Drainage pipe network anomaly detection method and electronic device

Abstract

This disclosure relates to a method and electronic device for detecting anomalies in drainage pipe networks. The method includes: determining candidate anomaly detection points based on the type of the drainage pipe network, the rainfall conditions in the area where the drainage pipe network is located, and time series data of at least one water quality indicator or flow rate corresponding to multiple monitoring points in the drainage pipe network; obtaining the target analysis indicators of quantum dot materials deployed at each deployment point, and obtaining time series data of the target analysis indicators of each quantum dot material corresponding to each candidate anomaly detection point in at least a portion of the candidate anomaly detection points; determining the location and degree of anomalies in the drainage pipe network based on the type of at least one deployment point corresponding to each candidate anomaly detection point and the time series data of the target analysis indicators of at least one quantum dot material corresponding to each candidate anomaly detection point. This method can achieve synchronous detection of all points in the entire area of ​​the drainage pipe network, improving both efficiency and accuracy.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and in particular to a method and electronic equipment for detecting anomalies in drainage pipe networks. Background Technology

[0002] For the detection and investigation of abnormalities in drainage pipe networks, it is difficult to directly determine whether there are any abnormalities in a certain area due to the intricate network.

[0003] Furthermore, when the area to be inspected is large and the pipe connections are complex, there are many potential points of cross-connection to be inspected, resulting in long inspection times and low efficiency. In addition, the continuous flow of water makes it difficult to accurately locate abnormal locations in the drainage network. Summary of the Invention

[0004] In view of this, this disclosure proposes a scheme for detecting anomalies in drainage pipe networks.

[0005] According to one aspect of this disclosure, a method for detecting anomalies in a drainage pipe network is provided, comprising: determining at least one candidate anomaly detection point based on the type of the drainage pipe network, the rainfall conditions in the area where the drainage pipe network is located, and time series data of at least one water quality indicator or flow rate corresponding to multiple monitoring points in the drainage pipe network; determining multiple delivery points located within a preset range upstream of each candidate anomaly detection point, and delivery of different types of quantum dot materials to each delivery point corresponding to each candidate anomaly detection point, wherein the spectral information of the different types of quantum dot materials delivered to each delivery point is different; using a spectral detection device deployed at at least some of the candidate anomaly detection points, acquiring the target analysis index of the quantum dot materials delivered to each delivery point, and obtaining time series data of the target analysis index of each quantum dot material corresponding to each candidate anomaly detection point in the at least some candidate anomaly detection points; wherein the target analysis index includes at least one of concentration, mass, and spectral information; determining the anomaly location and degree of anomaly in the drainage pipe network based on the type of at least one delivery point corresponding to each candidate anomaly detection point in the at least some candidate anomaly detection points and the time series data of the target analysis index of at least one quantum dot material corresponding to each candidate anomaly detection point.

[0006] In one possible implementation, the use of spectral detection equipment deployed at at least some of the candidate anomaly detection points includes: when multiple candidate anomaly detection points have an upstream-downstream adjacent position relationship, utilizing the spectral detection equipment deployed at the most upstream candidate anomaly detection point among the multiple candidate anomaly detection points; wherein the upstream-downstream adjacent position relationship means that, based on the water flow direction within the drainage network, any candidate anomaly detection point is located upstream or downstream of another candidate anomaly detection point in the water flow, and the two candidate anomaly detection points are directly adjacent to each other, with no other candidate anomaly detection points between them.

[0007] In one possible implementation, the at least some candidate anomaly detection points include: a first candidate anomaly detection point. The step of determining the anomaly location of the drainage network based on the type of at least one delivery point corresponding to each of the at least some candidate anomaly detection points and the time series data of the target analysis index of at least one quantum dot material corresponding to each of the at least some candidate anomaly detection points includes: when the time series data of the target analysis index of at least one quantum dot material corresponding to the first candidate anomaly detection point meets a first preset condition, and the type of the delivery point corresponding to the at least one quantum dot material is different from the type of the first candidate anomaly detection point, it is determined that a first pipe section between the first candidate anomaly detection point and an upstream adjacent monitoring point of the first candidate anomaly detection point has a rainwater and sewage mixing problem, and the anomaly location includes: the first pipe section.

[0008] In one possible implementation, the time series data of the target analysis indicators of multiple quantum dot materials corresponding to the first candidate anomaly detection point all meet a first preset condition, wherein the target analysis indicator is concentration. The method further includes: determining the concentration of the multiple quantum dot materials at the first candidate anomaly detection point based on the spectral detection device, and obtaining multiple first quantum dot concentration time series data corresponding to the first candidate anomaly detection point; obtaining a first detection quality corresponding to each of the multiple quantum dot materials at the first candidate anomaly detection point based on the flow rate, pipe diameter, multiple first quantum dot concentration time series data, and the detection frequency of the spectral detection device at the first candidate anomaly detection point; and determining the main source of rainwater and sewage mixing from each delivery point corresponding to the multiple quantum dot materials based on each first detection quality.

[0009] In one possible implementation, the degree of anomaly includes the degree of cross-connection. Determining the degree of anomaly in the drainage network includes: determining the quantum dot detection ratio corresponding to each first candidate anomaly detection point based on each first detection quality; determining the absolute pollution load corresponding to each first candidate anomaly detection point based on each first detection quality and each first quantum dot concentration time series data, wherein the absolute pollution load characterizes the pollution intensity of cross-connection to the first candidate anomaly detection point; obtaining the environmental sensitivity coefficient corresponding to each first candidate anomaly detection point; determining the cross-connection severity index corresponding to each first candidate anomaly detection point based on the quantum dot detection ratio, the absolute pollution load, and the environmental sensitivity coefficient; and determining the degree of cross-connection in each first pipe segment based on the cross-connection severity index.

[0010] In one possible implementation, determining the main source of rainwater and sewage mixing from each of the delivery points corresponding to the multiple quantum dot materials based on each of the first detection masses includes: determining the mass ratio of each quantum dot material among the multiple quantum dot materials based on the first input mass and the first detection mass detected by the first candidate anomaly detection point; and determining the main source of mixing according to each of the mass ratios.

[0011] In one possible implementation, the at least some candidate anomaly detection points include: a second candidate anomaly detection point. The step of determining the anomaly location and degree of anomaly in the drainage network based on the type of at least one delivery point corresponding to each of the at least some candidate anomaly detection points and the time series data of the target analysis indicators of at least one quantum dot material corresponding to each of the at least some candidate anomaly detection points includes: if the time series data of the target analysis indicators of at least one quantum dot material corresponding to the second candidate anomaly detection point meets a second preset condition, and the type of the delivery point corresponding to the at least one quantum dot material is the same as the type of the second candidate anomaly detection point, then determining that a second pipe segment between the delivery point corresponding to the at least one quantum dot material and the second candidate anomaly detection point has experienced an anomaly. The pipeline is damaged, and the abnormal location includes the second pipe segment; the degree of abnormality includes the degree of damage; based on the spectral detection device, the concentration of multiple quantum dot materials at the second candidate abnormal detection point is determined, and time series data of multiple second quantum dot concentrations corresponding to the second candidate abnormal detection point are obtained; based on the flow rate, pipe diameter, multiple second quantum dot concentration time series data and the detection frequency of the spectral detection device at the second candidate abnormal detection point, the second detection mass corresponding to each of the multiple quantum dot materials at the second candidate abnormal detection point is obtained; based on the second input mass and the second detection mass corresponding to each of the multiple quantum dot materials detected at each second candidate abnormal detection point, the degree of damage of each second pipe segment is determined.

[0012] In one possible implementation, the at least some candidate anomaly detection points include: a third candidate anomaly detection point. Determining the anomaly location of the drainage network based on the type of at least one delivery point corresponding to each of the at least some candidate anomaly detection points and the time series data of the target analysis index of at least one quantum dot material corresponding to each of the at least some candidate anomaly detection points includes: when the time series data of the target analysis index of at least one quantum dot material corresponding to the third candidate anomaly detection point satisfies a third preset condition, and the type of the delivery point corresponding to the at least one quantum dot material is the same as the type of the third candidate anomaly detection point, obtaining the first data of the target analysis index at the delivery point corresponding to the at least one quantum dot material; when the first data of the target analysis index at the delivery point corresponding to the at least one quantum dot material and the time series data of the target analysis index of the at least one quantum dot material corresponding to the third candidate anomaly detection point satisfy a fourth preset condition, determining that a third pipe segment between the third candidate anomaly detection point and the delivery point corresponding to the at least one quantum dot material has experienced pipe damage and / or rainwater and sewage mixing, the anomaly location including: the third pipe segment.

