Intelligent Analysis and Processing of Massive Data and Decision Support Methods for a Smart Water Management Integrated Platform Based on GIS and IoT

Abstract

This invention relates to the field of water pipeline network operation and maintenance technology. Specifically, it relates to a method for intelligent analysis, processing, and decision support of massive data in a smart water management integrated platform based on GIS and IoT. This invention marks pipe burst monitoring points and generates an initial impact domain, traces upstream nodes in reverse, constructs a pressure anomaly propagation map and corrects the hydraulic model, calculates the pressure attenuation gradient to generate valve closure boundaries, generates a tiered valve closure command set, verifies the effectiveness of valve closure, and dynamically optimizes the method. This method integrates GIS topology and IoT data, solving the problems of large estimation deviations in the impact range of traditional pipe bursts and lack of accuracy in valve closure commands. It improves the efficiency of emergency response to pipe bursts, reduces water waste, ensures water supply stability, and is suitable for refined management of urban water affairs.

Description

Technical Field

[0001] This invention relates to the field of water pipeline network operation and maintenance technology, and more specifically, to a method for intelligent analysis, processing and decision support of massive data in a smart water management integrated platform based on GIS and the Internet of Things. Background Technology

[0002] Water management and pipeline network operation and maintenance is an important technology. In urban water management, the stable operation of water supply networks is directly related to residents' lives and social production. Constructing the spatial topology of the pipeline network through GIS and combining it with the Internet of Things to collect data such as pressure in real time are the core technical means to achieve leakage control, emergency response to pipe bursts, and resource optimization.

[0003] This technology is of great significance for improving water management efficiency, reducing operating costs, and ensuring water supply security. Traditional management methods relying on manual inspections or static models are no longer sufficient to meet the dynamic operational needs of complex pipe networks. However, traditional smart water management platforms suffer from a core problem of insufficient accuracy in emergency response during pipe network fault handling. Existing solutions, when a pipe burst occurs, only roughly define the affected area based on the pressure anomaly value of a single sensor, without combining dynamic analysis with the GIS pipe network topology and pressure wave propagation patterns. After a pipe burst, the pressure anomaly will propagate backward along the pipe network, but traditional methods do not track the timing of pressure changes at upstream nodes, nor do they consider the impact of pipe material and diameter on pressure attenuation, resulting in a large deviation in the estimated affected area. This makes valve closing commands lack precise boundaries and priority classification, which may lead to situations where valves are not closed, resulting in increased leakage, or excessive valve closure affecting normal water supply. This not only wastes water resources and increases maintenance costs, but also causes user complaints due to uncontrolled water outages, making it difficult to meet the requirements of refined urban water management. To solve this technical problem, we provide a method for intelligent analysis and processing of massive data and decision support based on a GIS and IoT-integrated smart water management platform. Summary of the Invention

[0004] The purpose of this invention is to provide a method for intelligent analysis, processing and decision support of massive data in a smart water management integrated platform based on GIS and IoT, so as to solve the problems mentioned in the background art.

[0005] 1. Traditional solutions rely solely on a single sensor to define the impact range of a pipe burst, without considering the pipeline topology and pressure wave patterns, resulting in significant deviations in range estimation. Therefore, this case study reverse-tracks upstream nodes, constructs a pressure anomaly propagation map, and dynamically calculates a pressure wave velocity correction model, which can accurately determine the impact range and reduce leakage.

[0006] 2. Because traditional valve closing commands lack precise boundaries and priorities, they are prone to either missed or over-closing. Therefore, this case study generates valve closing boundaries by calculating the pressure attenuation gradient and generates tiered valve closing commands based on connectivity weights and distances. This optimizes valve closing operations and ensures stable water supply.

[0007] To achieve the above objectives, one of the objectives of this invention is to provide a method for intelligent analysis, processing, and decision support of massive data in a smart water management integrated platform based on GIS and IoT, comprising the following steps:

[0008] S1. Real-time monitoring of pressure sensor data. When the pressure value of the target sensor exceeds the threshold and continues to drop within a continuous preset period, the corresponding pipeline node is marked as a pipe burst monitoring point. Based on the coordinates and pipe diameter data of this point in the GIS topology network, an initial influence domain is generated.

[0009] S2. Starting from the burst pipe monitoring point, trace the upstream node in reverse along the water flow of the pipe network within the initial influence domain, extract the time series data of the associated sensors in the domain, compare the time difference of the pressure anomaly between the burst pipe monitoring point and the upstream sensor, combine the GIS spatial length of the pipe section, dynamically calculate the pressure wave velocity and correct the hydraulic model, and construct a pressure anomaly propagation map in the spatiotemporal dimension.

[0010] S3. Based on the pressure anomaly propagation map, identify the first sensor that detects the pressure anomaly as the origin of attenuation calculation, calculate the pressure attenuation gradient value layer by layer along the pipeline topology path, and when the pressure attenuation gradient value attenuates to a preset critical threshold, automatically generate the valve closing boundary range at the corresponding pipeline topology location. Within the valve closing boundary range, generate a graded valve closing instruction set based on the valve's connectivity weight in the GIS topology network and its spatial geometric distance from the attenuation calculation origin.

[0011] S4. After executing the graded valve closing instruction set, monitor the change in the recovery rate of the residual pressure value of the target sensor within the initial influence domain in real time. By analyzing the deviation of this rate from the hydraulic model prediction baseline curve, verify the effectiveness of the valve closing boundary range.

