Real-time monitoring and management method for sewage pipe network operation state based on GIS and internet of things

Abstract

This invention provides a real-time monitoring and management method for the operation status of sewage pipe networks based on GIS and IoT. First, multi-parameter water quality sensors and flow monitoring devices are deployed at key nodes of the sewage pipe network to collect real-time data on liquid level, flow velocity, and pollutant concentration. Then, the sensed data is integrated into a GIS spatial analysis engine and dynamically correlated with the pipe network topology to generate a visual monitoring layer. Subsequently, when the monitored indicators exceed preset thresholds, a spatial warning is automatically triggered, and the spatial location of pollution sources or blockage points is located by combining the pipe network flow direction model and the pollutant diffusion model. Finally, maintenance work orders are generated based on the location results and dispatched to the operation and maintenance platform. This invention, through the deep integration of GIS spatial analysis and IoT sensed data, achieves visualized monitoring of the pipe network's operation status and real-time closed-loop handling of abnormal events, solving the problem of the lag in traditional manual inspections and improving the response speed and accuracy of pipe network operation and maintenance.

Description

Technical Field

[0001] This invention relates to the field of intelligent management technology for urban drainage pipe networks. Specifically, it relates to a method, system, and computer-readable storage medium for real-time monitoring and management of the operation status of sewage pipe networks based on GIS and the Internet of Things. Background Technology

[0002] Wastewater pipe networks are core infrastructure for urban water pollution prevention and public health protection. The stability and reliability of their operation are directly related to the quality of urban water environment and the safety of residents' lives. With the acceleration of urbanization, the scale of wastewater pipe networks is constantly expanding and the structure of the networks is becoming increasingly complex. The traditional manual inspection mode faces prominent problems such as insufficient coverage, delayed response, and difficulty in locating anomalies.

[0003] In the prior art, CN121638981A discloses a method for constructing a smart monitoring and early warning system for sewage pipe networks that integrates multi-source data. This method achieves monitoring and early warning by building a unified data platform that integrates pipe network spatial topology, real-time monitoring data, environmental data, and historical business data. However, this solution focuses on the integration and display of multi-source data and lacks an automated work order dispatch and closed-loop handling mechanism after an abnormal event is triggered. Abnormal response still relies on manual intervention, making it impossible to achieve fully automated closed-loop management from early warning to handling.

[0004] Publication No. CN113947033A discloses an artificial intelligence-based system and method for tracing pollutant sources in drainage pipe networks. This system acquires pollutant concentration data by distributing monitoring points throughout the drainage pipe network and then uses an artificial intelligence model for pollution source analysis. However, this approach only uses single-dimensional pollutant concentration data for source tracing, failing to fully integrate multi-dimensional hydraulic parameters such as pipe network level and flow velocity. Under complex and variable hydraulic conditions in the pipe network, the accuracy and reliability of source tracing based on a single data dimension are difficult to guarantee. Furthermore, this approach lacks deep integration with a GIS spatial analysis engine, resulting in a lack of monitoring layer construction and spatial early warning capabilities at the spatial visualization level.

[0005] Therefore, there is an urgent need for a wastewater pipe network monitoring method that can integrate multi-dimensional sensing data, GIS spatial analysis and IoT real-time monitoring technology to achieve fully automated closed-loop management of the entire process from real-time sensing, spatial early warning, pollution source location to work order dispatch. Summary of the Invention

[0006] In view of the above problems, the purpose of this invention is to provide a method, system and computer-readable storage medium for real-time monitoring and management of sewage pipe network operation status based on GIS and IoT. Through the three-layer linkage of IoT sensing layer, GIS spatial analysis layer and operation and maintenance disposal layer, the invention realizes visualized monitoring of sewage pipe network operation status, accurate location of abnormal events and automatic dispatch of operation and maintenance work orders, thus solving the problem of lag in traditional manual inspection.

[0007] The first aspect of this invention provides a method for real-time monitoring and management of the operation status of a sewage pipe network based on GIS and the Internet of Things, comprising: Deploy multi-parameter water quality sensors and flow monitoring equipment at key nodes of the sewage pipe network; The multi-parameter water quality sensor and flow monitoring equipment are used to collect real-time data on liquid level, flow rate, and pollutant concentration at pipeline nodes. The collected sensing data is connected to the GIS spatial analysis engine and dynamically correlated with the pipeline network topology data to generate a visual monitoring layer. When the monitoring index of any monitoring node exceeds the preset corresponding threshold, a spatial early warning signal is automatically triggered. In response to the aforementioned spatial early warning signal, the spatial location of the pollution source or blockage point is located by combining the pipeline flow direction model and the pollutant diffusion model. A maintenance work order is generated based on the location results, and the maintenance work order is dispatched to the operation and maintenance platform.

[0008] In this scheme, when the monitoring index of any monitoring node exceeds the preset corresponding threshold, a spatial early warning signal is automatically triggered. Specifically, this includes: setting a first-level early warning threshold and a second-level early warning threshold, wherein the risk level corresponding to the second-level early warning threshold is higher than that of the first-level early warning threshold; when the liquid level data exceeds the first liquid level threshold, a liquid level anomaly early warning signal is triggered; when the pollutant concentration data exceeds the first concentration threshold, a water quality anomaly early warning signal is triggered; when the same monitoring node simultaneously meets the triggering conditions for both the liquid level anomaly early warning and the water quality anomaly early warning, the early warning level is upgraded to a comprehensive early warning signal, wherein the response priority of the comprehensive early warning signal is higher than that of a single-indicator early warning signal.

[0009] The system accesses meteorological forecast data sources to obtain predicted rainfall data for the target pipeline area within a preset forecast period. When the predicted rainfall data exceeds a preset rainfall investigation threshold, the pipeline monitoring mode is automatically switched from the regular monitoring frequency to the rainfall-period pipeline anomaly investigation frequency. Under the rainfall-period pipeline anomaly investigation frequency, the data acquisition interval is shortened from a first acquisition interval to a second acquisition interval, where the second acquisition interval is shorter than the first acquisition interval. The real-time liquid level change data of each monitoring node during rainfall is compared with preset sunny-day baseline liquid level data to identify anomaly node sets where the liquid level rise exceeds the normal fluctuation range. Combined with the pipeline flow direction model, upstream tracing analysis is performed on the anomaly node sets to locate target pipe sections suspected of rainwater and sewage mixing or pipeline damage and leakage, and an investigation and repair work order containing the type of suspicion and the target location is generated.

