A method, system, terminal and storage medium for monitoring water quality in municipal drainage pipelines

Abstract

This application relates to a method, system, terminal, and storage medium for monitoring water quality in municipal drainage pipelines, belonging to the field of water quality monitoring. The method includes: setting up multiple monitoring nodes in the drainage pipeline and dividing them into upstream and downstream monitoring nodes; acquiring water quality parameters of pollutants at each monitoring node and recording time stamps; comparing the water quality parameters with safety thresholds; if abnormal water quality parameters exist at both the upstream and downstream monitoring nodes, calculating a local pollution area; if abnormal water quality parameters exist only at a certain monitoring node segment, determining it as a local pollution area; triggering an early warning signal and switching to a high-frequency acquisition cycle mode based on the local pollution area; if the water quality parameters do not exceed the safety threshold for N consecutive high-frequency acquisition cycles, canceling the early warning signal and reverting to a fixed acquisition cycle mode. This application has the effect of improving the response speed for locating pollution sources and ensuring the safe operation of drainage pipelines and the stability of water environmental quality.

Description

Technical Field

[0001] This application relates to the field of water quality monitoring, and in particular to a method, system, terminal and storage medium for monitoring water quality in municipal drainage pipelines. Background Technology

[0002] In municipal drainage management, water quality monitoring systems are a key technological support for improving the speed of pollution source location and response, as well as ensuring the safe operation of drainage pipelines and the stability of water environment quality.

[0003] In related technologies, water quality monitoring systems are based on online sensing and remote communication technologies. They collect water quality parameters at key points in the pipeline network, compare them with preset emission standard thresholds, identify abnormalities exceeding standards, generate alarm information, and finally push the warning data to the operation and maintenance management platform for manual handling.

[0004] The aforementioned technologies suffer from insufficient accuracy in warnings and limited intelligence when identifying anomalies, leading to frequent false alarms and inaccurate identification of pollution events. Summary of the Invention

[0005] In order to improve the response speed of pollution source location and ensure the safe operation of drainage pipelines and the stability of water environment quality, this application provides a method, system, terminal and storage medium for monitoring water quality in municipal drainage pipelines.

[0006] Firstly, this application provides a method for monitoring water quality in municipal drainage pipelines, employing the following technical solution: A method for monitoring water quality in municipal drainage pipelines includes: Multiple monitoring nodes are set up in the drainage pipeline, and the monitoring nodes are divided into upstream monitoring nodes and downstream monitoring nodes according to the direction of water flow. Water quality parameters of pollutants at each monitoring node are acquired at a fixed collection cycle, and the time stamps of the water quality parameters are recorded. The water quality parameters include at least one of pH value, chemical oxygen demand, ammonia nitrogen content and suspended solids concentration. Compare the water quality parameters of each monitoring node with the safety threshold; If both upstream and downstream monitoring nodes have abnormal water quality parameters, the local pollution area is calculated based on the time stamp and the flow velocity in the drainage pipe. If abnormal water quality parameters are found only at the upstream or downstream monitoring nodes, the pipe section where the monitoring node with abnormal water quality parameters is located will be identified as a localized pollution area. Based on the localized pollution area, an early warning signal is triggered and the monitoring node corresponding to the localized pollution area is controlled to switch to high-frequency acquisition cycle mode. If the water quality parameters do not exceed the safety threshold in N consecutive high-frequency acquisition cycles, the warning signal is canceled and the monitoring node corresponding to the local pollution area is controlled to return to the fixed acquisition cycle mode.

[0007] By adopting the above technical solution, monitoring nodes are divided into upstream and downstream sections in the drainage pipeline according to the water flow direction. This is combined with water quality parameters, time stamps, and pipeline flow velocity. High-frequency data acquisition is switched to the monitoring nodes corresponding to locally polluted areas. Regular data acquisition is resumed after the water quality returns to normal for N consecutive cycles. This solution effectively avoids the frequent false alarms and resource waste caused by traditional all-area warning systems, significantly improving the accuracy of pollution identification, the timeliness of source tracing, and operational efficiency.

[0008] Optionally, upon receiving a warning signal for a pipe segment, the state variables associated with the pipe segment are initialized and set to their initial values. At the end of the high-frequency acquisition cycle, the water quality parameters of the current high-frequency acquisition cycle are obtained and compared with the safety threshold. If the water quality parameters exceed the safety threshold, the initial values ​​will be increased by a preset increment to obtain the updated state variables; If the water quality parameters do not exceed the safety threshold, the initial values ​​are reduced by a preset attenuation amount to obtain the updated state variables; Determine whether the updated state variable is less than the variable threshold; If not, perform high-frequency acquisition in the next cycle and repeat the above four steps; If so, a command to cancel the warning signal will be generated, and the corresponding monitoring node in the pipeline segment will be controlled to return to the fixed acquisition cycle mode.

[0009] By adopting the above technical solution, the state variables associated with the pipeline segment are adjusted based on the comparison results of water quality parameters and safety thresholds within the high-frequency acquisition cycle. The decision to continue high-frequency acquisition or cancel the warning is then made based on the comparison between the state variables and their thresholds. This solution achieves a quantitative assessment of the warning's persistence through incremental accumulation and attenuation adjustment, improving the response accuracy and resource utilization efficiency of high-frequency acquisition.

[0010] Optionally, obtain the early warning records of the upstream monitoring nodes corresponding to the localized pollution area within a preset time window; Extract the dominant pollutant type and warning trigger time from the warning records; Based on the pipe segment length and flow velocity information of the local pollution area and the upstream monitoring node, the estimated flow time is calculated; Determine whether the pollutant type and the dominant pollutant type are consistent in the current high-frequency collection cycle, and whether the difference between the time stamp and the warning trigger time is within the expected flow time. If so, the initial values ​​of the pipe section's state variables are calculated based on the state variables of the upstream monitoring nodes, the water quality parameters corresponding to the dominant pollutants, and the safety thresholds.

[0011] By employing the above technical solution, early warning records of upstream monitoring nodes corresponding to localized pollution areas are obtained within a preset time window. The dominant pollutant type and early warning trigger time are extracted, and the estimated flow time is calculated by combining pipe segment length, slope, and multi-level flow velocity information. The solution also verifies whether the current abnormal parameter type and time stamp match the upstream pollution propagation characteristics. If they match, the initial values ​​of the current pipe segment's state variables are calculated based on the upstream state variables and the degree of exceedance. This solution significantly improves the accuracy of pollution propagation correlation judgment and reduces deviations caused by ignoring upstream pollution propagation correlations.

