A multi-level water supply and drainage balance monitoring method and system for the water industry

Abstract

The application discloses a kind of water industry multilevel supply and discharge water balance monitoring method and system, it is related to water monitoring technical field.The present application includes the following steps: deployment multilevel monitoring network;Real-time data of multilevel monitoring network is collected, and data is preprocessed after executing space-time alignment operation;Quarterly three-dimensional water balance equation is constructed, and it is dynamically estimated by Kalman filtering;Based on pipe network topology, DBSCAN clustering is implemented, and leakage positioning is generated to generate leakage probability thermodynamic diagram;Establish hierarchical response mechanism to carry out multistage early warning linkage, render multi-layer perspective view in GIS engine.The present application constructs quarterly three-dimensional water balance equation by "city-district-enterprise" three-level dynamic weight model and hierarchical penetration algorithm, and it is dynamically estimated by Kalman filtering;Based on pipe network topology, DBSCAN clustering is implemented, and leakage positioning is generated to generate leakage probability thermodynamic diagram, improve water monitoring efficiency, reduce artificial investigation workload.

Description

Technical Field

[0001] This invention belongs to the field of water monitoring technology, and in particular relates to a multi-level water supply and drainage balance monitoring method and system for the water industry. By constructing a spatiotemporally coupled multi-level monitoring system, it innovatively integrates intelligent algorithms and water expertise to form a smart water solution with autonomous diagnostic capabilities. Background Technology

[0002] With the acceleration of urbanization in my country, the water supply and drainage balance management of the water system faces severe challenges. Traditional water monitoring technologies have the following prominent problems:

[0003] (1) Fragmented monitoring hierarchy: Existing systems mostly operate independently at a single level (such as a municipal platform or enterprise DCS system), lacking a dynamic linkage mechanism for data at the municipal, district, and enterprise levels. For example, when there is a discrepancy between the municipal water supply and drainage, it is necessary to manually check the district-level pipe network and enterprise water meter data level by level, resulting in poor response timeliness (usually taking 3-5 days).

[0004] (2) The time dimension is rough: conventional statistics are based on an annual cycle, which makes it difficult to capture the seasonal water volume fluctuation characteristics.

[0005] (3) Lack of indicator system: The existing method only calculates the water supply and sewage volume, ignoring the dynamic impact of external water volume (such as groundwater infiltration and inter-regional water transfer), resulting in deviations in the supply and drainage balance calculation.

[0006] (4) Insufficient algorithm intelligence: Water supply leakage detection relies heavily on manual inspection and zone metering, which cannot identify continuous leakage of less than 5%;

[0007] (4.1) Drainage efficiency assessment only focuses on the treatment volume and ignores the coupling relationship between energy consumption and water quality compliance rate, which makes it difficult to truly reflect the operating efficiency of the treatment plant;

[0008] (4.2) The balance analysis uses the static threshold method, which cannot adapt to dynamic factors such as pipeline aging and population flow.

[0009] There is an urgent need for a multi-level water supply and drainage balance monitoring method and system in the water industry. This patent improves the refined management and control capabilities of the water system by constructing a spatiotemporally coupled quarterly balance model and a hierarchical penetration mechanism, combined with an improved machine learning algorithm. Summary of the Invention

[0010] The purpose of this invention is to provide a multi-level water supply and drainage balance monitoring method and system for the water industry. By using a three-level dynamic weight model of "city-district-enterprise" and a hierarchical penetration algorithm, a quarterly three-dimensional water balance equation is constructed and dynamically estimated using Kalman filtering. Based on the pipeline topology, DBSCAN clustering is implemented to locate leaks and generate a leak probability heat map, which solves the problems of insufficient refined management and control, lack of linkage at the monitoring level, and insufficient intelligence in the existing water system.

[0011] To solve the above-mentioned technical problems, the present invention is achieved through the following technical solution:

[0012] This invention relates to a multi-level water supply and drainage balance monitoring method for the water industry, comprising the following steps:

[0013] Step S1: Deploy a multi-level monitoring network;

[0014] Step S2: Collect real-time data from the multi-level monitoring network, perform spatiotemporal alignment, and then preprocess the data;

[0015] Step S3: Calculate the information entropy value according to the hierarchy, generate an adaptive weight matrix, and perform dynamic weight allocation;

[0016] Step S4: Construct the quarterly three-dimensional water balance equation and dynamically estimate it using Kalman filtering;

[0017] Step S5: Based on the pipeline topology, perform DBSCAN clustering, overlay the minimum flow analysis at night, and generate a leak probability heatmap to locate leaks.

[0018] Step S6: Establish a tiered response mechanism to conduct multi-level early warning linkage and send abnormal information to the mobile inspection terminal;

[0019] Step S7: Render multi-layer perspective views in the GIS engine.

[0020] As a preferred technical solution, in step S1, the multi-level monitoring network includes: deploying a cloud platform server cluster at the municipal water dispatch center, installing pressure transmitters and electromagnetic flow meters at key nodes of the pipe network in each district and county, configuring ultrasonic water meters with RTU modules at the water intake of key enterprises, and deploying water quality spectrometers at the inlet and outlet of sewage treatment plants.

