An intelligent sewer network management system

Abstract

The application relates to the technical field of intelligent city management, in particular to an intelligent drainage pipe network management system, which comprises a drainage pipe network data monitoring module, a local health assessment module, an intelligent flow adjustment module, an abnormal fault identification module and an operation state optimization module.In the application, the accuracy of data integrity evaluation is improved, and the stability and reliability of data are enhanced through comprehensive monitoring and time series analysis of water flow velocity, pipeline pressure, fluid temperature, pipe wall vibration frequency and data transmission state, early warning capability for the health state of local pipelines can be improved through the analysis, flow distribution ratio calculation and identification of the flow difference ratio of adjacent pipelines, the pertinence of flow regulation is optimized, abnormal features and fault data are comprehensively analyzed to improve the refinement of fault diagnosis, and thus the operation state of the pipe network is optimized, and the management accuracy and operation stability of the whole are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent city management, and in particular to an intelligent drainage pipe network management system. Background Art

[0002] The field of smart city management technology includes the use of information technology, automation technology and intelligent means to efficiently manage and optimize the scheduling of urban public facilities and resources. The core content of this technology field is to achieve real-time monitoring, intelligent scheduling and automated management of urban infrastructure through sensors, network communications, data analysis and other means, thereby improving urban operation efficiency and residents' quality of life. Smart city management technology covers energy, transportation, environmental protection, drainage and other aspects. Among them, intelligent drainage management, as an important component, is committed to improving the management level of drainage pipelines and ensuring that urban drainage operates in an efficient and reliable state.

[0003] Among them, the intelligent drainage network management system refers to a system that uses sensors, communication networks and data processing technologies to perform real-time monitoring, data collection, analysis and processing, and fault warning management functions on the drainage network. The technical matters involved in the patent subject include real-time data collection and transmission of the drainage network, real-time monitoring of pipeline conditions, and analysis of the operating efficiency of the drainage system. The system collects key data such as water flow, pipeline pressure, and temperature through sensors installed in the pipeline network, and uses wireless communication technology to transmit the data to the central control platform. The pipeline network status is judged through data analysis and corresponding management decisions are made. The system can also automatically identify abnormal conditions in the pipeline, such as blockage, leakage, etc., and perform early warning processing to ensure the normal operation of the drainage network.

[0004] While existing technologies can collect data such as water flow, pipe pressure, and temperature from drainage networks through sensors and transmit it to a central control platform using wireless communication technology, they lack the ability to analyze data integrity and filter abnormal data. This can lead to abnormal fluctuations or loss of some data, affecting network status assessments and reducing data reliability. Assessments of pipeline health status lack analysis of trend change rates, making it difficult to accurately identify trends in pipeline operating conditions and preventing potential hazards from being discovered in a timely manner. Regarding flow control, existing technologies primarily rely on the overall flow status of the network for adjustments, failing to fully consider the flow distribution and difference ratios between adjacent pipelines. This leads to generalized flow adjustment strategies and difficulty in achieving local optimization. During abnormal fault identification, while existing technologies can detect problems such as pipeline blockages and leaks, they lack the specific classification of abnormalities and the detailed assessment of the impact range, resulting in misjudgments or delayed responses. Regarding operational status optimization, they fail to fully integrate upstream and downstream network pressure and flow data for dynamic adjustments, resulting in localized excessive pressure or uneven flow in some pipelines, impacting the stability of the overall drainage network. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent drainage network management system.

[0006] In order to achieve the above objectives, the present invention adopts the following technical solutions: an intelligent drainage network management system comprising:

[0007] The drainage network data monitoring module detects missing data in time series analysis based on drainage network data, calculates fluctuations based on adjacent time points, filters out abnormal data, analyzes data upload frequency to assess transmission anomalies, filters out data with errors that exceed the range, and obtains the drainage network data integrity index.

[0008] The local health assessment module extracts data of local drainage pipes based on the drainage pipe network data integrity index, calls the target time interval data to analyze the trend change rate, and obtains the local pipe health assessment value;

[0009] The intelligent flow adjustment module extracts drainage network node data based on the local pipeline health assessment value, calls adjacent pipeline data to identify flow difference ratios, filters out pipelines that exceed thresholds, and generates a flow balance adjustment parameter set;

[0010] The abnormal fault identification module calls the water flow state, pressure, and vibration characteristics of the pipeline in the abnormal area based on the flow balance adjustment parameter set, analyzes the abnormality category, calls the fault data, and obtains the pipeline abnormality impact range coefficient;

[0011] The operation status optimization module extracts the pressure data and flow status of the upstream and downstream pipeline networks based on the pipeline abnormality influence range coefficient, calls the flow balancing adjustment parameters to adjust the flow, and generates the intelligent drainage network operation management results.

[0012] As a further solution of the present invention, the drainage network data integrity index includes water flow velocity integrity, pipeline pressure integrity, fluid temperature integrity, pipe wall vibration frequency integrity, and data transmission status integrity; the local pipeline health assessment value includes water flow velocity change rate, pipeline pressure change rate, and pipe wall vibration frequency change rate; the flow balance adjustment parameter set includes flow distribution ratio, flow difference ratio, and pipeline exceeding threshold value; the pipeline abnormality impact range coefficient includes abnormality category, fault matching degree, and abnormality impact range; the intelligent drainage network operation management result includes pressure balance adjustment value, flow balance adjustment parameter, and optimized flow status.