[0013] In one possible implementation, determining at least one candidate anomaly detection point based on the drainage network type, rainfall conditions in the area where the drainage network is located, and time series data of at least one water quality indicator or flow rate corresponding to multiple monitoring points in the drainage network includes: when the network type is a stormwater network and the rainfall in the area where the stormwater network is located does not meet a preset rainfall threshold, for any given monitoring point, determining the median of a first target water quality indicator corresponding to that monitoring point based on the time series data of the first target water quality indicator corresponding to that monitoring point; when the median of the first target water quality indicator meets a fifth preset condition, determining that monitoring point as a candidate anomaly detection point; when the network type is a sewage network and the rainfall in the area where the sewage network is located meets a preset rainfall threshold, for any given monitoring point, determining the trend analysis result of each water quality indicator time series data in the at least two correlated water quality indicator time series data corresponding to that monitoring point based on the time series data of at least two correlated water quality indicators corresponding to that monitoring point; when the trend analysis result of the at least two correlated water quality indicator time series data corresponding to that monitoring point meets a sixth condition... Under preset conditions, the monitoring point is determined as a candidate anomaly detection point. If the pipe network type is a sewage pipe network and the rainfall in the area where the sewage pipe network is located within a preset time period does not meet a preset rainfall threshold, for any given monitoring point, the first target flow time series data corresponding to that monitoring point and the second target flow time series data corresponding to the upstream adjacent monitoring point are determined. If the first target flow time series data and the second target flow time series data meet a seventh preset condition, the monitoring point is determined as a candidate anomaly detection point. If the pipe network type is a stormwater pipe network and the rainfall in the area where the stormwater pipe network is located within a preset time period meets a preset rainfall threshold, for any given monitoring point, the third target flow time series data and the second target water quality index time series data corresponding to that monitoring point, as well as the fourth target flow time series data and the third target water quality index time series data corresponding to the upstream adjacent monitoring point are determined. If the third target flow time series data, the second target water quality index time series data, the fourth target flow time series data, and the third target water quality index time series data meet an eighth preset condition, the monitoring point is determined as a candidate anomaly detection point.

[0014] According to another aspect of this disclosure, a drainage pipe network anomaly detection device is provided, the device comprising:

[0015] The candidate anomaly detection point determination unit is used to determine at least one candidate anomaly detection point based on the type of the drainage pipe network, the rainfall in the area where the drainage pipe network is located, and time series data of at least one water quality indicator or flow rate corresponding to multiple monitoring points in the drainage pipe network.

[0016] A quantum dot delivery unit is used to determine multiple delivery points located within a preset range upstream of each candidate anomaly detection point, and to deliver different types of quantum dot materials to each delivery point corresponding to each candidate anomaly detection point, wherein the spectral information of the different types of quantum dot materials delivered to each delivery point is different;

[0017] The target analysis index time series data determination unit is used to acquire the target analysis index of the quantum dot material deployed at each of the deployment points using spectral detection equipment deployed at at least some of the candidate anomaly detection points, and obtain the target analysis index time series data of each quantum dot material corresponding to each of the at least some candidate anomaly detection points; wherein, the target analysis index includes at least one of concentration, mass and spectral information;

[0018] An anomaly location and anomaly degree determination unit is used to determine the anomaly location and anomaly degree of the drainage network based on the type of at least one delivery point corresponding to each of the at least some candidate anomaly detection points and the time series data of the target analysis index of at least one quantum dot material corresponding to each of the at least some candidate anomaly detection points.

[0019] In one possible implementation, the anomaly location and anomaly degree determination unit is further configured to:

[0020] When multiple candidate anomaly detection points have an upstream and downstream adjacent position relationship, the spectral detection device is deployed at the upstream candidate anomaly detection point among the multiple candidate anomaly detection points; wherein, the upstream and downstream adjacent position relationship means that, based on the water flow direction in the drainage pipe network, any candidate anomaly detection point is located upstream or downstream of another candidate anomaly detection point, and the two candidate anomaly detection points are directly adjacent to each other, with no other candidate anomaly detection points between them.

[0021] In one possible implementation, the at least some candidate anomaly detection points include: a first candidate anomaly detection point, and the anomaly location and anomaly degree determination unit is further configured to:

[0022] If the time series data of the target analysis index of at least one quantum dot material corresponding to the first candidate anomaly detection point meets the first preset condition, and the type of the deployment point corresponding to the at least one quantum dot material is different from the type of the first candidate anomaly detection point, it is determined that a first pipe section between the first candidate anomaly detection point and the monitoring point adjacent to the first candidate anomaly detection point upstream has a rainwater and sewage mixing, and the anomaly location includes: the first pipe section.

[0023] In one possible implementation, the time series data of the target analytical index of multiple quantum dot materials corresponding to the first candidate anomaly detection point all satisfy a first preset condition, wherein the target analytical index is concentration, and the device further includes:

[0024] The first quantum dot concentration time series data determination unit is used to determine the concentration of the multiple quantum dot materials at the first candidate anomaly detection point based on the spectral detection device, and obtain multiple first quantum dot concentration time series data corresponding to the first candidate anomaly detection point;

[0025] The first detection quality determination unit is used to obtain the first detection quality corresponding to the various quantum dot materials at the first candidate anomaly detection point based on the flow rate, pipe diameter, time series data of multiple first quantum dot concentrations at the first candidate anomaly detection point and the detection frequency of the spectral detection device.

[0026] The main source of contamination determination unit is used to determine the main source of contamination of rainwater and sewage from each of the various quantum dot materials based on each of the first detection quality.

[0027] In one possible implementation, the anomaly degree includes the degree of cross-connection, and the anomaly location and anomaly degree determination unit is further configured to:

[0028] Based on the first detection quality, determine the quantum dot detection ratio corresponding to each first candidate abnormal detection point;

[0029] Based on the first detection quality and the time series data of the first quantum dot concentration, the absolute pollution load corresponding to each first candidate anomaly detection point is determined. The absolute pollution load characterizes the pollution intensity of the mixed connection on the first candidate anomaly detection point.

[0030] Obtain the environmental sensitivity coefficient corresponding to each of the first candidate anomaly detection points;

[0031] Based on the quantum dot detection rate, the absolute pollution load, and the environmental sensitivity coefficient, the cross-connection severity index corresponding to each of the first candidate anomaly detection points is determined;

[0032] Based on the severity index of the cross-connection, the degree of cross-connection in each of the first pipe segments is determined.

[0033] In one possible implementation, the main mixing source location determination unit is further configured to:

[0034] Based on the first input mass and the first detection mass of each of the multiple quantum dot materials detected by the first candidate anomaly detection point, the mass ratio of each of the multiple quantum dot materials is determined.

[0035] The main source of contamination is determined based on the stated mass ratios.

[0036] In one possible implementation, the at least some candidate anomaly detection points include: a second candidate anomaly detection point, and the anomaly location and anomaly degree determination unit is further configured to:

[0037] If the time series data of the target analysis index of at least one quantum dot material corresponding to the second candidate anomaly detection point meets the second preset condition, and the type of the deployment point corresponding to the at least one quantum dot material is the same as the type of the second candidate anomaly detection point, it is determined that a pipe rupture has occurred in the second pipe section between the deployment point corresponding to the at least one quantum dot material and the second candidate anomaly detection point, and the anomaly location includes: the second pipe section;

[0038] The degree of abnormality includes the degree of damage;

[0039] Based on the spectral detection device, the concentrations of various quantum dot materials at the second candidate anomaly detection point are determined, and time series data of multiple second quantum dot concentrations corresponding to the second candidate anomaly detection point are obtained.

[0040] Based on the flow rate, pipe diameter, time series data of multiple second quantum dot concentrations at the second candidate anomaly detection point, and the detection frequency of the spectral detection device, the second detection quality corresponding to the various quantum dot materials at the second candidate anomaly detection point is obtained;

[0041] Based on the second input mass and the second detection mass of each of the multiple quantum dot materials detected at each of the second candidate anomaly detection points, the degree of damage to each of the second pipe segments is determined.

[0042] In one possible implementation, the at least some candidate anomaly detection points include: a third candidate anomaly detection point, and the anomaly location and anomaly degree determination unit is further configured to:

[0043] If the time series data of the target analysis index of at least one quantum dot material corresponding to the third candidate anomaly detection point meets the third preset condition, and the type of the deployment point corresponding to the at least one quantum dot material is the same as the type of the third candidate anomaly detection point, the first data of the target analysis index at the deployment point corresponding to the at least one quantum dot material is obtained.

[0044] If the first data of the target analysis index at the delivery point corresponding to the at least one quantum dot material and the time series data of the target analysis index of the at least one quantum dot material corresponding to the third candidate anomaly detection point satisfy the fourth preset condition, it is determined that a pipe rupture and / or rainwater and sewage mixing has occurred in the third pipe section between the third candidate anomaly detection point and the delivery point corresponding to the at least one quantum dot material, and the anomaly location includes: the third pipe section.

[0045] In one possible implementation, the candidate anomaly detection point determination unit is further configured to:

[0046] When the pipe network type is a rainwater pipe network and the rainfall in the area where the rainwater pipe network is located does not meet the preset rainfall threshold within a preset time period, for any monitoring point, the median of the first target water quality index corresponding to the monitoring point is determined based on the time series data of the first target water quality index corresponding to the monitoring point.