[0021] As a preferred technical solution, the specific process of performing the spatiotemporal alignment operation in step S2 is as follows:

[0022] Step S21, Dynamic Time Series Adjustment: Define the time series cost function, perform synchronous processing on batch data through a sliding window, output the alignment path, and generate a unified time series matrix;

[0023] Step S22, Spatial Topology Reconstruction: Construct the graph structure of the pipeline network GIS topology and perform spatial interpolation;

[0024] Step S23, Collaborative Filtering of Anomaly Data: Establish a hybrid detection model and generate a three-dimensional anomaly confidence cloud map;

[0025] Step S24, Spatiotemporal benchmark verification: Perform cross-validation mechanism in the time and space dimensions, and output alignment quality report; the alignment quality report includes: maximum time deviation distribution histogram, spatial reconstruction error heatmap and abnormal data repair log.

[0026] As a preferred technical solution, the specific process of dynamic timing adjustment in step S21 is as follows:

[0027] Step S211: Construct a cumulative distance matrix to allow time series from different monitoring devices to be aligned on a nonlinear path, thus solving the problems of clock drift and communication delay between devices;

[0028] Step S212: Introduce a Gaussian-weighted time deviation penalty term in the distance calculation:

[0029]

[0030] In the formula, γ is the penalty intensity coefficient, σ is the control time tolerance, and D(i,j) is the minimum cumulative alignment cost between the first i points of sequence x and the first j points of sequence y.

[0031] Step S213: Set the main window according to the quarterly data span, and overlay a floating sub-window of ±2 hours to adapt to the equipment clock synchronization error, limit the fluctuation of the regular path within the sub-window, and avoid cross-quarter data misalignment; perform composite feature calculation, in addition to water volume data, integrate multi-dimensional parameters such as pressure and flow rate;

[0032] Step S214: Search for the minimum cost path in reverse from the bottom right corner of the cumulative matrix to generate an aligned unified timestamp sequence;

[0033] Step S215: For consecutive jump points in the path, use cubic spline interpolation to repair data faults;

[0034] Step S216: Calculate the root mean square error of the aligned sequence, which should be ≤3%. The processing time for a single quarter's data should be ≤15 minutes to meet the real-time requirements.

[0035] As a preferred technical solution, in step S22, spatial topology reconstruction includes spatial alignment and temporal alignment; the spatial alignment is achieved by constructing a water affairs digital twin map in the EPSG coordinate system, loading a pipeline topology vector layer, and using the Delaunay triangulation algorithm to perform spatial interpolation on discrete monitoring points, as shown in the following formula:

[0036]

[0037] In the formula, w i Dynamic adjustment of the spatial density of detection points;

[0038] The time alignment is achieved by creating a quarterly timeline and using a sliding window mechanism to handle device clock skew, as shown in the following formula:

[0039]

[0040] In the formula, σ is 1.5 hours;

[0041] It also activates the NTP time synchronization service to perform a second timestamp remarking on delayed data packets.

[0042] In step S23, when establishing the hybrid detection model and generating the three-dimensional anomaly confidence cloud map, the XGBoost classifier is trained to identify anomaly patterns:

[0043] Input features: pressure fluctuation variance, flow rate change rate, water quality parameter gradient;

[0044] Output: Anomaly probability value P∈[0,1];

[0045] Sliding window validation (window length = 24h, step size = 1h) was used to ensure model stability.

[0046] Construct a three-dimensional anomaly confidence field: C(x,y,t)=w1δ+w2P; where w1 and w2 are the statistical model weight coefficient and machine learning weight coefficient, respectively; δ is the quarterly water balance deviation, and P represents the anomaly probability value; the three-dimensional anomaly confidence cloud map is generated using WebGL technology to achieve three-dimensional rendering on the browser side.

[0047] As a preferred technical solution, in step S3, the information entropy value is calculated according to the hierarchy, and an adaptive weight matrix is ​​generated for dynamic weight allocation;

[0048] The specific formula for calculating the information entropy value according to hierarchy is as follows:

[0049]

[0050] In the formula, m = 3 corresponds to the city, district, and enterprise levels, respectively, and p ij The standardized indicator value is the standardized value of the i-th indicator at the j-th level. When the entropy value E1 of the city is greater than 0.8, the city-level data is judged to have high disorder, and its weight ratio is automatically reduced.

[0051] As a preferred technical solution, the specific steps for constructing the quarterly three-dimensional water balance in step S4 are as follows:

[0052] Step S41: Construct a multi-source data cube, align the multi-source data, perform spatial interpolation on the meteorological satellite data, and match the coordinates of the pipeline network nodes;

[0053] The data dimensions include a time axis, a spatial axis, and a feature axis; the time axis is a quarterly slice (Q1-Q4) with a time resolution accurate to ±2 hours; the spatial axis is a three-level topology structure of city-district-enterprise (based on GIS pipeline node coding); the feature axis includes water supply, sewage, and external water inflow.

[0054] Step S42: Conduct dynamic assessment of external water inflow; the specific formula is as follows:

[0055]

[0056] In the formula, Q represents the city's total water supply. ext Where α is the inflow of water and α is the wastewater treatment rate correction factor. Let d be the wastewater volume in region d, β be the seasonal effluent factor, and ΔS be the change in effluent facility capacity.

[0057] The specific formula for dynamic estimation using Kalman filtering is as follows:

[0058] X t =AX t-1 +B(u t )+w t ;

[0059] In the formula, X t Let B(u) be the estimated external water volume at time t. t ) represents the real-time rainfall infiltration rate, w t The noise is dynamically adjusted based on groundwater monitoring data; A and B are weighting coefficients.

