Drainage pipe network monitoring method, system, electronic device and storage medium

Abstract

The present disclosure relates to technical solutions of a sewer network monitoring method, system, electronic device and storage medium. The method comprises: determining target monitoring time series data of any one monitoring point of a target sewer network; for any one monitoring point, constructing an external water intrusion analysis model of the monitoring point according to historical monitoring time series data, historical location influence factors and historical external water intrusion record data of the monitoring point; for any one monitoring point, determining an external water intrusion analysis result of the monitoring point based on the target monitoring time series data, target location influence factors of the monitoring point and the external water intrusion analysis model of the monitoring point. By introducing the historical location influence factors of each monitoring point, the external water intrusion analysis model can effectively utilize the geographical position information of each monitoring point, improve the sensitivity to high-risk monitoring points, and further improve the accuracy and reliability of the external water intrusion analysis result.

Description

Technical Field

[0001] This disclosure relates to the field of water environment health monitoring technology, and in particular to a monitoring method, system, electronic equipment, and storage medium for drainage pipe networks. Background Technology

[0002] Drainage pipe networks are a crucial part of urban infrastructure. Health issues within these networks, particularly external water intrusion, directly impact the water quality of the corresponding areas. Therefore, real-time monitoring of drainage pipe network health, analyzing the occurrence of external water intrusion, and identifying the location of such intrusions are essential for pipe maintenance. Summary of the Invention

[0003] In view of this, this disclosure proposes a technical solution for monitoring drainage pipe networks, including a method, system, electronic equipment, and storage medium.

[0004] According to one aspect of this disclosure, a method for monitoring a drainage network is provided, comprising: determining target monitoring time series data for any monitoring point of the target drainage network, wherein the target monitoring time series data for any monitoring point includes target liquid level time series data for the monitoring point and target monitoring value time series data for at least one water quality indicator; for any monitoring point, constructing an external water intrusion analysis model for the monitoring point based on historical monitoring time series data, historical location influencing factors, and historical external water intrusion records, wherein the historical monitoring time series data for any monitoring point includes historical liquid level time series data for the monitoring point and the target monitoring value time series data for at least one water quality indicator; The historical monitoring value time series data of the indicator, and the historical location influence factor of any monitoring point, are used to indicate the historical location relationship of the monitoring point relative to the external water source corresponding to the target drainage network. For any monitoring point, based on the target monitoring time series data, the target location influence factor, and the external water intrusion analysis model of the monitoring point, the external water intrusion analysis result of the monitoring point is determined. Among them, the target location influence factor of any monitoring point is used to indicate the real-time location relationship of the monitoring point relative to the external water source corresponding to the target drainage network, and the external water intrusion analysis result of any monitoring point includes the probability that the target drainage network will experience external water intrusion at the monitoring point.

[0005] In one possible implementation, the method further includes: for any given monitoring point, determining the real-time hydraulic gradient of the monitoring point based on the pipe bottom elevation of the monitoring point, the target pipeline path distance of the monitoring point relative to the external water source, and the water level time series data of the external water source, wherein the real-time hydraulic gradient of any monitoring point represents the real-time head difference per unit pipeline path length at the monitoring point; if the real-time hydraulic gradient of the monitoring point satisfies a first preset condition, determining the target location influence factor of the monitoring point based on a first preset value or the real-time hydraulic gradient of the monitoring point; if the real-time hydraulic gradient of the monitoring point satisfies a second preset condition, determining the target location influence factor of the monitoring point based on a second preset value.

[0006] In one possible implementation, the step of constructing an external water intrusion analysis model for any given monitoring point based on its historical monitoring time-series data, historical location influence factors, and historical external water intrusion records includes: determining the prior distribution of the external water intrusion analysis model parameters for any given monitoring point; constructing a likelihood function of the external water intrusion analysis model parameters for the given monitoring point based on its historical monitoring time-series data, historical location influence factors, and historical external water intrusion records; determining the posterior distribution of the external water intrusion analysis model parameters for the given monitoring point based on the prior distribution and likelihood function; determining the external water intrusion analysis model parameters for the given monitoring point based on the posterior distribution; and constructing the external water intrusion analysis model for the given monitoring point based on the external water intrusion analysis model parameters.

[0007] In one possible implementation, determining the prior distribution of the external water intrusion analysis model parameters for any given monitoring point includes: determining the theoretical background flow rate of any given monitoring point based on its upstream catchment area, surface runoff coefficient, historical flow time series data, and historical rainfall time series data; wherein the theoretical background flow rate of any given monitoring point represents the theoretical flow rate of the target drainage network at that monitoring point in the absence of external water intrusion; determining the physical feasible region of the external water intrusion analysis model parameters for that monitoring point based on the theoretical background flow rate; and determining the prior distribution of the external water intrusion analysis model parameters for that monitoring point based on the physical feasible region of the external water intrusion analysis model parameters.

[0008] In one possible implementation, the method further includes: for any monitoring point, if the external water intrusion analysis result of the monitoring point meets a third preset condition, determining the alarm information of the monitoring point, wherein the alarm information of the monitoring point is used to instruct the investigation of external water intrusion phenomena at the monitoring point.

[0009] In one possible implementation, the method further includes: if the investigation results of external water intrusion at the monitoring point meet the fourth preset condition, optimizing and updating the external water intrusion analysis model of the monitoring point based on the target monitoring time series data, target location influence factors, and external water intrusion investigation results of the monitoring point.

[0010] In one possible implementation, if the investigation results of external water intrusion at the monitoring point meet the fourth preset condition, the external water intrusion analysis model for the monitoring point is optimized and updated based on the target monitoring time series data, target location influence factors, and external water intrusion investigation results. This includes: determining the posterior distribution of the external water intrusion analysis model parameters for the monitoring point as the new prior distribution of the external water intrusion analysis model parameters for the monitoring point; constructing a new likelihood function for the external water intrusion analysis model parameters for the monitoring point based on the target monitoring time series data, target location influence factors, and external water intrusion investigation results for the monitoring point; determining the new posterior distribution of the external water intrusion analysis model parameters for the monitoring point based on the new likelihood function and the new prior distribution; determining the new external water intrusion analysis model parameters for the monitoring point based on the new posterior distribution; and optimizing and updating the external water intrusion analysis model for the monitoring point based on the new external water intrusion analysis model parameters.

[0011] According to another aspect of this disclosure, a monitoring system for a drainage network is provided, comprising: a data preprocessing module, configured to determine target monitoring time series data for any monitoring point of the target drainage network, wherein the target monitoring time series data for any monitoring point includes target liquid level time series data for the monitoring point, and target monitoring value time series data for at least one water quality indicator; and a model building module, configured to construct an external water intrusion analysis model for any monitoring point based on historical monitoring time series data, historical location influencing factors, and historical external water intrusion record data for the monitoring point, wherein the historical monitoring time series data for any monitoring point includes historical liquid level time series data for the monitoring point, and target monitoring value time series data for at least one water quality indicator; and a model building module, configured to construct an external water intrusion analysis model for any monitoring point based on historical monitoring time series data, historical location influencing factors, and historical external water intrusion record data for the monitoring point, wherein the historical monitoring time series data for any monitoring point includes historical liquid level time series data for the monitoring point, and target monitoring value time series data for at least one water quality indicator. The system includes: historical monitoring time series data of one water quality indicator; historical location influence factor of any monitoring point, used to indicate the historical location relationship of the monitoring point relative to the external water source corresponding to the target drainage network; and an external water intrusion analysis module, used to determine the external water intrusion analysis result of any monitoring point based on the target monitoring time series data, target location influence factor, and external water intrusion analysis model of the monitoring point. The target location influence factor of any monitoring point indicates the real-time location relationship of the monitoring point relative to the external water source corresponding to the target drainage network, and the external water intrusion analysis result of any monitoring point includes the probability of external water intrusion occurring at that monitoring point in the target drainage network.

[0012] According to another aspect of this disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above-described method.

[0013] According to another aspect of this disclosure, a non-volatile computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the above-described method.