[0012] Optionally, the pollutant similarity between the pollutants in the current high-frequency acquisition cycle and the dominant pollutants of each upstream monitoring node can be calculated to obtain a pollutant matching table. Based on the preset pollution source feature association table, each matching relationship in the pollutant matching relationship table is weighted and aggregated to generate the comprehensive similarity weight corresponding to each upstream monitoring node. Obtain the state variables of each upstream monitoring node when an early warning is triggered, and calculate the risk transmission value by combining the comprehensive similarity weights of each upstream monitoring node; The risk transmission values ​​are summed to obtain the summation result, which is then used as the initial value of the pipe segment state variable.

[0013] By employing the aforementioned technical solution, the similarity between water quality parameters in the current high-frequency acquisition cycle and the dominant pollutants at each upstream monitoring node is calculated. The matching relationships are then weighted and aggregated using a pre-defined pollution source feature association table to generate a comprehensive similarity weight. Finally, the risk transmission value is calculated by integrating the state variables of each upstream node, and the sum of these risk transmission values ​​is used as the initial value of the pipe segment's state variables. This solution significantly improves the accuracy of pollution source association identification and reduces the initial value deviation of state variables caused by relying solely on information from a single upstream node.

[0014] Optionally, it can be determined whether there is a pre-defined combination of interactions between pollutants, including antagonistic combinations and synergistic combinations; If present, the estimated values ​​of the residence time, reaction rate and mixing degree of pollutants in the pipe section are obtained, and it is determined whether the interaction combination has the conditions for reaction to occur. If so, then query the preset pollutant interaction coefficient table to obtain the effect correction coefficient corresponding to the interaction combination; The effect correction coefficient is associated with the upstream monitoring node corresponding to the pollutant involved in the interaction combination, in order to be used for the calculation of risk transfer value.

[0015] By employing the above technical solution, it is determined whether there are pre-defined antagonistic or synergistic interaction combinations among pollutants. The reaction conditions are then assessed by combining estimated values ​​of water quality parameters within the pipe section, such as residence time, reaction rate, and mixing degree. If the conditions are met, a pre-set pollutant interaction coefficient table is consulted to obtain the corresponding effect correction coefficient, which is then used to correct the risk transmission value. This solution significantly improves the accuracy of comprehensive pollution risk quantification and reduces risk assessment bias caused by neglecting the chemical interaction effects between pollutants.

[0016] Optionally, multiple interaction combinations can be detected to determine whether there is a contradiction in the effect correction of the same pollutant. A contradiction in the effect correction direction means that the same pollutant is a component of the first interaction combination and the same pollutant is a component of the second interaction combination, wherein the first interaction combination and the second interaction combination are different interaction combination types. If not, then the correction coefficients for multiple effects of the same pollutant are calculated together to obtain a unified correction coefficient; If so, the dominant effect combination is determined based on the preset pollutant response priority and the current concentration of each relevant pollutant, and the effect correction coefficient corresponding to the dominant effect combination is used as the unified correction coefficient. Based on a unified correction factor, the risk transmission value is corrected to obtain the corrected risk transmission value.

[0017] By employing the above technical solution, multiple interaction combinations are detected to determine whether the same pollutant simultaneously participates in different types of effect corrections. When conflicting correction directions exist, the dominant effect combination is determined by combining the preset pollutant response priority and current concentration to generate a unified correction coefficient. When there is no conflict, multiple correction coefficients are comprehensively calculated. This solution effectively avoids the confusion in risk assessment caused by conflicting correction rules when multiple pollutants coexist, and reduces the bias in state assessment caused by conflicting effects.

[0018] Optionally, multidimensional feature data of abnormal water quality parameters can be obtained. The multidimensional feature data includes at least one of the following: concentration variation range, synchronous variation relationship, or total flow variation information of abnormal water quality parameters. Based on multidimensional feature data, it is determined whether there are abnormal events. Abnormal events refer to the simultaneous decrease in the concentration of multiple abnormal water quality parameters and the increase in total flow exceeding the flow threshold. If so, the abnormal event is determined to be a runoff dilution event, and the current collection cycle is maintained; If not, determine whether the abnormal event conforms to the dimensional distribution characteristics. The dimensional distribution characteristics refer to the existence of the abnormal event within N consecutive collection cycles, and the abnormal event occurs on a single monitoring node or a few adjacent monitoring nodes. If so, the abnormal event is determined to be a case of unauthorized discharge, and an early warning signal is triggered.

[0019] By employing the above technical solution, multidimensional characteristic data of abnormal water quality parameters are obtained. Combined with the magnitude of concentration changes, the synchronous changes between parameters, and total flow rate changes, it is determined whether the characteristics of a runoff dilution event are met. If not, it is further determined whether the anomaly persists for N consecutive collection cycles and is limited to a single or a few adjacent monitoring nodes. This solution can more accurately distinguish between natural hydraulic disturbances and actual illegal discharge, reducing invalid warnings caused by misjudging pipeline scouring or hydraulic disturbances as illegal discharge.

[0020] Secondly, this application provides a municipal drainage pipeline water quality monitoring system, which adopts the following technical solution: A municipal drainage pipeline water quality monitoring system includes: The acquisition module is used to acquire multiple monitoring nodes and water quality parameters; A memory for storing the program of the municipal drainage pipeline water quality monitoring method; The processor and the program in the memory can be loaded and executed by the processor to implement the municipal drainage pipeline water quality monitoring method.

[0021] By adopting the above technical solution, the module collects water quality parameters from multiple monitoring nodes of the drainage pipeline, the processor efficiently executes monitoring logic such as pollution area determination and status variables, and the memory continuously supports the stable operation of the program. This achieves intelligent processing of the entire process from anomaly identification to early warning response, significantly improving the efficiency of pipeline monitoring while ensuring the accuracy of pollution identification, and providing an efficient and reliable intelligent supervision solution for municipal drainage systems.

[0022] Thirdly, this application provides a smart terminal, which adopts the following technical solution: A smart terminal includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed as described in any one of 1 to 7 above.

[0023] Fourthly, this application provides a computer storage medium capable of storing corresponding programs, which facilitates improving the response speed for locating pollution sources and ensuring the safe operation of drainage pipelines and the stability of water environmental quality. The technical solution adopted is as follows: A computer-readable storage medium storing a computer program that can be loaded by a processor and executed any of the above-described municipal drainage pipeline water quality monitoring methods.