[0060] Step S43: Dynamic calibration of equilibrium equation parameters;

[0061] Wastewater treatment rate correction factor α: In the formula, C out For the real-time concentration of COD in the effluent, C std These are emission standard values;

[0062] Step S44: Three-dimensional balance deviation analysis;

[0063] Time dimension: Calculate the difference between the current quarter's balance and the same period last year:

[0064]

[0065] Spatial Dimension: Analyzing Regional Imbalanced Clustering Using the Moran Index:

[0066]

[0067] In the formula, x i w represents the balance deviation value of the i-th district-level node. ij This is a spatial weighting matrix based on the hydraulic connectivity of the pipeline network;

[0068] Element Dimension: The formula for calculating the contribution of each element is as follows:

[0069]

[0070] In the formula, δ represents the total deviation.

[0071] Step S45: Dynamic feedback optimization, establish a quarterly rolling optimization window, execute at the end of each quarter, and use the quantum particle swarm optimization (QPSO) algorithm for rapid optimization.

[0072] As a preferred technical solution, the specific implementation process of step S5 is as follows:

[0073] Step S51: Construct a hydraulic model of the pipeline network based on the GIS topology, import basic pipeline network parameters such as pipe diameter, material, burial depth, etc., and establish the pressure fluctuation transmission equation. The specific formula is as follows:

[0074]

[0075] In the formula, ΔP is the total pressure drop between two points in the pipe, ρ is the fluid density, v1 and v2 are the average flow velocities at the front and end of the pipe, respectively, Δh is the elevation difference between the two ends of the pipe, f is the Darcy-Weisbach friction coefficient, L is the actual length of the pipe, and D is the nominal diameter of the pipe.

[0076] Step S52: Adjust the DBSCAN search radius according to the real-time pipe diameter, construct a spatiotemporal constraint matrix, and establish reachability constraints based on pipe connectivity in the spatial dimension, with 15-minute time slices.

[0077] Step S53: Establish a dynamic baseline model and calculate the flow baseline using the exponentially weighted moving average method. The specific formula is as follows:

[0078] Q t =λQ t-1 +(1-λ)Q obs ;

[0079] In the formula, λ = 0.85 is the seasonal adjustment factor;

[0080] Step S54: Construct a leakage probability model, generate a heatmap, and render the probability distribution on the official website's GIS map; the specific formula for the leakage probability model is:

[0081] P leak =0.6PDBSCAN +0.3P flow +0.1P vib ;

[0082] In the formula, P DBSCAN P represents the confidence score of the clustering results. flow P is the value mapped to the flow deviation. vib The characteristics of the fused acoustic vibrations.

[0083] As a preferred technical solution, in step S6, the graded response mechanism includes red alert, orange alert, and yellow alert; when the third-level indicator is abnormal and the joint probability is greater than 75%, a red alert is triggered and an emergency plan is generated; when the second-level indicator is abnormal and the balance deviation is greater than 8%, an orange alert is triggered and pipeline pressure regulation is initiated; when a single-level indicator is abnormal, a yellow indicator alert is triggered and an equipment maintenance work order is sent to the mobile inspection terminal.

[0084] This invention is a multi-level water supply and drainage balance monitoring system for the water industry, comprising a data acquisition layer, a data processing layer, an intelligent analysis layer, and an application interaction layer;

[0085] The data acquisition layer includes multi-source sensing terminals and a heterogeneous data gateway. The multi-source sensing terminals include smart water meters, pipeline pressure transmitters, and water quality analyzers. The smart water meters are deployed at water supply pipeline nodes to transmit water usage data via the NB-IoT network. The pipeline pressure transmitters are deployed at abrupt changes in the water supply pipeline, at the end of the main pipeline, valves, and pipeline outlets to collect pipeline pressure fluctuation data and dynamically generate pressure field heat maps. The water quality analyzers are deployed at the inlet and outlet to monitor water quality indicators through video spectral analysis. The heterogeneous data gateway is used to access the multi-source sensing terminal devices via the Modbus / OPCUA protocol, constructing a unified data channel. The heterogeneous data gateway can also perform data cleaning, filtering, and compression locally, reducing the amount of data uploaded to the cloud (e.g., filtering low-value data and reducing bandwidth consumption); perform real-time analysis (e.g., equipment status monitoring and energy efficiency calculation); generate early warning signals or control commands; and shorten response latency to the millisecond level.

[0086] The data processing layer includes a spatiotemporal database, a data cleaning engine, and a water balance calculator. The spatiotemporal database is used to store quarterly dimension data using a time-series database and establish a three-dimensional GIS spatial index. The data cleaning engine is used to automatically identify abnormal monitoring values ​​and perform data cleaning. The water balance calculator is used to execute the three-dimensional balance equation in real time and generate a dynamic balance heat map.

[0087] The intelligent analysis layer includes a multi-level diagnostic center, an early warning center, and a decision optimization platform; the multi-level diagnostic center includes a hierarchical penetration analysis module, a leakage location module, and a performance evaluation sub-module; the early warning center integrates the Prophet time series model and the XGBoost classifier; the decision optimization platform is used to provide multi-objective scheduling schemes;

[0088] The application interaction layer includes a 3D visualization terminal and a mobile inspection terminal; the 3D visualization terminal is used to display the quarterly balance index radar chart; the mobile inspection terminal is used to overlay the pipeline health status in real time.