[0012] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0013] This invention traces upstream nodes from the pipe burst monitoring point, dynamically calculates pressure wave velocity by combining the time difference of pressure anomalies with the spatial length of the pipe segment, and generates a spatiotemporal propagation map after correcting the hydraulic model. This clearly shows the diffusion path of pressure anomalies along the pipe network. Simultaneously, it adjusts the diffusion radius segmentally based on pipe diameter and material, solving the range estimation bias caused by traditional single-sensor data. This provides accurate spatial boundary references for subsequent valve closure operations, reducing the risk of leakage expansion or over-closure. Furthermore, it determines the valve closure boundary range by using pressure attenuation gradient values ​​and calculates operation priorities by combining valve connectivity weights and spatial distance coefficients, thus dividing the valve... The system is divided into three operation levels to ensure that critical valves are closed first, preventing leakage caused by unauthorized closures and minimizing the impact of unnecessary valve closures on normal water supply. This balances fault control with the demand for domestic water. After valve closure, the system monitors the deviation between the pressure recovery rate and the predicted curve to verify the effectiveness of the valve closure boundary. If the valve closure is ineffective, the system automatically lowers the critical threshold, recalculates the boundary, and generates supplementary instructions. At the same time, the system updates the historical parameter database to achieve model self-learning. This closed-loop optimization process enhances the system's adaptability to complex pipeline network conditions, ensures the continuous effectiveness of decision-making, reduces water waste and maintenance costs, and improves the level of refined management of urban water affairs. Attached Figure Description

[0014] Figure 1 This is a flowchart illustrating the overall workflow of the present invention. Detailed Implementation

[0015] 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.

[0016] Please see Figure 1 As shown, this embodiment provides a method for intelligent analysis, processing, and decision support of massive data in a smart water management integrated platform based on GIS and IoT, including the following steps:

[0017] S1. Real-time monitoring of pressure sensor data. When the pressure value of the target sensor exceeds the threshold and continues to drop within a continuous preset period, the corresponding pipeline node is marked as a pipe burst monitoring point. Based on the coordinates and pipe diameter data of this point in the GIS topology network, an initial influence domain is generated.

[0018] The generation of the initial influence domain includes:

[0019] After marking the pipe burst monitoring points, an initial impact domain needs to be generated to accurately define the direct impact range in the early stages of the burst. This process combines GIS pipe network topology and pipe attributes to achieve fine-grained division. Based on the pipe diameter data of the burst monitoring points, a preset pipe diameter-diffusion radius mapping table is queried. This table is constructed based on historical burst data and hydraulic simulation results to determine the basic diffusion radius, delineate the initial range of the impact domain, and ensure that the diffusion range matches the pipeline's transport capacity. All hydraulically connected pipe segments centered on the monitoring points are extracted from the GIS pipe network topology. When extending along the pipeline to tee or cross branch nodes, the boundaries need to be automatically segmented to form polygon vertices. The automatic segmentation adopts the "branch priority segmentation algorithm".

[0020] When extending to branch nodes, first identify the pipe diameter of each branch pipe at the node. If the main pipe diameter is larger than the branch pipe diameter, prioritize extending along the main pipe direction by 1.5 times the base diffusion radius. Then, allocate the extension length of each branch pipe according to the pipe diameter ratio. For example, if the main pipe extends 5 meters, the branch pipe extends 4 meters according to a pipe diameter ratio of 0.8. Mark the apex at each extension endpoint and branch node, and record the node type. T-junctions are marked as T-shaped apexes, and cross-junctions are marked as cross-shaped apexes. This method of dynamically allocating the extension distance according to the importance of the pipes makes the boundary segmentation more closely match the actual hydraulic influence path of the pipe network, avoiding the range distortion caused by simple equal segmentation. Afterwards, combine the permeability coefficient corresponding to the pipe segment material type to perform segmented compensation adjustment of the base diffusion radius. The specific process is as follows:

[0021] The connecting pipe section is divided into segments based on material, such as cast iron pipe, steel pipe, and PE pipe. The permeability coefficient of each segment is retrieved from a material-permeability coefficient comparison table. A higher permeability coefficient indicates poorer pipe sealing, and the easier it is for the impact of a pipe burst to spread. The compensation coefficient is calculated as (permeability coefficient of the segment / permeability coefficient of the cast iron pipe) × 0.3 + 1 (with cast iron pipe as the baseline, the compensation coefficient range is 1.0-1.5). The base diffusion radius is then multiplied by the compensation coefficient to obtain the actual diffusion radius of the segment. For example, if the permeability coefficient of the PE pipe is 1.2 times that of the cast iron pipe, the compensation coefficient is 1.06, and the actual diffusion radius = base diffusion radius × 1.06. By adjusting the segments, the diffusion range can reflect the differences in leakage characteristics of pipes of different materials, thus improving the impact... To improve the accuracy of the domain, all vertices are connected to form a closed polygon. Centered on the burst pipe monitoring point, the boundary distances of each pipe segment are determined according to the adjusted actual diffusion radius. The vertices and extension endpoints at the branch nodes are connected in the order of the pipe network topology. For non-straight pipe segments, Bézier curves are used to smoothly connect adjacent vertices, forming an irregular polygon covering the direct impact area of ​​the burst pipe. This polygon is marked as the initial impact domain in the GIS system. This polygon includes both the direct leakage area around the burst pipe point and reflects the constraint of the pipe network structure on the impact range through branching and material compensation. This provides an accurate spatial benchmark for subsequent pressure anomaly propagation analysis and effectively avoids the range estimation deviation caused by neglecting pipe network details in traditional methods.

[0022] S2. Starting from the burst pipe monitoring point, trace the upstream node in reverse along the water flow of the pipe network within the initial influence domain, extract the time series data of the associated sensors in the domain, compare the time difference of the pressure anomaly between the burst pipe monitoring point and the upstream sensor, combine the GIS spatial length of the pipe section, dynamically calculate the pressure wave velocity and correct the hydraulic model, and construct a pressure anomaly propagation map in the spatiotemporal dimension.