[0010] This solution also includes: establishing a data communication link with the municipal pumping station dispatching system; acquiring real-time operating status data of the pumping station through the data communication link, the operating status data including pumping station start / stop status parameters, operating power parameters, and drainage flow parameters; when any monitoring node triggers the spatial early warning signal, calculating the optimal dispatching strategy for the pumping station based on the pipeline flow direction model and the real-time operating status data of the pumping station; and sending a dispatching suggestion instruction to the pumping station dispatching system, the dispatching suggestion instruction being used to adjust the start / stop status or operating power of the pumping station to alleviate the operating pressure of abnormal nodes in the pipeline network.

[0011] In this scheme, the spatial location of pollution sources or blockages by combining pipeline flow direction models and pollutant diffusion models specifically includes: extracting a set of upstream nodes that are flow-directedly associated with the node that triggers the spatial early warning signal, based on the pipeline flow direction model; obtaining the liquid level change rate, flow velocity change rate, and pollutant concentration change rate of each node in the upstream node set; inputting the liquid level change rate of each node in the upstream node set into a first source tracing analysis module to obtain a first candidate location set; inputting the flow velocity change rate of each node into a second source tracing analysis module to obtain a second candidate location set; inputting the pollutant concentration change rate of each node into a third source tracing analysis module to obtain a third candidate location set; and performing cross-validation on the first, second, and third candidate location sets, determining the node locations that simultaneously appear in at least two candidate location sets as the final spatial locations of pollution sources or blockages.

[0012] This scheme further includes: selecting a first monitoring node and a second monitoring node that are adjacent along the flow direction in the pipeline network, with the first monitoring node located upstream of the second monitoring node; after acquiring the downstream monitoring data of the second monitoring node, sending the downstream monitoring data in reverse to the data quality verification unit associated with the first monitoring node; the data quality verification unit calculating the theoretical data range of the downstream monitoring data mapped to the position of the first monitoring node based on the pipeline network flow direction model; and generating sensor calibration prompt information for the first monitoring node when the actual monitoring data of the first monitoring node exceeds the theoretical data range.

[0013] A second aspect of the present invention provides a real-time monitoring and management system for the operation status of a sewage pipe network based on GIS and the Internet of Things (IoT), comprising a memory and a processor. The memory includes a method program for real-time monitoring and management of the operation status of a sewage pipe network based on GIS and IoT. When the processor executes the method program for real-time monitoring and management of the operation status of a sewage pipe network based on GIS and IoT, it performs the following steps: Deploy multi-parameter water quality sensors and flow monitoring equipment at key nodes of the sewage pipe network; The multi-parameter water quality sensor and flow monitoring equipment are used to collect real-time data on liquid level, flow rate, and pollutant concentration at pipeline nodes. The collected sensing data is connected to the GIS spatial analysis engine and dynamically correlated with the pipeline network topology data to generate a visual monitoring layer. When the monitoring index of any monitoring node exceeds the preset corresponding threshold, a spatial early warning signal is automatically triggered. In response to the aforementioned spatial early warning signal, the spatial location of the pollution source or blockage point is located by combining the pipeline flow direction model and the pollutant diffusion model. A maintenance work order is generated based on the location results, and the maintenance work order is dispatched to the operation and maintenance platform.

[0014] In this scheme, when the monitoring index of any monitoring node exceeds the preset corresponding threshold, a spatial early warning signal is automatically triggered. Specifically, this includes: setting a first-level early warning threshold and a second-level early warning threshold, wherein the risk level corresponding to the second-level early warning threshold is higher than that of the first-level early warning threshold; when the liquid level data exceeds the first liquid level threshold, a liquid level anomaly early warning signal is triggered; when the pollutant concentration data exceeds the first concentration threshold, a water quality anomaly early warning signal is triggered; when the same monitoring node simultaneously meets the triggering conditions for both the liquid level anomaly early warning and the water quality anomaly early warning, the early warning level is upgraded to a comprehensive early warning signal, wherein the response priority of the comprehensive early warning signal is higher than that of a single-indicator early warning signal.

[0015] The system accesses meteorological forecast data sources to obtain predicted rainfall data for the target pipeline area within a preset forecast period. When the predicted rainfall data exceeds a preset rainfall investigation threshold, the pipeline monitoring mode is automatically switched from the regular monitoring frequency to the rainfall-period pipeline anomaly investigation frequency. Under the rainfall-period pipeline anomaly investigation frequency, the data acquisition interval is shortened from a first acquisition interval to a second acquisition interval, where the second acquisition interval is shorter than the first acquisition interval. The real-time liquid level change data of each monitoring node during rainfall is compared with preset sunny-day baseline liquid level data to identify anomaly node sets where the liquid level rise exceeds the normal fluctuation range. Combined with the pipeline flow direction model, upstream tracing analysis is performed on the anomaly node sets to locate target pipe sections suspected of rainwater and sewage mixing or pipeline damage and leakage, and an investigation and repair work order containing the type of suspicion and the target location is generated.

[0016] A third aspect of the present invention provides a computer-readable storage medium comprising a method program for real-time monitoring and management of the operation status of a sewage pipe network based on GIS and the Internet of Things. When the method program is executed by a processor, it implements the steps of the method program for real-time monitoring and management of the operation status of a sewage pipe network based on GIS and the Internet of Things as described in any of the preceding claims.