[0014] In this embodiment of the disclosure, after determining the target monitoring time series data of any monitoring point in the target drainage network, including the target liquid level time series data of the monitoring point and the target monitoring value time series data of at least one water quality indicator, for any monitoring point, an external water intrusion analysis model for the monitoring point can be constructed based on the historical monitoring time series data of the monitoring point, the historical monitoring time series data of at least one water quality indicator, the historical location influence factor that can indicate the historical location relationship of the monitoring point relative to the external water source corresponding to the target drainage network, and the historical external water intrusion record data. Compared with the existing external water intrusion analysis method that only uses the monitoring data of water quality indicators and liquid levels for analysis, by introducing the historical location influence factor, the external water intrusion analysis model can effectively utilize the geographical location information of the monitoring point, fully characterize the external hydrological environment of the monitoring point, and thus improve the sensitivity to high-risk monitoring points. For any given monitoring point, the external water intrusion analysis results can be determined by comprehensively utilizing the target monitoring time series data, target location influencing factors, and external water intrusion analysis model of that monitoring point in both time and spatial dimensions. This indicates the probability of external water intrusion occurring in the target drainage network at that monitoring point, thereby improving the accuracy and reliability of the external water intrusion analysis results.

[0015] Other features and aspects of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0016] The accompanying drawings, which are included in and form part of this specification, illustrate exemplary embodiments, features, and aspects of this disclosure together with the specification and serve to explain the principles of this disclosure.

[0017] Figure 1 A flowchart illustrating a method for monitoring a drainage network according to an embodiment of the present disclosure is shown;

[0018] Figure 2 A block diagram of a monitoring system for a drainage network according to an embodiment of the present disclosure is shown;

[0019] Figure 3 A block diagram of an electronic device according to an embodiment of the present disclosure is shown. Detailed Implementation

[0020] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0021] As used herein, the terms “comprising,” “including,” “having,” or variations thereof are open-ended and include one or more of the stated features, integrals, elements, steps, components, or functions, but do not exclude the presence or addition of one or more other features, integrals, elements, steps, components, functions, or groups thereof.

[0022] When an element is referred to as “connected,” “coupled,” “responding,” or a variation thereof relative to another element, it may be directly connected, coupled, or responding to another element, or there may be an intermediate element present.

[0023] Although the terms first, second, third, etc., may be used herein to describe various elements / operations, these elements / operations should not be limited by these terms. These terms are only used to distinguish one element / operation from another. Therefore, without departing from the teachings of the inventive concept, a first element / operation in some embodiments may be referred to as a second element / operation in other embodiments.

[0024] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0025] Furthermore, to better illustrate this disclosure, numerous specific details are set forth in the following detailed description. Those skilled in the art will understand that this disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of this disclosure.

[0026] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, data stored, data displayed, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant regions.

[0027] Drainage pipe networks are a crucial part of urban infrastructure. Health issues within these networks, particularly external water intrusion, directly impact the water quality of the corresponding areas. Therefore, real-time monitoring of drainage pipe network health, analyzing the occurrence of external water intrusion, and identifying the location of such intrusions are essential for pipe maintenance.

[0028] The common methods for detecting external water intrusion in existing drainage pipe networks typically employ the traditional logistic regression model. The logistic regression model is a binary classification model whose core principle is to map the S-shaped growth curve (Sigmoid) function of linear combination features into probabilities, specifically expressed as formula (1):

[0029]

[0030] Where Y=1 represents the occurrence of external water intrusion; β represents the parameter vector; X represents the feature vector, i.e. the input data of the Logistic regression model; and σ(·) represents the Sigmoid function.

[0031] In existing technologies, the solution for the parameter vector β of the Logistic Regression model relies on point estimation methods such as Maximum Likelihood Estimation (MLE). This method can only obtain a single optimal parameter vector β and cannot quantify the uncertainty of the parameter vector β. As a result, the Logistic Regression model is prone to overfitting when dealing with high-dimensional data in application scenarios with small sample sizes. This leads to insufficient generalization ability of the model and makes it easy to misjudge and / or miss the detection of external water intrusion, which is difficult to meet the actual use requirements.

[0032] On the other hand, existing methods for detecting external water intrusion in drainage pipe networks typically do not take into account the influence of geographical environmental factors in which the drainage pipe network is located. They cannot reflect the risk differences of external water intrusion at different locations in the drainage pipe network with different relationships to external water sources, thus affecting the accuracy of identifying external water intrusion.

[0033] In view of this, this disclosure provides a monitoring method for drainage pipe networks. When constructing the external water intrusion analysis model for each monitoring point, it not only utilizes the target monitoring time series data for each monitoring point but also introduces the historical location influence factor for each monitoring point. This allows the external water intrusion analysis model to effectively utilize the geographical location information and its changes at each monitoring point, fully characterizing the external hydrological environment of each monitoring point, improving the sensitivity to high-risk monitoring points, and thus improving the accuracy and reliability of the external water intrusion analysis results. The monitoring method for drainage pipe networks provided in this disclosure is described in detail below.

[0034] Figure 1A flowchart illustrating a method for monitoring a drainage network according to an embodiment of this disclosure is provided. This method can be executed by an electronic device such as a terminal device or a server. The terminal device can be a user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, vehicle-mounted device, wearable device, etc. The method can be implemented by a processor calling computer-readable instructions stored in memory. Alternatively, the method can be executed by a server. Figure 1 As shown, the monitoring methods for this drainage network include:

[0035] In step S101, the target monitoring time series data of any monitoring point in the target drainage network is determined. The target monitoring time series data of any monitoring point includes the target liquid level time series data of the monitoring point and the target monitoring value time series data of at least one water quality indicator.

[0036] The target drainage network mentioned here can refer to any type of drainage network, and its specific form can be flexibly set according to actual usage needs, such as rainwater drainage network, sewage drainage network, or combined sewer system, etc. This disclosure does not impose specific limitations on it. The specific number of monitoring points in the target drainage network can be flexibly set according to actual usage needs, and this disclosure does not impose specific limitations on it.

[0037] The target monitoring time series data for any monitoring point may include the target liquid level time series data for that monitoring point, and the target monitoring value time series data for at least one water quality indicator. Specifically, the target liquid level time series data for any monitoring point can reflect the change in the liquid level in the pipeline at that monitoring point over time. Its specific form can be flexibly set according to actual usage requirements, and this disclosure does not impose specific limitations on it. The specific method for determining the target liquid level time series data corresponding to any monitoring point can refer to the implementation methods in related technologies, such as using a liquid level sensor for real-time monitoring, and this disclosure does not impose specific limitations on it.

[0038] The time series data of target monitoring values ​​of at least one water quality indicator at any monitoring point can reflect the change of the monitoring value of at least one water quality indicator at that monitoring point over time. Its specific format can be flexibly set according to actual usage needs, and this disclosure does not impose specific limitations on it. The specific number and type of water quality indicators can also be flexibly set according to actual usage needs, and this disclosure does not impose specific limitations on them.

[0039] In one possible implementation, water quality indicators may include at least one of the following: chemical oxygen demand (COD), conductivity, ammonia nitrogen, five-day biochemical oxygen demand, turbidity, total organic carbon, total hardness, total phosphorus, total nitrogen, suspended solids, total dissolved solids, petroleum hydrocarbons, pH (acidity / alkalinity), anionic surfactants, cyanide, sulfide, fluoride, chloride, organophosphorus compounds, sulfate, mercury, chromium, cadmium, arsenic, lead, nickel, beryllium, silver, selenium, copper, zinc, manganese, iron, volatile phenols, benzene series compounds, aniline compounds, nitrobenzene, and water temperature.

[0040] The time series data of the target monitoring value of at least one water quality indicator corresponding to any monitoring point can be determined by in-situ, real-time acquisition at that monitoring point using a spectral sensor. Compared to the method of sampling water bodies and then conducting laboratory tests to measure the values ​​of each water quality indicator, the spectral sensor enables online, in-situ, high-frequency, real-time measurement, increasing the acquisition frequency from once a day to once every 3-60 minutes. The monitoring efficiency and accuracy are higher than traditional testing methods, thus enabling the acquisition of water quality indicator monitoring values ​​at a higher frequency, effectively capturing the water quality characteristics of drainage networks. The spectral sensor is preferably a quantum dot spectral probe. The acquisition frequency of the spectral sensor can be flexibly set according to actual usage requirements, for example, it can be set to 5-30 minutes / time, 8-20 minutes / time, 10-15 minutes / time, etc., and this disclosure does not specifically limit this. Preferably, the acquisition frequency is set to 10-15 minutes / time.

[0041] In step S102, for any monitoring point, an external water intrusion analysis model is constructed based on the historical monitoring time series data, historical location influence factor, and historical external water intrusion record data of the monitoring point. The historical monitoring time series data of any monitoring point includes the historical liquid level time series data of the monitoring point and the historical monitoring value time series data of at least one water quality indicator. The historical location influence factor of any monitoring point is used to indicate the historical location relationship of the monitoring point relative to the external water source corresponding to the target drainage network.