[0047] If the median of the first target water quality index meets the fifth preset condition, the monitoring point is determined as a candidate anomaly detection point;

[0048] When the pipeline type is a sewage pipeline and the rainfall in the area where the sewage pipeline is located meets the preset rainfall threshold within a preset time period, for any monitoring point, based on the time series data of at least two correlated water quality indicators corresponding to the monitoring point, the trend analysis result of each water quality indicator time series data in the at least two correlated water quality indicator time series data is determined respectively.

[0049] If the trend analysis results of at least two correlated water quality index time series data corresponding to the monitoring point meet the sixth preset condition, the monitoring point is determined as a candidate anomaly detection point.

[0050] When the pipeline type is a sewage pipeline and the rainfall in the area where the sewage pipeline is located does not meet the preset rainfall threshold within a preset time period, for any monitoring point, the first target flow time series data corresponding to the monitoring point and the second target flow time series data corresponding to the monitoring point adjacent to the upstream of the monitoring point are determined.

[0051] If the first target traffic flow time series data and the second target traffic flow time series data meet the seventh preset condition, the monitoring point is determined as a candidate anomaly detection point;

[0052] When the pipe network type is a rainwater pipe network and the rainfall in the area where the rainwater pipe network is located meets the preset rainfall threshold within a preset time period, for any monitoring point, the third target flow time series data and the second target water quality index time series data corresponding to the monitoring point are determined, as well as the fourth target flow time series data and the third target water quality index time series data corresponding to the monitoring point adjacent to the upstream of the monitoring point.

[0053] If the time series data of the third target flow rate, the time series data of the second target water quality index, the time series data of the fourth target flow rate, and the time series data of the third target water quality index meet the eighth preset condition, the monitoring point is determined as a candidate anomaly detection point.

[0054] 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.

[0055] 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.

[0056] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the above-described method.

[0057] In this embodiment, the unique spectral information carried by quantum dot materials can be utilized to indicate the direction of water flow and determine the path of the water flow. This allows for the determination of whether an anomaly has occurred in the drainage network, the location of the anomaly, and the assessment of its severity. Furthermore, quantum dot materials with different spectral information can be detected at multiple candidate anomaly detection points simultaneously or in close proximity. This enables parallel detection of anomalies in multiple pipe sections, improving detection efficiency.

[0058] This method can perform synchronous detection at all points within the entire drainage network area, and is not limited to single-point detection, which greatly improves detection efficiency. Since candidate abnormal detection points have upstream and downstream relationships, they can directly reflect the detection results, so this method also improves detection accuracy.

[0059] 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

[0060] 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.

[0061] Figure 1 This is a flowchart illustrating the drainage network anomaly detection method provided in an embodiment of this disclosure.

[0062] Figure 2 This is a schematic diagram of rainwater and sewage mixing provided in an embodiment of this disclosure.

[0063] Figure 3 This is a schematic diagram of pipe damage provided in an embodiment of this disclosure.

[0064] Figure 4 This is a schematic diagram of rainwater and sewage mixing provided in an embodiment of this disclosure.

[0065] Figure 5 This is a schematic diagram of a combined rainwater and sewage system with a damaged pipeline, as provided in an embodiment of this disclosure.

[0066] Figure 6 This is a schematic diagram of the structure of the drainage network anomaly detection device provided in an embodiment of this disclosure.

[0067] Figure 7 This is a schematic diagram of the structure of an electronic device for detecting anomalies in a drainage pipe network, provided in an embodiment of this disclosure. Detailed Implementation

[0068] 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.

[0069] 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.

[0070] 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.

[0071] 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.

[0072] 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.

[0073] 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.

[0074] Figure 1 This is a schematic flowchart illustrating the drainage network anomaly detection method provided in this embodiment of the disclosure. Figure 1 As shown, the method includes:

[0075] S11. Based on the type of the drainage network, the rainfall in the area where the drainage network is located, and the time series data of at least one water quality indicator or flow rate corresponding to multiple monitoring points in the drainage network, determine at least one candidate abnormal detection point.

[0076] In this embodiment of the disclosure, the network type can be determined based on the type of water body in the drainage network. For example, the network type may include: sewage network and stormwater network. Rainfall conditions can indicate whether it is raining and / or the rainfall level. For example, rainfall conditions may include: rainy days and dry days.

[0077] Monitoring points can be any point on the drainage network. Different types of drainage networks may have different monitoring points. For example, monitoring of sewage networks should proceed upstream from the inlet of the downstream sewage treatment plant. Monitoring points should avoid manholes at junctions such as T-junctions or four-way junctions. It is advisable to select points on the upstream branch line near the manhole at the junction. If the straight-line distance is long and there are no intermediate pipelines joining the network, additional monitoring points can be added. Monitoring of stormwater networks should proceed upstream from the downstream stormwater outfall. Monitoring points should avoid manholes at junctions such as T-junctions or four-way junctions. It is advisable to select points on the upstream branch line near the manhole at the junction. If the straight-line distance is long and there are no intermediate pipelines joining the network, additional monitoring points can be added. At monitoring points, physical and chemical parameters of the water body can be monitored. For example, water quality indicators and water flow can be monitored at monitoring points. The water quality indicators may include one or more of the following: chemical oxygen demand, conductivity, ammonia nitrogen, total hardness, temperature, pH value, turbidity, total organic carbon, five-day biochemical oxygen demand, total phosphorus, total nitrogen, suspended solids, total dissolved solids, petroleum hydrocarbons, anionic surfactants, cyanide, sulfide, fluoride, organophosphorus compounds, sulfate, mercury, chromium, cadmium, arsenic, lead, nickel, beryllium, silver, selenium, copper, zinc, manganese, iron, volatile phenols, benzene series compounds, aniline compounds, and nitrobenzene, etc.

[0078] At monitoring points, water quality indicators or flow rates can be measured at preset time intervals, thereby obtaining time-series data of water quality indicators or flow rates corresponding to the monitoring points. By analyzing the time-series data of water quality indicators or flow rates, monitoring points where water anomalies have occurred can be identified. For ease of description, monitoring points where water anomalies have occurred are named candidate anomaly detection points.

[0079] S12, determine multiple delivery points located within a preset range upstream of each candidate anomaly detection point, and deliver different types of quantum dot materials to each delivery point corresponding to each candidate anomaly detection point, wherein the spectral information of the different types of quantum dot materials delivered to each delivery point is different.

[0080] The delivery point is the location where quantum dot material is delivered. The delivery point is located upstream of the candidate anomaly detection point. "Upstream" here includes locations within the drainage network topology (e.g., topology maps, obtainable from official agencies or authorized units) where the delivery point and the candidate anomaly detection point have a direct upstream-downstream connection. It also includes locations where the delivery point is situated above the candidate anomaly detection point, but based on the drainage network topology, there should be no connection between them. Delivery points can be upstream of the candidate anomaly detection point, where they have an upstream-downstream connection within the drainage network; alternatively, delivery points can be upstream of the candidate anomaly detection point where there should not be a connection, such as a rainwater well upstream of a candidate anomaly detection point (e.g., a sewage well) in a sewage network, where the rainwater well and sewage well do not originally have a topological relationship.

[0081] For a single candidate anomaly detection point, different types of quantum dot materials are deployed at each corresponding deployment point. This can be achieved by deploying one type of quantum dot material at each deployment point, or by deploying multiple different quantum dot materials at each deployment point. There is no specific limitation on the types of quantum dot materials deployed at each deployment point; "different types" (or "multiple different types") refers to the different spectral information of the quantum dot materials. Spectral information can include one or more of the following characteristics: absorption wavelength range, emission wavelength range, fluorescence intensity, etc. Spectral information can be the fluorescence emission wavelength of the quantum dot material. Quantum dot materials include quantum dots and / or fluorescent microspheres loaded with quantum dots. The quantum dots can be quantum dots of group II-VI compounds selected from CdS, CdSe, CdTe, ZnS, ZnSe, PbS, and PbSe; and / or quantum dots of group IV-VI compounds selected from SnTe, PbSe, GeS, GeSe, GeTe, SnS, SnSe, PbS, PbSe, and PbTe; and / or quantum dots of group III-V compounds selected from InP, GaP, GaN, and AlN; and / or quantum dots of core-shell structured materials selected from CdS / ZnS, CdSe / CdS, CdSe / ZnS, CdSe / CdS / ZnS, CdTe / CdS, CdTe / CdS / ZnS, ZnSe / ZnS, InP / ZnSe, InP / ZnS, InP / ZnSe / ZnS, and InP / GaP / ZnS; and / or perovskite quantum dots, and / or carbon quantum dots. Carbon quantum dots are preferred because they have high brightness, tunable fluorescence, and strong resistance to photobleaching, enabling stable and sensitive long-term tracking. As a carbon-based material, they also have the advantages of good biocompatibility, low cytotoxicity, and small size that facilitates metabolism, significantly reducing the risk of secondary pollution and making them more environmentally friendly.