[0017] This invention discloses a method, system, and computer-readable storage medium for real-time monitoring and management of sewage pipe network operation status based on GIS and IoT. It achieves real-time sensing of liquid level, flow velocity, and pollutant concentration by deploying multi-parameter sensors at key nodes of the pipe network. A GIS spatial analysis engine is used to dynamically correlate the sensed data with the pipe network topology to generate a visual monitoring layer. When monitoring indicators trigger spatial warnings, the pollution source is located through multi-dimensional data cross-validation using a pipe network flow direction model and a pollutant diffusion model, and a maintenance work order is automatically generated and dispatched to the operation and maintenance platform. This invention achieves full-process automation from real-time sensing to closed-loop disposal through the three-layer linkage of the IoT sensing layer, GIS spatial analysis layer, and operation and maintenance disposal layer. It effectively solves the problems of insufficient coverage and delayed response in traditional manual inspections, improving the accuracy and efficiency of sewage pipe network operation and maintenance. Simultaneously, it can automatically detect rainwater and sewage mixing and pipe network damage and leakage during rainfall, providing accurate decision-making basis for pipe network repair and improvement. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope.

[0019] Figure 1 A flowchart of a real-time monitoring and management method for the operation status of a sewage pipe network based on GIS and IoT is shown. Figure 2 A flowchart of a multi-level threshold spatial early warning system provided by an embodiment of the present invention is shown; Figure 3 This invention provides a flowchart for troubleshooting pipeline anomalies during rainfall periods, according to an embodiment of the present invention. Figure 4 A block diagram of a real-time monitoring and management system for the operation status of a sewage pipe network based on GIS and the Internet of Things is shown. Detailed Implementation

[0020] 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.

[0021] Unless otherwise defined, all terms used in embodiments of this invention, including technical and scientific terms, shall have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in a common dictionary shall be interpreted as having a meaning consistent with their meaning in the context of the relevant art, and not as being interpreted in an idealized or highly formalized sense, unless expressly defined in this embodiment of the invention.

[0022] The terms "one," "two," and similar words used in the embodiments of this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. The terms "a," "one," or similar words do not indicate a quantity limitation, but rather indicate the presence of at least one. Similarly, terms such as "include" or "contain" mean that the element or object preceding the word encompasses the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The steps preceding or following the steps in the methods of the embodiments of this invention are not necessarily performed in precise order. Instead, various steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0023] In addition, the functional modules in the various embodiments of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0024] Figure 1 The flowchart of a real-time monitoring and management method for the operation status of a sewage pipe network based on GIS and IoT is shown.

[0025] like Figure 1 As shown, the first aspect of this invention discloses a method for real-time monitoring and management of the operation status of a sewage pipe network based on GIS and the Internet of Things, the method comprising: S102, deploy multi-parameter water quality sensors and flow monitoring equipment at key nodes of the sewage pipe network; S104, The multi-parameter water quality sensor and flow monitoring device are used to collect the liquid level data, flow velocity data and pollutant concentration data of the pipeline nodes in real time; S106 connects the collected sensing data to the GIS spatial analysis engine and dynamically associates it with the pipeline network topology data to generate a visual monitoring layer. S108, When the monitoring index of any monitoring node exceeds the preset corresponding threshold, a spatial early warning signal is automatically triggered; S110, in response to the spatial early warning signal, locate the spatial location of the pollution source or blockage point by combining the pipeline flow direction model and the pollutant diffusion model; S112, Generate a maintenance work order based on the location result, and dispatch the maintenance work order to the operation and maintenance platform.

[0026] It should be noted that the deployment of sensors at key nodes in the pipeline network in this embodiment is not arbitrary, but determined based on hydraulically characteristic nodes in the pipeline network topology. Specifically, these include junctions of main and branch pipes, turning points in the pipeline flow direction, and high-risk nodes that have historically experienced blockages or overflows. The deployed sensors include level gauges, flow meters, and multi-parameter water quality probes, with the latter capable of simultaneously detecting core water quality indicators such as chemical oxygen demand (COD), ammonia nitrogen, and pH. In actual engineering, the sensor sampling frequency is set according to the pipeline network's operating period. During peak daytime drainage periods, a high-frequency sampling frequency of once every 15 seconds is used, while during off-peak nighttime periods, the frequency can be reduced to once every 5 minutes, ensuring data timeliness while considering equipment power consumption and communication bandwidth. The collected raw data first undergoes local filtering and outlier removal at the edge computing units of each monitoring node before being uploaded to the central server via 4G or NB-IoT wireless communication modules. After receiving the sensing data, the GIS spatial analysis engine does more than simply overlay the data points onto a map. Instead, it performs spatiotemporal correlation calculations between the real-time liquid level, flow rate, and concentration data of each monitoring node and static attributes in the pipeline network topology, such as pipe segment length, diameter, slope, and pipe friction coefficient, generating a thermal layer containing the spatial distribution of the pipeline network's operational status. When the liquid level at a node rises rapidly within a short period and the flow rate at adjacent downstream nodes decreases synchronously, this often indicates a blockage in that pipe segment, triggering a spatial warning. After the warning is triggered, the system traces the liquid level change rate, flow rate change rate, and concentration change rate of each node along the pipeline flow path in reverse. It outputs candidate anomaly locations through three independent source tracing analysis paths, then takes the intersection of the results from the three paths, identifying nodes that are simultaneously matched in at least two analysis paths as the anomaly source. Finally, the system calls the maintenance personnel location database, uses a spatial distance algorithm to find the nearest available maintenance platform to the anomaly source, automatically generates an electronic work order containing the anomaly type, location coordinates, and suggested handling plan, and pushes it to the maintenance personnel's mobile terminal. The above solution compresses the cumbersome process of manual inspection, telephone reporting, and manual work order dispatch into a closed-loop link of automatic sensor triggering, automatic system analysis, and automatic work order dispatch, reducing the average response time for pipeline anomalies from several hours to minutes.

[0027] Figure 2 A flowchart of a multi-level threshold spatial early warning method provided by an embodiment of the present invention is shown.