[0042] The historical monitoring time series data for any monitoring point may include historical liquid level time series data for that monitoring point, and historical monitoring value time series data for at least one water quality indicator. The format of the historical liquid level time series data for any monitoring point is the same as the format of its corresponding target liquid level time series data; the format of the historical monitoring value time series data for at least one water quality indicator for any monitoring point is the same as the format of its corresponding target monitoring value time series data for at least one water quality indicator, and both include the same number and type of water quality indicators.

[0043] The external water source corresponding to the target drainage network can be defined as a water source outside the target drainage network system that has a preset spatial relationship with the target drainage network and can cause external water to enter the target drainage network. Its specific form can be flexibly set according to actual usage needs. For example, it can include river water, groundwater, etc. This disclosure does not make specific limitations on this. In addition, due to factors such as the structure and layout of the inverted siphon, the probability of external water intrusion is usually higher when there is an inverted siphon in the target drainage network. Therefore, in the embodiments of this disclosure, the location of the inverted siphon can be regarded as an equivalent external water source so as to fully consider the influence of the special structure of the inverted siphon in the process of external water intrusion analysis.

[0044] The specific number of external water sources corresponding to the target drainage network can be flexibly set according to actual usage needs, and this disclosure does not impose specific limitations on this. The specific content of the preset spatial relationship can be flexibly set according to actual usage needs, for example, it may include the minimum distance between the target drainage network and the external water source, and this disclosure does not impose specific limitations on this.

[0045] Considering that the positional relationship between the external water source and each monitoring point may change over time—for example, in the case of groundwater, changes in groundwater level will affect its positional relationship with each monitoring point—a historical positional influence factor can be used for any given monitoring point to indicate its historical positional relationship relative to the external water source corresponding to the target drainage network, thus quantifying the degree of influence of the external water source on the pipeline at that monitoring point. The specific form of the historical positional influence factor can be flexibly set according to actual usage requirements, and this disclosure does not impose specific limitations on it. It should be noted that the historical positional influence factor for any monitoring point should be a normalized non-negative number, i.e., its value ranges from 0 to 1.

[0046] In one example, the historical location influence factor can be set as a static label in the form of a dichotomous variable. If the distance between any monitoring point and the external water source corresponding to the target drainage network is less than or equal to a preset distance threshold, the historical location influence factor of that monitoring point can be set to 1; if the distance between any monitoring point and the external water source corresponding to the target drainage network is greater than the preset distance threshold, the historical location influence factor of that monitoring point can be set to 0. The specific value of the preset distance threshold can be flexibly set according to actual usage requirements, and this disclosure does not impose specific limitations on it.

[0047] Historical external water intrusion record data may include: the location of external water intrusion phenomena in the target drainage network, and the hydraulic gradient of each external water intrusion phenomenon location, etc. The specific content can be flexibly set according to actual usage needs, and this disclosure does not make specific limitations on it.

[0048] The following sections will describe in detail the process of constructing an external water intrusion analysis model for any given monitoring point, based on its historical monitoring time series data, historical location influencing factors, and historical external water intrusion records, in conjunction with the possible implementation methods disclosed herein. These details will not be elaborated upon here.

[0049] In step S103, for any monitoring point, based on the target monitoring time series data, target location influence factor, and external water intrusion analysis model of the monitoring point, the external water intrusion analysis result of the monitoring point is determined. The target location influence factor of any monitoring point is used to indicate the real-time positional relationship of the monitoring point relative to the external water source corresponding to the target drainage network. The external water intrusion analysis result of any monitoring point includes the probability that the target drainage network will experience external water intrusion at the monitoring point.

[0050] The target location influence factor of any monitoring point can be used to indicate the real-time location relationship of the monitoring point relative to the external water source corresponding to the target drainage network. The specific form of the target location influence factor of any monitoring point can be flexibly set according to actual usage needs. It can be the same as the historical location influence factor of the monitoring point. For example, both the historical location influence factor and the target location influence factor of the monitoring point can be set as static labels in the form of binary variables. Alternatively, it can be in a different form than the historical location influence factor of the monitoring point. For example, the historical location influence factor of the monitoring point can be set as a static label in the form of binary variables, and the target location influence factor of the monitoring point can be set as a dynamic label with a value range of 0 to 1. This disclosure does not make specific limitations on this.

[0051] For any given monitoring point, the target monitoring time series data and target location influencing factors of that monitoring point can be input into the external water intrusion analysis model for that monitoring point. Compared with the existing external water intrusion analysis methods that only use water quality indicators and liquid level monitoring data for analysis, this method introduces a target location influencing factor that can reflect the spatial correlation between the monitoring point and the external water source. It analyzes the probability of external water intrusion occurring in the target drainage network at that monitoring point and determines it as the external water intrusion analysis result for that monitoring point. By comprehensively utilizing the characteristic information of the time and spatial dimensions, the accuracy and reliability of the external water intrusion analysis results are improved.

[0052] In this embodiment of the disclosure, after determining the target monitoring time series data of any monitoring point in the target drainage network, including the target liquid level time series data of the monitoring point and the target monitoring value time series data of at least one water quality indicator, for any monitoring point, an external water intrusion analysis model for the monitoring point can be constructed based on the historical monitoring time series data of the monitoring point, the historical monitoring time series data of at least one water quality indicator, the historical location influence factor that can indicate the historical location relationship of the monitoring point relative to the external water source corresponding to the target drainage network, and the historical external water intrusion record data. Compared with the existing external water intrusion analysis method that only uses the monitoring data of water quality indicators and liquid levels for analysis, by introducing the historical location influence factor, the external water intrusion analysis model can effectively utilize the geographical location information of the monitoring point, fully characterize the external hydrological environment of the monitoring point, and thus improve the sensitivity to high-risk monitoring points. For any given monitoring point, the external water intrusion analysis results can be determined by comprehensively utilizing the target monitoring time series data, target location influencing factors, and external water intrusion analysis model of that monitoring point in both time and spatial dimensions. This indicates the probability of external water intrusion occurring in the target drainage network at that monitoring point, thereby improving the accuracy and reliability of the external water intrusion analysis results.

[0053] In one possible implementation, determining the target monitoring time series data for any monitoring point of the target drainage network includes: for any monitoring point, determining the initial monitoring time series data for that monitoring point; performing data preprocessing on the initial monitoring time series data for that monitoring point to determine the target monitoring time series data for that monitoring point.

[0054] The specific methods for data preprocessing can be flexibly set according to actual usage needs, and this disclosure does not impose specific limitations on them.

[0055] In one example, negative values ​​(the liquid level cannot be negative), obviously unreasonable values ​​(e.g., the liquid level is greater than the inner diameter of the pipe in the target drainage network), invalid values ​​such as data exceeding the range of the liquid level monitoring equipment and data that violate business logic can be removed from the initial liquid level time series data corresponding to the target drainage network. Then, data completion methods such as ARIMA prediction model, smoothing algorithm, and averaging of data before and after the missing value are used to fill in the missing data at the aforementioned removal positions to obtain the target liquid level time series data.

[0056] In one example, for any given monitoring point, outliers such as negative values ​​(the monitoring value of any water quality indicator cannot be negative), obviously unreasonable data (e.g., the conductivity monitoring value is 0), invalid values ​​such as data exceeding the range of the water quality monitoring equipment, and data that violate business logic can be removed from the initial monitoring value time series data of at least one water quality indicator corresponding to that monitoring point. Then, data completion methods, such as ARIMA prediction models, smoothing algorithms, and averaging the data before and after the missing values, are used to fill in the missing data at the aforementioned removal locations, thereby obtaining the target monitoring value time series data of at least one water quality indicator corresponding to that monitoring point.

[0057] The specific content of the business logic can be flexibly set according to actual usage needs. For example, data when the water quality or liquid level monitoring equipment is offline, etc., are not limited in this disclosure. The specific method for determining whether the water quality or liquid level monitoring equipment is offline can be flexibly set according to actual usage needs. For example, when the conductivity concentration value at the monitoring point is less than a preset value (e.g., 300 μs / cm), it can be determined that the water quality monitoring equipment at the monitoring point is offline. In the case of water in the target drainage network, if the duration of the liquid level monitoring value at the monitoring point being equal to 0 meets the preset duration, it can be determined that the liquid level monitoring equipment at the monitoring point is offline. This disclosure does not specifically limit this.

[0058] By processing the initial monitoring time series data corresponding to each monitoring point, outliers can be removed from the data, and missing data at the removed locations can be filled in, thereby improving the accuracy and reliability of the data and ensuring the accuracy and reliability of subsequent analysis of external water intrusion phenomena.