[0082] Fluorescent microspheres loaded with quantum dots can have a core-shell structure. The fluorescent microspheres may include quantum dots, silica, and a protective layer, wherein the quantum dots serve as the outer shell, and the silica serves as the core, with the outer shell disposed on the outer surface of the core. Quantum dot microspheres may also include quantum dots and polymers, wherein the quantum dots are dispersed in the polymer, which may be polystyrene, polymethacrylate, etc., without specific limitations.

[0083] For individual candidate anomaly detection points, there is no specific limit to the amount of quantum dot material added at each point. As long as the target analytical indicators of the quantum dot material (described below, such as concentration, mass, fluorescence intensity, etc.) can be detected by the spectroscopic detection equipment deployed at the candidate anomaly detection point under ideal conditions where the pipeline between the point of application and the candidate anomaly detection point is connected and undamaged, reaching the low detection limit and within the detection range of the equipment, or if the detection equipment can detect the corresponding indicator and calculate the corresponding analytical indicator data, then it is acceptable. In other words, if, under ideal conditions, the point of application and its corresponding candidate anomaly detection point are connected and the pipeline is undamaged, allowing water to flow, then the amount of quantum dot material added at the point of application can be detected by the spectroscopic detection equipment deployed downstream.

[0084] For a single candidate anomaly detection point, the fluorescence emission wavelength of the quantum dot material deployed at each deployment point is different, creating a mapping relationship between the deployment point and the quantum dot material. Thus, when quantum dot material is detected at a candidate anomaly detection point, this mapping relationship can be used to determine the deployment point corresponding to the detected quantum dot material.

[0085] S13, using spectral detection equipment deployed at at least some of the candidate anomaly detection points, the target analysis index of the quantum dot material deployed at each of the deployment points is obtained, and time series data of the target analysis index of each quantum dot material corresponding to each of the at least some candidate anomaly detection points are obtained.

[0086] The target analytical index can be at least one of the following: concentration, mass, and spectral information of the quantum dot material. For example, spectral information could be fluorescence intensity. Specifically, the target analytical index can include indices directly detected by spectral detection equipment, such as the concentration and spectral information of the quantum dot material, or indices calculated using the data corresponding to the detected indices, such as the mass of the quantum dot material. The mass of the quantum dot material can be calculated from the concentration of the quantum dot material, the flow rate in the pipeline, and the diameter of the pipe section.

[0087] In this embodiment of the disclosure, at least some of the candidate anomaly detection points are candidate anomaly detection points among at least one candidate anomaly detection point determined in S11.

[0088] The spectroscopic detection equipment can be an in-situ high-frequency spectroscopic detection device. The detection frequency of the spectroscopic detection equipment can be 15 seconds to 60 minutes per cycle, preferably 15 seconds to 30 minutes per cycle, more preferably 15 seconds to 15 minutes per cycle, and most preferably 10 seconds to 10 minutes per cycle. The detection frequency of this spectroscopic detection equipment is much higher than that of traditional detection methods that involve sampling water and then conducting laboratory analysis. Therefore, it can obtain spectral data of quantum dot materials at a higher frequency to effectively capture the water characteristics of drainage pipe networks.

[0089] The in-situ high-frequency spectroscopic detection equipment can achieve 24-hour high-frequency monitoring of all candidate anomaly detection points, eliminating the need for sampling personnel as in traditional solutions and saving personnel costs. In this embodiment, the spectroscopic detection equipment can be deployed at all candidate anomaly detection points or at some candidate anomaly detection points. This embodiment does not limit the scope of the invention.

[0090] S14. Based on the type of at least one delivery point corresponding to each candidate anomaly detection point among the at least some candidate anomaly detection points and the time series data of the target analysis index of at least one quantum dot material corresponding to each candidate anomaly detection point, determine the anomaly location and anomaly degree of the drainage pipe network.

[0091] The type of each injection point or candidate anomaly detection point can characterize the type of water flow at the location in the drainage network. For example, if the water flow at a location is sewage, then the location is classified as a sewage location. If the water flow at a location is rainwater, then the location is classified as a rainwater location. Manholes (e.g., inspection wells) in the drainage network can be used as injection points and monitoring points (monitoring points include candidate anomaly detection points). Thus, the type of each injection point or candidate anomaly detection point can characterize the corresponding manhole type. Whether quantum dot material is detected at a candidate anomaly detection point can be determined based on the time series data of the target analysis index. For example, if quantum dot material is detected at a candidate anomaly detection point, then the time series data of the target analysis index is not 0. The water flow in the pipeline is continuous. Therefore, if quantum dot material is detected at a candidate anomaly detection point, the type of the delivery point and the candidate anomaly detection point can be used to determine whether the quantum dot material should be detected at that candidate anomaly detection point. This allows us to determine whether an anomaly has occurred in the drainage network, locate the anomaly location, and determine the degree of anomaly corresponding to the anomaly location.

[0092] In this embodiment, the unique spectral information carried by quantum dot materials can be utilized to indicate the direction of water flow and determine the path of the water flow. This allows for the determination of whether an anomaly has occurred in the drainage network, the location of the anomaly, and the assessment of its severity. Furthermore, quantum dot materials with different spectral information can be detected at multiple candidate anomaly detection points simultaneously or in close proximity. This enables parallel detection of anomalies in multiple pipe sections, improving detection efficiency.

[0093] This method can perform synchronous detection at all points within the entire drainage network area, and is not limited to single-point detection, which greatly improves detection efficiency. Since candidate abnormal detection points have upstream and downstream relationships, they can directly reflect the detection results, so this method also improves detection accuracy.

[0094] In one possible implementation, the use of spectral detection equipment deployed at at least some of the candidate anomaly detection points includes: when multiple candidate anomaly detection points have an upstream-downstream adjacent position relationship, utilizing the spectral detection equipment deployed at the most upstream candidate anomaly detection point among the multiple candidate anomaly detection points; wherein the upstream-downstream adjacent position relationship means that, based on the water flow direction within the drainage network, any candidate anomaly detection point is located upstream or downstream of another candidate anomaly detection point in the water flow, and the two candidate anomaly detection points are directly adjacent to each other, with no other candidate anomaly detection points between them.

[0095] In this embodiment of the disclosure, if there is an upstream-downstream adjacent position relationship among multiple candidate anomaly detection points, it indicates that the same quantum dot material can be detected at these candidate anomaly detection points. Therefore, a spectroscopic detection device can be deployed at the candidate anomaly detection point where the quantum dot material is detected first. That is, the spectroscopic detection device is deployed at the most upstream candidate anomaly detection point among all candidate anomaly detection points with upstream-downstream adjacent position relationships. "Most upstream" refers to the very upstream of all candidate anomaly detection points.

[0096] When the direction of water flow is not obvious or the upstream position cannot be determined by conventional methods, it can be determined by selecting a region: based on the principles of topography and gravity flow, drainage networks mainly rely on gravity flow, and water always flows from high to low. Therefore, when the upstream position cannot be determined by the adjacent positions of upstream and downstream, it is usually located at the high point of the region or in a high-altitude area.

[0097] In this embodiment of the disclosure, the number of spectral detection devices deployed can be reduced while ensuring detection accuracy, thereby reducing deployment costs.

[0098] In one possible implementation, the at least some candidate anomaly detection points include: a first candidate anomaly detection point; the step of determining the anomaly location of the drainage network based on the type of at least one delivery point corresponding to each of the at least some candidate anomaly detection points and the time series data of the target analysis index of at least one quantum dot material corresponding to each of the at least some candidate anomaly detection points includes:

[0099] If the time series data of the target analysis index of at least one quantum dot material corresponding to the first candidate anomaly detection point meets the first preset condition, and the type of the deployment point corresponding to the at least one quantum dot material is different from the type of the first candidate anomaly detection point, it is determined that a first pipe section between the first candidate anomaly detection point and the monitoring point adjacent to the upstream of the first candidate anomaly detection point has a rainwater and sewage mixing, and the anomaly location includes: the first pipe section.

[0100] In this embodiment, the first candidate anomaly detection point can be a candidate anomaly detection point where quantum dot material is detected, and the type of the location where the quantum dot material is detected is different from the type of the placement point. In this embodiment, the target analysis index can be the mass, concentration, or fluorescence intensity of the quantum dot material. The first preset condition can be the presence of multiple monitoring values ​​greater than 0 in the time series data of the target analysis index. Meeting the first preset condition indicates that quantum dot material is detected at the first candidate anomaly detection point. That is, quantum dot material is detected at the first candidate anomaly detection point. Moreover, the placement point corresponding to the quantum dot material is of a different type than the first candidate anomaly detection point. For example, in a sewage pipe network, the first candidate anomaly detection point is a sewage well, while the placement point where the quantum dot material is detected is a rainwater well, so the two are of different types. In this way, the first candidate anomaly detection point should not have detected the quantum dot material. If it has, it indicates that a pipe anomaly has occurred. This is because rainwater and sewage mixing has occurred between the first candidate anomaly detection point and its placement point, which is why the quantum dot material, which should not have been detected, was identified at the first candidate anomaly detection point. Rainwater and sewage mixing means that water from at least one placement point corresponding to a quantum dot material mixes into the first pipe section.

