through the set method.

[0185] The probability analysis submodule 064 is used to analyze the probability of abnormal water pressure nodes and pipe bursts, output a list of high-risk pipe sections and perform PID control.

[0186] It should be noted that the information interaction and execution process between the modules of the above system are based on the same concept as the method embodiment in Embodiment 1 of this application, and the resulting technical effects are the same as those in the method embodiment of this application. For details, please refer to the description in the method embodiment shown above in this application, and it will not be repeated here.

[0187] Example 3

[0188] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium storing program code for a rural water supply network pressure monitoring and analysis method based on digital twins. The program code includes instructions for executing the rural water supply network pressure monitoring and analysis method based on digital twins as described in Embodiment 1 or any possible implementation thereof.

[0189] Computer-readable storage media can be any available medium that a computer can access, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives, SSDs).

[0190] Example 4

[0191] Embodiment 4 of the present invention provides an electronic device, including: a memory and a processor;

[0192] The processor and the memory communicate with each other via a bus; the memory stores program instructions that can be executed by the processor, and the processor can execute the digital twin-based rural water supply network pressure monitoring and analysis method of Embodiment 1 or any possible implementation thereof by calling the program instructions.

[0193] Specifically, a processor can be implemented in hardware or software. When implemented in hardware, the processor can be a logic circuit, an integrated circuit, etc. When implemented in software, the processor can be a general-purpose processor that reads software code stored in memory. This memory can be integrated into the processor or located outside the processor and exist independently.

[0194] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable system. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0195] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing systems. They can be centralized on a single computing system or distributed across a network of multiple computing systems. Optionally, they can be implemented using program code executable by a computing system, thereby storing them in a storage system for execution by the computing system. In some cases, the steps shown or described can be performed in a different order than those presented herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0196] Although the present invention has been described in detail above with general descriptions and specific embodiments, modifications or improvements can be made to it, which will be obvious to those skilled in the art. Therefore, all such modifications or improvements made without departing from the spirit of the present invention fall within the scope of protection claimed by the present invention.

Claims

1. A method for monitoring and analyzing pressure in rural water supply networks based on digital twins, characterized in that, include: Collect data on the designated rural prediction area to obtain historical baseline data for the rural prediction area; Based on the node selection principle, select nodes for the rural water supply network; Deploy flow and pressure sensors at selected nodes to acquire monitoring data; The historical basic data and the monitoring data are uploaded to the server through a data stream processing framework; The server performs preprocessing on the historical basic data and the monitoring data to obtain preprocessed data; A relational database management system is built based on MySQL; through the relational database management system, Hadoop and Spark tools are used to batch process the preprocessed data to obtain batch-processed historical basic data and monitoring data; A rural water pressure prediction model is constructed; the rural water pressure prediction model is trained using the historical basic data to obtain a trained rural water pressure prediction model; the batch-processed historical basic data and monitoring data are input into the trained rural water pressure prediction model to obtain rural water pressure prediction data through prediction; A pipe burst detection and water pressure control model is constructed. The batch-processed monitoring data and the predicted water pressure data of the rural pipe network are input into the pipe burst detection and water pressure control model. The model is then processed to detect and output a list of high-risk pipe sections and implement PID control. Collect physical data on rural water supply networks; Based on the physical data, a geometric model of the rural water supply network was constructed using ArcGIS. Based on the rural water pressure prediction model, the burst pipe detection and water pressure control model, and the rural water supply network geometric model, a data model of the rural water supply network system is constructed. The backend program of the rural water supply network system data model is written in Python. The rural water supply network system data model outputs time series curves of real-time data and predicted data, realizing the visualization of the operation status of the water supply network. The expression for the rural pipe network water pressure prediction model is as follows: ； In the formula, pre. This is the predicted value for a certain node; Time The time inertia term of this node includes the average water pressure in the previous time period, the average water pressure in the same month and week, the average water pressure in the same year and quarter, and the average water pressure in the same quarter and week of the previous three years. Space This is the spatial inertia term for this node, which includes the monitored water pressure of the upstream node during the same time period and the predicted water pressure of the upstream node during the same time period. This term does not exist for the initial calculation node. H This serves as the baseline for that node, representing the actual monitored water pressure at that node at the same moment. Q This is the water pressure correction term for this node, which includes the water volume monitoring values ​​of all nodes at the same time. ε This is the bias term for the node, used to explain any unconsidered patterns that may exist during model learning; α, β, γ, δ These are the learning rates for various parameters in the LSTM model, which are adjusted by the total hyperparameter lr and the model learning rate. The detection and processing steps of the pipe burst detection and water pressure control model are as follows: The batch-processed monitoring data and the predicted water pressure of the rural pipe network are identified using a decision tree model, and the risk of pipe burst is output and marked. Optimize low-explosion pipe risk data using fuzzy control strategies; Time-based monitoring and processing of high-risk pipe bursting data; If the set time period is exceeded, logs will be automatically uploaded, and monitoring personnel will be notified through the set method. Analyze abnormal water pressure nodes and the possibility of pipe bursts, output a list of high-risk pipe sections, and implement PID control.