[0028] like Figure 2As shown in the embodiment of the present invention, when the monitoring index of any monitoring node exceeds a preset corresponding threshold, the automatic triggering of a spatial early warning signal specifically includes: S202, a first-level warning threshold and a second-level warning threshold are preset, and the risk level corresponding to the second-level warning threshold is higher than that of the first-level warning threshold; S204, when the liquid level data exceeds the first liquid level threshold, a liquid level abnormality warning signal is triggered; S206, When the pollutant concentration data exceeds the first concentration threshold, a water quality anomaly warning signal is triggered; S208, when the same monitoring node simultaneously meets the triggering conditions for the abnormal liquid level warning and the abnormal water quality warning, the warning level is upgraded to a comprehensive warning signal, and the response priority of the comprehensive warning signal is higher than that of the warning signal for a single indicator.

[0029] It should be noted that in actual pipeline operation, the risk levels corresponding to a single indicator exceeding the limit and multiple indicators exceeding the limit simultaneously are completely different. For example, a single high liquid level may be a temporary backlog caused by a short-term shutdown of a downstream pumping station, which will naturally recover after a while; a single high ammonia nitrogen concentration may be an occasional discharge from a resident, with a limited impact. However, if the liquid level and concentration at a certain node both surge simultaneously, it most likely means that an upstream enterprise is illegally discharging or the pipeline section is severely blocked, requiring immediate response. In this embodiment, the first liquid level threshold is usually set to 85% of the designed fill level of the node, and the first concentration threshold is set with reference to the influent design standards of the sewage treatment plant in the area, such as triggering when the chemical oxygen demand exceeds 500 mg / L. When either the liquid level or concentration exceeds the limit alone, the system initiates the first-level response, pushes an alarm notification to the on-duty personnel, and automatically increases the sampling frequency of the node and its upstream and downstream nodes to once every 30 seconds, continuously observing for 15 minutes. If a second indicator also exceeds the limit within this observation window, the system immediately raises the response level to the highest level, directly packaging and pushing the spatial coordinates of the abnormal node, the time-series curves of all indicators within the preceding and following 5 minutes, and the pipeline flow path to the regional maintenance team. This tiered and progressive strategy avoids the fatigue of frequent, minor alarms and ensures that genuine emergencies are addressed immediately. Compared to a one-size-fits-all single threshold solution, the two-tiered progressive judgment adds a confirmation step to the system, reducing false alarm rates and avoiding delays when a real incident occurs.

[0030] Figure 3 The flowchart illustrates a method for troubleshooting pipeline anomalies during rainfall periods, as provided in an embodiment of the present invention.

[0031] like Figure 3 As shown, according to an embodiment of the present invention, it further includes: The system accesses meteorological forecast data sources to obtain predicted rainfall data for the target pipeline area within a preset forecast period. When the predicted rainfall data exceeds a preset rainfall investigation threshold, the pipeline monitoring mode is automatically switched from the regular monitoring frequency to the rainfall-period pipeline anomaly investigation frequency. Under the rainfall-period pipeline anomaly investigation frequency, the data acquisition interval is shortened from a first acquisition interval to a second acquisition interval, where the second acquisition interval is shorter than the first acquisition interval. The system compares the real-time liquid level change data of each monitoring node during rainfall with preset sunny-day baseline liquid level data to identify nodes with abnormal liquid level rises. Combined with the pipeline flow direction model, the system locates target pipe sections suspected of rainwater and sewage mixing or pipeline damage and leakage, and generates an investigation and repair work order.

[0032] It should be noted that, theoretically, sewage pipe networks are closed systems, and under normal operating conditions, their internal liquid levels should not be significantly affected by rainfall events. However, in actual engineering projects, due to issues such as rainwater pipes being mistakenly connected to sewage pipe networks (mixed rainwater and sewage), and pipe aging and damage leading to the infiltration of groundwater, river water, or rainwater, some sewage pipe sections may experience abnormal liquid level rises during rainfall. This embodiment uses the rainfall period as a natural detection window for the health status of the pipe network: when weather forecast data triggers the rainfall investigation threshold, the system automatically increases the sampling frequency to the rainfall period investigation frequency, intensively capturing the liquid level change characteristics of each node. By comparing the liquid level data of each node during rainfall with the baseline liquid level on sunny days, the system identifies target areas with abnormal liquid level rises. Then, combined with the pipe network flow direction model, upstream tracing analysis is performed to locate specific pipe sections suspected of rainwater and sewage mixing or pipe damage and leakage. A repair work order containing the type of suspicion and the target location is generated to guide maintenance personnel in accurately repairing pipe network defects, thereby continuously improving the pipe system.

[0033] According to an embodiment of the present invention, it further includes: Establish a data communication link with the municipal pumping station dispatch system; The real-time operating status data of the pumping station is obtained through the data communication link. The operating status data includes pumping station start / stop status parameters, operating power parameters, and drainage flow parameters. When any monitoring node triggers the spatial early warning signal, the optimal scheduling strategy of the pumping station is calculated based on the pipeline flow direction model and the real-time operating status data of the pumping station. A scheduling suggestion instruction is sent to the pump station scheduling system. The scheduling suggestion instruction is used to adjust the start-up and shutdown status or operating power of the pump station to alleviate the operating pressure of abnormal nodes in the pipeline network.

[0034] It's important to note that while relying solely on the pipeline network's own monitoring data is sufficient for identifying problems, resolving them requires the involvement of pumping stations. This embodiment breaks down the information silos between pipeline monitoring and pumping station scheduling by establishing standardized data communication links, enabling the pipeline monitoring platform to read pumping station operating parameters in real time. For example, when an upstream node detects a rapid rise in liquid level and triggers an alert, the system automatically analyzes which pumping stations downstream can help alleviate the flow. If a downstream pumping station is currently operating at 50% power, the system calculates that increasing its power to 80% will allow the upstream node's liquid level to fall below the safety line within an estimated 8 minutes, and then generates a scheduling suggestion instruction for the pumping station control system. Conversely, if all downstream pumping stations are operating at full capacity, the system will suggest that upstream pumping stations reduce their inflow to prevent further pressure buildup in the pipeline network. The core of this collaborative mechanism is treating the pipeline network as a holistic pressure system, rather than focusing solely on the problematic node. By introducing pumping stations as an external execution resource, the average handling time for pipeline anomalies can be further reduced by 3 to 5 minutes.