[0101] The anomaly location is the first pipe segment between the first candidate anomaly detection point and its upstream adjacent monitoring point. If sewage mixing has already occurred upstream of the upstream adjacent monitoring point, then the upstream adjacent monitoring point will be identified as a candidate anomaly detection point. Furthermore, as explained above, a spectral detection device will be deployed at the upstreammost candidate anomaly detection point in the upstream-downstream positional relationship, but not at the first candidate anomaly detection point in this embodiment. Therefore, the sewage mixing is described as occurring on the first pipe segment between this monitoring point and the first candidate anomaly detection point.

[0102] Figure 2This is a schematic diagram of rainwater and sewage mixing provided in an embodiment of this disclosure. Figure 2 In the diagram, the hollow circle represents the first candidate anomaly detection point A, the triangle represents one of the delivery points B corresponding to the first candidate anomaly detection point A, and the solid circle represents the upstream adjacent monitoring point C. Quantum dot material delivered from delivery point B was detected at the first candidate anomaly detection point A; however, delivery point B and the first candidate anomaly detection point A have different material types. Therefore, it can be determined that rainwater and sewage mixing occurred between monitoring point C and the first candidate anomaly detection point A.

[0103] In this embodiment of the disclosure, anomalies in the drainage network can be accurately identified, and the anomaly type is mixed rainwater and sewage. Furthermore, the location where the mixed rainwater and sewage occurs can be accurately located.

[0104] In one possible implementation, the time series data of the target analysis indicators of multiple quantum dot materials corresponding to the first candidate anomaly detection point all meet a first preset condition, wherein the target analysis indicator is concentration. The method further includes: determining the concentration of the multiple quantum dot materials at the first candidate anomaly detection point based on the spectral detection device, and obtaining multiple first quantum dot concentration time series data corresponding to the first candidate anomaly detection point; obtaining a first detection quality corresponding to each of the multiple quantum dot materials at the first candidate anomaly detection point based on the flow rate, pipe diameter, multiple first quantum dot concentration time series data, and the detection frequency of the spectral detection device at the first candidate anomaly detection point; and determining the main source of rainwater and sewage mixing from each delivery point corresponding to the multiple quantum dot materials based on each first detection quality.

[0105] At the first candidate anomaly detection point, the concentrations of various quantum dot materials can be detected at a preset detection frequency, yielding multiple time-series data of the first quantum dot concentration. In one example, the aforementioned spectroscopic detection device can be used to detect the concentration of quantum dot materials at a preset detection frequency.

[0106] For ease of understanding, Equation (1) is used to demonstrate the process of determining the first detection quality of quantum dot materials.

[0107] (1)

[0108] in, This indicates the first detection quality at which quantum dot material was detected at the first candidate anomaly detection point; This represents the concentration of the quantum dot material at time t; The flow velocity in the pipe at time t can be dynamically measured using a flow meter. ; The pipe cross-sectional area at the first candidate anomaly detection point at time t can be determined using the pipe diameter. The pipe diameter can be obtained from official records; Indicates the start time of the detection. Indicates the end time of the detection, i.e. The moment when the nth detection cycle ends.

[0109] The method of formula (1) can capture the dynamic changes (such as rise / fall) of the concentration of quantum dot materials by difference, avoiding the "step error" of discrete sampling; by accumulating the infinitesimal elements, the overall error is reduced, which is more suitable for the unsteady flow of water in drainage pipe networks, thereby improving the accuracy of determining the first detection quality of quantum dot materials.

[0110] To simplify the calculation, the first detection quality of the quantum dot material can also be determined using formula (2).

[0111] (2)

[0112] in, This indicates the first detection quality at which quantum dot material was detected at the first candidate anomaly detection point; This represents the concentration of the quantum dot material detected in the i-th test (i.e., at the i-th time step). By sorting the data chronologically, a time series of concentration values ​​for quantum dot materials can be generated. The average flow velocity of the pipe where the first candidate anomaly detection point is located is represented by , and S represents the cross-sectional area of ​​the pipe where the first candidate anomaly detection point is located. This cross-sectional area can be determined using the pipe diameter. n represents the total number of detections. This indicates the time interval between two consecutive detections. It can be obtained from the detection frequency when the quantum dot concentration is detected by the spectroscopic equipment.

[0113] In this embodiment, equal masses of quantum dot material can be placed at each placement point to ensure that the initial concentration of quantum dot material at each placement point is the same. When the mass of quantum dot material placed at each placement point is equal, the placement point corresponding to the quantum dot material with the highest detection mass detected by the first candidate anomaly detection point can be designated as the primary source of contamination.

[0114] In this embodiment, the quantum dot material detected at the first candidate anomaly detection point can be quickly and quantitatively measured to obtain the first detection quality. This improves the efficiency and accuracy of determining the first detection quality. Furthermore, based on the first detection quality of the quantum dot material, the main source of contamination can be identified, providing a reference for prioritizing the treatment of combined sewer overflows.

[0115] In one possible implementation, the degree of anomaly includes the degree of cross-connection. Determining the degree of anomaly in the drainage network includes: determining the quantum dot detection ratio corresponding to each first candidate anomaly detection point based on each first detection quality; determining the absolute pollution load corresponding to each first candidate anomaly detection point based on each first detection quality and each first quantum dot concentration time series data, wherein the absolute pollution load characterizes the pollution intensity of cross-connection to the first candidate anomaly detection point; obtaining the environmental sensitivity coefficient corresponding to each first candidate anomaly detection point; determining the cross-connection severity index corresponding to each first candidate anomaly detection point based on the quantum dot detection ratio, the absolute pollution load, and the environmental sensitivity coefficient; and determining the degree of cross-connection in each first pipe segment based on the cross-connection severity index.

[0116] The quantum dot detection rate can indirectly characterize the amount of water mixed into the first pipeline. The quantum dot detection rate can be the ratio of the first detected mass of quantum dot material detected at the first candidate anomaly detection point (which should not appear there) to the input mass. The absolute pollution load can characterize the maximum instantaneous impact intensity on the receiving water body when water from the discharge point passes through the mixing point. The absolute pollution load can be the ratio of the peak mass of pollutants caused by the mixing to the limit mass of pollutants that the receiving water body can accept. The receiving water body is the water body that receives the water discharged from the pipe network. The environmental sensitivity coefficient can characterize the tolerance of the receiving water body to acceptable pollution. In this embodiment, for each first pipe section, the quantum dot detection rate, absolute pollution load, and environmental sensitivity coefficient corresponding to the first candidate anomaly detection point of the first pipe section can be weighted and calculated to obtain the mixing severity index. Furthermore, multiple first threshold intervals can be obtained. Each of the multiple first threshold intervals corresponds to a priority for handling pipeline mixing. Based on the first threshold range described in the cross-connection severity index, the degree of cross-connection can be determined, and the priority for processing the first pipe segment can be obtained.

[0117] To enable calculations using data with different dimensions and numerical ranges, the detection rate of quantum dots, absolute pollution load, and environmental sensitivity coefficient can be normalized. For example, the detection rate of quantum dots, absolute pollution load, and environmental sensitivity coefficient can all be mapped to a unified score range.

[0118] For ease of understanding, formula (3) can be used to represent the process of normalizing the quantum dot detection rate. Formula (4) can be used to represent the process of normalizing the absolute pollution load.

[0119] (3)

[0120] Where R represents the quantum dot detection rate. This indicates the preset upper limit of the quantum dot detection rate. It can be 30% or 50%, if R exceeds Then you can directly take another ; This represents the normalized quality detection rate.

[0121] (4)

[0122] Where L represents the absolute pollution load, This indicates the preset maximum load, or the historical maximum pollution load. This represents the normalized absolute pollution load.

[0123] For example, the process of determining the absolute pollution load can be represented by formula (5).

[0124] (5)

[0125] in, Indicates the first test quality (total quality). The peak concentration of pollutants caused by cross-contamination can be determined based on the time series data of the first quantum dot concentration. ; The acceptable concentration limits for pollutants in receiving water bodies can be determined based on relevant pollution standards and the water quality of the receiving water body. .

[0126] In this embodiment, an environmental sensitivity coefficient can be set based on the location, purpose, and other characteristics of the receiving water body. For example: when the receiving water body is a drinking water source protection area, an ecological red line area, or a sensitive lake / reservoir, the environmental sensitivity coefficient is a first coefficient; when the receiving water body is an urban landscape water body or a swimming area, the environmental sensitivity coefficient is a second coefficient; when the receiving water body is the sea, a ditch, or other areas with excellent diffusion conditions, the environmental sensitivity coefficient is a third coefficient; and when the receiving water body is a drinking water source protection area, an ecological red line area, or a sensitive lake / reservoir, the environmental sensitivity coefficient is a fourth coefficient. In one example, the first coefficient is 10, the second coefficient is 7, the third coefficient is 4, and the fourth coefficient is 1. In this example, the normalized environmental sensitivity coefficient is equal to the environmental sensitivity coefficient.