2. The method for monitoring and analyzing pressure in rural water supply networks based on digital twins according to claim 1, characterized in that, In the process of collecting the set data for the rural prediction area, the set data includes: historical water supply and actual water consumption hourly data, temperature and humidity data at corresponding time points, data on the week number corresponding to the current day, and numerical data on whether the current day is a holiday.

3. The method for monitoring and analyzing rural water supply network pressure based on digital twins according to claim 2, characterized in that, In the process of selecting nodes for rural water supply networks according to the node selection principles, the node selection principles include: laying at user inlet points, network intersections, and at intervals along straight sections of the network.

4. The method for monitoring and analyzing pressure in rural water supply networks based on digital twins according to claim 3, characterized in that, During the preprocessing of the historical basic data and the monitoring data by the server, the historical basic data is stored as a data sequence along with the temperature and humidity data of the corresponding time node, holiday information and week number data. For the monitoring data, the data for that hour and the predicted data obtained from the rural pipeline water pressure prediction model are stored as a data sequence. If there is no predicted data, the default value None is used. For abnormal data in the monitoring data, if the abnormality is a missing parameter value, the average of the corresponding data from the six hours before and after that hour is used to fill the gap; if the abnormality is a parameter value that repeats for a long time, the data from the same time period in the same month is used, multiplied by a deviation coefficient, and then used to fill the gap. The deviation coefficient is the average of the divisors of the non-repeating data from the same time period in the same month and the non-repeating data from the repetitive time period; if the abnormality is a parameter value fluctuation error, the average of the data from the same time period in recent days is used to fill the gap.

5. A rural water supply network pressure monitoring and analysis device based on digital twins, employing the rural water supply network pressure monitoring and analysis method based on digital twins as described in any one of claims 2-4, characterized in that, include: The historical basic data collection module is used to collect the set data of the rural prediction area and obtain the historical basic data of the rural prediction area. The monitoring data acquisition module is used to select nodes of the rural water supply network according to the node selection principle; deploy flow and pressure sensors at the selected nodes, and acquire monitoring data through the flow and pressure sensors; The data preprocessing module is used to upload the historical basic data and the monitoring data to the server through the data stream processing framework; The server performs preprocessing on the historical basic data and the monitoring data to obtain preprocessed data; The data batch processing module is used to build a relational database management system based on MySQL; through the relational database management system, Hadoop and Spark tools are used to batch process the preprocessed data to obtain batch-processed historical basic data and monitoring data; The rural pipeline water pressure prediction model construction and processing module is used to construct a rural pipeline water pressure prediction model; train the rural pipeline water pressure prediction model using the historical basic data to obtain a trained rural pipeline water pressure prediction model; input the batch-processed historical basic data and monitoring data into the trained rural pipeline water pressure prediction model to obtain rural pipeline water pressure prediction data through prediction; The burst pipe detection and water pressure control model construction and processing module is used to construct a burst pipe detection and water pressure control model; the batch-processed monitoring data and the predicted water pressure data of the rural pipe network are input into the burst pipe detection and water pressure control model, and the burst pipe detection and water pressure control model is used to detect and process the data, output a list of high-risk pipe sections and perform PID control; The rural water supply network geometric model construction module is used to collect physical data of the rural water supply network. Based on the physical data, a geometric model of the rural water supply network was constructed using ArcGIS. The rural water supply network system data model construction module is used to construct a rural water supply network system data model based on the rural network water pressure prediction model, the pipe burst detection and water pressure control model, and the rural water supply network geometric model. The rural water supply network system data model visualization output module is used to write the backend program of the rural water supply network system data model in Python. The rural water supply network system data model outputs time series curves of real-time data and predicted data to realize the visualization of the operation status of the water supply network.