[0013] As a further solution of the present invention, the drainage network data monitoring module includes:

[0014] The data anomaly detection submodule extracts water flow velocity, pipe pressure, fluid temperature, pipe wall vibration frequency, and data transmission status based on drainage network data. It detects missing time series data, calculates the volatility of adjacent time points, and filters data with volatility exceeding the threshold to obtain data fluctuation anomalies.

[0015] The data transmission analysis submodule analyzes the data upload frequency based on the data fluctuation abnormal value, identifies the data transmission time interval, compares it with the benchmark value, filters the abnormal interval data, and obtains the data transmission abnormal value;

[0016] The data integrity assessment submodule calls the data fluctuation anomaly and data transmission anomaly to filter out the data with errors exceeding the range, using the formula:

[0017] ;

[0018] Calculate the drainage network data integrity index;

[0019] in, represents the drainage network data integrity index, represents the effectiveness score of the i-th data point, represents the average effectiveness score of the data points, represents the maximum effectiveness score, Represents the total number of data points, Represents the cumulative value of the abnormal data transmission time interval, Represents the total time of data transmission.

[0020] As a further solution of the present invention, the local health assessment module includes:

[0021] The flow rate measurement submodule calls the pipeline flow data and pipeline cross-sectional area data within the target time interval based on the drainage network data integrity index, filters abnormal flow rate data and makes corrections using the formula:

[0022] ;

[0023] Call the pipeline water flow parameters to obtain the water flow speed adjustment value;

[0024] in, Represents the water flow speed adjustment value, Represents the pipeline flow data within the target time interval, Represents the pipe cross-sectional area data, represents the pipeline pressure difference, represents the density of water, represents the length of the pipeline, represents the flow rate correction factor;

[0025] The pipe pressure monitoring submodule calls the water flow velocity adjustment value, combines the pipe wall thickness data and the pipe material data, analyzes the pressure distribution inside the pipe, compares the pipe safety pressure threshold, screens abnormal points, and obtains the pipe pressure assessment value;

[0026] The pipe wall structure vibration assessment submodule, based on the pipeline pressure assessment value, calls the pipe wall vibration frequency data, identifies the vibration amplitude, filters abnormal signals, analyzes the pipeline structure stability, calls the target time interval data, and analyzes the trend change rate to obtain the local pipeline health assessment value.

[0027] As a further solution of the present invention, the intelligent flow adjustment module includes:

[0028] The pipeline water flow parameter calculation submodule extracts the water flow velocity, flow rate, and pressure of the drainage network node based on the local pipeline health assessment value, analyzes the flow distribution ratio of the pipeline section, and obtains the water flow balance parameter set;

[0029] The flow difference ratio identification submodule calls the water flow balance parameter set to identify the flow difference ratios of adjacent pipes and screen out pipes that exceed the flow threshold using the formula:

[0030] ;

[0031] Calculate the flow difference ratio, filter out the pipes outside the threshold, and obtain a list of pipes exceeding the threshold;

[0032] in, represents the flow difference ratio, 、 represents the pipeline flow distribution ratio, 、 represents the pipe water pressure, 、 represents the pipeline flow rate, 、 Represents the water flow velocity in the pipe;

[0033] The flow balancing parameter acquisition submodule identifies flow adjustment parameters based on the list of pipelines exceeding the threshold, optimizes the flow balancing coefficient, adjusts the flow distribution, and obtains a flow balancing adjustment parameter set.

[0034] As a further solution of the present invention, the abnormal fault identification module includes:

[0035] The abnormal area data extraction submodule calls the water flow state, pressure, and vibration characteristics of the abnormal area pipeline based on the flow balance adjustment parameter set, extracts the instantaneous flow velocity, flow change trend, and flow velocity fluctuation range, analyzes the pressure fluctuation, calculates the vibration frequency, and obtains the abnormal area pipeline feature data set;

[0036] The fault category analysis submodule calls the pipeline feature dataset of the abnormal area, analyzes the water flow state, pressure, and vibration data, and identifies the vibration characteristics, pressure change, and flow balance adjustment parameters of the differentiated pipelines using the formula:

[0037] ;

[0038] Determine the fault category, match known fault mode data, and obtain the fault category matching value;

[0039] in, Represents the fault category matching value, Representative The vibration characteristic value of each pipe, Represents the pressure change of the corresponding pipe section, Represents the flow balancing adjustment parameter, Indicates the total number of pipelines;

[0040] The abnormal impact range identification submodule calls the fault data based on the fault category matching value, screens the pipelines matching the fault mode, analyzes the impact range, and obtains the pipeline abnormal impact range coefficient according to the pipeline structure relationship.

[0041] As a further solution of the present invention, the operating state optimization module includes:

[0042] The abnormal impact range assessment submodule extracts the pressure data and flow status of the upstream and downstream pipeline networks based on the pipeline abnormal impact range coefficient, analyzes the abnormal impact range, screens the pipeline pressure mutation area, and obtains the pipeline pressure mutation area distribution data;

[0043] The pressure equalization adjustment calculation submodule calls the pipeline pressure mutation area distribution data, identifies the pressure equalization adjustment value, identifies the pressure fluctuation trend, and uses the formula:

[0044] ;

[0045] Calculate the pressure balance offset, compare it with the balance threshold, and obtain the pressure adjustment amount;

[0046] in, Represents the pressure equalization deviation, represents the pressure value of the pipe network at location j, Represents the average pressure of the entire pipe network, represents the flow rate of the pipe network at the jth location, represents the average flow rate of the entire pipe network, Represents the number of pressure mutation areas;

[0047] The flow balance optimization submodule calls the pressure adjustment amount, adjusts the flow balance parameters, analyzes the flow change trend, screens and optimizes the flow distribution, and obtains the intelligent drainage network operation management results.