[0127] In this embodiment of the disclosure, weights can be preset, and the cross-connection severity index can be calculated by weighting the quantum dot detection rate, absolute pollution load, and environmental sensitivity coefficient using these weights. For ease of understanding, the process of determining the cross-connection severity index can be represented by formula (6).

[0128] (6)

[0129] in, Indicates the severity of cross-connection. Indicates the first weight. Indicates the second weight. This indicates the third weight. In one example, the first weight is 0.3, the second weight is 0.3, and the third weight is 0.4.

[0130] The severity metric is positively correlated with response priority; the higher the value, the higher the priority. In one example, the first threshold range and its corresponding priority are shown in Table 1:

[0131] Table 1

[0132]

[0133] In this disclosed embodiment, a technological leap can be achieved from qualitative diagnosis to quantitative classification and decision-making regarding the problem of combined sewer overflows. By coupling the entire chain from internal hydraulic anomalies in the pipe network to actual risks in the external environment according to three dimensions (quantum dot detection rate, absolute pollution load, and environmental sensitivity coefficient), an objective Sewer Severity Index (SSI) is determined. This effectively solves the technical pain points of traditional methods relying on human experience for judgment, which are characterized by strong subjectivity, inconsistent standards, and low efficiency. It can accurately determine the severity of combined sewer overflows, thereby guiding limited management and engineering resources to prioritize the overflow points that pose the greatest actual environmental harm and risk, significantly improving the scientific nature, accuracy, and investment efficiency of drainage pipe network management.

[0134] In one possible implementation, determining the main source of rainwater and sewage mixing from each of the delivery points corresponding to the multiple quantum dot materials based on each of the first detection masses includes: determining the mass ratio of each quantum dot material among the multiple quantum dot materials based on the first input mass and the first detection mass detected by the first candidate anomaly detection point; and determining the main source of mixing according to each of the mass ratios.

[0135] In some scenarios, the input mass of quantum dot materials at different delivery points cannot be consistent, or it may be difficult to maintain consistency due to operational errors. Therefore, the input mass of each quantum dot material at each delivery point can be recorded. If quantum dot material is detected at the first candidate anomaly detection point, the input mass and detection mass of the detected quantum dot material are obtained, and the ratio of the detection mass to the input mass is determined. This ratio is named the "mass ratio" for ease of description. Assuming that the attenuation characteristics of each quantum dot material are similar, the mass ratio is positively correlated with the inflow rate successfully flowing into the first pipe section from the delivery point. Therefore, the delivery point with the largest mass ratio can be considered the main source of contamination.

[0136] In this embodiment of the disclosure, the input quality of quantum dot materials is not limited, which is more suitable for practical operation and reduces the error caused by the difficulty in controlling the input quality, making the determined main mixing source sites more reliable.

[0137] In one possible implementation, the method further includes: determining the amount of each of the multiple quantum dot materials mixed into the first pipe segment at its respective dispensing point, based on the mass ratios and the total flow rate of the first pipe segment.

[0138] As mentioned earlier, the mass ratio is positively correlated with the inflow rate of water from the injection point into the first pipe section. Therefore, the mass ratio can characterize the proportion of the initial flow rate of water from the injection point into the first pipe section relative to the total flow rate of the first pipe section. Consequently, the product of the mass ratio and the total flow rate of the first pipe section can be used as the amount of water mixed into the first pipe section at that injection point.

[0139] In this embodiment of the disclosure, the amount of water mixed into the first pipe section can be quantitatively determined, providing a reference for subsequent work (e.g., determining the amount of purifying agent to be added in order to purify the water quality of the pipe network), thereby improving the accuracy and efficiency of subsequent work.

[0140] In one possible implementation, the at least some candidate anomaly detection points include: a second candidate anomaly detection point. The step of determining the anomaly location of the drainage network based on the type of at least one delivery point corresponding to each of the at least some candidate anomaly detection points and the time series data of the target analysis index of at least one quantum dot material corresponding to each of the at least some candidate anomaly detection points includes: if the time series data of the target analysis index of at least one quantum dot material corresponding to the second candidate anomaly detection point satisfies a second preset condition, and the type of the delivery point corresponding to the at least one quantum dot material is the same as the type of the second candidate anomaly detection point, then determining that a second pipe section between the delivery point corresponding to the at least one quantum dot material and the second candidate anomaly detection point has suffered pipe damage, the anomaly location including: the second pipe section. The degree of anomaly includes the degree of damage; based on the spectral detection device, the concentration of multiple quantum dot materials at the second candidate anomaly detection point is determined, and time series data of multiple second quantum dot concentrations corresponding to the second candidate anomaly detection point are obtained; based on the flow rate, pipe diameter, multiple second quantum dot concentration time series data and the detection frequency of the spectral detection device at the second candidate anomaly detection point, the second detection mass corresponding to each of the multiple quantum dot materials at the second candidate anomaly detection point is obtained; based on the second input mass and the second detection mass corresponding to each of the multiple quantum dot materials detected at each of the second candidate anomaly detection points, the degree of damage of each second pipe segment is determined.

[0141] The second candidate anomaly detection point can be a candidate anomaly detection point where no quantum dot material was detected, and the type of the detected location of the quantum dot material is the same as the type of the delivery point. The second preset condition can be that the monitoring value of the target analysis index of the quantum dot material at each time step in the time series data is 0, that is, the quantum dot material delivered at the delivery point corresponding to the second candidate anomaly detection point was not detected.

[0142] In other words, if quantum dot material is placed at a location of the same type as the second candidate anomaly detection point, but this quantum dot material is not detected by the spectral detection equipment deployed at the second candidate anomaly detection point, then it indicates that the quantum dot material has been lost. For ease of description, the pipe between the placement point corresponding to the undetected quantum dot material and the second candidate anomaly detection point is named the second pipe segment. Thus, if at least one quantum dot material is not detected at the second candidate anomaly detection point, and the type of the placement point corresponding to the undetected quantum dot material is the same as the type of the third candidate anomaly detection point (e.g., both the candidate anomaly detection point and the placement point are sewage wells), it indicates that the quantum dot material in the pipe has been lost, thus causing an anomaly. This anomaly is a pipe rupture, and the location of the anomaly is the second pipe segment.

[0143] In this embodiment of the disclosure, the situation of pipe damage can be accurately identified, and the location of the pipe damage can be accurately located.

[0144] Additionally, a second detection mass of the quantum dot material can be determined based on a spectral detection device. The second detection mass can be the mass of the quantum dot material that should be detected at the second detection point and whose mass should not be reduced compared to the initial mass (or can be reduced within a preset range). The second detection mass may be zero, or less than or equal to the initial mass of the quantum dot material. For ease of distinction, the initial mass in this embodiment is referred to as the second initial mass. For the quantum dot material detected at the second candidate anomaly detection point, a mass ratio of the second detection mass to the second initial mass can be determined. A confidence interval for the mass ratio is preset. If the mass ratio is less than the lower limit of the confidence interval, the damage is considered severe. If the mass ratio falls within the confidence interval, the damage is considered moderate. If the mass ratio is greater than the upper limit of the confidence interval, the damage is considered minor. For example, the confidence interval for the mass ratio can be [50%, 70%]. The higher the severity, the higher the priority for pipeline repair.

[0145] In this embodiment, not only can the location of the pipeline damage be pinpointed, but the extent of the damage can also be quantified. This allows for precise determination of the severity of the pipeline damage, enabling the rational allocation of pipeline repair resources and improving the rationality and economy of drainage network management.

[0146] In one possible implementation, the at least some candidate anomaly detection points include: a third candidate anomaly detection point. The step of determining the anomaly location of the drainage network based on the type of at least one delivery point corresponding to each of the at least some candidate anomaly detection points and the time series data of the target analysis index of at least one quantum dot material corresponding to each of the at least some candidate anomaly detection points includes: when the time series data of the target analysis index of at least one quantum dot material corresponding to the third candidate anomaly detection point satisfies a third preset condition, and the type of the delivery point corresponding to the at least one quantum dot material is the same as the type of the third candidate anomaly detection point, obtaining the first data of the target analysis index at the delivery point corresponding to the at least one quantum dot material; when the first data of the target analysis index at the delivery point corresponding to the at least one quantum dot material and the time series data of the target analysis index of the at least one quantum dot material corresponding to the third candidate anomaly detection point satisfy a fourth preset condition, determining that a third pipe segment between the third candidate anomaly detection point and the delivery point corresponding to the at least one quantum dot material has experienced pipe damage and / or rainwater and sewage mixing, the anomaly location including: the third pipe segment.

[0147] The third preset condition can be the presence of multiple monitoring values ​​greater than 0 in the time series data of the target analysis index. Meeting the third preset condition indicates that quantum dot material was detected at the third candidate anomaly detection point. In this embodiment, the target analysis index can be mass. The first data can be a mass time series.