[0024] In summary, this application includes at least one of the following beneficial technical effects: 1. Monitoring nodes are divided into upstream and downstream sections within the drainage pipeline according to the water flow direction. Combining water quality parameters, time stamps, and pipeline flow velocity, high-frequency data acquisition is switched to the monitoring nodes corresponding to locally polluted areas. Regular data acquisition is resumed after N consecutive cycles of normal water quality. This solution effectively avoids the frequent false alarms and resource waste caused by traditional all-area warning systems, significantly improving the accuracy of pollution identification, the timeliness of source tracing, and operational efficiency. 2. Obtain early warning records from upstream monitoring nodes corresponding to localized pollution areas within a preset time window, extract the dominant pollutant type and early warning trigger time, and calculate the estimated flow time by combining pipe segment length, slope, and multi-level flow velocity information. Verify whether the current abnormal parameter type and time stamp match the upstream pollution propagation characteristics; if they match, calculate the initial values ​​of the current pipe segment's state variables based on the upstream state variables and the degree of exceedance. This scheme significantly improves the accuracy of pollution propagation correlation judgment and reduces deviations caused by ignoring upstream pollution propagation correlations. 3. Acquire multidimensional characteristic data of abnormal water quality parameters, and combine this data with the concentration change amplitude, synchronous change relationship between parameters, and total flow change information to identify whether the characteristics of a runoff dilution event are met. If not, further determine whether the anomaly persists for N consecutive collection cycles and is limited to a single or a few adjacent monitoring nodes. This scheme can more accurately distinguish between natural hydraulic disturbances and actual illegal discharge behavior, reducing invalid early warnings caused by misjudging pipeline flushing or hydraulic disturbances as illegal discharge. Attached Figure Description

[0025] Figure 1 This is a flowchart illustrating a method for monitoring water quality in municipal drainage pipelines provided in an embodiment of this application.

[0026] Figure 2 This is a schematic flowchart of a water quality parameter monitoring method based on state variables provided in an embodiment of this application.

[0027] Figure 3 This is a flowchart illustrating a method for determining pipe segment state variables provided in an embodiment of this application.

[0028] Figure 4 This is a flowchart illustrating a method for determining the initial value of a pipe segment with multiple upstream weighting, as provided in an embodiment of this application.

[0029] Figure 5 This is a flowchart illustrating a method for correcting risk transfer values ​​provided in an embodiment of this application.

[0030] Figure 6 This is a flowchart illustrating a method for handling conflicting correction coefficients provided in an embodiment of this application.

[0031] Figure 7This is a flowchart illustrating a method for identifying drainage anomalies provided in an embodiment of this application.

[0032] Figure 8 This is a schematic diagram of the structure of a municipal drainage pipeline water quality monitoring system provided in an embodiment of this application. Detailed Implementation

[0033] To make the purpose, technical solution, and advantages of this application clearer, the following description is provided in conjunction with the appendix. Figures 1 to 8 The present application will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the application.

[0034] This application discloses a method for monitoring water quality in municipal drainage pipelines. (Refer to...) Figure 1 The method includes: Step S101: Set up multiple monitoring nodes in the drainage pipe and divide the multiple monitoring nodes into upstream monitoring nodes and downstream monitoring nodes according to the water flow direction.

[0035] Monitoring nodes refer to water quality monitoring devices installed in municipal drainage pipelines to collect water quality parameters of pollutants.

[0036] When dividing the upstream and downstream monitoring nodes, the monitoring nodes located on the side where the water flows in are classified as upstream, and the monitoring nodes located on the side where the water flows out are classified as downstream, based on the actual water flow direction of the drainage pipeline. This is used to distinguish the order in which pollutants spread.

[0037] Step S102: Obtain water quality parameters of pollutants at each monitoring node at a fixed collection cycle, and record the time stamp of the water quality parameters. The water quality parameters include at least one of pH value, chemical oxygen demand, ammonia nitrogen content and suspended solids concentration.

[0038] Water quality parameters are physicochemical indicators that represent the characteristics of pollutants in drainage pipes, reflecting the water quality status and pollution level within the pipes. These parameters are obtained through water quality monitoring devices installed at monitoring nodes.

[0039] A time stamp is a time information that is recorded synchronously each time a water quality parameter is collected, used to identify the specific moment when the water quality parameter was generated.

[0040] Step S103: Compare the water quality parameters of each monitoring node with the safety threshold to identify monitoring nodes with abnormal water quality parameters.

[0041] Abnormal water quality parameters refer to water quality parameter values ​​collected by monitoring nodes that exceed the safety threshold, indicating that the water quality at the location of the monitoring node may be polluted and requires further analysis and judgment.

[0042] Step S104: If both the upstream and downstream monitoring nodes have abnormal water quality parameters, calculate the local pollution area based on the time stamp and the flow velocity in the drainage pipe.

[0043] Localized pollution areas refer to the range of locations in the pipe section where pollutants are most likely to enter, calculated based on the difference in time stamps of abnormal occurrences at upstream and downstream monitoring nodes and the water flow velocity within the drainage pipe.

[0044] The calculation of local pollution areas is based on the relationship between the migration time and flow velocity of pollutants in the pipeline. It is estimated using the formula L=v×Δt, where L is the distance from the pollution source to the upstream monitoring node, v is the average flow velocity of sewage in the drainage pipeline, and Δt is the difference between the downstream abnormal time mark and the upstream abnormal time mark. The possible location of the pollution source in the pipeline section can be deduced through this formula.

[0045] For example, if the upstream monitoring node detects an abnormal chemical oxygen demand (COD) at 10:00:00 and the downstream monitoring node also detects an abnormal COD at 10:15:00, with a time difference Δt = 900 seconds; if the measured average flow velocity of this pipe section is v = 0.4 m / s, then the estimated distance from the pollution source to the upstream node is L = 0.4 × 900 = 360 meters. Therefore, the pipe section approximately 360 meters downstream of the upstream node is designated as a local pollution area.

[0046] Step S105: If only the upstream or downstream monitoring nodes have abnormal water quality parameters, the pipe section where the monitoring node with abnormal water quality parameters is located is determined to be a local pollution area.

[0047] When abnormal water quality parameters appear only at monitoring nodes in the upstream or downstream sections, the pipe section where the abnormal node is located is directly regarded as a localized pollution area.

[0048] Step S106: Based on the local pollution area, trigger the early warning signal and control the monitoring node corresponding to the local pollution area to switch to high-frequency acquisition cycle mode.

[0049] The high-frequency acquisition cycle mode refers to shortening the data acquisition interval of monitoring nodes from a long time to a short time, so as to acquire water quality parameters more frequently during suspected pollution periods and improve the timeliness of monitoring response.

[0050] After identifying areas of localized pollution, an early warning signal is issued, and the monitoring nodes in these areas are switched from the regular collection cycle to a high-frequency collection cycle in order to acquire water quality data intensively and strengthen the monitoring of suspected pollution areas.

[0051] Step S107: If the water quality parameters do not exceed the safety threshold in N consecutive high-frequency acquisition cycles, cancel the warning signal and control the monitoring node corresponding to the local pollution area to return to the fixed acquisition cycle mode.