[0048] Compared with the prior art, the advantages and positive effects of the present invention are:

[0049] In the present invention, by comprehensively monitoring the water flow velocity, pipeline pressure, fluid temperature, pipe wall vibration frequency, and data transmission status, and combining the time series analysis of data missing conditions, the assessment accuracy of the integrity of the drainage network data is improved, the interference of abnormal data on the analysis results is reduced, the fluctuation rate is calculated by combining adjacent time points, abnormal data is screened, and the data upload frequency is analyzed, the stability and reliability of the data are enhanced, and the data integrity index can accurately reflect the status of the pipeline network. Based on the data integrity index, the key parameters of the local pipeline are further extracted, and the health status of the pipeline is accurately identified by calculating the trend change rate of the target time interval, thereby improving the detection of local pipeline abnormalities. The early warning capability of the situation is improved by calculating the flow distribution ratio, calling the adjacent pipeline data to identify the flow difference ratio, and screening the pipelines that exceed the threshold, so as to improve the accuracy of flow balancing adjustment and make flow control more targeted. Abnormal fault identification is based on the flow balancing adjustment parameter set, combined with the water flow state, pressure, and vibration characteristics, to analyze the abnormal category, and evaluate the abnormal impact range through the fault data matching degree, so as to make the pipeline abnormality diagnosis more refined. Combined with the upstream and downstream pipeline pressure data and flow state, by calculating the pressure balancing adjustment value and flow balancing adjustment parameters, the pipeline network operation status is optimized, and the overall operation stability and management accuracy of the drainage pipeline network are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a system flow chart of the present invention;

[0051] Figure 2 This is a flow chart for obtaining the drainage network data monitoring module in the present invention;

[0052] Figure 3 This is a flowchart of obtaining the local health assessment module in the present invention;

[0053] Figure 4 This is a flowchart of obtaining the intelligent flow adjustment module in the present invention;

[0054] Figure 5 This is a flowchart of obtaining the abnormal fault identification module in the present invention;

[0055] Figure 6 This is a flowchart for obtaining the operating status optimization module in the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0057] In the description of the present invention, it should be understood that the terms "length," "width," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended only to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, in the description of the present invention, "plurality" means two or more, unless otherwise expressly and specifically defined.

[0058] See also Figure 1 , an intelligent drainage network management system includes:

[0059] The drainage network data monitoring module collects data from the drainage network, including water flow velocity, pipe pressure, fluid temperature, pipe wall vibration frequency, and data transmission status. It detects missing data in time series analysis, calculates fluctuations based on adjacent time points, filters out abnormal data, analyzes data upload frequency to assess transmission anomalies, filters data with errors exceeding the specified range, and obtains a drainage network data integrity index.

[0060] The local health assessment module extracts the water velocity, pipe pressure, and pipe wall vibration frequency of the local drainage pipe based on the drainage network data integrity index. It then uses the target time interval data to analyze the trend change rate and obtain the local pipeline health assessment value.

[0061] The intelligent flow adjustment module extracts the water velocity, flow rate, and pressure of drainage network nodes based on local pipeline health assessment values, calculates the flow distribution ratio, calls adjacent pipeline data to identify flow difference ratios, filters out pipelines that exceed thresholds, and generates a flow balancing adjustment parameter set.

[0062] The abnormal fault identification module uses the flow balance adjustment parameter set to call the water flow state, pressure, and vibration characteristics of the pipeline in the abnormal area, analyze the abnormality category, call the fault data to identify the matching degree, and obtain the pipeline abnormality impact range coefficient;

[0063] The operation status optimization module extracts the pressure data and flow status of the upstream and downstream pipeline networks based on the pipeline abnormality influence range coefficient, calculates the pressure equalization adjustment value, calls the flow equalization adjustment parameter to adjust the flow, and generates the intelligent drainage network operation management results.

[0064] The drainage network data integrity index includes water flow velocity integrity, pipeline pressure integrity, fluid temperature integrity, pipe wall vibration frequency integrity, and data transmission status integrity. The local pipeline health assessment value includes the water flow velocity change rate, pipeline pressure change rate, and pipe wall vibration frequency change rate. The flow balance adjustment parameter set includes the flow distribution ratio, flow difference ratio, and pipelines exceeding the threshold. The pipeline abnormality impact range coefficient includes the abnormality category, fault matching degree, and abnormality impact range. The intelligent drainage network operation management results include pressure balance adjustment value, flow balance adjustment parameters, and optimized flow status.

[0065] See also Figure 2 , the drainage network data monitoring module includes:

[0066] The data anomaly detection submodule extracts water flow velocity, pipe pressure, fluid temperature, pipe wall vibration frequency, and data transmission status based on drainage network data. It detects missing time series data, calculates the volatility of adjacent time points, and filters data with volatility exceeding the threshold to obtain data fluctuation anomalies.