[0148] The third candidate anomaly detection point can be a candidate anomaly detection point where quantum dot material is detected, and the type of the location where the quantum dot material is detected is the same as the type of the delivery point. In this embodiment, the first data is the mass of the quantum dot material detected at the delivery point. The fourth preset condition for the mass concentration of the quantum dot material detected by the third candidate anomaly detection point can be that the mass at the delivery point corresponding to the quantum dot material is greater than the mass of the quantum dot material corresponding to the third candidate anomaly detection point, and the difference between the two is greater than a preset threshold. That is, at each time point, each mass value in the mass time series corresponding to the first data is greater than each mass value in the mass time series data of the quantum dot material detected by the third candidate anomaly detection point, and the difference between the two is greater than the preset threshold. The specific threshold setting can be selected according to the actual application situation, and there is no specific limitation thereto.

[0149] The reason for setting a preset threshold is that, when the two points are connected and the pipeline is closed and unbroken, the mass of the quantum dot material at the delivery point and the mass of the quantum dot material detected at the candidate anomaly detection point are usually equal or approximately equal. Setting a preset threshold so that an anomaly is only identified when the mass difference between the two points meets this threshold condition can further improve the detection precision and accuracy.

[0150] For ease of understanding, the first data is named the first mass, and the mass time series data of the quantum dot material corresponding to the third candidate anomaly detection point (i.e. the detected mass) is named the second mass.

[0151] For the same quantum dot material, if its second mass is less than its first mass and the difference between the two exceeds a preset threshold, three scenarios may occur: 1. Water has seeped out of the pipe; 2. Water that does not contain the quantum dot material has mixed in, or water has been diverted from the original straight pipe; 3. Both water seepage from the pipe and water that does not contain the quantum dot material has mixed in, or water has been diverted from the original straight pipe. Therefore, it can be determined that an anomaly has occurred in the pipe, specifically pipe damage and / or rainwater / sewage mixing.

[0152] For ease of description, the point where the quantum dot material with a second mass less than the first mass is placed is designated as the first placement point; the pipe between the first placement point and the third candidate anomaly detection point is designated as the third pipe segment. Therefore, if the third candidate anomaly detection point detects that at least one quantum dot material with a second mass less than the first mass, and the difference between the first mass and the second mass exceeds a preset threshold, it indicates that the quantum dot material in the pipe may be lost, or that the quantum dot material in the pipe may be diluted or diverted, thus causing an anomaly. This anomaly is identified as pipe damage and / or rainwater / sewage mixing, and the anomaly location is the third pipe segment.

[0153] Figure 3 This is a schematic diagram of pipe damage provided in an embodiment of this disclosure. Figure 3 In the diagram, the hollow circle represents the third candidate anomaly detection point A, the triangles represent the delivery points corresponding to the third candidate anomaly detection point A, and "×" indicates the damage location D. Quantum dot material delivered from delivery point B is detected at the third candidate anomaly detection point A. Delivery point B is of the same type as the third candidate anomaly detection point A, and the second mass of this quantum dot material is less than its first mass. Simultaneously, the difference between the first mass and the second mass exceeds a preset threshold. Because a pipe rupture occurred between delivery point B and the third candidate anomaly detection point A, the quantum dot material leaked out, and the second mass became less than the first mass.

[0154] Figure 4 This is a schematic diagram illustrating the combined sewer overflow system provided in an embodiment of this disclosure. Figure 4In the diagram, the hollow circle represents the third candidate anomaly detection point A, and the triangles represent the various delivery points corresponding to the third candidate anomaly detection point A. Quantum dot material delivered from delivery point B is detected at the third candidate anomaly detection point A. Delivery point B and the third candidate anomaly detection point A are of the same type, and the second mass of the quantum dot material is less than its first mass. This indicates that rainwater and sewage mixing has occurred between delivery point B and the third candidate anomaly detection point A. Because of this rainwater and sewage mixing, the quantum dot material is diluted, resulting in a second mass less than its first mass.

[0155] Figure 5 This is a schematic diagram illustrating a combined sewer overflow and damaged pipe configuration as provided in an embodiment of this disclosure. Figure 5 In the diagram, the hollow circle represents the third candidate anomaly detection point A, the triangles represent the delivery points corresponding to the third candidate anomaly detection point A, and "×" indicates the damage location D. Quantum dot material delivered to delivery point B is detected at the third candidate anomaly detection point A. Delivery point B and the third candidate anomaly detection point A are of the same type, and the second mass of the quantum dot material is less than the first mass, and the difference between the first mass and the second mass exceeds a preset threshold. This confirms that a pipe rupture and rainwater / sewage mixing have occurred between delivery point B and the third candidate anomaly detection point A. Due to the pipe rupture and rainwater / sewage mixing between delivery point B and the third candidate anomaly detection point A, the quantum dot material is lost and diluted, resulting in a second mass that is significantly less than the first mass.

[0156] In one possible implementation, determining at least one candidate anomaly detection point based on the drainage network type, rainfall conditions in the area where the drainage network is located, and time series data of at least one water quality indicator or flow rate corresponding to multiple monitoring points in the drainage network includes: when the network type is a stormwater network and the rainfall in the area where the stormwater network is located does not meet a preset rainfall threshold, for any given monitoring point, determining the median of a first target water quality indicator corresponding to that monitoring point based on the time series data of that first target water quality indicator; when the median of the first target water quality indicator meets a fifth preset condition, determining that monitoring point as a candidate anomaly detection point; when the network type is a sewage network and the rainfall in the area where the sewage network is located meets a preset rainfall threshold, for any given monitoring point, determining the trend of each water quality indicator time series data in the at least two correlated water quality indicator time series data corresponding to that monitoring point. Analysis results: If the trend analysis results of at least two correlated water quality index time series data corresponding to the monitoring point meet the sixth preset condition, the monitoring point is determined as a candidate anomaly detection point; If the pipe network type is a sewage pipe network and the rainfall in the area where the sewage pipe network is located within a preset time period does not meet the preset rainfall threshold, for any monitoring point, the first target flow time series data corresponding to the monitoring point and the second target flow time series data corresponding to the monitoring point adjacent upstream of the monitoring point are determined; If the first target flow time series data and the second target flow time series data meet the seventh preset condition, the monitoring point is determined as a candidate anomaly detection point; If the pipe network type is a rainwater pipe network and the rainfall in the area where the rainwater pipe network is located within a preset time period meets the preset rainfall threshold, for any monitoring point, the third target flow time series data and the second target water quality index time series data corresponding to the monitoring point, as well as the fourth target flow time series data and the third target water quality index time series data corresponding to the monitoring point adjacent upstream of the monitoring point are determined;

[0157] If the time series data of the third target flow rate, the time series data of the second target water quality index, the time series data of the fourth target flow rate, and the time series data of the third target water quality index meet the eighth preset condition, the monitoring point is determined as a candidate anomaly detection point.

[0158] The preset duration can be set according to actual application conditions, such as 3 days or 5 days. The preset rainfall threshold can also be set according to actual application conditions, for example, 0.1-1 mm. Meeting the preset rainfall threshold requires rainfall greater than that threshold. Not meeting the preset rainfall threshold requires rainfall not greater than that threshold.

[0159] If the rainfall in the area where the stormwater drainage network is located does not meet the preset rainfall threshold within a preset time period, monitoring values ​​of the first target water quality indicator can be obtained at monitoring points according to a preset collection frequency. The obtained monitoring values ​​of the first target water quality indicator are then arranged in time series to obtain time series data of the first target water quality indicator. For example, the first target water quality indicator could be ammonia nitrogen or chemical oxygen demand, etc.

[0160] In this embodiment, the median of each monitoring value in the time series data composed of the first target water quality indicator can be calculated. The median satisfies a fifth preset condition if it is greater than a preset first concentration threshold. If the median satisfies the fifth preset condition, the monitoring point corresponding to the time series data of the first target water quality indicator is determined as a candidate anomaly detection point.

[0161] If the rainfall in the area where the sewage pipe network is located meets the preset rainfall threshold within a preset time period, at least two correlated water quality indicators can be acquired at monitoring points according to a preset collection frequency, resulting in time series data of at least two correlated water quality indicators. Here, correlated water quality indicators can be those in the drainage pipe network that have an inherent relationship of mutual influence, interdependence, or joint response to external factors. When one water quality indicator changes, another one or more water quality indicators will also undergo predictable and regular changes. For example, correlated water quality indicators could be conductivity and chemical oxygen demand, or conductivity and ammonia nitrogen, or conductivity and water temperature. Specific methods for determining correlation can include the Pearson correlation coefficient method, etc., without specific limitations.

[0162] In this embodiment, the Tylsen slope or average slope of the time series data for each water quality indicator can be determined. The Tylsen slope or average slope is used as the trend analysis result. The sixth preset condition can be that the time series data of correlated water quality indicators have the same trend analysis result. That is, the time series data of correlated water quality indicators all show an upward trend, a downward trend, or a stable trend. If the trend analysis results of at least two correlated water quality indicator time series data corresponding to a monitoring point meet the sixth preset condition, the monitoring point is determined as a candidate anomaly detection point.