[0052] Continuing to collect water quality parameters in the high-frequency acquisition cycle mode is to confirm whether the water quality parameters have returned to normal levels, to prevent premature cancellation of the warning due to accidental fluctuations or temporary drops, and to ensure the accuracy of the warning exit.

[0053] By adopting the above technical solution, monitoring nodes are divided into upstream and downstream sections in the drainage pipeline according to the water flow direction. This is combined with water quality parameters, time stamps, and pipeline flow velocity. High-frequency data acquisition is switched to the monitoring nodes corresponding to locally polluted areas. Regular data acquisition is resumed after the water quality returns to normal for N consecutive cycles. This solution effectively avoids the frequent false alarms and resource waste caused by traditional all-area warning systems, significantly improving the accuracy of pollution identification, the timeliness of source tracing, and operational efficiency.

[0054] This application discloses a method for monitoring water quality parameters based on state variables. (Refer to...) Figure 2 The method includes: Step S201: After receiving the warning signal for the pipe segment, initialize the state variables associated with the pipe segment and set the state variables to their initial values.

[0055] State variables refer to the values ​​set for each pipe segment that is under warning, which are used to reflect the degree of persistence of the pipe segment's pollution risk during high-frequency data acquisition.

[0056] Setting initial values ​​is to provide a unified starting point for state variables when an early warning is triggered, ensuring that the logical starting point for subsequent assessments of pollution persistence based on water quality changes is consistent, and avoiding judgment bias due to the lack of initial values ​​or random assignment.

[0057] Step S202: At the end of the high-frequency acquisition cycle, obtain the water quality parameters of the current high-frequency acquisition cycle and compare the water quality parameters with the safety threshold.

[0058] At the end of each high-frequency acquisition cycle, the latest water quality parameters are read and compared with the safety threshold to determine whether pollution still exists, providing a basis for subsequent adjustment of state variables.

[0059] Step S203: If the water quality parameters exceed the safety threshold, the initial values ​​are increased by a preset increment to obtain the updated state variables.

[0060] When water quality parameters exceed the safety threshold, a preset increment is added to the state variable to reflect the continued existence or aggravation of pollution, thereby extending the high-frequency sampling time.

[0061] The specific value of the preset increment is usually set according to the actual characteristics of the pipeline network and management needs, and the common value range is 1 to 5. For example, if the initial value of the pipeline segment status variable is 10 and the preset increment is 2, and the current high-frequency acquisition measures a chemical oxygen demand of 120 mg / L, which exceeds the safety threshold of 100 mg / L, then the status variable will be updated to 10 plus 2, that is, 12, indicating that the pollution is still ongoing and high-frequency monitoring needs to continue.

[0062] Step S204: If the water quality parameters do not exceed the safety threshold, the initial values ​​are reduced by a preset attenuation amount to obtain the updated state variables.

[0063] When water quality parameters do not exceed the safety threshold, a preset attenuation amount is subtracted from the state variable to reflect that the pollution may be weakening or receding, gradually reducing the risk assessment value and providing a basis for timely withdrawal from high-frequency data collection.

[0064] The specific value of the preset attenuation amount is usually set based on practical application experience, and commonly ranges from 1 to 3. In most municipal drainage monitoring systems, it is generally set to 1 or 2 to ensure that the state variable gradually decreases as the water quality recovers, thus avoiding premature exit from the warning and preventing long-term ineffective high-frequency data collection. For example, if the current state variable of a pipe section is 8 and the preset attenuation amount is 1, and the current high-frequency data collection shows that the chemical oxygen demand is 90 mg / L, which is below the safety threshold of 100 mg / L, then the state variable is updated to 8 minus 1, i.e., 7, indicating that the pollution risk has decreased.

[0065] Step S205: Determine whether the updated state variable is less than the variable threshold.

[0066] The updated state variables are compared with variable thresholds to determine whether the pollution risk has been reduced to an acceptable level.

[0067] Step S206: If not, perform high-frequency acquisition for the next cycle and repeat the above four steps.

[0068] If the state variable is not lower than the variable threshold, continue to perform high-frequency data collection for the next cycle, and continuously compare water quality parameters, update state variables and judge thresholds to continuously track pollution changes until the risk is truly eliminated.

[0069] Step S207: If yes, generate a command to cancel the early warning signal and control the corresponding monitoring node of the pipeline segment to return to the fixed acquisition cycle mode.

[0070] When the state variable is below the variable threshold, a command to cancel the warning signal is generated, and the collection cycle of the corresponding monitoring node is restored from high frequency mode to fixed collection cycle to avoid long-term unnecessary dense sampling and reduce the burden on equipment and communication.

[0071] By adopting the above technical solution, the state variables associated with the pipeline segment are adjusted based on the comparison results of water quality parameters and safety thresholds within the high-frequency acquisition cycle. The decision to continue high-frequency acquisition or cancel the warning is then made based on the comparison between the state variables and their thresholds. This solution achieves a quantitative assessment of the warning's persistence through incremental accumulation and attenuation adjustment, improving the response accuracy and resource utilization efficiency of high-frequency acquisition.

[0072] This application discloses a method for determining the state variables of a pipe segment. (Refer to...) Figure 3 The method includes: Step S301: Obtain the early warning records of the upstream monitoring nodes corresponding to the local pollution area within a preset time window.

[0073] Early warning records refer to the early warning information generated by upstream monitoring nodes within a preset time window due to water quality parameters exceeding limits. This includes data such as the trigger time, the types of pollutants involved, and the state variables at that time.

[0074] By querying historical early warning logs stored in the monitoring platform database, upstream monitoring nodes that are associated with the current local pollution area are selected, and all early warning records generated within a preset time window are extracted.

[0075] Step S302: Extract the dominant pollutant type and warning trigger time from the warning records.

[0076] The dominant pollutant type refers to the type of pollutant that most significantly causes water quality parameters to exceed the safe threshold in a single warning record, and is used to represent the main characteristics of this pollution event.

[0077] The warning trigger time refers to the specific moment when the monitoring node first detects that the water quality parameters exceed the safety threshold and generates a warning signal.

[0078] Step S303: Calculate the estimated flow time based on the pipe segment length and flow velocity information of the local contamination area and the upstream monitoring node.

[0079] The estimated flow time refers to the estimated time required for pollutants to migrate from the upstream monitoring node to the current localized pollution area. It is calculated using the formula T=L / V, where T represents the estimated flow time, L represents the pipe length between the upstream monitoring node and the localized pollution area, and V represents the flow velocity in the pipe segment. Flow velocity information is preferentially based on real-time velocity, followed by the recent moving average velocity, and only when recent flow velocity data is unavailable is the historical average velocity for the same period used.