[0067] First, install corresponding sensors at key nodes of the drainage network. For example, arrange flow rate sensors and pressure sensors at the intersection of the main pipeline and the branch line to monitor the water flow rate and pressure in the pipeline in real time. Assume that the normal water flow rate of a certain pipe section is 1.5 m / s, the pipeline pressure is 0.2 MPa, the fluid temperature is 20 degrees Celsius, the pipe wall vibration frequency is 50 Hz, and the data transmission status is once per minute. Detect missing data in the collected time series data. For example, there should be 60 data points in a certain period of time, but in reality, Only 55 data points are received, so there are 5 missing data points. The missing rate is calculated as (5 / 60)×100%=8.33%. The fluctuation rate of adjacent time points is calculated. Taking the water flow velocity as an example, if the speed measured at time t1 is 1.5 m / s and at time t2 is 1.8 m / s, the fluctuation rate is ((1.8-1.5) / 1.5)×100%=20%. If the fluctuation rate threshold is set to 15%, the change exceeds the threshold and needs to be marked as an anomaly. All abnormal data exceeding the set threshold are filtered out to obtain the data fluctuation anomaly value.

[0068] The data transmission analysis submodule analyzes the data upload frequency based on the data fluctuation anomaly, identifies the data transmission time interval, compares it with the benchmark value, filters the abnormal interval data, and obtains the data transmission anomaly value;

[0069] First, count the time intervals for data transmission. For example, ideally, data should be uploaded once every minute. However, in actual monitoring, some time intervals are found to exceed 1 minute. Suppose that within a certain period of time, the time intervals for data transmission are 1 minute, 1.5 minutes, 2 minutes, 1 minute, 0.5 minutes, etc., and the intervals of 1.5 minutes and 2 minutes exceed the set 1-minute benchmark value and are marked as abnormal. Calculate the cumulative value of the abnormal intervals. For example, in the above example, the cumulative abnormal intervals are (1.5-1)+(2-1)=1.5 minutes. Filter out the data points with abnormal time intervals to obtain the data transmission abnormal value.

[0070] The data integrity assessment submodule calls data fluctuation anomalies and data transmission anomalies to filter out data with errors exceeding the range, using the formula:

[0071] ;

[0072] Calculate the drainage network data integrity index;

[0073] in, represents the drainage network data integrity index, represents the effectiveness score of the i-th data point, represents the average effectiveness score of the data points, represents the maximum effectiveness score, Represents the total number of data points, Represents the cumulative value of the abnormal data transmission time interval, Represents the total time of data transmission;

[0074] Call data fluctuation anomalies and data transmission anomalies to filter out data with errors exceeding the set range. Set an error range, such as ±10%. For data outside this range, mark it as abnormal and calculate the data integrity score;

[0075] Assume that during a monitoring period, 100 data points are collected, of which 80 have an effectiveness score of 90 and 20 have an effectiveness score of 70. , , the cumulative value of abnormal data transmission time interval Total transfer time is 5 minutes Assuming the time is 100 minutes, substitute the value into the formula and calculate:

[0076] ;

[0077] ;

[0078] ;

[0079] ;

[0080] The results show that the integrity index of the drainage network data is approximately 0.8825, which is close to 1, indicating that the data integrity is high.

[0081] See also Figure 3 , the local health assessment module includes:

[0082] The flow rate measurement submodule is based on the drainage network data integrity index, calls the pipeline flow data and pipeline cross-sectional area data within the target time interval, filters out abnormal flow rate data and makes corrections using the formula:

[0083] ;

[0084] Call the pipeline water flow parameters to obtain the water flow speed adjustment value;

[0085] in, Represents the water flow speed adjustment value, Represents the pipeline flow data within the target time interval, Represents the pipe cross-sectional area data, represents the pipeline pressure difference, represents the density of water, represents the length of the pipeline, represents the flow rate correction factor;

[0086] First, based on the drainage pipeline data integrity index, the pipeline flow data and pipeline cross-sectional area data within the target time interval are retrieved. This process can be exemplified in urban drainage, where the flow and cross-sectional data within a continuous time period are obtained through a monitoring system. For specific examples, such as during the flood season, the flow increase in a specific pipe section is monitored and the water flow velocity in the pipe is calculated. The formula involves dividing the flow by the cross-sectional area to obtain a preliminary flow velocity. Considering that the cross-sectional area actually decreases due to sediment accumulation in actual applications, the flow velocity data needs to be adjusted, and abnormal flow velocity data needs to be screened and corrected. If the flow velocity of a certain section of the pipe is found to be significantly lower than that of the surrounding area, further inspection and correction are required, such as adjusting for the change in cross-sectional area caused by sediment. The corrected flow velocity is closer to the actual situation. This corrected value will support decision-making on maintenance work and preventive measures.

[0087] Item 1 represents the preliminary water velocity calculated based on the flow rate and cross-sectional area;

[0088] Item 2 Represents the correction amount for flow rate based on pipeline pressure difference, where the pressure difference affects the change of flow rate, while density and pipeline length are used to normalize the effect. The correction coefficient Represents the empirical correction factor under different pipeline environments;

[0089] Data sources and assumptions:

[0090] Monitored traffic data (Based on the water flow monitoring system);

[0091] Calculated cross-sectional area (Depending on the pipe diameter Calculated, the formula );

[0092] Pressure differential measured on site (monitored by pressure sensor);

[0093] Density of water (standard density of fresh water);

[0094] Pipeline length (field measurement);

[0095] Experience correction factor (Selected based on pipe type and roughness coefficient);

[0096] Substitute the values ​​into the calculation:

[0097] ;

[0098] Calculate step by step:

[0099] ;

[0100] ;

[0101] ;

[0102] The final calculated water velocity adjustment value is 1.6012 m / s. This result can be used to further calculate the pipeline pressure assessment value and serve as input data for subsequent analysis.