[0035] According to an embodiment of the present invention, the method of locating the spatial location of pollution sources or blockage points by combining pipeline flow direction models and pollutant diffusion models specifically includes: Based on the pipeline flow direction model, extract the set of upstream nodes that are flow directionally associated with the node that triggered the spatial early warning signal; Obtain the liquid level change rate, flow rate change rate, and pollutant concentration change rate for each node in the upstream node set; The liquid level change rate of each node in the upstream node set is input into the first source tracing analysis module to obtain the first candidate location set; the flow velocity change rate of each node is input into the second source tracing analysis module to obtain the second candidate location set; the pollutant concentration change rate of each node is input into the third source tracing analysis module to obtain the third candidate location set. Cross-validation is performed on the first candidate location set, the second candidate location set, and the third candidate location set. The node location that appears in at least two candidate location sets at the same time is determined as the final spatial location of the pollution source or blockage point.

[0036] It's important to note that relying on a single indicator for source tracing can easily lead to errors in complex pipe network environments. For example, a rise in liquid level in a section of pipe could be due to an upstream blockage or a downstream pumping station reducing its frequency; simply looking at the liquid level isn't enough to distinguish between them. Similarly, an increase in pollutant concentration doesn't necessarily indicate whether the discharged water is industrial wastewater or domestic sewage. This embodiment uses three analytical lines simultaneously: the liquid level change rate line is good at detecting blockages, the flow velocity change rate line is good at detecting pipe deformation or rupture, and the concentration change rate line is good at detecting illegal discharges. Each line independently runs the change rate data of upstream nodes, outputting its own ranking of suspected nodes. Then, the results of the three lines are compared; nodes that intersect are essentially confirmed anomaly sources. For example, if the liquid level line suggests wells 3 and 5 are the most likely suspects, the flow velocity line suggests wells 5 and 7, and the concentration line suggests wells 3 and 5, then well 5 must appear in the candidate sets of at least two lines, thus identifying it as the final anomaly location. This cross-validation approach is far more reliable than single-indicator tracing. In actual testing, the tracing accuracy can be improved from around 60% for single indicators to over 85%. Furthermore, if the results from the three lines have absolutely no overlap, the system will not force a selection but will mark it as a vague result requiring manual verification, thus avoiding misleading operations and maintenance personnel.

[0037] According to an embodiment of the present invention, it further includes: Select a first monitoring node and a second monitoring node that are adjacent along the flow direction in the pipeline network, with the first monitoring node located upstream of the second monitoring node; After obtaining the downstream monitoring data of the second monitoring node, the downstream monitoring data is sent in reverse to the data quality verification unit associated with the first monitoring node; The data quality verification unit calculates the theoretical data range that maps the downstream monitoring data to the location of the first monitoring node based on the pipeline flow direction model. When the actual monitoring data of the first monitoring node exceeds the theoretical data range, a sensor calibration prompt message is generated for the first monitoring node.

[0038] It's important to note that sensors in pipeline networks are constantly immersed in sewage, making scaling, drift, and blockage common occurrences. The traditional approach is to periodically send personnel down to inspect and calibrate each sensor individually, which is time-consuming, labor-intensive, and unreliable. This implementation takes a different approach: instead of letting the sensor determine its accuracy, it relies on its downstream neighbors for evaluation. The logic is simple: based on pipeline flow models and fluid mechanics principles, if there are no branch pipes connecting to the upstream and downstream nodes, and no significant leaks or blockages, then the flow rate through these two nodes should be conserved, and the concentration should be essentially the same. In other words, the data measured downstream can be used to estimate the theoretically expected value upstream. For example, if the downstream flow rate is 0.5 cubic meters per second, the upstream flow rate should be between 0.48 and 0.52 cubic meters per second based on the pipe parameters. If the actual upstream reading jumps to 0.8 cubic meters per second, the upstream flow meter is likely clogged with debris or miscalibrated, and the system will directly send a sensor calibration prompt to the maintenance personnel. This mechanism, which allows downstream data to back-verify upstream sensors, is equivalent to providing each sensor with a free online calibration reference source. This allows abnormal drift of the sensors to be detected and addressed within hours, rather than waiting until regular inspections to discover the problem.

[0039] Furthermore, it also includes: Collect data drift characteristics and noise fluctuation characteristics of sensors at each monitoring node within a preset time window; A sensor health baseline model is established based on data drift characteristics and noise fluctuation characteristics during historical normal operation periods; The real-time data drift characteristics and noise fluctuation characteristics of the current time window are compared with the sensor health baseline model; When the comparison deviation exceeds the preset degradation threshold, it is determined that the sensor of the monitoring node has performance degradation. After determining that the sensor's performance has degraded, the weighting coefficient of the sensor's data in spatial early warning and pollution source location calculations is automatically reduced.

[0040] It's important to note that sensors often undergo a gradual performance degradation process before complete failure. During this period, they may still report data, but the data becomes inaccurate. If the system is unaware of this and continues to use this inaccurate data for early warning and tracing, the consequences can be severe. This embodiment does not attempt to eliminate this performance degradation of the sensor, as this is impractical in a wastewater environment. Instead, it treats the degradation itself as a signal. Specifically, for the first 30 days after the sensor is installed and calibrated, its daily data drift curve and noise amplitude are recorded as a health baseline. Afterward, the system automatically compares the current drift amount with the baseline drift amount daily. The output curve of a normal sensor is relatively smooth, while the output curve of a sensor nearing failure will show increased spikes and a slow baseline shift. Once these degradation characteristics are detected, the system does not directly discard the sensor's data. Instead, it gradually reduces its weight from 1.0 to 0.3, meaning that its data still participates in the tracing calculation but is less decisive. This mechanism allows the system to maintain basic monitoring capabilities even when the sensor is partially disabled, rather than waiting until the sensor completely fails.

[0041] Furthermore, it also includes: The system includes at least three pipeline monitoring modes: a standard monitoring mode, an event response mode, and a source tracing analysis mode. Each monitoring mode corresponds to a set of operating parameters, which include sensor sampling frequency, data upload cycle, and alarm trigger sensitivity. Receive pipeline management intent instructions, wherein the management intent instructions indicate the management priority of the current pipeline operation; Based on the management intent instruction, the target monitoring mode is automatically selected from the set of monitoring modes that match the management priority; Configure each monitoring node according to the operating parameter group corresponding to the target monitoring mode.