[0080] For example, if the pipeline length between the upstream monitoring node and the current pipe segment is 480 meters, and the real-time flow velocity of this segment is measured to be 0.6 m / s, then the estimated flow time T = 800 seconds, approximately 13 minutes and 20 seconds. If there is no real-time flow velocity, but the pipe segment slope is known to be 0.005 and the pipe diameter to be 800 mm, the average flow velocity is estimated to be 0.4 m / s using the Manning formula, then the estimated flow time T = 1200 seconds, or 20 minutes. Here, a pipe segment slope of 0.005 refers to a hydraulic gradient of 0.5%, meaning that for every 1000 meters of horizontal distance, the elevation of the bottom of the pipe decreases by 5 meters. For example, if the distance is 200 meters, the upstream elevation is 10.00 meters and the downstream elevation is 9.00 meters, then the elevation difference is 1.00 meter, and the slope is 0.005.

[0081] Step S304: Determine whether the pollutant type and the dominant pollutant type of the current high-frequency collection cycle are consistent, and whether the difference between the time stamp and the warning trigger time is within the expected flow time.

[0082] By comparing the types of abnormal pollutants in the current high-frequency collection cycle with the dominant pollutant types of upstream monitoring nodes, and verifying whether the difference between the current anomaly occurrence time and the early warning trigger time falls within the expected flow time range, it can be determined whether the current anomaly is caused by upstream pollution events migrating through the water flow.

[0083] Step S305: If so, calculate the initial value of the state variable of the pipe section based on the state variable of the upstream monitoring node, the water quality parameters corresponding to the dominant pollutant, and the safety threshold.

[0084] After confirming that the type of pollutant causing the current anomaly is consistent with the dominant pollutant type upstream, and that the difference between the current anomaly occurrence time and the warning trigger time is within the expected flow time range, the fixed default value is no longer used as the initial value for the current pipe segment's state variables. Instead, calculations are performed based on the state variables of the upstream monitoring nodes and the degree to which water quality parameters exceed safety thresholds, making the initial values ​​more accurately reflect the pollution intensity. The formula V0=V up ×β×(C up / C th The calculation is performed, where V0 represents the initial value of the state variable of the pipe segment, and V... up C is the state variable of the upstream monitoring node when an early warning is triggered. up C represents the measured concentration of the dominant pollutant in the upstream early warning record. th β is the safety threshold corresponding to the pollutant, and β is the preset attenuation coefficient, which is set according to the pipe section length, material and historical data, with a typical value of 0.5 to 0.8.

[0085] For example, an upstream monitoring node triggers an early warning due to excessive chemical oxygen demand (COD), and its state variable V... up =10, Measured COD value C up=140mg / L, safety threshold C th =100mg / L, and the attenuation coefficient β=0.7 is set according to the characteristics of the pipe section. Substituting into the formula, V0=9.8.

[0086] By employing the above technical solution, early warning records of upstream monitoring nodes corresponding to localized pollution areas are obtained within a preset time window. The dominant pollutant type and early warning trigger time are extracted, and the estimated flow time is calculated by combining pipe segment length, slope, and multi-level flow velocity information. The solution also verifies whether the current abnormal parameter type and time stamp match the upstream pollution propagation characteristics. If they match, the initial values ​​of the current pipe segment's state variables are calculated based on the upstream state variables and the degree of exceedance. This solution significantly improves the accuracy of pollution propagation correlation judgment and reduces deviations caused by ignoring upstream pollution propagation correlations.

[0087] This application discloses a method for determining the initial value of a pipe segment using a multi-upstream weighted approach. (Refer to...) Figure 4 The method includes: Step S401: Calculate the pollutant similarity between the pollutants in the current high-frequency acquisition cycle and the dominant pollutants of each upstream monitoring node to obtain the pollutant matching relationship table.

[0088] Pollutant similarity refers to the degree of matching between the currently frequently collected pollutants and the dominant pollutants in the upstream monitoring nodes in terms of type and exceedance characteristics, and is used to measure whether the two may originate from the same pollution.

[0089] The pollutant matching table is a table that records the similarity values ​​between pollutants and the dominant pollutants at each upstream monitoring node.

[0090] To identify which pollutants exceed safe water quality thresholds during the current high-frequency sampling period, these are designated as the current set of abnormal pollutants. Then, each pollutant is compared to the dominant pollutant type in the early warning records of each upstream monitoring node. If the types are the same, the ratio of the current measured concentration of that pollutant to the safe threshold is calculated, and this ratio is compared with the ratio of the same type of dominant pollutant upstream. The smaller of the two ratios is divided by the larger value to determine the similarity of the match. If the types are different, the similarity is set to 0.

[0091] For example, the current high-frequency monitoring shows a chemical oxygen demand (COD) of 150 mg / L, with a safety threshold of 100 mg / L, resulting in an exceedance ratio of 1.5. An upstream monitoring node previously issued a COD warning; its measured value was 120 mg / L, with an exceedance ratio of 1.2. Since the pollutant types are the same, the similarity is 0.8. If the dominant pollutant at another upstream node is ammonia nitrogen, then it does not match the current COD, and the similarity is 0. All matching results are summarized to form a pollutant matching table, listing each upstream node and its corresponding similarity value.

[0092] Step S402: Based on the preset pollution source feature association table, weighted aggregation is performed on each matching relationship in the pollutant matching relationship table to generate the comprehensive similarity weight corresponding to each upstream monitoring node.

[0093] The comprehensive similarity weight refers to the value obtained by multiplying the pollutant similarity by the preset weight of the corresponding pollutant in the pollution source feature association table for each upstream monitoring node, and aggregating the weighted results of all matching items of the upstream monitoring node, so as to measure the degree of contribution of the upstream monitoring node to the current anomaly.

[0094] For example, upstream monitoring node A has chemical oxygen demand (COD) as its dominant pollutant, and COD also shows an anomaly in the current high-frequency collection cycle. The calculated pollutant similarity between the two is 0.9. According to the pollution source characteristic association table, the preset weight of COD in domestic sewage pollution is 0.7, so the weighted value of this matching item is 0.63. Since node A only involves this one dominant pollutant, its overall similarity weight is 0.63. If another upstream node B is associated with both COD and ammonia nitrogen, with weighted values ​​of 0.5 and 0.3 respectively, then these are added together, resulting in an overall similarity weight of 0.8 for node B.

[0095] Step S403: Obtain the state variables of each upstream monitoring node when the early warning is triggered, and calculate the risk transmission value by combining the comprehensive similarity weights of each upstream monitoring node.

[0096] Risk transmission value refers to the numerical value obtained by multiplying the state variable of the upstream monitoring node at the time of the early warning with its corresponding comprehensive similarity weight. It is used to represent the quantitative degree of transmission of the pollution risk reflected by the upstream monitoring node to the current pipe section.