[0103] The pipe pressure monitoring submodule uses the water flow velocity adjustment value, combines the pipe wall thickness data and pipe material data, analyzes the pressure distribution inside the pipe, compares the pipe safety pressure threshold, screens abnormal points, and obtains the pipe pressure assessment value;

[0104] First, the water velocity calculation results obtained by the water velocity calculation submodule are called. For example, in an industrial drainage system, flow velocity data is collected by flowmeters installed in specific areas of the pipeline. This data is combined with pipe wall thickness and material data (e.g., 5mm wall thickness and PVC material). This data is provided by the manufacturer or obtained through field measurements. The pressure distribution within the pipeline is then calculated using basic fluid mechanics formulas, such as pressure = flow velocity × density × acceleration due to gravity. The pipe material and wall thickness have a significant impact on the pressure distribution, such as the elasticity of PVC, which affects its pressure tolerance. The pressure is then compared to the pipeline's safety pressure threshold, which is set based on the pipeline material and design standards. For example, the safe working pressure of PVC pipe is set at 0.6 MPa. By comparing the actual calculated pressure with the safety threshold, abnormal pressure points outside the safety range are screened out and trend analysis is performed. The results are used to assess the pipeline's safety status and guide maintenance work. Ultimately, a pipeline pressure assessment is obtained, which is used to formulate emergency response and long-term maintenance strategies.

[0105] The pipe wall structure vibration assessment submodule uses pipe wall vibration frequency data based on the pipeline pressure assessment value, identifies vibration amplitude, filters abnormal signals, analyzes pipeline structure stability, calls target time interval data, and analyzes trend change rates to obtain local pipeline health assessment values.

[0106] First, based on the pipeline pressure assessment value, pipe wall vibration frequency data is retrieved. This data can be obtained by installing vibration sensors in the pipeline system for real-time monitoring. For example, vibration sensors can be installed in the main drainage pipe under a bridge to monitor changes in vibration frequency caused by traffic flow and calculate the vibration amplitude. This calculation process can be performed using the formula: vibration amplitude = vibration energy / mass. For example, if the actual measured vibration energy and pipe material mass are 200J and the pipe mass is 50kg, the vibration amplitude is 4. Abnormal vibration signals are screened and those that exceed the normal range are analyzed in detail. For example, a sudden increase in vibration amplitude is found to be caused by construction activities near the pipeline. The vibration stability threshold is compared. The threshold is set based on historical data and engineering experience. For example, the vibration threshold under normal operating conditions is set to 3. Through analysis, the stability of the pipeline structure is assessed. Data for the target time interval is retrieved and the trend change rate is analyzed to obtain a local pipeline health assessment value, providing a quantitative method to assess pipeline health and prevent potential risks.

[0107] See also Figure 4 , the intelligent traffic shaping module includes:

[0108] The pipeline water flow parameter calculation submodule extracts the water flow velocity, flow rate, and pressure of the drainage network nodes based on the local pipeline health assessment value, analyzes the flow distribution ratio of the pipeline section, and obtains the water flow balance parameter set;

[0109] First, data on water velocity, flow rate, and pressure are obtained for each node in the drainage network. For example, in a certain urban drainage system, monitoring equipment records a water velocity of 1.5 m / s, a flow rate of 0.75 m3 / s, and a pressure of 200 kPa at Node A. The flow distribution ratio for each pipe section is calculated. Assuming the cross-sectional area of ​​the pipe between Node A and Node B is 0.5 m2, the flow distribution ratio for this section is 0.75 m3 / s ÷ 0.5 m2 = 1.5 m / s. The flow parameters for each node are normalized to eliminate the effects of different pipe sizes and flow rates and ensure data comparability. The flow balance of each pipe section is calculated to assess whether the flow distribution is uniform. For example, if the flow rate of a pipe section is significantly higher than that of an adjacent section, there is a problem of uneven flow distribution. A set of flow balance parameters is obtained, providing data for subsequent flow difference analysis.

[0110] The flow difference ratio identification submodule calls the water flow balance parameter set to identify the flow difference ratio of adjacent pipes and screen out pipes that exceed the flow threshold using the formula:

[0111] ;

[0112] Calculate the flow difference ratio, filter out the pipes outside the threshold, and obtain a list of pipes exceeding the threshold;

[0113] in, represents the flow difference ratio, 、 represents the pipeline flow distribution ratio, 、 represents the pipe water pressure, 、 represents the pipeline flow rate, 、 Represents the water flow velocity in the pipe;

[0114] First, calculate the flow difference ratio between adjacent pipes. For example, assume that the flow distribution ratio of pipe 1 is 1.2, the water pressure is 150 kPa, the flow rate is 0.6 cubic meters per second, and the water velocity is 1.0 m / s; and the flow distribution ratio of pipe 2 is 1.5, the water pressure is 180 kPa, the flow rate is 0.9 cubic meters per second, and the water velocity is 1.2 m / s. Substituting the above values ​​into the formula, we get:

[0115] ;

[0116] Set the threshold of the flow difference ratio, for example, 2.5, and compare the calculation results. If If the value is greater than the threshold, it is determined that the pipeline has flow anomaly. In this example, If the value is greater than 2.5, the pipeline is marked as exceeding the threshold, and a list of pipelines exceeding the threshold is generated to provide a basis for subsequent traffic balancing adjustments.