[0042] It's important to note that routine management and emergency response of sewage pipe networks operate at entirely different paces. During routine inspections, nobody wants to receive dozens of alarms every minute; a lower sampling frequency and a more lenient alarm threshold allow maintenance personnel to simply check trend charts. However, in the event of an incident, such as a report of black water in a river section, the sampling frequency in the relevant area needs to be increased to the highest level, the alarm threshold narrowed, and all data pushed in real time. This embodiment abstracts these different work paces into different monitoring modes, each bound to its own parameter group, with one-click switching. For example, in the normal mode, the liquid level alarm threshold is set at 85% of the design fill level, with a sampling interval of 5 minutes; in the event response mode, the threshold is tightened to 70%, with a sampling interval of 30 seconds; and in the source tracing analysis mode, cross-comparison calculations of upstream and downstream node data are added. This switching logic prevents the system from being a rigid set of fixed parameters, allowing it to flexibly adjust according to different management intentions, finding a balance between power and data saving and timeliness.

[0043] Furthermore, it also includes: Obtain the on-site verification information returned by the operation and maintenance platform after completing the maintenance work order. The on-site verification information includes the actual type of on-site anomaly and the actual location of the anomaly. The actual abnormal location in the on-site verification information is compared with the spatial location of the pollution source or blockage point to obtain the positioning deviation data; Based on the positioning deviation data, update the model parameters in the pipeline flow direction model and the pollutant diffusion model; The updated model parameters are synchronized to the GIS spatial analysis engine.

[0044] It's important to note that the location of the pollution source automatically determined by the system and the actual location confirmed by maintenance personnel on-site will not always be exactly the same; there will always be a deviation. If this deviation is ignored, the positioning model will continue to run with the initial parameters, resulting in low accuracy. In this embodiment, the on-site feedback from each work order is used as training samples for model self-calibration. After maintenance personnel confirm the work order on their mobile phones, the system requires them to fill in real-time on-site information, including the actual anomaly points found and the anomaly type. After receiving this accurate value, the system compares it with its initial positioning results, calculates the direction and distance of the deviation, and adjusts the parameters in the flow direction and diffusion models accordingly. For example, if the system locates the blockage point 15 to 20 meters downstream three times consecutively, the model will automatically increase the pipe wall friction coefficient, causing the next location to be moved slightly upstream. After accumulating feedback from approximately 50 to 100 work orders, the positioning deviation can converge from an average of 15 meters to 3 to 5 meters, which is already a very good level of accuracy in pipeline maintenance.

[0045] Furthermore, it also includes: Construct a feature library of historical abnormal events. Each record in the feature library includes a multi-node liquid level feature vector, a flow velocity feature vector, and a pollutant concentration feature vector at the time of the historical abnormality. When any monitoring node triggers the spatial early warning signal, the feature vector of the multi-node monitoring data of the current abnormal event is extracted; The feature vector of the multi-node monitoring data of the current abnormal event is matched with each record in the feature library of historical abnormal events based on similarity. If a historical record with a similarity exceeding a preset matching threshold is found, the anomaly type and handling solution corresponding to that historical record will be pushed to the operation and maintenance platform as recommendation information.

[0046] It's important to note that long-term pipeline operation accumulates a large number of records of handling abnormal events. This historical experience is invaluable for quickly responding to new events. This embodiment stores these historical records in a structured feature library. Each record contains a time-series feature vector of the liquid level, flow rate, and concentration at various nodes on the relevant pipeline segment at the time the event occurred. When a new event triggers an alert, the system extracts the current feature vector and performs a similarity match in the feature library—essentially, it checks which previous event is most similar. If a historical event with a similarity exceeding 80% is found, the system directly pushes the event type label and the handling plan used at that time to the maintenance personnel, saving them the time of analyzing from scratch. Experience shows that for areas with pipeline networks operating for more than three years, approximately 60% of abnormal events can find highly similar precedents in the historical library, and the accuracy rate of directly reusing historical handling plans exceeds 90%. This allows new maintenance personnel to quickly get started even without prior experience.

[0047] Please see Figure 4 The present invention also provides a real-time monitoring and management system 4 for the operation status of a sewage pipe network based on GIS and the Internet of Things. The system includes a memory 401 and a processor 402. The memory includes a method program for real-time monitoring and management of the operation status of a sewage pipe network based on GIS and the Internet of Things. When the processor executes the method program for real-time monitoring and management of the operation status of a sewage pipe network based on GIS and the Internet of Things, the following steps are implemented: Deploy multi-parameter water quality sensors and flow monitoring equipment at key nodes of the sewage pipe network; The multi-parameter water quality sensor and flow monitoring equipment are used to collect real-time data on liquid level, flow rate, and pollutant concentration at pipeline nodes. The collected sensing data is connected to the GIS spatial analysis engine and dynamically correlated with the pipeline network topology data to generate a visual monitoring layer. When the monitoring index of any monitoring node exceeds the preset corresponding threshold, a spatial early warning signal is automatically triggered. In response to the aforementioned spatial early warning signal, the spatial location of the pollution source or blockage point is located by combining the pipeline flow direction model and the pollutant diffusion model. A maintenance work order is generated based on the location results, and the maintenance work order is dispatched to the operation and maintenance platform.