[0097] For example, if the state variable of upstream monitoring node A is 12 when an early warning is triggered, and its corresponding comprehensive similarity weight is 0.6, then the risk transmission value of node A is 7.2; if the state variable of upstream node B is 8, and its comprehensive similarity weight is 0.4, then the risk transmission value is 3.2. These values ​​reflect the degree of contribution of nodes A and B to the current pipeline section's pollution risk, respectively.

[0098] Step S404: Sum the risk transfer values ​​to obtain the summation result, and use the summation result as the initial value of the pipe segment state variable.

[0099] The risk transmission values ​​of all upstream monitoring nodes are summed, and the sum is directly used as the initial value of the pipe segment status variable. This is used to more accurately reflect the combined effect of each upstream node on the current anomaly when high-frequency data acquisition begins.

[0100] By employing the aforementioned technical solution, the similarity between water quality parameters in the current high-frequency acquisition cycle and the dominant pollutants at each upstream monitoring node is calculated. The matching relationships are then weighted and aggregated using a pre-defined pollution source feature association table to generate a comprehensive similarity weight. Finally, the risk transmission value is calculated by integrating the state variables of each upstream node, and the sum of these risk transmission values ​​is used as the initial value of the pipe segment's state variables. This solution significantly improves the accuracy of pollution source association identification and reduces the initial value deviation of state variables caused by relying solely on information from a single upstream node.

[0101] This application discloses a method for correcting risk transfer values. (Refer to...) Figure 5 The method includes: Step S501: Determine whether there is a pre-defined combination of interactions between pollutants. The combination of interactions includes antagonistic combinations and synergistic combinations.

[0102] An interaction combination refers to a situation where two pollutants coexist in a drainage pipe and undergo chemical or physical interactions, thereby altering their performance in water quality monitoring or their environmental impact. If the overall effect after the reaction is weaker than the sum of the effects of each pollutant when it exists alone, it is an antagonistic combination; if the overall effect after the reaction is stronger than the sum of the effects of each pollutant when it exists alone, it is a synergistic combination.

[0103] Determining whether a pre-defined combination of interactions exists is to identify whether the pollution effect of currently coexisting pollutants is weakened or enhanced due to chemical or physical effects, thereby introducing corrections in risk assessments and avoiding misjudgments caused by simple superposition.

[0104] Step S502: If present, obtain estimated values ​​of the residence time, reaction rate, and mixing degree of pollutants in the pipe section, and determine whether the interaction combination meets the conditions for reaction to occur.

[0105] The residence time is calculated in the same way as the expected flow time in step S303, and the reaction rate is retrieved from a preset database according to the pollutant type.

[0106] The estimated mixing degree is a quantitative indicator calculated based on the flow ratio of each upstream segment. The higher the value, the more thorough the mixing. This is determined by the formula... The calculation yields a result where n represents the number of upstream flows in the current pipe segment, with flow rates Q1, Q2, ..., Q... n Q totalThis represents the total flow rate. For example, if a pipe section has two upstream flow rates of 10 cubic meters per hour and 90 cubic meters per hour, with a total flow rate of 100 cubic meters per hour, then the estimated mixing degree, according to the formula M=0.18, indicates that the two flow rates differ significantly and the mixing is insufficient. If both flow rates are 50 cubic meters per hour, then M=0.5, indicating a higher degree of mixing uniformity.

[0107] By comparing whether the residence time of pollutants in the pipe section exceeds the minimum reaction time required for interaction, and combining this with whether the estimated degree of mixing reaches a preset uniformity threshold, while also considering whether the reaction rate is sufficient to produce a significant effect under these conditions, a comprehensive judgment is made as to whether the interaction combination meets the conditions for a reaction. For example, if sulfides and copper ions in the pipe section form an antagonistic combination, and the minimum reaction time is found to be 10 minutes (relatively fast), and the calculated residence time in the pipe section is 15 minutes, the estimated degree of mixing is 0.75, and the preset uniformity threshold is 0.6, then the residence time is sufficient, the mixing is thorough, and the conditions for a reaction are met.

[0108] If there is no pre-defined combination of interactions, proceed directly to the step of calculating the risk transmission value; there is no need to obtain the effect correction coefficient.

[0109] Step S503: If yes, then query the preset pollutant interaction coefficient table to obtain the effect correction coefficient corresponding to the interaction combination.

[0110] The pollutant interaction coefficient table is a pre-established database that records the effect correction coefficients corresponding to antagonistic or synergistic effects of different pollutant combinations.

[0111] The effect correction factor is a pre-set value used in risk transfer value calculation to reflect the weakening or strengthening of pollution effects caused by antagonistic or synergistic effects between pollutants.

[0112] If the interaction combination does not meet the conditions for a reaction to occur, the effect correction coefficient is not used.

[0113] Step S504: Associate the effect correction coefficient with the upstream monitoring node corresponding to the pollutant participating in the interaction combination for use in the calculation of risk transfer value.

[0114] The obtained effect correction coefficients are bound to the upstream monitoring nodes involved in the interaction and introduced as multiplicative factors in the subsequent calculation of risk transfer values ​​to reflect the impact of antagonistic or synergistic effects between pollutants on risk assessment. When calculating the risk transfer value, the coefficients are multiplied by the state variables and the overall similarity weights, where antagonistic combinations correspond to coefficients less than 1, and synergistic combinations correspond to coefficients greater than 1.

[0115] By employing the above technical solution, it is determined whether there are pre-defined antagonistic or synergistic interaction combinations among pollutants. The reaction conditions are then assessed by combining estimated values ​​of water quality parameters within the pipe section, such as residence time, reaction rate, and mixing degree. If the conditions are met, a pre-set pollutant interaction coefficient table is consulted to obtain the corresponding effect correction coefficient, which is then used to correct the risk transmission value. This solution significantly improves the accuracy of comprehensive pollution risk quantification and reduces risk assessment bias caused by neglecting the chemical interaction effects between pollutants.

[0116] This application discloses a method for handling conflicts in correction coefficients. (Refer to...) Figure 6 The method includes: Step S601: Detect multiple interaction combinations and determine whether there is a contradiction in the effect correction of the same pollutant. A contradiction in the effect correction direction means that the same pollutant is a component of the first interaction combination and the same pollutant is a component of the second interaction combination, wherein the first interaction combination and the second interaction combination are different interaction combination types.

[0117] Effect correction contradiction refers to the situation where the same pollutant participates in two different types of interaction combinations, one of which corresponds to a correction coefficient less than 1, and the other of which corresponds to a correction coefficient greater than 1.

[0118] Determining whether there are contradictions in effect correction is to avoid the situation where the same pollutant is simultaneously enhanced and weakened due to participating in different types of interaction combinations, which could lead to distortion or logical conflicts in the risk transfer value calculation results.