[0089] The hierarchical penetration analysis module is used to establish a vertical penetration mechanism for monitoring data at the city, district, and enterprise levels. When city-level indicators are abnormal, the weighted model automatically triggers the source tracing of lower-level data. The leakage location module is used to integrate GIS topology data and real-time sensor information to accurately identify pipeline leakage points. The efficiency evaluation submodule is used to calculate the treatment energy efficiency ratio (treatment capacity × compliance rate / design capacity × energy consumption), optimize the operation mode of sewage treatment plants, construct a quarterly balance index radar chart, compare the LSTM prediction curve with the measured value, and identify seasonal capacity deviations. The Copula coupling model is used to analyze the matching degree between water supply reliability and drainage carrying capacity, and to provide early warning of system imbalance risks.

[0090] As a preferred technical solution, the hierarchical penetration analysis module is used to establish a vertical penetration mechanism for monitoring data at the city, district, and enterprise levels. When city-level indicators are abnormal, the lower-level data tracing is automatically triggered through a weighted model. The leakage location module is used to integrate GIS topology data and real-time sensor information to accurately identify pipeline leakage points. The efficiency evaluation submodule is used to calculate the treatment energy efficiency ratio (treatment capacity × compliance rate / design capacity × energy consumption), optimize the operation mode of the sewage treatment plant, construct a quarterly balance index radar chart, compare the LSTM prediction curve with the measured value, and identify seasonal capacity deviations. The Copula coupling model is used to analyze the matching degree between water supply reliability and drainage carrying capacity.

[0091] As a preferred technical solution, the above is described.

[0092] The present invention has the following beneficial effects:

[0093] (1) This invention constructs a quarterly three-dimensional water balance equation through a three-level dynamic weight model of “city-district-enterprise” and a hierarchical penetration algorithm, and dynamically estimates it through Kalman filtering; DBSCAN clustering is implemented based on the pipeline topology to locate leakage and generate a leakage probability heat map, thereby improving the efficiency of water monitoring and reducing the workload of manual investigation.

[0094] (2) This invention achieves nonlinear time warping through dynamic windows to adapt to equipment clock drift and communication delay. It introduces pipeline flow direction parameters in IDW interpolation to improve the accuracy of spatial correlation calculation of pressure data. It integrates rapid screening of isolated forests with spatiotemporal correlation Z-score fine screening, active shielding test and periodic verification, and establishes quantifiable alignment quality evaluation indicators to improve data consistency.

[0095] (3) By applying hydraulic transient pressure fluctuation comparison technology and combining it with the improved DBSCAN algorithm, this invention can detect micro-leakage of more than 0.5% of the pipe diameter by adjusting the clustering radius of the pipe diameter, thereby improving the accuracy of leakage location and reducing water waste.

[0096] (4) This invention improves the speed at which managers can perceive quarterly indicator anomalies by integrating a GIS engine-based supply and drainage balance map with an AR inspection system, and shortens the time for auxiliary decision-making. In particular, it improves the timeliness of emergency dispatching plan generation when dealing with extreme weather such as rainstorms.

[0097] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0098] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0099] Figure 1 This is a flowchart of a multi-level water supply and drainage balance monitoring method for the water industry according to the present invention;

[0100] Figure 2 This is a schematic diagram of a multi-level water supply and drainage balance monitoring system for the water industry according to the present invention. Detailed Implementation

[0101] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. 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.

[0102] Furthermore, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0103] To make the purpose, technical solution, and advantages of this application clearer, the following description is provided in conjunction with the appendix. Figure 1-2 The present application will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the application.

[0104] Example 1

[0105] Please see Figure 1 As shown, this invention provides a multi-level water supply and drainage balance monitoring method for the water industry, comprising the following steps:

[0106] Step S1: Deploy a multi-level monitoring network;

[0107] Step S2: Collect real-time data from the multi-level monitoring network, perform spatiotemporal alignment, and then preprocess the data;

[0108] Step S3: Calculate the information entropy value according to the hierarchy, generate an adaptive weight matrix, and perform dynamic weight allocation;

[0109] Step S4: Construct the quarterly three-dimensional water balance equation and dynamically estimate it using Kalman filtering;

[0110] Step S5: Based on the pipeline topology, perform DBSCAN clustering, overlay the minimum flow analysis at night, and generate a leak probability heatmap to locate leaks.

[0111] Step S6: Establish a tiered response mechanism to conduct multi-level early warning linkage and send abnormal information to the mobile inspection terminal;

[0112] Step S7: Render multi-layer perspective views in the GIS engine.

[0113] In step S1, the multi-level monitoring network includes: deploying a cloud platform server cluster at the municipal water dispatch center; installing pressure transmitters and electromagnetic flow meters at key nodes of the pipe network in each district and county; configuring ultrasonic water meters with RTU modules at the water intakes of key enterprises; and deploying water quality spectrometers at the inlet and outlet of sewage treatment plants.

[0114] In step S2, the specific process for performing the spatiotemporal alignment operation is as follows:

[0115] Step S21, Dynamic Time Series Adjustment: Define the time series cost function, perform synchronous processing on batch data through a sliding window, output the alignment path, and generate a unified time series matrix;

[0116] Step S22, Spatial Topology Reconstruction: Construct the graph structure of the pipeline network GIS topology and perform spatial interpolation;

[0117] Step S23, Collaborative Filtering of Anomaly Data: Establish a hybrid detection model and generate a three-dimensional anomaly confidence cloud map;

[0118] Step S24, Spatiotemporal benchmark verification: Perform cross-validation mechanism in the time and space dimensions, and output alignment quality report; the alignment quality report includes: maximum time deviation distribution histogram, spatial reconstruction error heatmap and abnormal data repair log.