[0059] In one possible implementation, the method further includes: for any given monitoring point, determining the real-time hydraulic gradient of the monitoring point based on the pipe bottom elevation of the monitoring point, the target pipeline path distance of the monitoring point relative to the external water source, and the water level time series data of the external water source, wherein the real-time hydraulic gradient of any monitoring point is used to represent the real-time head difference per unit pipeline path length at the monitoring point; if the real-time hydraulic gradient of the monitoring point meets a first preset condition, determining the target location influence factor of the monitoring point based on a first preset value or the real-time hydraulic gradient of the monitoring point; if the real-time hydraulic gradient of the monitoring point meets a second preset condition, determining the target location influence factor of the monitoring point based on a second preset value.

[0060] Specifically, the pipe bottom elevation at any monitoring point, also known as the pipe inner bottom elevation, can be used to represent the absolute altitude (i.e., absolute elevation) of the lowest point of the pipe inner wall at that monitoring point. For specific methods of determining the pipe bottom elevation at any monitoring point, refer to the implementation methods in related technologies; this disclosure does not impose specific limitations on these methods.

[0061] The path distance of any monitoring point relative to the target pipeline network of the external water source can be used to represent the shortest pipeline length required to reach the external water source from that monitoring point, along the water flow direction of the target drainage pipeline network, and through the connecting pipes of the target drainage pipeline network. This is different from the geometric straight-line distance of the monitoring point relative to the external water source. Specific methods for determining the path distance of any monitoring point relative to the target pipeline network of the external water source can refer to implementation methods in related technologies; this disclosure does not specifically limit this method.

[0062] Time series data of water level of external water source can reflect the change of water level of external water source over time; the specific method for determining the time series data of water level of external water source can refer to the implementation methods in related technologies, and this disclosure does not make specific limitations thereto.

[0063] For any given monitoring point, the real-time hydraulic gradient of that monitoring point can be determined based on the pipe bottom elevation, the distance of the monitoring point from the target pipeline path of the external water source, and the water level time series data of the external water source. This gradient represents the real-time head difference per unit pipeline path length at the monitoring point, and thus reflects the strength of the intrusion driving force of the external water source at that monitoring point. Specifically, the real-time hydraulic gradient of any monitoring point can be expressed by formulas (2) and (3):

[0064]

[0065] Where I(t) represents the real-time hydraulic gradient at the monitoring point at monitoring time t; H w (t) represents the water level of the external water source at monitoring time t; H p The elevation of the bottom of the pipe at the monitoring point is indicated; L represents the distance of the monitoring point relative to the target pipeline path of the external water source; δ represents the direction indicator factor, which is used to reflect whether the overflow of the external water source can flow to the monitoring point.

[0066] For any given monitoring point, if the real-time hydraulic gradient at that monitoring point meets a first preset condition, the target location influence factor for that monitoring point can be determined based on the first preset value or the real-time hydraulic gradient at that monitoring point. The specific content of the first preset condition can be flexibly set according to actual usage requirements, and this disclosure does not impose specific limitations on it.

[0067] In one example, the first preset condition may include: the real-time hydraulic gradient at any monitoring point is greater than a preset gradient threshold. The specific value of the preset gradient threshold can be flexibly set according to actual usage requirements, and this disclosure does not impose specific limitations on it.

[0068] In one example, for any monitoring point, statistical analysis can be performed based on the historical external water intrusion records of the target drainage network to determine the minimum hydraulic gradient statistical value, and the minimum hydraulic gradient statistical value can be set as the preset gradient threshold.

[0069] In one example, for any monitoring point, a preset gradient threshold can be determined based on the minimum back slope requirement of the target drainage network at that monitoring point.

[0070] The specific method for determining the target location influencing factor of a monitoring point based on a first preset value or the real-time hydraulic gradient of any monitoring point can be flexibly set according to actual usage requirements, and this disclosure does not impose specific limitations on it.

[0071] In one example, for any monitoring point, if the real-time hydraulic gradient at that monitoring point meets a first preset condition, the first preset value can be directly determined as the target location influence factor for that monitoring point. The specific value of the first preset value can be flexibly set according to actual usage requirements, and this disclosure does not impose specific limitations on it. For example, the first preset value can be set to 1, where 1 indicates a risk of external water intrusion.

[0072] Preferably, for any monitoring point, if the real-time hydraulic gradient of the monitoring point meets the first preset condition, the real-time hydraulic gradient of the monitoring point can be directly determined as the target location influence factor of the monitoring point, so as to directly reflect the strength of the external water intrusion driving force through the magnitude of the real-time hydraulic gradient.

[0073] In one example, for any monitoring point, if the real-time hydraulic gradient at that monitoring point meets a first preset condition, the real-time hydraulic gradient at that monitoring point can be normalized, and the normalized mapping value obtained after processing can be determined as the target location influence factor of that monitoring point. The specific method for normalizing the real-time hydraulic gradient at any monitoring point can be flexibly set according to actual usage requirements, and this disclosure does not impose specific limitations on it.

[0074] For any given monitoring point, if the real-time hydraulic gradient at that point meets the second preset condition, the target location influence factor for that monitoring point can be determined based on the second preset value. The specific content of the second preset condition can be flexibly set according to actual usage requirements, and this disclosure does not impose specific limitations on it.

[0075] In one example, the second preset condition may include: the real-time hydraulic gradient of any monitoring point is less than 0, or the real-time hydraulic gradient of any monitoring point is greater than or equal to 0 and less than or equal to a preset gradient threshold.

[0076] The specific method for determining the target location influence factor of any monitoring point based on the second preset value can be flexibly set according to actual usage needs, and this disclosure does not impose specific limitations on it.

[0077] In one example, for any monitoring point, if the real-time hydraulic gradient at that monitoring point meets the second preset condition, the second preset value can be directly determined as the target location influence factor for that monitoring point. The specific value of the second preset value can be flexibly set according to actual usage requirements, and this disclosure does not impose specific limitations on it. For example, the second preset value can be set to 0, where 0 indicates no risk of external water intrusion.

[0078] Through the above process, for any monitoring point, a continuous and real-time target location influence factor can be formed using the real-time hydraulic gradient of that monitoring point. This allows the external water intrusion analysis model for that monitoring point to dynamically perceive changes in the external water intrusion risk at each monitoring moment, thereby improving the accuracy and reliability of external water intrusion analysis. Furthermore, the method described above for determining the target location influence factor in dynamic label form can also be used to determine the historical location influence factor for any monitoring point. Specifically:

[0079] For any given monitoring point, the historical hydraulic gradient of that monitoring point is determined based on its historical pipe bottom elevation, historical pipeline path distance relative to the external water source, and historical water level time series data of the external water source. The historical hydraulic gradient of any given monitoring point represents the historical head difference per unit pipeline path length at that monitoring point. If the historical hydraulic gradient of a monitoring point meets the fifth preset condition, the historical location influence factor of that monitoring point is determined based on the third preset value or the historical hydraulic gradient itself. If the historical hydraulic gradient of a monitoring point meets the sixth preset condition, the historical location influence factor of that monitoring point is determined based on the fourth preset value.

[0080] The fifth preset condition may include: the historical hydraulic gradient at any monitoring point is greater than a preset historical gradient threshold. The specific value of the preset historical gradient threshold can be flexibly set according to actual usage requirements, and this disclosure does not impose specific limitations on it. The sixth preset condition may include: the historical hydraulic gradient at any monitoring point is less than 0, or the historical hydraulic gradient at any monitoring point is greater than or equal to 0 and less than or equal to the preset historical gradient threshold. The specific values ​​of the third and fourth preset values ​​can be flexibly set according to actual usage requirements, and this disclosure does not impose specific limitations on them. In one possible implementation, for any given monitoring point, an external water intrusion analysis model is constructed based on the historical monitoring time series data, historical location influence factors, and historical external water intrusion records of that monitoring point. This includes: determining the prior distribution of the external water intrusion analysis model parameters for any given monitoring point; constructing the likelihood function of the external water intrusion analysis model parameters for that monitoring point based on the historical monitoring time series data, historical location influence factors, and historical external water intrusion records of that monitoring point; determining the posterior distribution of the external water intrusion analysis model parameters for that monitoring point based on the prior distribution and likelihood function of the external water intrusion analysis model parameters for that monitoring point; determining the external water intrusion analysis model parameters for that monitoring point based on the posterior distribution of the external water intrusion analysis model parameters for that monitoring point; and constructing the external water intrusion analysis model for that monitoring point based on the external water intrusion analysis model parameters.