[0023] Reverse tracing of upstream nodes specifically includes:

[0024] After generating the initial influence domain, to trace the propagation path of pressure anomalies in the pipeline network, it is necessary to trace upstream nodes in reverse from the burst monitoring point. This process achieves precise positioning by combining GIS topology and sensor data. Pre-set water flow direction arrow data in the GIS pipeline network topology is loaded. These arrows, based on the water supply direction preset during pipeline network design, clearly mark the path of water flow from the water plant to the user. Starting from the burst monitoring point, upstream nodes directly connected are identified hop-by-hop in the reverse direction of the arrows. For example, the valve or tee node connected to the monitoring point is the first upstream node, the node connected to the node before that is the second upstream node, and so on. This allows tracing potentially affected upstream areas along the reverse direction of water flow, providing a basis for subsequent pressure anomaly analysis. To define the scope, the hydraulic connectivity between nodes is verified within the initial influence domain boundary. Hydraulic connectivity refers to the existence of a continuous, water-transferable pipeline path between two nodes, with the pipeline in a normal flow state, neither completely closed nor broken. During verification, the pipeline connection relationships between nodes are first retrieved from the GIS topology database to confirm the existence of physical connections. Then, the real-time on / off status of valves on the connecting pipe sections is queried through the IoT platform. Fully open or partially open is considered connectivity, while fully closed is considered obstruction. Simultaneously, historical hydraulic model data is used to determine whether the pipe section has lost its flow capacity due to long-term siltation. Only when all three conditions—physical connection, valves not fully closed, and normal flow capacity—are met simultaneously can hydraulic connectivity between nodes be determined. This detailed verification process... Verification ensures that blocked nodes are not included in the tracking scope, guaranteeing that subsequent analyses focus on valid nodes actually involved in pressure propagation. After identifying valid upstream nodes, all pressure sensor devices installed on these nodes are selected. These sensors collect pressure data within the pipe section in real time and are crucial for detecting pressure anomalies. An IoT data bus connects the data transmission channels between the sensors and the platform, supporting real-time data retrieval. The system retrieves the original sampling data sequence from selected sensors within the pressure anomaly time window. The time window is set from 10 minutes before the first occurrence of a pressure anomaly at the pipe burst monitoring point to the present time, ensuring coverage of the complete process before and after the anomaly. From these data sequences, the system extracts the initial recorded pressure drop value from each sensor. A timestamp for a safety threshold is set, which is based on the normal operating pressure range of the pipe section. This threshold serves as a key time-series marker. These markers accurately reflect the time when pressure anomalies arrive at each upstream node, providing a temporal basis for subsequent pressure wave velocity calculations. By loading water flow direction data to determine the tracking path, refining and verifying hydraulic connectivity to ensure node validity, and retrieving sensor data and extracting time-series markers, the reverse tracing process not only clarifies spatial relationships based on GIS topology but also captures pressure changes in the time dimension using sensor time-series data. This lays a dual spatiotemporal foundation for constructing a pressure anomaly propagation map, making subsequent pressure wave velocity calculations and model corrections more accurate and effectively overcoming the limitations of traditional methods that rely solely on single-node data.

[0025] Dynamic calculation of pressure wave velocity includes:

[0026] After completing the reverse tracing of upstream nodes and extracting key time-series markers, the pressure wave velocity needs to be dynamically calculated to accurately grasp the propagation speed of pressure anomalies in the pipeline network. This process achieves quantitative analysis by combining time difference and spatial distance. The difference between the pressure anomaly timestamps of the pipe burst monitoring point and each upstream sensor is calculated as the pressure wave propagation delay. Specifically, the timestamp of the first occurrence of pressure anomaly at the pipe burst monitoring point (denoted as T0) and the timestamp of the first occurrence of pressure anomaly at each upstream sensor (denoted as Ti, where i represents different upstream sensors) are extracted from the key time-series markers. Since the pressure wave propagates upstream from the pipe burst point, Ti must be later than T0. This propagation delay is the difference between Ti and T0. For example, if T0 is 10:00:00 and Ti of an upstream sensor is 10:00:05, then the delay is 5 seconds. This calculation can intuitively reflect the time required for the pressure wave to propagate from the burst pipe point to each upstream node, providing a quantitative basis for the time dimension of subsequent wave velocity calculation. The three-dimensional broken line path length of the pipe segment between the burst pipe monitoring point and the corresponding upstream node is retrieved from the GIS spatial database as the spatial reference distance. This length is the sum of the three-dimensional path calculated based on the actual direction of the pipeline network, including horizontal turns and vertical elevation changes, rather than the straight-line distance, which can more realistically reflect the actual propagation path length of the pressure wave. Dividing the spatial reference distance by the conduction delay time yields the measured pressure wave velocity value for that pipe section. For example, if the path length is 500 meters and the delay time is 5 seconds, the measured wave velocity is 100 meters per second. The measured pressure wave velocity is then compared with the previously preset wave velocity in the hydraulic model, and the deviation rate is calculated (deviation rate = |measured wave velocity - preset wave velocity| ÷ preset wave velocity × 100%). When the deviation rate exceeds the set tolerance threshold, it indicates that the preset wave velocity can no longer accurately reflect the actual condition of the current pipe network. At this time, the wave velocity parameters of the hydraulic model are updated using a time-weighted moving average algorithm, that is, the wave velocities of the most recent 5 times are weighted according to time, with more recent measured values ​​having higher weights. For example, the weight of the most recent value is 0. 3. The previous value was 0.25, and so on. The weighted average value is calculated as the new wave velocity parameter, and the correction time, wave velocity values ​​before and after correction, and deviation rate are recorded in the correction log to trace the model adjustment process. By accurately calculating the time difference to obtain the delay duration, combining it with the three-dimensional path length to obtain the measured wave velocity, and dynamically correcting the model parameters based on the deviation rate, this process not only quantifies the propagation characteristics of pressure waves, but also ensures the consistency between the hydraulic model and the actual operating state of the pipeline network through real-time correction. This provides reliable wave velocity data support for the subsequent construction of pressure anomaly propagation maps, effectively improves the accuracy of pressure anomaly propagation analysis, and avoids prediction deviations caused by the solidification of model parameters.