[0117] The flow balancing parameter acquisition submodule identifies the flow adjustment parameters based on the list of pipelines exceeding the threshold, optimizes the flow balancing coefficient, adjusts the flow distribution, and obtains the flow balancing adjustment parameter set;

[0118] First, for each pipeline that exceeds the threshold, analyze the flow difference between it and the adjacent pipelines. For example, the flow of a pipeline that exceeds the threshold is 0.9 cubic meters per second, while the average flow of the adjacent pipelines is 0.6 cubic meters per second, which is a significant difference. Calculate the flow parameters that need to be adjusted to achieve flow balance. Assuming that the goal is to reduce the flow of the pipeline to a level close to the average flow of the adjacent pipelines, that is, 0.6 cubic meters per second, the flow difference that needs to be adjusted is 0.9-0.6=0.3 cubic meters per second. Determine the adjustment plan, such as by adjusting the valve opening, increasing or decreasing the pipe diameter, etc., to achieve precise control of the flow rate. Generate a flow balance adjustment parameter set, including the adjustment plan and specific parameters for each pipeline that exceeds the threshold, to provide guidance for flow optimization of the pipeline network.

[0119] See also Figure 5 , the abnormal fault identification module includes:

[0120] The abnormal area data extraction submodule uses the flow balance adjustment parameter set to call the water flow state, pressure, and vibration characteristics of the abnormal area pipeline, extract the instantaneous flow velocity, flow change trend, flow velocity fluctuation range, analyze the pressure fluctuation, calculate the vibration frequency, and obtain the abnormal area pipeline feature data set;

[0121] First, the pipeline water flow state is extracted, including instantaneous flow velocity, flow change trend, and flow velocity fluctuation range. When obtaining flow velocity data, the water flow rate within a specific time period is monitored by a flow sensor, and the flow fluctuation trend is calculated using a moving average. At the same time, the flow velocity variation coefficient is calculated to characterize the degree of fluctuation. The pipeline pressure data is collected, and the pressure change value at each time node is recorded by a pressure sensor. The pressure change rate is calculated to determine whether there is abnormal pressure fluctuation. The pipeline vibration characteristics are measured, the change value of the pipe wall vibration acceleration is recorded, and the vibration frequency is calculated. The vibration characteristic spectrum is analyzed by Fourier transform, the high-frequency vibration point is identified, and the root mean square value of the vibration signal is calculated. Based on the above extracted data, the pipeline state parameter matrix is ​​constructed, including a multi-dimensional data combination of flow, pressure, and vibration characteristics to form a pipeline characteristic data set in the abnormal area.

[0122] The fault category analysis submodule calls the pipeline feature dataset in the abnormal area, analyzes the water flow state, pressure, and vibration data, and identifies the vibration characteristics, pressure changes, and flow balance adjustment parameters of differentiated pipelines using the formula:

[0123] ;

[0124] Determine the fault category, match known fault mode data, and obtain the fault category matching value;

[0125] in, Represents the fault category matching value, Representative The vibration characteristic value of each pipe, Represents the pressure change of the corresponding pipe section, Represents the flow balancing adjustment parameter, Indicates the total number of pipelines;

[0126] Calculate the vibration characteristic values, pressure changes, and flow balance adjustment parameters of different pipelines. The vibration characteristic values ​​are measured by acceleration sensors and converted into frequency characteristics. The pressure changes are calculated through time series analysis to quantify the local pressure fluctuations in the pipeline. The flow balance adjustment parameters are derived from historical flow data and flow deviation calculations.

[0127] Assume that the vibration characteristic values ​​of a pipeline are 、 、 , and the corresponding pressure change is kPa, kPa, kPa, flow balance adjustment parameter , the calculation process is as follows:

[0128] calculate :

[0129] , , ;

[0130] Compute the weighted sum term:

[0131] ;

[0132] Calculate the final matching value: ;

[0133] Calculate the fault category matching value ,This value is used to match known fault patterns, determine the category of pipeline anomalies, and obtain the fault category matching value.

[0134] The abnormal impact range identification submodule calls fault data based on the fault category matching value, screens pipelines that match the fault mode, analyzes the impact range, and obtains the pipeline abnormal impact range coefficient based on the pipeline structure relationship;

[0135] First, historical fault records that match the current pipeline fault category are screened out. The pipeline material, pipeline structure, and flow status in the historical data are compared to ensure that the selected historical data are similar to the current pipeline condition. The impact range is calculated. Based on the structural relationship between pipelines, an impact propagation matrix is ​​constructed, the connection coefficient between adjacent pipelines is set, and the impact factor between each pipeline is calculated. Combined with the faulty pipe section matching data, the impact range of the abnormal fault is comprehensively calculated to obtain the pipeline abnormal impact range coefficient.

[0136] See also Figure 6 , the operation status optimization module includes:

[0137] The abnormal impact range assessment submodule extracts the pressure data and flow status of the upstream and downstream pipeline networks based on the pipeline abnormal impact range coefficient, analyzes the abnormal impact range, screens the pipeline pressure mutation area, and obtains the pipeline pressure mutation area distribution data;

[0138] First, sensors collect real-time upstream and downstream pressure and flow data. This data is then wirelessly transmitted to a central processing system, where it undergoes preliminary screening to remove any obvious anomalies or errors. For example, if the detected pressure suddenly drops to an abnormally low level, the system will determine that it is a sensor failure or a data transmission error. Statistical analysis is then performed on the remaining valid data, calculating the average pressure and flow for each area and plotting time series graphs of the pressure and flow. Graphical analysis identifies abnormal fluctuations in pressure or flow. For example, if the flow in a certain area suddenly increases within a short period of time, this indicates a pipeline leak or illegal water use. This analysis ultimately identifies the specific areas affected by the pipeline anomaly, generating regional distribution data for pipeline pressure mutations for further analysis and processing. For example, in one case study, data analysis identified unstable pressure in the water supply line in the city's southern new district. The problem area was quickly located and repairs were prepared. This method enables real-time monitoring and rapid response to the city's water supply system, ensuring water supply safety and efficiency.