[0081] In order to quantify the uncertainty of the external water intrusion analysis model parameters at any monitoring point, reduce the probability of overfitting the external water intrusion analysis model at that monitoring point to high-dimensional data, and ensure that the external water intrusion analysis model at that monitoring point can be dynamically updated using new target monitoring time series data obtained at that monitoring point, thereby improving the matching degree with the actual situation of that monitoring point, this embodiment of the disclosure constructs an external water intrusion analysis model for each monitoring point based on a coupled model of Bayesian inference and Logistic regression (Bayes-Logistic coupled model). The principle of the Bayes-Logistic coupled model can be expressed as formula (4):

[0082]

[0083] Where β represents the parameter vector; D represents the feature vector, i.e. the input data of the Bayes-Logistic coupled model; P(β) represents the prior distribution of the parameter vector of the Bayes-Logistic coupled model; P(D|β) represents the likelihood function of the Bayes-Logistic coupled model; P(β|D) represents the posterior distribution of the parameter vector of the Bayes-Logistic coupled model; and P(D) represents the marginal likelihood probability of the Bayes-Logistic coupled model, which is used to ensure that the posterior distribution of the Bayes-Logistic coupled model is valid (i.e., the integral of the posterior distribution is equal to 1).

[0084] Since there is no dependency between P(D) and the parameter vector β in Bayesian inference, formula (4) can be simplified to formula (5) of proportional relationship:

[0085]

[0086] The above simplification makes the computation more efficient. The parameter vector β can be regarded as the independent variable to be solved. Based on prior knowledge, it is assigned a corresponding prior distribution P(β). The posterior distribution P(β|D) is optimized by input data, and then the parameter vector β is determined.

[0087] Specifically, for any monitoring point, the prior distribution of the parameters of the external water intrusion analysis model for that monitoring point can be determined first. The specific method for determining the prior distribution can be flexibly set according to actual usage requirements, and this disclosure does not impose any specific limitations on it.

[0088] In one possible implementation, for any monitoring point, the prior distribution of the parameters of the external water intrusion analysis model for that monitoring point is determined, including: for any monitoring point, the prior distribution of the parameters of the external water intrusion analysis model for that monitoring point can be determined according to a preset prior relationship and a preset distribution function, wherein the preset prior relationship may include: the correlation between the monitoring point, at least one water quality indicator, and historical location influencing factors and the external water intrusion phenomenon.

[0089] The specific content of the preset prior relationships can be flexibly set according to actual usage needs, and this disclosure does not impose specific limitations on it.

[0090] In one example, the historical monitoring time series data for any monitoring point includes: historical liquid level time series data, COD monitoring value time series data, and conductivity monitoring value time series data. When external water intrusion occurs at any monitoring point, the COD and conductivity monitoring values ​​typically decrease due to the dilution of wastewater within the target drainage network, while the liquid level rises. Therefore, the pre-defined prior relationships can include: a negative correlation between COD monitoring values ​​and external water intrusion, a negative correlation between conductivity monitoring values ​​and external water intrusion, and a positive correlation between liquid level and external water intrusion.

[0091] In one example, monitoring points that are less than a preset distance threshold from an external water source are more likely to experience water intrusion due to the influence of the external water source. Therefore, the preset prior relationship may also include: the historical location influence factor of any monitoring point is positively correlated with the phenomenon of water intrusion.

[0092] The specific form of the preset prior distribution can be flexibly set according to actual usage requirements. For example, it can be set to a normal distribution, etc. This disclosure does not impose specific limitations on it. The parameters of the preset prior distribution can also be flexibly set according to actual usage requirements. This disclosure does not impose specific limitations on it.

[0093] In one example, the target drainage network includes a sewage well identified as JH-12, which is set as a monitoring point for the target drainage network. The target monitoring time series data for monitoring point JH-12 includes: target monitoring value time series data for COD, target monitoring value time series data for conductivity, and target liquid level time series data. The historical location influence factor corresponding to monitoring point JH-12 is set as a static label, and the historical location influence factor is equal to 1, indicating that the distance between monitoring point JH-12 and the river corresponding to the target drainage network is less than a preset distance threshold, and it is located within the external water intrusion influence zone.

[0094] Referring to Table 1, the pre-defined prior relationships for monitoring point JH-12 include: a negative correlation between COD monitoring values ​​and external water intrusion, a negative correlation between conductivity monitoring values ​​and external water intrusion, a positive correlation between liquid level and external water intrusion, and a positive correlation between historical location influence factors and external water intrusion. The pre-defined prior distribution for monitoring point JH-12 is a normal distribution, and the prior distribution of its external water intrusion analysis model parameters includes: β COD ~N(-2.5,1.0), β EC ~N(-2.0,1.0), β LEVEL ~N(1.5,1.0), and β NEAR ~N(1.0,0.5).

[0095] Table 1

[0096]

[0097] In one possible implementation, for any monitoring point, the prior distribution of the parameters of the external water intrusion analysis model for that monitoring point is determined, including: for any monitoring point, based on a preset prior distribution, statistical analysis of the historical monitoring time series data of that monitoring point is performed to determine the prior distribution of the parameters of the external water intrusion analysis model for that monitoring point.

[0098] The specific method for statistical analysis of historical monitoring time series data of any monitoring point can be flexibly set according to actual usage needs, and this disclosure does not impose specific limitations on it.

[0099] For any given monitoring point, statistical analysis of its historical monitoring time-series data can be performed to determine the parameters of a pre-defined prior distribution, thereby obtaining the prior distribution of the parameters for the external water intrusion analysis model at that monitoring point. Furthermore, if historical monitoring time-series data for that monitoring point is insufficient, weak prior information reflecting the correlation between the monitoring values, liquid levels, historical location influencing factors, and external water intrusion phenomena can be used to determine the parameters of the pre-defined prior distribution.

[0100] In one possible implementation, for any given monitoring point, the prior distribution of the external water intrusion analysis model parameters for that monitoring point is determined, including: for any given monitoring point, determining the theoretical background flow rate of that monitoring point based on the upstream catchment area, surface runoff coefficient, historical flow time series data, and historical rainfall time series data, wherein the theoretical background flow rate of any given monitoring point represents the theoretical flow rate of the target drainage network at that monitoring point in the absence of external water intrusion; determining the physical feasible region of the external water intrusion analysis model parameters for that monitoring point based on the theoretical background flow rate; and determining the prior distribution of the external water intrusion analysis model parameters for that monitoring point based on the physical feasible region of the external water intrusion analysis model parameters.

[0101] Specifically, the upstream catchment area of ​​any monitoring point can be represented as the total area upstream of that monitoring point, where all surface runoff, groundwater, and surrounding water flow can naturally converge under gravity. For specific methods of determining the upstream catchment area of ​​any monitoring point, refer to the implementation methods in related technologies; this disclosure does not impose specific limitations on them.

[0102] The surface runoff coefficient at any monitoring point can represent the ratio of the rainfall that actually forms surface runoff at that monitoring point to the total rainfall, reflecting the ability of rainfall to be converted into surface runoff. Specific methods for determining the surface runoff coefficient at any monitoring point can be found in related technical implementations, and this disclosure does not impose specific limitations on them.

[0103] Historical flow time series data at any monitoring point can reflect the change of flow in the pipeline at that monitoring point over time. Its specific form can be flexibly set according to actual usage needs, and this disclosure does not make specific limitations on it. The specific method for determining the historical flow time series data at any monitoring point can refer to the implementation methods in related technologies, such as monitoring using flow sensors, and this disclosure does not make specific limitations on it.

[0104] Historical rainfall time series data for any monitoring point can reflect the changes in rainfall over time within the geographical area corresponding to that monitoring point. It can be used to distinguish whether the monitoring point is in a rainfall period or a non-rainfall period, and to determine the start time, end time, and rainfall amount for each rainfall period corresponding to that monitoring point. Specific methods for determining the historical rainfall time series data for any monitoring point can refer to implementation methods in related technologies, such as obtaining data from official meteorological data websites; this disclosure does not specifically limit this method.

[0105] For any given monitoring point, a dry-day flow baseline can be determined based on its historical flow time series data and historical rainfall time series data. The specific method for determining the dry-day flow baseline can be flexibly set according to actual usage requirements, and this disclosure does not impose specific limitations on it.

[0106] In one example, for any given monitoring point, a continuous rainless period of a preset duration can be determined based on the historical rainfall time series data of that monitoring point. Then, based on the historical flow time series data of that monitoring point, statistical analysis is performed on the pipeline flow at that monitoring point during the continuous rainless period, and a dry-day flow baseline for that monitoring point is plotted. The specific value of the preset duration can be flexibly set according to actual usage requirements; for example, it can be set to 24 hours, etc., and this disclosure does not impose a specific limitation on it.