[0119] Step S602: If not, then perform a comprehensive calculation of the correction coefficients for multiple effects of the same pollutant to obtain a unified correction coefficient.

[0120] A unified correction factor refers to combining multiple effect correction factors corresponding to the same pollutant into a single value for subsequent calculations, thus avoiding duplication or conflict.

[0121] When the same pollutant participates in multiple interactions of the same type, its effect correction coefficients act sequentially according to the reaction order. Multiplying the correction coefficients together yields a unified correction coefficient.

[0122] Step S603: If so, determine the dominant effect combination based on the preset pollutant reaction priority and the current concentration of each relevant pollutant, and use the effect correction coefficient corresponding to the dominant effect combination as the unified correction coefficient.

[0123] The dominant effect combination refers to the combination that plays the main role in the current water quality when there are multiple conflicting interaction combinations, taking into account the pollutant response priority and current concentration.

[0124] Step S604: Based on the unified correction coefficient, correct the risk transmission value to obtain the corrected risk transmission value.

[0125] The unified correction coefficient is multiplied by the state variables and comprehensive similarity weights of the corresponding upstream monitoring nodes to generate the corrected risk transmission value, which reflects the actual impact of pollutant interactions on risk assessment.

[0126] By employing the above technical solution, multiple interaction combinations are detected to determine whether the same pollutant simultaneously participates in different types of effect corrections. When conflicting correction directions exist, the dominant effect combination is determined by combining the preset pollutant response priority and current concentration to generate a unified correction coefficient. When there is no conflict, multiple correction coefficients are comprehensively calculated. This solution effectively avoids the confusion in risk assessment caused by conflicting correction rules when multiple pollutants coexist, and reduces the bias in state assessment caused by conflicting effects.

[0127] This application discloses a method for identifying drainage anomaly events. (Refer to...) Figure 7 The method includes: Step S701: Obtain multidimensional feature data of abnormal water quality parameters. The multidimensional feature data includes at least one of the following: concentration change range, synchronous change relationship, or total flow change information of abnormal water quality parameters.

[0128] Multidimensional feature data refers to quantitative information extracted from different observation dimensions that can reflect the abnormal characteristics of water quality and is used to distinguish the causes of abnormal events.

[0129] Synchronous change relationship refers to two or more water quality parameters showing a consistent upward or downward trend over time. Specifically, the concentration change magnitude is obtained by comparing the current collected value with the average concentration of the parameter over several past collection periods. The synchronous change relationship is determined by judging whether multiple parameters change in the same direction within a continuous collection period. Total flow rate change information is collected in real time by the flow meter, and its change ratio relative to the recent average flow rate is calculated.

[0130] Step S702: Based on multidimensional feature data, determine whether there are any abnormal events. An abnormal event refers to the simultaneous decrease in the concentration of multiple abnormal water quality parameters and the increase in total flow rate exceeding the flow rate threshold.

[0131] An abnormal event refers to a significant change in water quality parameters that does not conform to normal sewage discharge patterns. For example, the concentrations of multiple abnormal water quality parameters decrease simultaneously while the total flow rate increases significantly. This may be caused by rainwater dilution or human interference.

[0132] Step S703: If yes, then determine the abnormal event as a runoff dilution event and maintain the current collection cycle.

[0133] A runoff dilution event refers to the phenomenon where surface runoff generated by rainfall enters drainage pipes, resulting in the dilution of wastewater, a decrease in pollutant concentration, and a significant increase in total flow.

[0134] When an anomaly is confirmed to be a simultaneous decrease in the concentration of multiple abnormal water quality parameters and a significant increase in flow rate, it is identified as a runoff dilution event caused by rainfall, and a fixed collection period is maintained.

[0135] Step S704: If not, determine whether the abnormal event conforms to the dimensional distribution characteristics. The dimensional distribution characteristics refer to the existence of the abnormal event within N consecutive collection cycles, and the abnormal event occurs on a single monitoring node or a few adjacent monitoring nodes.

[0136] Dimensional distribution characteristics refer to the distribution pattern in which abnormal events occur continuously over multiple consecutive collection cycles in time and are limited to a single or a few adjacent monitoring nodes in space.

[0137] Determining whether an event conforms to dimensional distribution characteristics is to identify whether the abnormal event is localized and persistent, thereby distinguishing between transient interference and unauthorized data dumping.

[0138] Step S705: If so, the abnormal event is determined to be a stolen discharge event, and an early warning signal is triggered.

[0139] After confirming that the abnormal event has localized and persistent characteristics and ruling out the possibility of dilution, it is determined to be a case of unauthorized discharge, and an early warning signal is issued to notify the operation and maintenance personnel to handle the situation.

[0140] By employing the above technical solution, multidimensional characteristic data of abnormal water quality parameters are obtained. Combined with the magnitude of concentration changes, the synchronous changes between parameters, and total flow rate changes, it is determined whether the characteristics of a runoff dilution event are met. If not, it is further determined whether the anomaly persists for N consecutive collection cycles and is limited to a single or a few adjacent monitoring nodes. This solution can more accurately distinguish between natural hydraulic disturbances and actual illegal discharge, reducing invalid early warnings caused by misjudging pipeline scouring or hydraulic disturbances as illegal discharge.

[0141] Based on the same inventive concept, this application provides a municipal drainage pipeline water quality monitoring system, see reference. Figure 8 The system includes: The acquisition module 801 is used to acquire multiple monitoring nodes and water quality parameters; The memory 802 is used to store the program for the municipal drainage pipeline water quality monitoring method; The processor 803 can load and execute programs in memory to implement the municipal drainage pipeline water quality monitoring method.

[0142] By adopting the above technical solution, the module collects water quality parameters from multiple monitoring nodes of the drainage pipeline, the processor efficiently executes monitoring logic such as pollution area determination and status variables, and the memory continuously supports the stable operation of the program. This achieves intelligent processing of the entire process from anomaly identification to early warning response, significantly improving the efficiency of pipeline monitoring while ensuring the accuracy of pollution identification, and providing an efficient and reliable intelligent supervision solution for municipal drainage systems.

[0143] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0144] This application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed for a municipal drainage pipeline water quality monitoring method.

[0145] Computer storage media include, for example, USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media that can store program code.

[0146] Based on the same inventive concept, embodiments of this application provide a smart terminal, including a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed as a method for monitoring the water quality of municipal drainage pipelines.

[0147] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0148] The above are all preferred embodiments of this application and are not intended to limit the scope of protection of this application. Any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features unless specifically stated otherwise. That is, unless specifically stated otherwise, each feature is only one example of a series of equivalent or similar features.