[0119] In step S21, the specific process for dynamic timing adjustment is as follows:

[0120] Step S211: Construct a cumulative distance matrix to allow time series from different monitoring devices to be aligned on a nonlinear path, thus solving the problems of clock drift and communication delay between devices;

[0121] Step S212: Introduce a Gaussian-weighted time deviation penalty term in the distance calculation:

[0122]

[0123] In the formula, γ is the penalty intensity coefficient, σ is the control time tolerance, and D(i,j) is the minimum cumulative alignment cost between the first i points of sequence x and the first j points of sequence y.

[0124] Step S213: Set the main window according to the quarterly data span, and overlay a floating sub-window of ±2 hours to adapt to the equipment clock synchronization error, limit the fluctuation of the regular path within the sub-window, and avoid cross-quarter data misalignment; perform composite feature calculation, in addition to water volume data, integrate multi-dimensional parameters such as pressure and flow rate;

[0125] Step S214: Search for the minimum cost path in reverse from the bottom right corner of the cumulative matrix to generate an aligned unified timestamp sequence;

[0126] Step S215: For consecutive jump points in the path, use cubic spline interpolation to repair data faults;

[0127] Step S216: Calculate the root mean square error of the aligned sequence, which should be ≤3%. The processing time for a single quarter's data should be ≤15 minutes to meet the real-time requirements.

[0128] In step S22, spatial topology reconstruction includes spatial alignment and temporal alignment. Spatial alignment is achieved by constructing a water affairs digital twin map in the EPSG coordinate system, loading a pipeline topology vector layer, and using the Delaunay triangulation algorithm to perform spatial interpolation on discrete monitoring points. The specific formula is as follows:

[0129]

[0130] In the formula, w i Dynamic adjustment of the spatial density of detection points;

[0131] Time alignment is achieved by creating a quarterly timeline and using a sliding window mechanism to handle device clock skew, as shown in the following formula:

[0132]

[0133] In the formula, σ is 1.5 hours;

[0134] It also activates the NTP time synchronization service to perform a second timestamp remarking on delayed data packets.

[0135] In step S23, when establishing the hybrid detection model and generating the three-dimensional anomaly confidence cloud map, the XGBoost classifier is trained to identify anomaly patterns:

[0136] Input features: pressure fluctuation variance, flow rate change rate, water quality parameter gradient;

[0137] Output: Anomaly probability value P∈[0,1];

[0138] Sliding window validation (window length = 24h, step size = 1h) was used to ensure model stability.

[0139] Construct a three-dimensional anomaly confidence field: C(x,y,t)=w1δ+w2P; where w1 and w2 are the statistical model weight coefficient and machine learning weight coefficient, respectively; δ is the quarterly water balance deviation, and P represents the anomaly probability value; the three-dimensional anomaly confidence cloud map is generated using WebGL technology to achieve three-dimensional rendering on the browser side.

[0140] In step S3, the information entropy value is calculated according to the hierarchy, and an adaptive weight matrix is ​​generated for dynamic weight allocation;

[0141] The specific formula for calculating the information entropy value according to hierarchy is as follows:

[0142]

[0143] In the formula, m = 3 corresponds to the city, district, and enterprise levels, respectively, and p ij The standardized indicator value is the standardized value of the i-th indicator at the j-th level. When the entropy value E1 of the city is greater than 0.8, the city-level data is judged to have high disorder, and its weight ratio is automatically reduced.

[0144] In step S4, the specific steps for constructing the quarterly three-dimensional water balance are as follows:

[0145] Step S41: Construct a multi-source data cube, align the multi-source data, perform spatial interpolation on the meteorological satellite data, and match the coordinates of the pipeline network nodes;

[0146] The data dimensions include a time axis, a spatial axis, and a feature axis; the time axis is a quarterly slice (Q1-Q4) with a time resolution accurate to ±2 hours; the spatial axis is a three-level topology structure of city-district-enterprise (based on GIS pipeline node coding); the feature axis includes water supply, sewage, and external water inflow.

[0147] Step S42: Conduct dynamic assessment of external water inflow; the specific formula is as follows:

[0148]

[0149] In the formula, Q represents the city's total water supply. ext Where α is the inflow of water and α is the wastewater treatment rate correction factor. Let d be the wastewater volume in region d, β be the seasonal effluent factor, and ΔS be the change in effluent facility capacity.

[0150] The specific formula for dynamic estimation using Kalman filtering is as follows:

[0151] X t =AX t-1 +B(u t )+w t ;

[0152] In the formula, X t Let B(u) be the estimated external water volume at time t. t ) represents the real-time rainfall infiltration rate, w t The noise is dynamically adjusted based on groundwater monitoring data; A and B are weighting coefficients.

[0153] Step S43: Dynamic calibration of equilibrium equation parameters;

[0154] Wastewater treatment rate correction factor α: In the formula, C out For the real-time concentration of COD in the effluent, C std These are emission standard values;

[0155] Step S44: Three-dimensional balance deviation analysis;

[0156] Time dimension: Calculate the difference between the current quarter's balance and the same period last year:

[0157]

[0158] Spatial Dimension: Analyzing Regional Imbalanced Clustering Using the Moran Index:

[0159]

[0160] In the formula, x i w represents the balance deviation value of the i-th district-level node. ijThis is a spatial weighting matrix based on the hydraulic connectivity of the pipeline network;

[0161] Element Dimension: The formula for calculating the contribution of each element is as follows:

[0162]

[0163] In the formula, δ represents the total deviation.