[0107] For any given monitoring point, the theoretical runoff increment during rainy days can be determined based on the upstream catchment area, surface runoff coefficient, and historical rainfall time series data. This allows for the quantification of the contribution of rainfall-generated runoff to the pipeline flow at the monitoring point and the differentiation between the impact of rainfall and external water intrusion on the monitoring point.

[0108] For any given monitoring point, assuming no external water intrusion occurs at that point, since the runoff generated by rainfall and the existing sewage in the target drainage network are independent of each other, the theoretical background flow of that monitoring point can be determined by summing the dry-day flow baseline and the theoretical runoff increment during rainy days. This indicates the theoretical flow of the target drainage network at that monitoring point in the absence of external water intrusion.

[0109] Typically, the parameters of an external water intrusion analysis model for any monitoring point include: monitoring index coefficients and location influence factor coefficients. The monitoring index coefficients include the liquid level influence coefficient of the monitoring point and the different water quality influence coefficients corresponding to various water quality indicators, which can characterize the contribution coefficient of external water intrusion to the liquid level and various water quality indicators of the monitoring point. The location influence factor coefficients can reflect the basic risk of external water intrusion at the monitoring point.

[0110] The monitoring index coefficients are constrained by physical laws such as the water balance law and the water quality mixing law. The water balance law can be expressed as formula (6):

[0111]

[0112] Among them, Q obs (t) represents the historical flow at any monitoring point at monitoring time t; Q local (t) represents the theoretical background flow rate at the monitoring point at monitoring time t; Q in (t) represents the external water intrusion flow rate at the monitoring point at monitoring time t.

[0113] For any given monitoring point, the historical monitoring time series data of that monitoring point are traversed based on formula (6) to determine the maximum external water intrusion flow, and then the maximum proportion of external water intrusion at that monitoring point is calculated, which can be specifically expressed as formula (7):

[0114]

[0115] Among them, I max Q represents the maximum percentage of external water intrusion at any given monitoring point; in (t1) max Q represents the maximum external water intrusion flow rate at this monitoring point; obs (t1) represents the historical flow rate at the monitoring point at monitoring time t1. Based on the water mixing law, the level influence coefficient of any monitoring point and the different water quality influence coefficients corresponding to various water quality indicators can be limited to non-negative numbers, and the sum is less than or equal to the maximum proportion of external water intrusion at the monitoring point, which can be expressed as formula (8):

[0116]

[0117] Where, β 液 β represents the level influence coefficient at any monitoring point; i Let represent the water quality influence coefficient of the i-th water quality indicator, where 1 ≤ i ≤ n, and n is a positive integer.

[0118] Furthermore, the historical location influence factor of any monitoring point should be a normalized non-negative number, which can be expressed as formula (9):

[0119]

[0120] Where, β p This represents the location influence factor coefficient of any monitoring point.

[0121] Therefore, for any monitoring point, formulas (8) and (9) can be used to determine the physical feasible region of the external water intrusion analysis model parameters of the monitoring point based on the historical flow time series data, theoretical background flow, and historical external water intrusion record data of the monitoring point. The physical feasible region gives the external water intrusion analysis model parameters of the monitoring point a real physical meaning and applies physical constraints to the external water intrusion analysis model parameters of the monitoring point, so that the external water intrusion analysis model parameters of the monitoring point change from black box coefficients lacking interpretability to physical variables with interpretability. This solves the problem that the pure data-driven model may violate the actual physical laws, and makes the subsequent external water intrusion analysis model still reasonable when the historical monitoring time series data is sparse or extrapolated.

[0122] For any given monitoring point, a pre-defined sampling distribution is used to sample the physical feasible region of the external water intrusion analysis model parameters for that monitoring point. This determines the prior distribution of the external water intrusion analysis model parameters for that monitoring point, ensuring that the function value space of the prior distribution is confined within the physical feasible region. This makes the prior distribution no longer a purely subjective assumption, but an objective constraint determined by the physical properties and historical data of the monitoring point. Consequently, when estimating the posterior distribution, it is ensured that the external water intrusion analysis model parameters for that monitoring point can both fit the historical monitoring time series data and conform to the basic hydrodynamic laws of the target drainage network.

[0123] For any given monitoring point, the likelihood function of the external water intrusion analysis model parameters can be constructed based on the historical monitoring time series data, historical location influence factors, and historical external water intrusion records of that monitoring point. Specifically, the likelihood function of any monitoring point can be expressed as formula (10):

[0124]

[0125] Where, D=(X i ,Y i ) i N ;X i Y represents the historical monitoring time series data of the i-th monitoring point; i represents the historical external water intrusion record data of the i-th monitoring point; N represents the total number of monitoring points in the target drainage network.

[0126] Based on the above formula (5), for any monitoring point, the posterior distribution of the parameters of the external water intrusion analysis model at the monitoring point can be solved according to the prior distribution and likelihood function of the parameters of the external water intrusion analysis model at the monitoring point. However, since the likelihood function is a non-Gaussian function and the Bayes-Logistic coupling model has non-conjugate properties, the posterior distribution cannot be solved directly. Therefore, a numerical approximation method can be used to determine the posterior distribution of the parameters of the external water intrusion analysis model at the monitoring point. Then, based on the posterior distribution of the parameters of the external water intrusion analysis model at the monitoring point, the parameters of the external water intrusion analysis model at the monitoring point can be determined, and the external water intrusion analysis model at the monitoring point can be constructed.

[0127] The specific form of the numerical approximation method can be flexibly set according to actual usage requirements. For example, the Markov Chain Monte Carlo (MCMC) method or the Variational Inference (VI) method can be used. This disclosure does not specifically limit this.

[0128] In one possible implementation, the method further includes: for any monitoring point, if the external water intrusion analysis result of the monitoring point meets a third preset condition, determining the alarm information of the monitoring point, wherein the alarm information of the monitoring point is used to instruct the investigation of external water intrusion at the monitoring point.

[0129] The specific content of the third preset condition can be flexibly set according to actual usage needs, and this disclosure does not impose specific limitations on it.

[0130] In one example, the third preset condition may include: the value of the external water intrusion analysis result at any monitoring point is greater than or equal to a preset probability threshold. For any monitoring point, if the external water intrusion analysis result at that monitoring point is greater than or equal to the preset probability threshold, it can be considered that the risk of external water intrusion at that monitoring point is high, and an alarm message for that monitoring point is determined to instruct an investigation into external water intrusion at that monitoring point.

[0131] The specific content of the alarm information for any monitoring point may include, for example, the identifier and location of the monitoring point, as well as the analysis results of external water intrusion, etc., which can be flexibly set according to actual usage needs. This disclosure does not impose specific limitations on this.

[0132] Taking the aforementioned target drainage network, including monitoring point JH-12, as an example, the preset probability threshold for monitoring point JH-12 is 0.9.

[0133] After continuous heavy rainfall occurred in the area where the target drainage network is located, causing the river level to rise, at monitoring time T1, based on the target monitoring time series data of monitoring point JH-12, the input data required for the external water intrusion analysis model of monitoring point JH-12 are determined as follows: COD change =-40%, EC change =-35%, LEVEL ratio =2.1, and NEAR river =1. After receiving the input data, the external water intrusion analysis model at monitoring point JH-12 can perform predictive analysis of external water intrusion phenomena, and the analysis result of external water intrusion at monitoring point JH-12 is P(Y=1|X)=0.98.

[0134] Therefore, the analysis result of external water intrusion at monitoring point JH-12 is greater than the preset probability threshold, which meets the third preset condition. Thus, it can be considered that the risk of external water intrusion at monitoring point JH-12 is high, and an alarm message for monitoring point JH-12 is generated to instruct the operation and maintenance personnel to investigate the external water intrusion at monitoring point JH-12.

[0135] In one possible implementation, the method further includes: if the investigation results of external water intrusion at the monitoring point meet the fourth preset condition, optimizing and updating the external water intrusion analysis model of the monitoring point based on the target monitoring time series data, target location influence factors, and external water intrusion investigation results of the monitoring point.

[0136] The specific content of the fourth preset condition can be flexibly set according to actual usage needs, and this disclosure does not impose specific limitations on it.

[0137] In one example, the fourth preset condition may include: the investigation result of external water intrusion at any monitoring point is a confirmed external water intrusion (True Positive). If the investigation result of external water intrusion at that monitoring point is a confirmed external water intrusion, it can be confirmed that the investigation result of external water intrusion at that monitoring point meets the fourth preset condition. Based on the target monitoring time series data, target location influencing factors, and the investigation result of external water intrusion at that monitoring point, the external water intrusion analysis model for that monitoring point is then optimized and updated.