[0048] It should be noted that in actual deployment, the processor of this system can be a cloud server or a local edge computing server, and the complete monitoring and management method program is deployed in the memory. During system operation, the processor loads program instructions from the memory and executes steps such as data acquisition, GIS correlation analysis, threshold judgment, source tracing and location, and work order dispatch sequentially. The front-end perception layer consists of sensor terminals deployed at each pipeline node. Each terminal includes a liquid level sensor, flow rate sensor, multi-parameter water quality probe, and wireless communication module, and uses a solar-powered and battery-powered solution to adapt to the harsh underground environment. The intermediate analysis layer, with a GIS spatial analysis engine at its core, runs on the server and is responsible for receiving, cleaning, correlating, and analyzing the perception data uploaded by each node. The service processing layer includes a work order management system and a mobile operation and maintenance platform. Based on the anomaly location results output by the analysis layer, the work order management system matches the nearest available operation and maintenance personnel using a spatial distance algorithm and pushes the work order to their mobile terminal. The three-tier architecture has a clear division of labor: the perception layer is responsible for data collection and uploading, the analysis layer is responsible for calculation and judgment, and the processing layer is responsible for receiving and executing data. They communicate with each other through standardized data interfaces, and upgrading or replacing any layer will not affect the normal operation of other layers. This layered and decoupled design facilitates phased construction and flexible expansion in practical engineering.

[0049] According to an embodiment of the present invention, when the monitoring index of any monitoring node exceeds a preset corresponding threshold, automatically triggering a spatial early warning signal specifically includes: A first-level warning threshold and a second-level warning threshold are preset, and the risk level corresponding to the second-level warning threshold is higher than that of the first-level warning threshold. When the liquid level data exceeds the first liquid level threshold, a liquid level abnormality warning signal is triggered; When the pollutant concentration data exceeds the first concentration threshold, a water quality anomaly warning signal is triggered; When the same monitoring node simultaneously meets the triggering conditions for both the abnormal liquid level warning and the abnormal water quality warning, the warning level will be upgraded to a comprehensive warning signal. The response priority of the comprehensive warning signal is higher than that of a single indicator warning signal.

[0050] It should be noted that when the system performs multi-level threshold judgments, the first liquid level threshold and the first concentration threshold are stored as configurable parameters in the system configuration file. Maintenance and management personnel can dynamically adjust these thresholds based on the actual operating characteristics of different pipe networks and seasonal changes. During the rainy season, the thresholds are appropriately tightened to improve early warning sensitivity, while during the dry season, they are appropriately relaxed to reduce the false alarm rate.

[0051] According to an embodiment of the present invention, it further includes: The system accesses meteorological forecast data sources to obtain predicted rainfall data for the target pipeline area within a preset forecast period. When the predicted rainfall data exceeds a preset rainfall investigation threshold, the pipeline monitoring mode is automatically switched from the regular monitoring frequency to the rainfall-period pipeline anomaly investigation frequency. Under the rainfall-period pipeline anomaly investigation frequency, the data acquisition interval is shortened from a first acquisition interval to a second acquisition interval, where the second acquisition interval is shorter than the first acquisition interval. The system compares the real-time liquid level change data of each monitoring node during rainfall with preset sunny-day baseline liquid level data to identify nodes with abnormal liquid level rises. Combined with the pipeline flow direction model, the system locates target pipe sections suspected of rainwater and sewage mixing or pipeline damage and leakage, and generates an investigation and repair work order.

[0052] It should be noted that the system connects to meteorological data sources through a standard application programming interface (API), supporting access to gridded forecast data from the National Meteorological Administration or local meteorological bureaus. The specific values ​​for rainfall screening thresholds, the first data collection interval, and the second data collection interval are preset during system initialization. A manual adjustment option is also provided in the system management interface to adapt to the rainfall characteristics and pipeline capacity of different cities. Dynamic switching of the data collection interval is executed automatically by the system without manual intervention.

[0053] The present invention also provides a computer-readable storage medium having a computer program stored thereon, the computer-readable storage medium including a method program for real-time monitoring and management of the operation status of a sewage pipe network based on GIS and the Internet of Things, the method program for real-time monitoring and management of the operation status of a sewage pipe network based on GIS and the Internet of Things being executed by a processor to implement the steps of the above-described method for real-time monitoring and management of the operation status of a sewage pipe network based on GIS and the Internet of Things.

[0054] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for real-time monitoring and management of the operation status of a sewage pipe network based on GIS and IoT, characterized in that, The method includes: Deploy multi-parameter water quality sensors and flow monitoring equipment at key nodes of the sewage pipe network; The multi-parameter water quality sensor and flow monitoring equipment are used to collect real-time data on liquid level, flow rate, and pollutant concentration at pipeline nodes. The collected sensing data is connected to the GIS spatial analysis engine and dynamically correlated with the pipeline network topology data to generate a visual monitoring layer. When the monitoring index of any monitoring node exceeds the preset corresponding threshold, a spatial early warning signal is automatically triggered. In response to the aforementioned spatial early warning signal, the spatial location of the pollution source or blockage point is located by combining the pipeline flow direction model and the pollutant diffusion model. A maintenance work order is generated based on the location results, and the maintenance work order is dispatched to the operation and maintenance platform.

2. The method for real-time monitoring and management of sewage pipe network operation status based on GIS and IoT as described in claim 1, characterized in that, When the monitoring index of any monitoring node exceeds the preset corresponding threshold, a spatial early warning signal is automatically triggered, specifically including: A first-level warning threshold and a second-level warning threshold are preset, and the risk level corresponding to the second-level warning threshold is higher than that of the first-level warning threshold. When the liquid level data exceeds the first liquid level threshold, a liquid level abnormality warning signal is triggered; When the pollutant concentration data exceeds the first concentration threshold, a water quality anomaly warning signal is triggered; When the same monitoring node simultaneously meets the triggering conditions for both the abnormal liquid level warning and the abnormal water quality warning, the warning level will be upgraded to a comprehensive warning signal. The response priority of the comprehensive warning signal is higher than that of a single indicator warning signal.

3. The method for real-time monitoring and management of sewage pipe network operation status based on GIS and IoT as described in claim 1, characterized in that, Also includes: Access meteorological forecast data sources to obtain predicted rainfall data for the target pipeline area within a preset forecast period; When the predicted rainfall data exceeds the preset rainfall investigation threshold, the pipeline monitoring mode is automatically switched from the regular monitoring frequency to the rainfall-period pipeline anomaly investigation frequency. Under the rainfall-period pipeline anomaly investigation frequency, the data acquisition interval is shortened from the first acquisition interval to the second acquisition interval, where the second acquisition interval is shorter than the first acquisition interval. The real-time liquid level change data of each monitoring node during rainfall is compared with the preset sunny day baseline liquid level data to identify the abnormal node set where the liquid level rise exceeds the normal fluctuation range. Combined with the pipeline flow direction model, upstream tracing analysis is performed on the abnormal node set to locate the target pipe section suspected of rainwater and sewage mixing or pipeline damage and leakage, and an investigation and repair work order containing the type of suspicion and the target location is generated.