[0164] Step S45: Dynamic feedback optimization, establish a quarterly rolling optimization window, execute at the end of each quarter, and use the quantum particle swarm optimization (QPSO) algorithm for rapid optimization.

[0165] The specific implementation process in step S5 is as follows:

[0166] Step S51: Construct a hydraulic model of the pipeline network based on the GIS topology, import basic pipeline network parameters such as pipe diameter, material, burial depth, etc., and establish the pressure fluctuation transmission equation. The specific formula is as follows:

[0167]

[0168] In the formula, ΔP is the total pressure drop between two points in the pipe, ρ is the fluid density, v1 and v2 are the average flow velocities at the front and end of the pipe, respectively, Δh is the elevation difference between the two ends of the pipe, f is the Darcy-Weisbach friction coefficient, L is the actual length of the pipe, and D is the nominal diameter of the pipe.

[0169] Step S52: Adjust the DBSCAN search radius according to the real-time pipe diameter, construct a spatiotemporal constraint matrix, and establish reachability constraints based on pipe connectivity in the spatial dimension, with 15-minute time slices.

[0170] Step S53: Establish a dynamic baseline model and calculate the flow baseline using the exponentially weighted moving average method. The specific formula is as follows:

[0171] Q t =λQ t-1 +(1-λ)Q obs ;

[0172] In the formula, λ = 0.85 is the seasonal adjustment factor;

[0173] Step S54: Construct a leakage probability model, generate a heatmap, and render the probability distribution on the official website's GIS map; the specific formula for the leakage probability model is:

[0174] P leak =0.6P DBSCAN +0.3P flow +0.1P vib ;

[0175] In the formula, P DBSCANP represents the confidence score of the clustering results. flow P is the value mapped to the flow deviation. vib The characteristics of the fused acoustic vibrations.

[0176] In step S6, the graded response mechanism includes red, orange, and yellow alerts. When a level 3 indicator is abnormal and the combined probability is greater than 75%, a red alert is triggered and an emergency plan is generated. When a level 2 indicator is abnormal and the balance deviation is greater than 8%, an orange alert is triggered and pipeline pressure regulation is initiated. When a single level indicator is abnormal, a yellow alert is triggered and an equipment maintenance work order is sent to the mobile inspection terminal.

[0177] Example 2

[0178] See Figure 2 As shown, the present invention is a multi-level water supply and drainage balance monitoring system for the water industry, which can be used to execute the method content of Embodiment 1 of the present invention, including: a data acquisition layer, a data processing layer, an intelligent analysis layer and an application interaction layer;

[0179] The data acquisition layer includes multi-source sensing terminals and a heterogeneous data gateway. Multi-source sensing terminals include smart water meters, pipeline pressure transmitters, and water quality analyzers. Smart water meters are deployed at nodes in the water supply pipeline to transmit water usage data via the NB-IoT network. Pipeline pressure transmitters are deployed at abrupt changes in the water supply pipeline, at the end of the main pipeline, valves, and pipeline outlets to collect pipeline pressure fluctuation data and dynamically generate pressure field heat maps. Water quality analyzers are deployed at the inlet and outlet to monitor water quality indicators through video spectral analysis. The heterogeneous data gateway connects to the multi-source sensing terminal devices via the Modbus / OPCUA protocol, building a unified data channel. The heterogeneous data gateway can also perform data cleaning, filtering, and compression locally, reducing the amount of data uploaded to the cloud (e.g., filtering low-value data and reducing bandwidth consumption); perform real-time analysis (e.g., equipment status monitoring and energy efficiency calculation); generate early warning signals or control commands; and shorten response latency to the millisecond level.

[0180] The data processing layer includes a spatiotemporal database, a data cleaning engine, and a water balance calculator. The spatiotemporal database is used to store quarterly dimension data using a time-series database and to build a three-dimensional GIS spatial index. The data cleaning engine is used to automatically identify abnormal monitoring values ​​and perform data cleaning. The water balance calculator is used to execute the three-dimensional balance equation in real time and generate a dynamic balance heat map.

[0181] The intelligent analysis layer includes a multi-level diagnostic center, an early warning center, and a decision optimization platform. The multi-level diagnostic center contains a hierarchical penetration analysis module, a leakage location module, and a performance evaluation sub-module. The early warning center integrates the Prophet time series model and the XGBoost classifier. The decision optimization platform is used to provide multi-objective scheduling solutions.

[0182] The application interaction layer includes a 3D visualization terminal and a mobile inspection terminal; the 3D visualization terminal is used to display the quarterly balance index radar chart; the mobile inspection terminal is used to overlay the pipeline health status in real time.

[0183] The hierarchical penetration analysis module is used to establish a vertical penetration mechanism for monitoring data at the city, district, and enterprise levels. When city-level indicators are abnormal, the weighted model automatically triggers the source tracing of lower-level data. The leakage location module is used to integrate GIS topology data and real-time sensor information to accurately identify leakage points in the pipeline network. The efficiency evaluation submodule is used to calculate the treatment energy efficiency ratio (treatment capacity × compliance rate / design capacity × energy consumption), optimize the operation mode of the sewage treatment plant, construct a quarterly balance index radar chart, compare the LSTM prediction curve with the measured value, and identify seasonal capacity deviations. The Copula coupling model is used to analyze the matching degree between water supply reliability and drainage carrying capacity and to warn of system imbalance risks.