[0139] The pressure equalization adjustment calculation submodule calls the pipeline pressure mutation area distribution data, identifies the pressure equalization adjustment value, and identifies the pressure fluctuation trend using the formula:

[0140] ;

[0141] Calculate the pressure balance offset, compare it with the balance threshold, and obtain the pressure adjustment amount;

[0142] in, Represents the pressure equalization deviation, represents the pressure value of the pipe network at location j, Represents the average pressure of the entire pipe network, represents the flow rate of the pipe network at the jth location, represents the average flow rate of the entire pipe network, Represents the number of pressure mutation areas;

[0143] First, using the acquired pipeline pressure mutation regional distribution data, the specific locations of all pressure mutations are marked on the map through the GIS system. For example, in a city water supply network, abnormal pressure fluctuations in four areas A, B, C, and D are found. The average pressure value of each marked area is calculated using statistical analysis software. , and based on this, the actual pressure in each area Compare and calculate the deviation from the average pressure, which is used to assess whether the pressure needs to be adjusted;

[0144] The specific calculation is as follows: Assuming the pressure in area A MPa, pressure in area B MPa, C area pressure MPa, D area pressure MPa;

[0145] Then the average pressure is: ;

[0146] Then calculate the pressure deviation of each area:

[0147] ;

[0148] ;

[0149] ;

[0150] ;

[0151] Get the total pressure deviation:

[0152] ;

[0153] Recalculate traffic data Deviation, assuming that the flow rates of the four areas A, B, C, and D are L / s, L / s, L / s, L / s, then:

[0154] ;

[0155] Calculate the sum of squares of flow deviations:

[0156] ;

[0157] ;

[0158] ;

[0159] ;

[0160] ;

[0161] Final calculation of pressure equalization deviation :

[0162] ;

[0163] Assuming the pressure equalization threshold is set to 25, after comparison, it is found that It is greater than the threshold of 25, so the system needs to adjust the pressure and generate a pressure adjustment amount. Specific adjustment measures include reducing the flow in areas B and C where the pressure is too high, and increasing the flow in areas A and D where the pressure is lower, so that the pressure in the pipe network tends to be balanced, thereby optimizing the operating efficiency of the overall water supply scheduling system and ensuring stable water supply in each area.

[0164] The flow balance optimization submodule calls the pressure adjustment amount, adjusts the flow balance parameters, analyzes the flow change trend, screens and optimizes the flow distribution, and obtains the operation and management results of the intelligent drainage network;

[0165] First, based on the pressure adjustment amount obtained in the previous step, the setting parameters of the flow controller are adjusted to match the adjusted pressure demand. This is completed by the automatic control system. The system calculates the corresponding flow adjustment parameters based on the input pressure adjustment amount, monitors the flow changes after adjustment, and analyzes the stability of the flow and the speed of achieving the expected effect through continuous flow and pressure data collection. If it is found that the flow fails to achieve the expected adjustment effect, the parameters are adjusted again until the flow stabilizes in the ideal state. For example, in a practical application case, the problem of insufficient water supply in the industrial zone during peak hours was successfully solved through meticulous flow regulation, and finally the intelligent drainage network operation management results were generated, which not only optimized the water pressure and flow distribution of the entire industrial zone, but also continuously monitored the system operation status through the data feedback mechanism, providing stable and reliable water resource support for industrial users.

[0166] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. An intelligent drainage network management system, characterized in that: The system comprises: The drainage network data monitoring module detects missing data in time series analysis based on drainage network data, calculates fluctuations based on adjacent time points, filters out abnormal data, analyzes data upload frequency to assess transmission anomalies, filters out data with errors that exceed the range, and obtains the drainage network data integrity index. The local health assessment module extracts data of local drainage pipes based on the drainage pipe network data integrity index, calls the target time interval data to analyze the trend change rate, and obtains the local pipe health assessment value; The intelligent flow adjustment module extracts drainage network node data based on the local pipeline health assessment value, calls adjacent pipeline data to identify flow difference ratios, filters out pipelines that exceed thresholds, and generates a flow balance adjustment parameter set; The abnormal fault identification module calls the water flow state, pressure, and vibration characteristics of the pipeline in the abnormal area based on the flow balance adjustment parameter set, analyzes the abnormality category, calls the fault data, and obtains the pipeline abnormality impact range coefficient; The operation status optimization module extracts the pressure data and flow status of the upstream and downstream pipe networks based on the pipeline abnormality influence range coefficient, calls the setting parameters of the flow controller to adjust the flow, and generates the intelligent drainage pipe network operation management results; The operating state optimization module includes: The abnormal impact range assessment submodule extracts the pressure data and flow status of the upstream and downstream pipeline networks based on the pipeline abnormal impact range coefficient, analyzes the abnormal impact range, screens the pipeline pressure mutation area, and obtains the pipeline pressure mutation area distribution data; The pressure equalization adjustment calculation submodule calls the pipeline pressure mutation area distribution data, identifies the pressure equalization adjustment value, identifies the pressure fluctuation trend, and uses the formula: ； Calculate the pressure balance offset, compare it with the balance threshold, and obtain the pressure adjustment amount; in, Represents the pressure equalization deviation, represents the pressure value of the pipe network at location j, Represents the average pressure of the entire pipe network, represents the flow rate of the pipe network at the jth location, represents the average flow rate of the entire pipe network, Represents the number of pressure mutation areas; The flow balance optimization submodule calls the pressure adjustment amount, adjusts the setting parameters of the flow controller, analyzes the flow change trend, screens and optimizes the flow distribution, and obtains the operation management results of the intelligent drainage network.