[0027] The construction of the pressure anomaly propagation map includes:

[0028] After dynamically calculating the pressure wave velocity and correcting the hydraulic model, a pressure anomaly propagation map needs to be constructed to visually represent the propagation pattern of pressure anomalies in the pipeline network. This map integrates spatial topology and temporal characteristics, providing a visualization basis for subsequent analysis. Using the GIS pipeline network topology as the spatial coordinate system base, that is, utilizing the existing pipeline spatial coordinate system in the GIS system as the spatial reference frame for the map, ensures that the spatial location of the map completely corresponds to the actual pipeline network. This allows the map to accurately reflect the spatial path of pressure anomaly propagation, providing a reliable benchmark for spatial topology analysis. The spatial geographic coordinates of each pressure sensor (obtained from the sensor's metadata, including specific latitude and longitude information) are used. The pressure anomaly is directly mapped to the node positions in the graph. Each node represents a pipeline node where a pressure sensor is located. The size of the nodes can be differentiated according to the monitoring accuracy level of the sensor. This operation can clearly mark the key points involved in pressure anomaly monitoring, facilitating the rapid location of each sensor in the graph. The direction of pressure anomaly propagation is indicated by time-series connecting lines with arrows. Since the pressure anomaly propagates upstream along the pipeline, the arrows uniformly point to the upstream sensor nodes. At the same time, the thickness of the connecting lines is dynamically adjusted according to the magnitude of the pressure wave velocity, thus intuitively reflecting the difference in propagation speed. This design can clearly show the propagation path and direction of pressure anomalies in space. By combining the thickness of the line, the propagation speed characteristics can be quickly determined. Dynamic parameters such as the percentage of pressure drop, the duration of conduction delay in seconds, and the measured wave velocity value of the pipe segment are embedded in the node attribute table. The percentage of pressure drop is calculated as (initial pressure - minimum pressure) ÷ initial pressure × 100%, the conduction delay is the difference between Ti and T0 calculated above, and the measured wave velocity value of the pipe segment is the ratio of the spatial reference distance to the delay duration. The embedding of these parameters enables each node to not only be a spatial marker but also carry rich temporal and quantitative information, providing data support for time series backtracking analysis. At the same time, the pipe segment material code and pipe diameter value are marked in the connection line attribute, and this information is directly related to... The physical properties of pipe segments can help analyze the impact of material and pipe diameter on the propagation of pressure anomalies, enhancing the analytical depth of the map. Through the above steps, the final pressure anomaly propagation map is a multi-dimensional dynamic network model that supports spatial topology analysis and temporal backtracking. It not only preserves the spatial topology of the GIS pipe network but also incorporates the temporal parameters and pipe segment properties of pressure anomaly propagation. Detailed parameters can be viewed by clicking on nodes or connecting lines, and the pressure anomaly propagation status at different times can be traced back by sliding along the time axis. This provides an intuitive and comprehensive visualization tool for subsequently determining the origin of attenuation calculation and analyzing pressure attenuation patterns, effectively improving the efficiency and accuracy of pressure anomaly propagation analysis.

[0029] S3. Based on the pressure anomaly propagation map, identify the first sensor that detects the pressure anomaly as the origin of attenuation calculation, calculate the pressure attenuation gradient value layer by layer along the pipeline topology path, and when the pressure attenuation gradient value attenuates to the preset critical threshold, automatically generate the valve closing boundary range at the corresponding pipeline topology location. Within the valve closing boundary range, generate a graded valve closing instruction set based on the valve's connectivity weight in the GIS topology network and its spatial geometric distance from the attenuation calculation origin.

[0030] The calculation of the pressure decay gradient includes:

[0031] After constructing the pressure anomaly propagation map, to accurately determine the attenuation boundary of the pressure anomaly, it is necessary to calculate the pressure attenuation gradient value. This process achieves quantitative analysis by combining the pipeline network topology and pipe segment attributes. The origin of attenuation calculation is identified from the pressure anomaly propagation map. This origin is the first sensor node in the map that detects the pressure anomaly, i.e., the starting point of the pressure anomaly propagation. Starting from this origin, the process expands outward along the pipeline network topology path, traversing adjacent nodes level by level. Specifically, a "breadth-first hierarchical traversal method" is adopted.

[0032] The origin of the attenuation calculation is set as layer 0. All directly connected adjacent nodes are traversed and marked as layer 1. Then, starting from the nodes in layer 1, the unmarked adjacent nodes of each node are traversed and marked as layer 2, and so on, until the initial influence domain boundary is reached. Nodes in each layer are sorted in ascending order of topological distance from the origin. This hierarchical expansion method clearly reflects the hierarchical relationship of pressure anomalies propagating outward from the origin, providing an ordered sequence of nodes for subsequent gradient calculations. When expanding to a new node, the material type of the pipe segment to which the node belongs is first queried. A preset attenuation coefficient benchmark table is then called. This table presets basic attenuation coefficients based on the pressure conduction characteristics of different materials. The absolute value of the attenuation at the current layer is then calculated by combining the pipe diameter compensation coefficient and the service life reduction factor. The pipe diameter compensation coefficient is calculated as follows:

[0033] Taking the standard pipe diameter (200mm) as the benchmark, the square root of the ratio of the actual pipe diameter to the standard pipe diameter is calculated (the compensation coefficient for a pipe diameter of 300mm is √(300 / 200)≈1.22). The larger the pipe diameter, the slower the pressure decay and the larger the compensation coefficient. The service life reduction factor is calculated as follows: 1-(service life / design service life)×0.3 (e.g., for a pipe designed for a service life of 30 years, the reduction factor after 10 years of use is 1-(10 / 30)×0.3=0.9). The longer the service time, the faster the pressure decay caused by pipe aging and the smaller the reduction factor. The influence of pipe diameter and service life is quantified as a dynamic coefficient rather than a fixed value, making the attenuation calculation more closely reflect the actual pipeline condition. The final absolute value of the attenuation is calculated as: Basic Attenuation Coefficient × Pipe Diameter Compensation Coefficient × Service Life Reduction Factor × Pipe Segment Length. This pipe segment is the length of the pipeline between the current node and the previous level node. For example, if a pipe segment is a cast iron pipe (basic coefficient 0.05), 300mm diameter (compensation coefficient 1.22), with a service life of 10 years (reduction factor 0.9), and a length of 50 meters, then the absolute value of the attenuation is 0.05 × 1.22 × 0.9 × 50 ≈ 2.75. After calculating the attenuation at the current level, the gradient value of the previous node is subtracted from this attenuation to obtain the gradient value of this node. Initially, the gradient value of the origin of the attenuation calculation is set as the initial amplitude of the pressure anomaly, representing the maximum pressure drop. The gradient value of the first-level node is calculated as: Origin Gradient Value - First-Level Attenuation. The gradient value of the second-layer node is equal to the gradient value of the first-layer node minus the attenuation of the second-layer node. This process is repeated, calculating the gradient value of each node layer by layer. These gradient values ​​are then connected according to the pipeline topology path to form a gradient value curve continuously distributed along the pipeline path. The horizontal axis represents the topological distance from the origin, and the vertical axis represents the gradient value. Finally, the gradient values ​​of all nodes are stored in the attribute set of the GIS topology nodes for easy subsequent querying and analysis. By traversing nodes layer by layer to clarify the calculation order, combining dynamic coefficients to accurately calculate the attenuation, and deriving the gradient curve layer by layer, the calculation process of the pressure attenuation gradient value reflects the attenuation law of pressure anomalies with propagation distance, and also incorporates the influence of actual factors such as pipeline material, pipe diameter, and service life. This allows the gradient value to truly reflect the propagation and attenuation characteristics of pressure anomalies, providing a quantitative basis for the subsequent generation of valve closure boundaries and effectively improving the accuracy of boundary delineation.

[0034] The generated valve closing boundary range includes:

[0035] After calculating the pressure attenuation gradient value and forming a continuously distributed gradient curve, a valve closure boundary range needs to be generated to determine the effective valve closure operation range. This process achieves precise division by tracking gradient value changes and combining them with pipeline network topology characteristics. First, the pipeline node where the pressure attenuation gradient value first falls below a preset critical threshold is located from the gradient curve. This critical threshold is set based on the safe operating pressure gradient of the pipeline network. A value below this indicates that the impact of pressure anomalies has weakened to a controllable range. A boundary starting anchor point is set at this node location. The specific setting process is as follows:

[0036] The spatial coordinates of the node are marked using a GIS system, and the material, diameter, and other attributes of the pipe segment to which it belongs are recorded. A "starting anchor point" label is added to the node in the topology network. The logic is that the node where the gradient value first falls below the critical threshold is the turning point where the pressure anomaly's influence shifts from significant to weak. Using this as the boundary starting point ensures that the valve closure range covers the affected area while avoiding excessive expansion. The search continues upstream along the topological path from the starting anchor point. Because the pressure anomaly propagates upstream, there may still be affected areas upstream. The gradient value changes of nodes along the path are monitored in real time. When the gradient value of a node rises back above the critical threshold, a boundary termination anchor point is set at that node, using the same method as the starting anchor point, marking the coordinates... The attributes are added with a "Termination Anchor Point" tag, connecting all pipeline paths between the starting and ending anchor points. Specifically, all connected pipe segments between the two points are extracted using GIS topology analysis. The endpoints of these pipe segments are then connected sequentially to form a closed polygon, i.e., a hydraulic isolation closed loop. The function of this closed loop is to prevent the pressure anomaly from spreading further by closing the valves within the loop, thus forming a hydraulic isolation area. Its formation logic utilizes the connectivity of the pipeline topology to ensure that the closed loop can completely surround the upstream area affected by the pressure anomaly. When the closed loop traverses a pipeline ring structure, such as a loop path in a ring network, to reduce the impact of valve closure on normal water supply, the optimal segmentation algorithm is automatically activated to select the segmentation path with the fewest interruptions to the main pipeline. This algorithm introduces a "main pipeline priority index":

[0037] First, identify the priority level of all main pipes within the closed loop (determined based on pipe diameter, water volume, etc.; for example, pipes with a diameter ≥ 500mm that supply the main water to the area are classified as primary main pipes, those between 300-500mm are secondary, and those below are branch pipes). Assign a priority index of 3 to primary main pipes, 2 to secondary main pipes, and 1 to branch pipes. Traverse all possible segmentation paths of the closed loop through the ring structure, and calculate the sum of the priority indices of the main pipes interrupted on each path. If a path interrupts one primary main pipe and one secondary main pipe, the sum is 3 + 2 = 5. Select the path with the smallest sum as the optimal segmentation path, and integrate the optimal segmentation path with the original closed loop. The final valve closure boundary range is generated by updating the boundary line of the closed loop in the GIS system, extending it along the optimal segmentation path. This ensures that all valves that need to be closed are included within the boundary range, while minimizing the impact on the main pipeline. The boundary range is determined by setting start and end anchor points, the connection path forms a closed loop to achieve isolation, and the boundary path in the ring network is optimized using the optimal segmentation algorithm. The generated valve closure boundary range can accurately surround the area affected by abnormal pressure and reduce interference with normal water supply. This provides a scientific spatial basis for the subsequent generation of a tiered valve closure instruction set, effectively improving the accuracy and feasibility of valve closure operations.