Claims

1. A method for monitoring water quality in municipal drainage pipelines, characterized in that, include: Multiple monitoring nodes are set up in the drainage pipeline, and the monitoring nodes are divided into upstream monitoring nodes and downstream monitoring nodes according to the direction of water flow. Water quality parameters of pollutants at each monitoring node are acquired at a fixed collection cycle, and the time stamps of the water quality parameters are recorded. The water quality parameters include at least one of pH value, chemical oxygen demand, ammonia nitrogen content and suspended solids concentration. Compare the water quality parameters of each monitoring node with the safety threshold; If both upstream and downstream monitoring nodes have abnormal water quality parameters, the local pollution area is calculated based on the time stamp and the flow velocity in the drainage pipe. If abnormal water quality parameters are found only at the upstream or downstream monitoring nodes, the pipe section where the monitoring node with abnormal water quality parameters is located will be identified as a localized pollution area. Based on the localized pollution area, an early warning signal is triggered and the monitoring node corresponding to the localized pollution area is controlled to switch to high-frequency acquisition cycle mode. If the water quality parameters do not exceed the safety threshold in N consecutive high-frequency acquisition cycles, the warning signal is canceled and the monitoring node corresponding to the local pollution area is controlled to return to the fixed acquisition cycle mode.

2. The method for monitoring water quality in municipal drainage pipelines according to claim 1, characterized in that, After triggering an early warning signal and controlling the monitoring node corresponding to the local pollution area to switch to high-frequency acquisition cycle mode based on the local pollution area, the method further includes: Upon receiving a warning signal for a pipe segment, initialize the state variables associated with the pipe segment and set the state variables to their initial values; At the end of the high-frequency acquisition cycle, the water quality parameters of the current high-frequency acquisition cycle are obtained and compared with the safety threshold. If the water quality parameters exceed the safety threshold, the initial values ​​will be increased by a preset increment to obtain the updated state variables; If the water quality parameters do not exceed the safety threshold, the initial values ​​are reduced by a preset attenuation amount to obtain the updated state variables; Determine whether the updated state variable is less than the variable threshold; If not, perform high-frequency acquisition in the next cycle and repeat the above four steps; If so, a command to cancel the warning signal will be generated, and the corresponding monitoring node in the pipeline segment will be restored to the fixed acquisition cycle mode.

3. The method for monitoring water quality in municipal drainage pipelines according to claim 2, characterized in that, Before initializing the state variables associated with the pipe segment after receiving a warning signal for that segment, the process further includes: Acquire early warning records from upstream monitoring nodes corresponding to localized pollution areas within a preset time window; Extract the dominant pollutant type and warning trigger time from the warning records; Calculate the estimated flow time based on the pipe segment length and flow velocity information of the local pollution area and the upstream monitoring node; Determine whether the pollutant type and the dominant pollutant type are consistent in the current high-frequency collection cycle, and whether the difference between the time stamp and the warning trigger time is within the expected flow time. If so, the initial values ​​of the pipe section's state variables are calculated based on the state variables of the upstream monitoring nodes, the water quality parameters corresponding to the dominant pollutants, and the safety thresholds.

4. The method for monitoring water quality in municipal drainage pipelines according to claim 3, characterized in that, The method further includes: Calculate the pollutant similarity between the pollutants in the current high-frequency acquisition cycle and the dominant pollutants of each upstream monitoring node to obtain a pollutant matching table; Based on the preset pollution source feature association table, each matching relationship in the pollutant matching relationship table is weighted and aggregated to generate the comprehensive similarity weight corresponding to each upstream monitoring node. Obtain the state variables of each upstream monitoring node when an early warning is triggered, and calculate the risk transmission value by combining the comprehensive similarity weights of each upstream monitoring node; The risk transmission values ​​are summed to obtain the summation result, which is then used as the initial value of the pipe segment state variable.

5. A method for monitoring water quality in municipal drainage pipelines according to claim 4, characterized in that, Before obtaining the state variables of each upstream monitoring node when the early warning is triggered, and calculating the risk transmission value by combining the comprehensive similarity weights corresponding to each upstream monitoring node, the process also includes: Determine whether there are pre-defined interaction combinations among pollutants; these combinations include antagonistic and synergistic combinations. If present, the estimated values ​​of the residence time, reaction rate and mixing degree of pollutants in the pipe section are obtained, and it is determined whether the interaction combination has the conditions for reaction to occur. If so, then query the preset pollutant interaction coefficient table to obtain the effect correction coefficient corresponding to the interaction combination; The effect correction coefficient is correlated to the upstream monitoring node corresponding to the pollutants involved in the interaction combination, in order to be used for the calculation of risk transfer value.

6. A method for monitoring water quality in municipal drainage pipelines according to claim 5, characterized in that, The method further includes: Multiple interaction combinations are detected to determine whether there is a contradiction in the effect correction of the same pollutant. A contradiction in the effect correction direction means that the same pollutant is a component of the first interaction combination and the same pollutant is a component of the second interaction combination, wherein the first interaction combination and the second interaction combination are different interaction combination types. If not, then the correction coefficients for multiple effects of the same pollutant are calculated together to obtain a unified correction coefficient; If so, the dominant effect combination is determined based on the preset pollutant response priority and the current concentration of each relevant pollutant, and the effect correction coefficient corresponding to the dominant effect combination is used as the unified correction coefficient. Based on a unified correction factor, the risk transmission value is corrected to obtain the corrected risk transmission value.

7. The method for monitoring water quality in municipal drainage pipelines according to claim 1, characterized in that, The method further includes: Obtain multidimensional feature data of abnormal water quality parameters. The multidimensional feature data includes at least one of the following: concentration variation range, synchronous variation relationship, or total flow variation information of abnormal water quality parameters. Based on multidimensional feature data, it is determined whether there are abnormal events. Abnormal events refer to the simultaneous decrease in the concentration of multiple abnormal water quality parameters and the increase in total flow exceeding the flow threshold. If so, the abnormal event is determined to be a runoff dilution event, and the current collection cycle is maintained; If not, determine whether the abnormal event conforms to the dimensional distribution characteristics. The dimensional distribution characteristics refer to the existence of the abnormal event within N consecutive collection cycles, and the abnormal event occurs on a single monitoring node or a few adjacent monitoring nodes. If so, the abnormal event is determined to be a case of unauthorized discharge, and an early warning signal is triggered.

8. A municipal drainage pipeline water quality monitoring system, characterized in that, The system is used to perform the municipal drainage pipeline water quality monitoring method as described in any one of claims 1 to 7, including: The acquisition module is used to acquire multiple monitoring nodes and water quality parameters; A memory for storing the program of the municipal drainage pipeline water quality monitoring method; The processor and the program in the memory can be loaded and executed by the processor to implement the municipal drainage pipeline water quality monitoring method.

9. A smart terminal, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer program is stored that can be loaded by a processor and execute the method as described in any one of claims 1 to 7.

Images