4. The method for real-time monitoring and management of sewage pipe network operation status based on GIS and IoT as described in claim 1, characterized in that, Also includes: Establish a data communication link with the municipal pumping station dispatch system; The real-time operating status data of the pumping station is obtained through the data communication link. The operating status data includes pumping station start / stop status parameters, operating power parameters, and drainage flow parameters. When any monitoring node triggers the spatial early warning signal, the optimal scheduling strategy of the pumping station is calculated based on the pipeline flow direction model and the real-time operating status data of the pumping station. A scheduling suggestion instruction is sent to the pump station scheduling system. The scheduling suggestion instruction is used to adjust the start-up and shutdown status or operating power of the pump station to alleviate the operating pressure of abnormal nodes in the pipeline network.

5. The method for real-time monitoring and management of sewage pipe network operation status based on GIS and IoT as described in claim 1, characterized in that, The method of locating the spatial position of pollution sources or blockage points by combining pipeline flow direction models and pollutant diffusion models specifically includes: Based on the pipeline flow direction model, extract the set of upstream nodes that are flow directionally associated with the node that triggered the spatial early warning signal; Obtain the liquid level change rate, flow rate change rate, and pollutant concentration change rate for each node in the upstream node set; The liquid level change rate of each node in the upstream node set is input into the first source tracing analysis module to obtain the first candidate location set; the flow velocity change rate of each node is input into the second source tracing analysis module to obtain the second candidate location set; the pollutant concentration change rate of each node is input into the third source tracing analysis module to obtain the third candidate location set. Cross-validation is performed on the first candidate location set, the second candidate location set, and the third candidate location set. The node location that appears in at least two candidate location sets at the same time is determined as the final spatial location of the pollution source or blockage point.

6. The method for real-time monitoring and management of sewage pipe network operation status based on GIS and IoT as described in claim 1, characterized in that, Also includes: Select a first monitoring node and a second monitoring node that are adjacent along the flow direction in the pipeline network, with the first monitoring node located upstream of the second monitoring node; After obtaining the downstream monitoring data of the second monitoring node, the downstream monitoring data is sent in reverse to the data quality verification unit associated with the first monitoring node; The data quality verification unit calculates the theoretical data range that maps the downstream monitoring data to the location of the first monitoring node based on the pipeline flow direction model. When the actual monitoring data of the first monitoring node exceeds the theoretical data range, a sensor calibration prompt message is generated for the first monitoring node.

7. A real-time monitoring and management system for the operation status of a sewage pipe network based on GIS and the Internet of Things, characterized in that, The system includes a memory and a processor. The memory includes a program for real-time monitoring and management of the operation status of a sewage pipe network based on GIS and IoT. When the processor executes the program, the program performs the following steps: Deploy multi-parameter water quality sensors and flow monitoring equipment at key nodes of the sewage pipe network; The multi-parameter water quality sensor and flow monitoring equipment are used to collect real-time data on liquid level, flow rate, and pollutant concentration at pipeline nodes. The collected sensing data is connected to the GIS spatial analysis engine and dynamically correlated with the pipeline network topology data to generate a visual monitoring layer. When the monitoring index of any monitoring node exceeds the preset corresponding threshold, a spatial early warning signal is automatically triggered. In response to the aforementioned spatial early warning signal, the spatial location of the pollution source or blockage point is located by combining the pipeline flow direction model and the pollutant diffusion model. A maintenance work order is generated based on the location results, and the maintenance work order is dispatched to the operation and maintenance platform.

8. The real-time monitoring and management system for the operation status of sewage pipe networks based on GIS and IoT as described in claim 7, characterized in that, When the monitoring index of any monitoring node exceeds the preset corresponding threshold, a spatial early warning signal is automatically triggered, specifically including: A first-level warning threshold and a second-level warning threshold are preset, and the risk level corresponding to the second-level warning threshold is higher than that of the first-level warning threshold. When the liquid level data exceeds the first liquid level threshold, a liquid level abnormality warning signal is triggered; When the pollutant concentration data exceeds the first concentration threshold, a water quality anomaly warning signal is triggered; When the same monitoring node simultaneously meets the triggering conditions for both the abnormal liquid level warning and the abnormal water quality warning, the warning level will be upgraded to a comprehensive warning signal. The response priority of the comprehensive warning signal is higher than that of a single indicator warning signal.

9. The real-time monitoring and management system for the operation status of sewage pipe networks based on GIS and IoT as described in claim 7, characterized in that, Also includes: Access meteorological forecast data sources to obtain predicted rainfall data for the target pipeline area within a preset forecast period; When the predicted rainfall data exceeds the preset rainfall investigation threshold, the pipeline monitoring mode is automatically switched from the regular monitoring frequency to the rainfall-period pipeline anomaly investigation frequency. Under the rainfall-period pipeline anomaly investigation frequency, the data acquisition interval is shortened from the first acquisition interval to the second acquisition interval, where the second acquisition interval is shorter than the first acquisition interval. The real-time liquid level change data of each monitoring node during rainfall is compared with the preset sunny day baseline liquid level data to identify the abnormal node set where the liquid level rise exceeds the normal fluctuation range. Combined with the pipeline flow direction model, upstream tracing analysis is performed on the abnormal node set to locate the target pipe section suspected of rainwater and sewage mixing or pipeline damage and leakage, and an investigation and repair work order containing the type of suspicion and the target location is generated.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer-readable storage medium includes a method program for real-time monitoring and management of the operation status of a sewage pipe network based on GIS and the Internet of Things. When the method program is executed by a processor, it implements the steps of the method for real-time monitoring and management of the operation status of a sewage pipe network based on GIS and the Internet of Things as described in any one of claims 1 to 6.

Images