[0184] In this embodiment,

[0185] (1) The locations where smart water meters are deployed include:

[0186] Residential water meter wells: located at the entrance of water supply pipes in residential buildings, covering household water usage monitoring;

[0187] Commercial building pipe room: The main water supply pipe node in public buildings such as office buildings and shopping malls;

[0188] Industrial park water inlet: The point where the main pipeline for factory production water connects;

[0189] Farmland irrigation hub: At the main water conveyance pipeline or branch valve of the agricultural irrigation area;

[0190] Specific effects: Minute-level water consumption data transmission is achieved through the NB-IoT network, replacing manual meter reading and enabling remote meter reading and data management; AI algorithms analyze water consumption curves to identify abnormal minimum flow rates at night and locate hidden leaks (accuracy >99%), enabling leakage monitoring and early warning; remote valve control and pre-paid fees are supported, automatically executing tiered water pricing rules to achieve prepaid and tiered water pricing; user water consumption profiles are generated, providing data support for water conservation strategy formulation and enabling water consumption behavior analysis.

[0191] (2) The locations where pipeline pressure transmitters are deployed include:

[0192] Pressure-sensitive areas of the pipeline network: places where the water flow direction changes abruptly in the main water supply pipe (such as elbows and tees);

[0193] Water-intensive areas: the ends of main pipelines in areas with concentrated water loads, such as residential and commercial areas;

[0194] Pipeline junctions: key valves or pump station outlets for multi-flow distribution;

[0195] Low-pressure / high-pressure risk areas: areas with significant elevation differences or long-distance water pipeline sections;

[0196] Specific effects:

[0197] Collect pipeline pressure fluctuation data, dynamically generate pressure field heat maps, and realize real-time pressure monitoring; identify pipe burst accidents by pressure drop characteristics, and locate anomalies by combining GIS to realize pipe burst early warning and location; coordinate with water supply pump stations to adjust output pressure, reduce energy consumption by 10%-20%; provide measured pressure data for pipeline network simulation, and improve the model prediction accuracy.

[0198] (3) The locations where water quality analyzers are deployed include:

[0199] Key nodes in a water plant include: raw water inlet, sedimentation tank outlet, and clear water tank.

[0200] Secondary water supply facilities: community booster pump room, rooftop water tank outlet;

[0201] Rivers / sewage outlets: key river sections and sewage treatment plant discharge outlets;

[0202] Emergency monitoring points: sites of sudden pollution incidents or water source protection areas;

[0203] Specific effects:

[0204] By using video spectral analysis to detect indicators such as turbidity, color, and suspended solids, real-time monitoring of water quality parameters can be achieved; abnormal events such as oil pollution, algae proliferation, and floating garbage in water bodies can be automatically identified; the dosage of coagulant can be dynamically adjusted in conjunction with the dosing system to improve treatment efficiency by 20%; and pollution sources can be quickly located by combining water flow trajectory analysis to achieve pollution source tracing and early warning.

[0205] It is worth noting that the various units included in the above system embodiments are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0206] Furthermore, those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware, and the corresponding program can be stored in a computer-readable storage medium.

[0207] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A multi-tiered water industry supply and sewerage balance monitoring method, characterized in that, The method comprises the following steps: Step S1: deploying a multi-level monitoring network; Step S2: collecting real-time data of the multi-level monitoring network, and performing preprocessing on the data after performing a time-space alignment operation; Step S3: calculating an information entropy value according to the level, and generating an adaptive weight matrix for dynamic weight distribution; Step S4: constructing a quarterly three-dimensional water balance equation, and dynamically estimating by Kalman filtering; Step S5: implementing DBSCAN clustering based on the pipe network topology, superimposing night minimum flow analysis, and generating a leakage probability heat map for leakage positioning; Step S6: establishing a hierarchical response mechanism for multi-level early warning linkage, and sending abnormal information to a mobile inspection terminal; Step S7: rendering a multi-layer perspective view in a GIS engine. In the step S4, the specific steps of constructing the quarterly three-dimensional water balance equation are as follows: Step S41: constructing a multi-source data cube, aligning multi-source data, spatially interpolating meteorological satellite data, and matching pipe network node coordinates; Step S42: performing dynamic evaluation of external water quantity; Step S43: dynamically calibrating balance equation parameters; Step S44: three-dimensional balance deviation analysis; Step S45: dynamic feedback optimization.

2. A multi-tiered water supply and sewerage balance monitoring method in the water industry according to claim 1, characterized in that, In the step S1, the multi-level monitoring network comprises: deploying a cloud platform server cluster at the municipal water management center, installing pressure transmitters and electromagnetic flow meters at key nodes of the pipe network in each district and county, configuring ultrasonic water meters with RTU modules at the water intake of key enterprises, and deploying water quality spectrum analyzers at the inlet and outlet of sewage treatment plants.

3. A multi-tiered water supply and sewerage balance monitoring method in the water industry as claimed in claim 1, characterized in that, In the step S2, the specific process of performing the time-space alignment operation is as follows: Step S21, time sequence dynamic adjustment: defining a time sequence cost function, synchronously processing batch data through a sliding window, outputting an alignment path, and generating a unified time sequence matrix; Step S22, spatial topology reconstruction: constructing a graph structure of the pipe network GIS topology, and performing spatial interpolation; Step S23, abnormal data collaborative filtering: establishing a hybrid detection model, and generating a three-dimensional abnormal confidence cloud map; Step S24, time-space benchmark verification: performing a cross verification mechanism in the time dimension and the space dimension, and outputting an alignment quality report; The alignment quality report comprises: a maximum time deviation distribution histogram, a spatial reconstruction error heat map, and an abnormal data repair log.