[0138] In one possible implementation, if the investigation results of external water intrusion at the monitoring point meet the fourth preset condition, the external water intrusion analysis model for the monitoring point is optimized and updated based on the target monitoring time series data, target location influencing factors, and external water intrusion investigation results. This includes: determining the posterior distribution of the external water intrusion analysis model parameters for the monitoring point as the new prior distribution of the external water intrusion analysis model parameters for the monitoring point; constructing a new likelihood function for the external water intrusion analysis model parameters for the monitoring point based on the target monitoring time series data, target location influencing factors, and external water intrusion investigation results for the monitoring point; determining the new posterior distribution of the external water intrusion analysis model parameters for the monitoring point based on the new likelihood function and the new prior distribution; determining the new external water intrusion analysis model parameters for the monitoring point based on the new posterior distribution of the external water intrusion analysis model parameters for the monitoring point; and optimizing and updating the external water intrusion analysis model for the monitoring point based on the new external water intrusion analysis model parameters.

[0139] Specifically, for any given monitoring point, if the investigation results of external water intrusion at that monitoring point meet the fourth preset condition, the posterior distribution of the external water intrusion analysis model parameters at that monitoring point can be used as known prior knowledge and determined as the new prior distribution of the external water intrusion analysis model parameters at that monitoring point. Simultaneously, the target monitoring time series data, target location influencing factors, and external water intrusion investigation results at that monitoring point can be used as new training samples to construct a new likelihood function for the external water intrusion analysis model parameters at that monitoring point. Then, based on the new likelihood function and the new prior distribution of the external water intrusion analysis model parameters at that monitoring point, the new posterior distribution of the external water intrusion analysis model parameters at that monitoring point is determined, enabling the external water intrusion analysis model at that monitoring point to learn the new knowledge brought about by the latest external water intrusion phenomena.

[0140] If the investigation results of external water intrusion at any monitoring point meet the fourth preset condition, the new external water intrusion analysis model parameters for that monitoring point are determined based on the new posterior distribution of the external water intrusion analysis model parameters. Based on the new external water intrusion analysis model parameters for that monitoring point, the external water intrusion analysis model for that monitoring point is optimized and updated, realizing the dynamic self-updating of the external water intrusion analysis model for that monitoring point. This further improves the accuracy and reliability of the external water intrusion analysis model for that monitoring point and makes the external water intrusion analysis model for that monitoring point more sensitive to external water intrusion phenomena that occurred before the update.

[0141] In this embodiment of the disclosure, after determining the target monitoring time series data of any monitoring point in the target drainage network, including the target liquid level time series data of the monitoring point and the target monitoring value time series data of at least one water quality indicator, for any monitoring point, an external water intrusion analysis model for the monitoring point can be constructed based on the historical monitoring time series data of the monitoring point, the historical monitoring time series data of at least one water quality indicator, the historical location influence factor that can indicate the historical location relationship of the monitoring point relative to the external water source corresponding to the target drainage network, and the historical external water intrusion record data. Compared with the existing external water intrusion analysis method that only uses the monitoring data of water quality indicators and liquid levels for analysis, by introducing the historical location influence factor, the external water intrusion analysis model can effectively utilize the geographical location information of the monitoring point, fully characterize the external hydrological environment of the monitoring point, and thus improve the sensitivity to high-risk monitoring points. For any given monitoring point, the external water intrusion analysis results can be determined by comprehensively utilizing the target monitoring time series data, target location influencing factors, and external water intrusion analysis model of that monitoring point in both time and spatial dimensions. This indicates the probability of external water intrusion occurring in the target drainage network at that monitoring point, thereby improving the accuracy and reliability of the external water intrusion analysis results.

[0142] It is understood that the various method embodiments mentioned above in this disclosure can be combined with each other to form combined embodiments without violating the principle and logic. Due to space limitations, this disclosure will not elaborate further. Those skilled in the art will understand that in the above methods of specific implementation, the specific execution order of each step should be determined by its function and possible internal logic.

[0143] In addition, this disclosure also provides a monitoring system, electronic equipment and computer-readable storage medium for drainage pipe networks. All of the above can be used to implement any of the monitoring methods for drainage pipe networks provided in this disclosure. The corresponding technical solutions and descriptions can be found in the relevant records in the method section, and will not be repeated here.

[0144] Figure 2 A block diagram of a monitoring system for a drainage network according to an embodiment of the present disclosure is shown. Figure 2 As shown, system 200 includes:

[0145] The data preprocessing module 201 is used to determine the target monitoring time series data of any monitoring point in the target drainage network, wherein the target monitoring time series data of any monitoring point includes the target liquid level time series data of the monitoring point and the target monitoring value time series data of at least one water quality indicator.

[0146] The model building module 202 is used to construct an external water intrusion analysis model for any monitoring point based on the historical monitoring time series data, historical location influencing factors, and historical external water intrusion record data of that monitoring point. The historical monitoring time series data of any monitoring point includes the historical liquid level time series data of that monitoring point and the historical monitoring value time series data of at least one water quality indicator. The historical location influencing factor of any monitoring point is used to indicate the historical location relationship of the monitoring point relative to the external water source corresponding to the target drainage network.

[0147] The external water intrusion analysis module 203 is used to determine the external water intrusion analysis result for any monitoring point based on the target monitoring time series data, the target location influence factor, and the external water intrusion analysis model of the monitoring point. The target location influence factor of any monitoring point is used to indicate the real-time positional relationship of the monitoring point relative to the external water source corresponding to the target drainage network. The external water intrusion analysis result of any monitoring point includes the probability that the target drainage network will experience external water intrusion at the monitoring point.

[0148] In one possible implementation, system 200 further includes a location influence factor determination module, used to: for any monitoring point, determine the real-time hydraulic gradient of the monitoring point based on the pipe bottom elevation of the monitoring point, the target pipeline path distance of the monitoring point relative to the external water source, and the water level time series data of the external water source, wherein the real-time hydraulic gradient of any monitoring point is used to represent the real-time head difference per unit pipeline path length at the monitoring point; if the real-time hydraulic gradient of the monitoring point meets a first preset condition, determine the target location influence factor of the monitoring point based on a first preset value or the real-time hydraulic gradient of the monitoring point; if the real-time hydraulic gradient of the monitoring point meets a second preset condition, determine the target location influence factor of the monitoring point based on a second preset value.

[0149] In one possible implementation, the model building module 202 is used to: determine the prior distribution of the external water intrusion analysis model parameters for any given monitoring point; construct the likelihood function of the external water intrusion analysis model parameters for the monitoring point based on the historical monitoring time series data, historical location influence factors, and historical external water intrusion records of the monitoring point; determine the posterior distribution of the external water intrusion analysis model parameters for the monitoring point based on the prior distribution and likelihood function of the external water intrusion analysis model parameters for the monitoring point; determine the external water intrusion analysis model parameters for the monitoring point based on the posterior distribution of the external water intrusion analysis model parameters for the monitoring point; and construct the external water intrusion analysis model for the monitoring point based on the external water intrusion analysis model parameters for the monitoring point.

[0150] In one possible implementation, the model building module 202 is further configured to: for any given monitoring point, determine the theoretical background flow of the monitoring point based on its upstream catchment area, surface runoff coefficient, historical flow time series data, and historical rainfall time series data, wherein the theoretical background flow of any given monitoring point represents the theoretical flow of the target drainage network at that monitoring point in the absence of external water intrusion; determine the physical feasible region of the external water intrusion analysis model parameters for the monitoring point based on the theoretical background flow of the monitoring point; and determine the prior distribution of the external water intrusion analysis model parameters for the monitoring point based on the physical feasible region of the external water intrusion analysis model parameters for the monitoring point.

[0151] In one possible implementation, the system 200 further includes an alarm module, which is used to: determine an alarm message for any monitoring point when the external water intrusion analysis result of the monitoring point meets a third preset condition, wherein the alarm message of the monitoring point is used to instruct an investigation of the external water intrusion phenomenon at the monitoring point.

[0152] In one possible implementation, the system 200 also includes a model optimization module, which is used to: optimize and update the external water intrusion analysis model of the monitoring point based on the target monitoring time series data, target location influence factors and external water intrusion investigation results, when the external water intrusion phenomenon investigation results of the monitoring point meet the fourth preset condition.