[0038] Connection weight calculation includes:

[0039] After generating the valve closure boundary range, to clarify the priority of valve closure operations, it is necessary to calculate the valve's connectivity weight. This weight comprehensively reflects the importance of the valve in the pipeline network and provides a quantitative basis for graded valve closure. The number of pipelines directly connected to each valve device in the GIS topology network is counted as the basic connectivity value. The basic connectivity value reflects the valve's control range over pipeline branches. The more pipelines connected, the more significant the valve's pivotal role in the pipeline topology. The specific process is as follows:

[0040] Using the topology analysis function of the GIS system, the location of each valve in the pipeline network is determined. The system traverses all directly connected pipes (excluding indirect connections) and counts the number of pipes. For example, if a valve is directly connected to 3 pipes, its basic connectivity value is 3. This value directly reflects the physical connection scale of the valve, laying the foundation for subsequent weight calculations. The system also identifies the hierarchical depth of the pipeline network zone where the valve is located within the global topology and assigns it an exponential weighting coefficient. The hierarchical depth reflects the importance of the valve's position in the water supply path; the closer to the water plant, the deeper the hierarchical level, and the greater the impact on the overall water supply. The specific process is as follows:

[0041] Taking the water supply origin of the water plant as the root node, the network is divided into levels according to the pipe network topology. For example, the root node is level 1, the zone to which the pipe directly connected to the root node belongs is level 2, and so on. The path analysis function of the GIS system is used to determine the level depth (denoted as n) of the zone where each valve is located. Then, the coefficient is calculated according to the formula "exponential weighting coefficient = 2^(n-1)" (for example, the weighting coefficient of level 3 is 2^(3-1) = 4). The deeper the level, the faster the coefficient increases, thus highlighting the importance of deep-level valves. This exponential growth design can more accurately reflect the differences in the impact of different levels on the overall water supply, avoiding insufficient differentiation of importance caused by linear weighting. Then, the number of water meters downstream affected after the valve is closed is calculated as an impact factor. The impact factor reflects the scope of the impact of valve closure on user water use. The more meters affected, the more cautious the valve closure needs to be. The specific process is as follows:

[0042] By using GIS topology tracking to trace all connecting pipe segments downstream of the valve, the water meters connected to these segments are located, and the total number of water meters is counted (e.g., if there are 500 water meters downstream of a valve, the impact factor is 500). Water meters are assigned weights according to water usage type (e.g., industrial water meters have a weight of 1.5, and residential water meters have a weight of 1). The weighted total number of water meters is calculated as the final impact factor (e.g., for 300 residential water meters + 200 industrial water meters, the impact factor = 300 × 1 + 200 × 1.5 = 600), making the impact factor more closely reflect actual water usage impact. A linear normalization algorithm is used to fuse the basic connectivity value, hierarchical weighting coefficients, and impact factor to generate a standardized comprehensive connectivity weight value. The specific process is as follows:

[0043] The three indicators are normalized (i.e., (indicator value - minimum value) ÷ (maximum value - minimum value) to unify the numerical range to 0-1). Then, a comprehensive value is calculated according to the weight ratio of "basic connectivity value × 0.3 + hierarchical weighting coefficient × 0.4 + influence factor × 0.3". The weight ratio is set according to the importance of the indicators to the valve closing decision. The higher the comprehensive connectivity weight value, the higher the priority of the valve in the valve closing operation. By statistically analyzing the basic connectivity value to reflect the physical connection scale, assigning an exponential coefficient according to the hierarchical depth to highlight the global impact, and combining the number of weighted water meters to reflect the user impact, the comprehensive weight is obtained after normalization. This process comprehensively considers the topological position and actual impact of the valve, making the classification of valve closing priorities more scientific and reasonable. It provides a reliable basis for the subsequent generation of accurate hierarchical valve closing instruction sets and effectively balances the needs of fault control and user water supply guarantee.

[0044] The generation of a tiered valve closing instruction set includes:

[0045] After calculating the comprehensive connectivity weight value of each valve, to ensure that valve closure operations can quickly control the impact of pipe bursts and minimize interference with normal water supply, a tiered valve closure instruction set needs to be generated within the valve closure boundary. All valve equipment is traversed within the valve closure boundary, and the valve with the highest comprehensive connectivity weight value is prioritized as the primary valve closure target. This is because valves with higher comprehensive connectivity weight values ​​play a more significant pivotal role in the pipeline topology, control more pipeline branches, and have a greater impact on the overall water supply. Prioritizing the closure of these valves can quickly cut off the critical path of abnormal pressure propagation, curb the expansion of leakage at its source, and buy time for subsequent valve closure operations. Using the spatial coordinates of the attenuation calculation origin as a reference, the Euclidean distance between the latitude and longitude coordinates of each valve within the boundary is calculated and normalized to a distance coefficient. The specific process is as follows:

[0046] Extract the latitude and longitude coordinates (denoted as (x0, y0)) of the attenuation calculation origin and the latitude and longitude coordinates (denoted as (xi, yi)) of each valve from the GIS system. Calculate the straight-line distance between each valve and the origin using the Euclidean distance formula. Then, find the maximum distance (denoted as Dmax) and minimum distance (denoted as Dmin) from the origin among all valves. Normalize the distance coefficient using the formula "distance coefficient = (distance - Dmin) / (Dmax - Dmin)" so that the distance coefficient ranges from 0 to 1. The closer the valve is to the origin, the closer the coefficient is to 0; the farther away it is, the closer it is to 1. This coefficient reflects the spatial correlation between the valve and the source of pressure anomalies, providing a spatial dimension reference for priority scoring. Calculate the valve operation priority score based on the decision model of "comprehensive connectivity weight × priority factor A + distance coefficient × priority factor B", where priority factors A and B are set according to the valve closing strategy. The specific operation process is as follows:

[0047] The overall connectivity weight (normalized, range 0-1) of each valve is multiplied by factor A, and the distance coefficient is multiplied by factor B. The two products are then added together to obtain the priority score (e.g., if a valve has an overall connectivity weight of 0.9 and a distance coefficient of 0.2, then the score = 0.9 × 0.7 + 0.2 × 0.3 = 0.63 + 0.06 = 0.69). This score combines the topological importance and spatial distance of the valve, making the priority ranking more closely reflect the actual valve closure requirements. Valves are divided into three operating levels in descending order of score. The specific process is as follows:

[0048] All valves are prioritized and ranked from highest to lowest score. The total score is calculated, and grading thresholds are determined according to a 30%, 50%, and 20% ratio (the top 30% of valves are Level 1, the middle 50% are Level 2, and the bottom 20% are Level 3). Level 1 valves are those with the highest scores and must be closed first to quickly control the core affected area. Level 2 valves are those with the next highest scores and are closed sequentially after Level 1 valves to further reduce the impact range. Level 3 valves are those with the lowest scores and can be closed in the final stage or flexibly adjusted according to the actual situation. This grading method ensures that critical valves are operated first, avoids inefficiency caused by chaotic valve closing sequences, makes valve closing instructions more organized and executable, effectively improves the accuracy and timeliness of emergency response to pipe bursts, and further balances the needs of fault control and water supply stability.