6. The rural water supply network pressure monitoring and analysis device based on digital twin as described in claim 5, characterized in that, In the data preprocessing module, during the preprocessing of the historical basic data and the monitoring data by the server, the historical basic data is stored as a data sequence along with the temperature and humidity data, holiday information and week number data of the corresponding time node. For the monitoring data, the data for that hour and the predicted data obtained from the rural pipeline water pressure prediction model are stored as a data sequence. If there is no predicted data, the default value None is used. For abnormal data in the monitoring data, if the abnormality is a missing parameter value, the average of the corresponding data from the six hours before and after that hour is used to fill the gap; if the abnormality is a parameter value that repeats for a long time, the data from the same time period in the same month is used, multiplied by a deviation coefficient, and then used to fill the gap. The deviation coefficient is the average of the divisors of the non-repeating data from the same time period in the same month and the non-repeating data from the repetitive time period; if the abnormality is a parameter value fluctuation error, the average of the data from the same time period in recent days is used to fill the gap.

7. The rural water supply network pressure monitoring and analysis device based on digital twin as described in claim 6, characterized in that, In the rural pipeline water pressure prediction model construction and processing module, the expression of the rural pipeline water pressure prediction model is: ； In the formula, pre. This is the predicted value for a certain node; Time The time inertia term of this node includes the average water pressure in the previous time period, the average water pressure in the same month and week, the average water pressure in the same year and quarter, and the average water pressure in the same quarter and week of the previous three years. Space This is the spatial inertia term for this node, which includes the monitored water pressure of the upstream node during the same time period and the predicted water pressure of the upstream node during the same time period. This term does not exist for the initial calculation node. H This serves as the baseline for that node, representing the actual monitored water pressure at that node at the same moment. Q This is the water pressure correction term for this node, which includes the water volume monitoring values ​​of all nodes at the same time. ε This is the bias term for the node, used to explain any unconsidered patterns that may exist during model learning; α, β, γ, δ These are the learning rates for various parameters in the LSTM model, which are adjusted by the total hyperparameter lr and the model learning rate.

8. The rural water supply network pressure monitoring and analysis device based on digital twin as described in claim 7, characterized in that, The detection and evaluation sub-module in the pipe burst detection and water pressure control model construction and processing module includes: The data identification and labeling submodule is used to identify the batch-processed monitoring data and the rural pipeline water pressure prediction data through a decision tree model, output the risk of pipe burst, and label the risk of pipe burst. The low-explosion tube risk data optimization submodule is used to optimize the low-explosion tube risk data through fuzzy control strategies; The high-explosive pipe risk data processing submodule is used to monitor and process high-explosive pipe risk data over time; if the set time is exceeded, the log will be automatically uploaded and the monitoring personnel will be notified through the set method. The probability analysis submodule is used to analyze the probability of abnormal water pressure nodes and pipe bursts, output a list of high-risk pipe sections and perform PID control.

Images