2. The intelligent drainage network management system according to claim 1, characterized in that: The drainage network data integrity index includes water flow velocity integrity, pipeline pressure integrity, fluid temperature integrity, pipe wall vibration frequency integrity, and data transmission status integrity. The local pipeline health assessment value includes the water flow velocity change rate, pipeline pressure change rate, and pipe wall vibration frequency change rate. The flow balance adjustment parameter set includes the flow distribution ratio, flow difference ratio, and pipelines exceeding the threshold. The pipeline abnormality impact range coefficient includes the abnormality category, fault matching degree, and abnormality impact range. The intelligent drainage network operation management results include the pressure balance adjustment value, the setting parameters of the flow controller, and the optimized flow status.

3. The intelligent drainage network management system according to claim 1, characterized in that: The drainage network data monitoring module includes: The data anomaly detection submodule extracts water flow velocity, pipe pressure, fluid temperature, pipe wall vibration frequency, and data transmission status based on drainage network data. It detects missing time series data, calculates the volatility of adjacent time points, and filters data with volatility exceeding the threshold to obtain data fluctuation anomalies. The data transmission analysis submodule analyzes the data upload frequency based on the data fluctuation abnormal value, identifies the data transmission time interval, compares it with the benchmark value, filters the abnormal interval data, and obtains the data transmission abnormal value; The data integrity assessment submodule calls the data fluctuation anomaly and data transmission anomaly to filter out the data with errors exceeding the range, using the formula: ； Calculate the drainage network data integrity index; in, represents the drainage network data integrity index, represents the effectiveness score of the i-th data point, represents the average effectiveness score of the data points, represents the maximum effectiveness score, Represents the total number of data points, Represents the cumulative value of the abnormal data transmission time interval, Represents the total time of data transmission.

4. The intelligent drainage network management system according to claim 2, characterized in that: The local health assessment module includes: The flow rate measurement submodule calls the pipeline flow data and pipeline cross-sectional area data within the target time interval based on the drainage network data integrity index, filters abnormal flow rate data and makes corrections using the formula: ； Call the pipeline water flow parameters to obtain the water flow speed adjustment value; in, Represents the water flow speed adjustment value, Represents the pipeline flow data within the target time interval, Represents the pipe cross-sectional area data, represents the pipeline pressure difference, represents the density of water, represents the length of the pipeline, represents the flow rate correction factor; The pipe pressure monitoring submodule calls the water flow velocity adjustment value, combines the pipe wall thickness data and the pipe material data, analyzes the pressure distribution inside the pipe, compares the pipe safety pressure threshold, screens abnormal points, and obtains the pipe pressure assessment value; The pipe wall structure vibration assessment submodule, based on the pipeline pressure assessment value, calls the pipe wall vibration frequency data, identifies the vibration amplitude, filters abnormal signals, analyzes the pipeline structure stability, calls the target time interval data, and analyzes the trend change rate to obtain the local pipeline health assessment value.

5. The intelligent drainage network management system according to claim 3, characterized in that: The intelligent flow adjustment module includes: The pipeline water flow parameter calculation submodule extracts the water flow velocity, flow rate, and pressure of the drainage network node based on the local pipeline health assessment value, analyzes the flow distribution ratio of the pipeline section, and obtains the water flow balance parameter set; The flow difference ratio identification submodule calls the water flow balance parameter set to identify the flow difference ratios of adjacent pipes and screen out pipes that exceed the flow threshold using the formula: ； Calculate the flow difference ratio, filter out the pipes outside the threshold, and obtain a list of pipes exceeding the threshold; in, represents the flow difference ratio, 、 represents the pipe flow distribution ratio of adjacent pipes, 、 represents the pipe water pressure of the adjacent pipe, 、 represents the pipe flow rate of the adjacent pipe, 、 represents the pipe water velocity in the adjacent pipe; The flow balancing parameter acquisition submodule identifies flow adjustment parameters based on the list of pipelines exceeding the threshold, optimizes the flow balancing coefficient, adjusts the flow distribution, and obtains a flow balancing adjustment parameter set.

6. The intelligent drainage network management system according to claim 4, characterized in that: The abnormal fault identification module includes: The abnormal area data extraction submodule calls the water flow state, pressure, and vibration characteristics of the abnormal area pipeline based on the flow balance adjustment parameter set, extracts the instantaneous flow velocity, flow change trend, and flow velocity fluctuation range, analyzes the pressure fluctuation, calculates the vibration frequency, and obtains the abnormal area pipeline feature data set; The fault category analysis submodule calls the pipeline feature dataset of the abnormal area, analyzes the water flow state, pressure, and vibration data, and identifies the vibration characteristics, pressure change, and flow balance adjustment parameters of the differentiated pipelines using the formula: ； Determine the fault category, match known fault mode data, and obtain the fault category matching value; in, Represents the fault category matching value, Representative The vibration characteristic value of each pipe, Represents the pressure change of the corresponding pipe section, Represents the flow balancing adjustment parameter, Indicates the total number of pipelines; The abnormal impact range identification submodule calls the fault data based on the fault category matching value, screens the pipelines matching the fault mode, analyzes the impact range, and obtains the pipeline abnormal impact range coefficient according to the pipeline structure relationship.

Images