[0049] S4. After executing the graded valve closing command set, monitor the change in the recovery rate of the residual pressure value of the target sensor within the initial influence domain in real time. By analyzing the deviation of this rate from the hydraulic model prediction baseline curve, verify the effectiveness of the valve closing boundary range.

[0050] In the integrated smart water management platform based on GIS and IoT, each step—from marking the monitoring points of the burst pipe to generate the initial impact domain, to tracing upstream nodes in reverse and constructing a pressure anomaly propagation map, to calculating the pressure attenuation gradient and generating the valve closure boundary range—is closely linked, forming a logically coherent emergency response process for burst pipes. The generation of the initial impact domain defines the basic scope for subsequent analysis, while tracing upstream nodes in reverse within this scope involves following the propagation path of the pressure anomaly along the opposite direction of water flow. By verifying the hydraulic connectivity between nodes, it is ensured that the traced nodes are all effective nodes actually involved in pressure propagation. This lays the foundation for accurately capturing the temporal characteristics of pressure anomalies. Dynamically calculating the pressure wave velocity and correcting the hydraulic model combines the time-dimensional pressure anomaly propagation data with the spatial dimension of pipe segment length data, making the model more closely match the actual operating state of the pipe network. This provides reliable wave velocity parameters for constructing the pressure anomaly propagation map. The construction of the pressure anomaly propagation map integrates the spatial information of the GIS topology and the temporal data of the pressure anomaly, intuitively showing the propagation law of the pressure anomaly in the pipe network and providing a clear visual basis for determining the origin of pressure attenuation calculation. Based on this, the pressure attenuation gradient value is calculated. By traversing nodes layer by layer and combining pipe segment attributes to quantify the attenuation amount, the resulting gradient curve can accurately reflect the attenuation trend of pressure anomalies. This naturally leads to the generation of the valve closure boundary range. Anchor points are set based on the critical change of the gradient value, and the connection path forms a hydraulic isolation closed loop to ensure that the valve closure range can cover the affected area while reducing interference with normal water supply. After the valve closure boundary range is determined, calculating the valve connectivity weight becomes crucial. By comprehensively considering the physical connection scale of the valve, its hierarchical depth in the pipe network, and its impact on users, a quantitative standard for valve closure priority is provided. Finally, a hierarchical valve closure instruction set is generated based on the connectivity weight and distance coefficient, enabling valve closure operations to be executed in an orderly manner according to priority. From quickly controlling the core affected area to gradually narrowing the scope, the process is progressive, effectively improving the emergency response efficiency and processing accuracy of the smart water platform for pipe burst events.

[0051] This invention marks pipe burst monitoring points and generates an initial influence domain, traces upstream nodes in reverse, constructs a pressure anomaly propagation map and corrects the hydraulic model, calculates the pressure attenuation gradient to generate valve closure boundaries, generates a tiered valve closure command set, verifies the effectiveness of valve closure and dynamically optimizes it. This method integrates GIS topology and IoT data, solving the problems of large estimation deviations in the traditional pipe burst influence range and lack of accuracy in valve closure commands. It improves the efficiency of pipe burst emergency response, reduces water waste, ensures water supply stability, and is suitable for refined urban water management.

[0052] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely preferred examples and are not intended to limit the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for intelligent analysis, processing, and decision support of massive data in a smart water management integrated platform based on GIS and IoT, characterized by: Includes the following steps: S1. Real-time monitoring of pressure sensor data. When the pressure value of the target sensor exceeds the threshold and continues to drop within a continuous preset period, the corresponding pipeline node is marked as a pipe burst monitoring point. Based on the coordinates and pipe diameter data of this point in the GIS topology network, an initial influence domain is generated. S2. Starting from the burst pipe monitoring point, trace the upstream node in reverse along the water flow of the pipe network within the initial influence domain, extract the time series data of the associated sensors in the domain, compare the time difference of the pressure anomaly between the burst pipe monitoring point and the upstream sensor, combine the GIS spatial length of the pipe section, dynamically calculate the pressure wave velocity and correct the hydraulic model, and construct a pressure anomaly propagation map in the spatiotemporal dimension. The construction of the pressure anomaly propagation map includes: Using the GIS pipeline network topology as the spatial coordinate system base, the spatial geographic coordinates of each pressure sensor are mapped to the node positions of the map. The direction of pressure anomaly propagation is represented by time-series connection lines with arrows pointing to upstream sensor nodes. Dynamic parameters such as the percentage of pressure drop, the duration of propagation delay in seconds, and the measured wave velocity value of the pipe segment are embedded in the node attribute table. The pipe segment material code and pipe diameter value are marked in the connection line attributes to form a multi-dimensional dynamic network model that supports spatial topology analysis and time-series backtracking as a pressure anomaly propagation map. S3. Based on the pressure anomaly propagation map, identify the first sensor that detects the pressure anomaly as the origin of attenuation calculation, calculate the pressure attenuation gradient value layer by layer along the pipeline topology path, and when the pressure attenuation gradient value attenuates to a preset critical threshold, automatically generate the valve closing boundary range at the corresponding pipeline topology location. Within the valve closing boundary range, generate a graded valve closing instruction set based on the valve's connectivity weight in the GIS topology network and its spatial geometric distance from the attenuation calculation origin. The generated valve boundary range includes: Set a boundary starting anchor point at the location of the pipeline node where the pressure decay gradient value first falls below the preset critical threshold, and continue to expand the search upstream along the topological path. When a node is detected where the gradient value rises back to above the critical threshold, set a boundary ending anchor point. Connect all pipeline paths between the starting anchor point and the ending anchor point to form a hydraulic isolation closed loop. When the closed loop crosses the pipeline ring structure, the optimal segmentation algorithm is automatically started to select the segmentation path with the fewest interruptions to the main pipeline and generate the final valve closing boundary range. S4. After executing the graded valve closing instruction set, monitor the change in the recovery rate of the residual pressure value of the target sensor within the initial influence domain in real time. By analyzing the deviation of this rate from the hydraulic model prediction baseline curve, verify the effectiveness of the valve closing boundary range.