[0153] In one possible implementation, the model optimization module is further configured to: determine the posterior distribution of the external water intrusion analysis model parameters for the monitoring point as the new prior distribution of the external water intrusion analysis model parameters for the monitoring point; construct a new likelihood function for the external water intrusion analysis model parameters for the monitoring point based on the target monitoring time series data, target location influencing factors, and external water intrusion phenomenon investigation results for the monitoring point; determine the new posterior distribution of the external water intrusion analysis model parameters for the monitoring point based on the new likelihood function and the new prior distribution; determine the new external water intrusion analysis model parameters for the monitoring point based on the new posterior distribution of the external water intrusion analysis model parameters for the monitoring point; and optimize and update the external water intrusion analysis model for the monitoring point based on the new external water intrusion analysis model parameters.

[0154] In some embodiments, the functions or modules of the apparatus provided in this disclosure can be used to perform the methods described in the above method embodiments. The specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0155] This disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above method.

[0156] This disclosure also provides a non-volatile computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the above-described method.

[0157] Figure 3 A block diagram of an electronic device according to an embodiment of the present disclosure is shown. For example, electronic device 1900 may be provided as a server or terminal device. (Refer to...) Figure 3 The electronic device 1900 includes a processing component 1922, which further includes one or more processors, and memory resources represented by memory 1932 for storing instructions executable by the processing component 1922, such as application programs. The application programs stored in memory 1932 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 1922 is configured to execute instructions to perform the methods described above.

[0158] Electronic device 1900 may also include a power supply component 1926 configured to perform power management of electronic device 1900, a wired or wireless network interface 1950 configured to connect electronic device 1900 to a network, and an input / output interface 1958 (I / O interface). Electronic device 1900 can operate on an operating system, such as Windows Server, stored in memory 1932. TM Mac OS X TM Unix TM Linux TM FreeBSD TM Or similar.

[0159] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions that can be executed by a processing component 1922 of an electronic device 1900 to perform the above-described method.

[0160] Computer-readable storage media can be tangible devices capable of holding and storing programs / instructions used by instruction execution devices. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0161] The computer program (or computer-readable program instructions) described herein can be downloaded from a computer-readable storage medium to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage medium in the respective computing / processing device.

[0162] The computer program (or computer program instructions) used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions to implement various aspects of this disclosure.

[0163] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0164] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0165] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0166] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0167] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for monitoring a drainage pipe network, characterized in that, include: Determine the target monitoring time series data for any monitoring point in the target drainage network, wherein the target monitoring time series data for any monitoring point includes the target liquid level time series data for that monitoring point, and the target monitoring value time series data for at least one water quality indicator. For any given monitoring point, an external water intrusion analysis model is constructed based on the historical monitoring time series data, historical location influence factors, and historical external water intrusion records of that monitoring point. The historical monitoring time series data of any given monitoring point includes the historical liquid level time series data of that monitoring point and the historical monitoring value time series data of the at least one water quality indicator. The historical location influence factor of any given monitoring point is used to indicate the historical location relationship of that monitoring point relative to the external water source corresponding to the target drainage network. For any given monitoring point, based on the target monitoring time series data, the target location influence factor, and the external water intrusion analysis model for that monitoring point, the external water intrusion analysis result for that monitoring point is determined. The target location influence factor for any given monitoring point is used to indicate the real-time positional relationship of that monitoring point relative to the external water source corresponding to the target drainage network. The external water intrusion analysis result for any given monitoring point includes the probability that the target drainage network will experience external water intrusion at that monitoring point.

2. The method according to claim 1, characterized in that, The method further includes: For any given monitoring point, the real-time hydraulic gradient of the monitoring point is determined based on the pipe bottom elevation of the monitoring point, the distance of the monitoring point from the target pipeline path of the external water source, and the water level time series data of the external water source. The real-time hydraulic gradient of any monitoring point is used to represent the real-time head difference per unit pipeline path length at the monitoring point. If the real-time hydraulic gradient at the monitoring point meets the first preset condition, the target location influence factor of the monitoring point is determined according to the first preset value or the real-time hydraulic gradient at the monitoring point. If the real-time hydraulic gradient at the monitoring point meets the second preset condition, the target location influence factor of the monitoring point is determined according to the second preset value.

3. The method according to claim 1 or 2, characterized in that, For any given monitoring point, an external water intrusion analysis model is constructed based on the historical monitoring time series data, historical location influencing factors, and historical external water intrusion records of that monitoring point, including: For any given monitoring point, determine the prior distribution of the parameters of the external water intrusion analysis model for that monitoring point; Based on the historical monitoring time series data, historical location influencing factors, and historical external water intrusion records of this monitoring point, the likelihood function of the external water intrusion analysis model parameters for this monitoring point is constructed. Based on the prior distribution and likelihood function of the external water intrusion analysis model parameters at the monitoring point, determine the posterior distribution of the external water intrusion analysis model parameters at the monitoring point. Based on the posterior distribution of the external water intrusion analysis model parameters at the monitoring point, the external water intrusion analysis model parameters at the monitoring point are determined. Based on the parameters of the external water intrusion analysis model for this monitoring point, an external water intrusion analysis model for this monitoring point is constructed.

4. The method according to claim 3, characterized in that, The determination of the prior distribution of external water intrusion analysis model parameters for any given monitoring point includes: For any given monitoring point, the theoretical background flow rate of that monitoring point is determined based on the upstream catchment area, surface runoff coefficient, historical flow time series data, and historical rainfall time series data. The theoretical background flow rate of any given monitoring point represents the theoretical flow rate of the target drainage network at that monitoring point in the absence of external water intrusion. Based on the theoretical background flow rate at the monitoring point, the physical feasible region of the external water intrusion analysis model parameters at the monitoring point is determined. Based on the physical feasible region of the external water intrusion analysis model parameters at the monitoring point, the prior distribution of the external water intrusion analysis model parameters at the monitoring point is determined.

5. The method according to claim 1 or 2, characterized in that, The method further includes: For any given monitoring point, if the analysis results of external water intrusion at that monitoring point meet the third preset condition, an alarm message for that monitoring point is determined. The alarm message for that monitoring point is used to instruct an investigation into the phenomenon of external water intrusion at that monitoring point.

6. The method according to claim 5, characterized in that, The method further includes: If the results of the investigation of external water intrusion at the monitoring point meet the fourth preset condition, the external water intrusion analysis model for the monitoring point will be optimized and updated based on the target monitoring time series data, target location influencing factors, and external water intrusion investigation results.

7. The method according to claim 6, characterized in that, When the investigation results of external water intrusion at the monitoring point meet the fourth preset condition, the external water intrusion analysis model for the monitoring point is optimized and updated based on the target monitoring time series data, target location influencing factors, and external water intrusion investigation results, including: The posterior distribution of the external water intrusion analysis model parameters at this monitoring point is determined as the new prior distribution of the external water intrusion analysis model parameters at this monitoring point. Based on the target monitoring time series data, target location influencing factors, and external water intrusion investigation results of the monitoring point, a new likelihood function for the external water intrusion analysis model parameters of the monitoring point is constructed. Based on the new likelihood function and new prior distribution of the external water intrusion analysis model parameters at the monitoring point, determine the new posterior distribution of the external water intrusion analysis model parameters at the monitoring point. Based on the new posterior distribution of the external water intrusion analysis model parameters at this monitoring point, determine the new external water intrusion analysis model parameters for this monitoring point. Based on the parameters of the new external water intrusion analysis model for this monitoring point, the external water intrusion analysis model for this monitoring point is optimized and updated.

8. A monitoring system for a drainage pipe network, characterized in that, include: The data preprocessing module is used to determine the target monitoring time series data of any monitoring point in the target drainage network. The target monitoring time series data of any monitoring point includes the target liquid level time series data of the monitoring point and the target monitoring value time series data of at least one water quality indicator. The model building module is used to construct an external water intrusion analysis model for any monitoring point based on the historical monitoring time series data, historical location influence factors, and historical external water intrusion record data of that monitoring point. The historical monitoring time series data of any monitoring point includes the historical liquid level time series data of that monitoring point and the historical monitoring value time series data of the at least one water quality indicator. The historical location influence factor of any monitoring point is used to indicate the historical location relationship of the monitoring point relative to the external water source corresponding to the target drainage network. The external water intrusion analysis module is used to determine the external water intrusion analysis result for any monitoring point based on the target monitoring time series data, target location influence factor, and external water intrusion analysis model of that monitoring point. The target location influence factor of any monitoring point indicates the real-time positional relationship of the monitoring point relative to the external water source corresponding to the target drainage network. The external water intrusion analysis result of any monitoring point includes the probability that the target drainage network will experience external water intrusion at that monitoring point.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

10. A non-volatile computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images