4. A multi-tiered water industry supply and drainage balance monitoring method as claimed in claim 3, wherein, In the step S21, the specific process of time sequence dynamic adjustment is as follows: Step S211: constructing a cumulative distance matrix, allowing time sequences of different monitoring devices to be aligned in a nonlinear path; Step S212: introducing a Gaussian weighted time deviation penalty term in distance calculation; Step S213: setting a main window according to the data span of a quarter, and superimposing a floating sub-window of ±2 hours to limit the fluctuation of the regular path within the sub-window; Step S214: searching for a minimum cost path from the lower right corner of the cumulative matrix in reverse, and generating a unified timestamp sequence after alignment; Step S215: using cubic spline interpolation to repair data faults at continuous jump points in the path; Step S216: calculating the root mean square error of the aligned sequence, and calculating the single-quarter data processing time.

5. A multi-tiered water industry supply and drainage balance monitoring method as claimed in claim 3, wherein, In the step S22, the spatial topology reconstruction includes spatial alignment and time alignment; the spatial alignment is performed by constructing a water digital twin map in an EPSG coordinate system, loading a pipe network topology structure vector layer, and performing spatial interpolation on discrete monitoring points by using a Delaunay triangulation algorithm; the time alignment is performed by creating a quarterly time axis, processing device clock deviation by using a sliding window mechanism, activating an NTP time service, and performing secondary time stamp re-labeling on lag data packets.

6. A multi-tiered water supply and sewerage balance monitoring method in the water industry as claimed in claim 1, wherein, In the step S5, the following process is specifically implemented: Step S51: constructing a pipe network hydraulic model based on GIS topology, importing pipe network basic parameters, and establishing a pressure fluctuation transmission equation; Step S52: adjusting a DBSCAN search radius according to a real-time pipe diameter, and constructing a space-time constraint matrix; Step S53: establishing a dynamic baseline model, and calculating a flow baseline by using an exponential weighted moving average method; Step S54: constructing a leakage probability model, generating a heat map, and rendering probability distribution on a GIS map of an official website.

7. A multi-tiered water industry supply and drainage homeostasis monitoring method as claimed in claim 1, wherein, In the step S6, the hierarchical response mechanism includes red, orange and yellow early warnings; when three-level indicators are abnormal and the joint probability is greater than 75%, the red early warning is triggered and an emergency plan is generated; when two-level indicators are abnormal and the balance deviation is greater than 8%, the orange early warning is triggered and pipe network pressure regulation is initiated; when single-level indicators are abnormal, the yellow indicator early warning is triggered and a device maintenance work order is sent to a mobile inspection terminal.

8. A multi-level supply and drainage water balance monitoring system in the water industry, comprising a data acquisition layer, a data processing layer, an intelligent analysis layer and an application interaction layer, characterized in that: The data acquisition layer comprises a multi-source sensing terminal and a heterogeneous data gateway; the multi-source sensing terminal comprises an intelligent water meter, a pipe network pressure transmitter and a water quality analyzer; the intelligent water meter is deployed on a water supply pipeline node to realize water consumption feedback through an NB-IoT network; the pipe network pressure transmitter is deployed at a mutation point of a water supply pipeline, an end of a main pipeline, a valve and a pipeline outlet to collect pipeline pressure fluctuation data and dynamically generate a pressure field heat map; the water quality analyzer is deployed at an inlet and an outlet to monitor water quality indicators by video spectrum analysis; the heterogeneous data gateway is used to access multi-source sensing terminal devices through Modbus / OPCUA protocols to build a unified data channel; The data processing layer comprises a space-time database, a data cleaning engine and a water balance calculator; the space-time database is used to store quarterly dimension data by using a time series database and establish a three-dimensional GIS spatial index; the data cleaning engine is used to automatically identify abnormal monitoring values and perform data cleaning; the water balance calculator is used to execute a three-dimensional balance equation in real time to generate a dynamic balance heat map; The intelligent analysis layer comprises a multi-level diagnosis center, an early warning center and a decision optimization platform; the multi-level diagnosis center comprises a hierarchical penetration analysis module, a leakage positioning module and an efficiency evaluation submodule; the early warning center integrates a Prophet time series model and an XGBoost classifier; the decision optimization platform is used to provide a multi-objective scheduling scheme; The application interaction layer comprises a three-dimensional visualization terminal and a mobile inspection terminal; The three-dimensional visualization terminal is used for displaying a quarterly balance index radar chart; and the mobile inspection terminal is used for superimposing a pipe network health state in real time.

9. A system for implementing the water industry multi-tiered supply and demand water balance monitoring method according to claim 1, characterized in that, The hierarchical penetration analysis module is used for establishing a longitudinal penetration mechanism of monitoring data at the municipal, district and enterprise levels, and when a municipal index is abnormal, the lower-level data is automatically triggered for tracing through a weight model; the leakage positioning module is used for fusing GIS topological data and real-time sensing information to identify a pipe network leakage point; the efficiency evaluation submodule is used for calculating and processing an energy efficiency ratio, optimizing an operation mode of a sewage treatment plant, constructing a quarterly balance index radar chart, comparing an LSTM prediction curve with a measured value, and identifying a seasonal energy production deviation; and the water supply reliability and the drainage carrying capacity matching degree are analyzed through a Copula coupling model.

Images