2. The method for intelligent analysis, processing, and decision support of massive data in a smart water affairs integrated platform based on GIS and IoT as described in claim 1, characterized in that, The generation of the initial influence domain includes: Based on the pipe diameter data of the burst pipe monitoring point, the basic diffusion radius is determined by querying the preset pipe diameter-diffusion radius mapping table. All hydraulically connected pipe segments centered on the monitoring point are extracted in the GIS pipe network topology. When the pipe extends along the pipeline to the tee or cross branch node, the boundary is automatically divided to form polygon vertices. The basic diffusion radius is adjusted by segment compensation based on the permeability coefficient corresponding to the pipe segment material type. Finally, an irregular polygonal influence domain covering the area directly affected by the burst pipe is generated and marked as the initial influence domain.

3. The method for intelligent analysis, processing, and decision support of massive data in a smart water affairs integrated platform based on GIS and IoT as described in claim 1, characterized in that, The reverse tracing of upstream nodes specifically includes: Load the pre-set water flow direction arrow data in the GIS pipe network topology, identify directly connected upstream nodes hop by hop starting from the burst pipe monitoring point, verify the hydraulic connectivity between nodes within the initial influence domain boundary, screen out all pressure sensor devices with continuous water flow paths to the monitoring point, retrieve the original sampling data sequence of the selected sensors in real time within the pressure anomaly time window through the IoT data bus, and extract the timestamp of the first recorded pressure value drop below the set safety threshold of each sensor as the key time sequence marker point.

4. The method for intelligent analysis, processing, and decision support of massive data in a smart water affairs integrated platform based on GIS and IoT as described in claim 1, characterized in that, The dynamic calculation of pressure wave velocity includes: The difference between the timestamps of the pressure anomaly at the pipe burst monitoring point and each upstream sensor is calculated as the pressure wave propagation delay. The three-dimensional polyline path length of the corresponding pipe segment is retrieved from the GIS spatial database as the spatial reference distance. The spatial reference distance is divided by the propagation delay to obtain the measured pressure wave velocity value of the pipe segment. The deviation rate between the measured pressure wave velocity and the preset wave velocity of the hydraulic model is compared. When the deviation rate exceeds the tolerance threshold, the wave velocity parameters of the hydraulic model are updated using a time-weighted moving average algorithm and the correction log is recorded.

5. The method for intelligent analysis, processing, and decision support of massive data in a smart water affairs integrated platform based on GIS and IoT as described in claim 1, characterized in that, The calculation of the pressure attenuation gradient value includes: Starting from the origin of attenuation calculation identified by the pressure anomaly propagation map, the process expands outward along the pipeline topology path, traversing adjacent nodes layer by layer. When a new node is reached, the material type of the pipe segment to which the node belongs is queried, and a preset attenuation coefficient benchmark table is called. The absolute value of the attenuation of the current level is calculated by combining the pipe diameter compensation coefficient and the service life reduction factor. The gradient value of the previous node is subtracted from the attenuation of the current level to obtain the gradient value of the current node, forming a gradient value curve that is continuously distributed along the pipeline path and stored in the topology node attribute set.

6. The method for intelligent analysis, processing, and decision support of massive data in a smart water affairs integrated platform based on GIS and IoT as described in claim 1, characterized in that, The connection degree weight calculation includes: In the GIS topology network, the number of pipes directly connected to each valve device is counted as the basic connectivity value. The hierarchical depth of the pipe network partition where the valve is located in the global topology is identified and an exponential weighting coefficient is assigned. The number of water meters downstream affected after the valve is closed is calculated as the influencing factor. The basic connectivity value, hierarchical weighting coefficient and influencing factor are integrated through a linear normalization algorithm to generate a standardized comprehensive connectivity weight value.

7. The method for intelligent analysis, processing, and decision support of massive data in a smart water affairs integrated platform based on GIS and IoT as described in claim 1, characterized in that, The generation of the graded valve closing instruction set includes: Within the valve closure boundary, all valve equipment is traversed, and the valve with the highest comprehensive connectivity weight value is selected as the first-level valve closure target. The Euclidean distance of the latitude and longitude coordinates of each valve within the boundary is calculated based on the spatial coordinates of the attenuation calculation origin and normalized to a distance coefficient. The valve operation priority score is calculated according to the decision model of "comprehensive connectivity weight × priority factor A + distance coefficient × priority factor B". The valves are divided into three operation levels in descending order of the score.

8. The method for intelligent analysis, processing, and decision support of massive data in a smart water affairs integrated platform based on GIS and IoT as described in claim 7, is characterized in that... When verifying the validity of the valve closing boundary range, if the valve closing is found to be invalid, the optimization mechanism is automatically triggered. The pressure attenuation critical threshold is gradually lowered and the gradient value calculation is re-executed. Based on the new threshold, an expanded valve closing boundary range is generated. Within the expanded boundary, the connectivity weight calculation model and distance coefficient analysis process are reused to dynamically generate a supplementary valve closing instruction set for the newly added valve. The optimized threshold parameters and execution results are fed back to the historical parameter library of the gradient calculation model to achieve self-learning evolution.

Images