[0163] If the rainfall in the area where the sewage pipe network is located does not meet the preset rainfall threshold within a preset time period, flow data can be acquired at the monitoring point and its upstream adjacent monitoring point at a preset collection frequency. This yields the first target flow time series data for the monitoring point and the second target flow time series data for the upstream adjacent monitoring point. The Tylsen slope or average slope of the first and second target flow time series data can be determined separately and used as the flow trend analysis result. The seventh preset condition allows for identical flow trend analysis results for the monitoring point and its upstream adjacent monitoring point. That is, the first and second target flow time series data for each monitoring point and its upstream adjacent monitoring point both show an upward trend, a downward trend, or a stable trend. If the flow trend analysis results for each monitoring point and its upstream adjacent monitoring point meet the seventh preset condition, the monitoring point is designated as a candidate anomaly detection point.

[0164] If the rainfall in the area where the stormwater drainage network is located meets the preset rainfall threshold within a preset time period, flow data and target water quality indicators are acquired at the monitoring point and its upstream adjacent monitoring point according to a preset collection frequency. This yields the third target flow time series data and the second target water quality indicator time series data for that monitoring point, as well as the fourth target indicator time series data and the third target water quality indicator time series data for the upstream adjacent monitoring point. The second and third target water quality indicators are the same, with suspended solids being preferred. The Tylsen slope or average slope of the second and third target water quality indicator time series data can be determined separately. The Tylsen slope or average slope of the third and fourth flow time series data is used as the flow trend analysis result. The Tylsen slope or average slope of the second and third target water quality indicator time series data is used as the concentration trend analysis result of the target water quality indicator time series data.

[0165] The eighth preset condition is that the flow trend analysis results of the monitoring point and its upstream adjacent monitoring point are the same, and their corresponding concentration trend analysis results are also the same. If the flow trend analysis results of the monitoring point and its upstream adjacent monitoring point are the same, and their concentration trend analysis results are also the same, then the monitoring point is identified as a candidate anomaly detection point.

[0166] It should be noted that the Tylsen slope and average slope in the embodiments of this disclosure are only examples for ease of understanding, and other feature values ​​that represent the trend analysis results of numerical time series data can also be used.

[0167] In this embodiment of the disclosure, candidate anomaly detection points can be effectively identified under different pipeline network types and rainfall conditions, thereby improving the effectiveness of identifying candidate anomaly detection points.

[0168] In one possible implementation, multiple delivery points located within a preset range upstream of each candidate anomaly detection point are determined, including: for the mixed rainwater and sewage connection, multiple delivery points of different types from the candidate anomaly detection points are determined within the preset range; for the pipeline damage, multiple delivery points of the same type as the candidate anomaly detection points are determined within the preset range.

[0169] When a pipeline anomaly has been identified and further anomaly localization is required, a delivery point of the same type can be determined upstream of the candidate anomaly detection point. This standardizes the type of delivery point corresponding to the candidate anomaly detection point before detecting quantum dot material. During subsequent localization, it's unnecessary to analyze whether the delivery point type matches the candidate anomaly detection point type; as long as quantum dot material is detected, the anomaly can be directly located. This improves anomaly localization efficiency.

[0170] In one possible implementation, the background spectral information of the water body at the release point is determined; candidate quantum dot materials whose spectral information differs from the background spectral information are then identified as the quantum dot material.

[0171] In this embodiment, background spectral information of the water at the injection point can be obtained. Background spectral information and spectral information refer to the same type, both including characteristic fluorescence emission peaks. Therefore, spectral information of multiple candidate quantum dot materials can be obtained, and candidate quantum dot materials whose spectral information differs from the background spectral information are selected as the quantum dot materials in this disclosure.

[0172] For example, the background spectral information at the release point A is 500nm. 500nm refers to the characteristic peak of pollutant fluorescence emission in the water at release point A. However, the characteristic peak has a half-width, so the entire fluorescence emission spectrum may be relatively wide. Therefore, it is more reliable to select quantum dot materials whose fluorescence emission peak is far from 500nm. Thus, quantum dot materials with the central peak position of the characteristic peak of fluorescence emission wavelength between 300nm and 400nm can be selected.

[0173] In this embodiment, the spectral information of the quantum dot material differs from the background spectral information of the water at the point of release. This allows for more sensitive detection of the quantum dot material at candidate anomaly detection points, improving the accuracy and sensitivity of identifying and detecting target analytical indicators of the quantum dot material.

[0174] Figure 6 A schematic diagram of the drainage pipe network anomaly detection device provided in an embodiment of this disclosure. The device 20 includes:

[0175] The candidate anomaly detection point determination unit 21 is used to determine at least one candidate anomaly detection point based on the type of the drainage pipe network, the rainfall in the area where the drainage pipe network is located, and the time series data of at least one water quality indicator or flow rate corresponding to multiple monitoring points in the drainage pipe network.

[0176] The quantum dot delivery unit 22 is used to determine multiple delivery points located within a preset range upstream of each candidate anomaly detection point, and to deliver different types of quantum dot materials to each delivery point corresponding to each candidate anomaly detection point, wherein the spectral information of the different types of quantum dot materials delivered to each delivery point is different.

[0177] The target analysis index time series data determination unit 23 is used to obtain the target analysis index of the quantum dot material deployed at each of the deployment points using spectral detection equipment deployed at at least some of the candidate anomaly detection points, and to obtain the target analysis index time series data of each quantum dot material corresponding to each of the at least some candidate anomaly detection points; wherein, the target analysis index includes at least one of concentration, mass and spectral information.

[0178] The abnormal location and abnormality determination unit 24 is used to determine the abnormal location and abnormality of the drainage network based on the type of at least one delivery point corresponding to each of the at least some candidate abnormality detection points and the time series data of the target analysis index of at least one quantum dot material.

[0179] In one possible implementation, the anomaly location and anomaly degree determination unit 24 is further configured to:

[0180] When multiple candidate anomaly detection points have an upstream and downstream adjacent position relationship, the spectral detection device is deployed at the upstream candidate anomaly detection point among the multiple candidate anomaly detection points; wherein, the upstream and downstream adjacent position relationship means that, based on the water flow direction in the drainage pipe network, any candidate anomaly detection point is located upstream or downstream of another candidate anomaly detection point, and the two candidate anomaly detection points are directly adjacent to each other, with no other candidate anomaly detection points between them.

[0181] In one possible implementation, the at least some candidate anomaly detection points include: a first candidate anomaly detection point, and the anomaly location and anomaly degree determination unit 24 is further configured to:

[0182] If the time series data of the target analysis index of at least one quantum dot material corresponding to the first candidate anomaly detection point meets the first preset condition, and the type of the deployment point corresponding to the at least one quantum dot material is different from the type of the first candidate anomaly detection point, it is determined that a first pipe section between the first candidate anomaly detection point and the monitoring point adjacent to the first candidate anomaly detection point upstream has a rainwater and sewage mixing, and the anomaly location includes: the first pipe section.

[0183] In one possible implementation, the time series data of the target analytical indicators of multiple quantum dot materials corresponding to the first candidate anomaly detection point all satisfy a first preset condition, wherein the target analytical indicator is concentration, and the device 20 further includes:

[0184] The first quantum dot concentration time series data determination unit is used to determine the concentration of the multiple quantum dot materials at the first candidate anomaly detection point based on the spectral detection device, and obtain multiple first quantum dot concentration time series data corresponding to the first candidate anomaly detection point;

[0185] The first detection quality determination unit is used to obtain the first detection quality corresponding to the various quantum dot materials at the first candidate anomaly detection point based on the flow rate, pipe diameter, time series data of multiple first quantum dot concentrations at the first candidate anomaly detection point and the detection frequency of the spectral detection device.

[0186] The main source of contamination determination unit is used to determine the main source of contamination of rainwater and sewage from each of the various quantum dot materials based on each of the first detection quality.

[0187] In one possible implementation, the anomaly level includes the degree of crossover, and the anomaly location and anomaly level determination unit 24 is further configured to:

[0188] Based on the first detection quality, determine the quantum dot detection ratio corresponding to each first candidate abnormal detection point;

[0189] Based on the first detection quality and the time series data of the first quantum dot concentration, the absolute pollution load corresponding to each first candidate anomaly detection point is determined. The absolute pollution load characterizes the pollution intensity of the mixed connection on the first candidate anomaly detection point.

[0190] Obtain the environmental sensitivity coefficient corresponding to each of the first candidate anomaly detection points;

[0191] Based on the quantum dot detection rate, the absolute pollution load, and the environmental sensitivity coefficient, the cross-connection severity index corresponding to each of the first candidate anomaly detection points is determined;

[0192] Based on the severity index of the cross-connection, the degree of cross-connection in each of the first pipe segments is determined.

[0193] In one possible implementation, the main mixing source location determination unit is further configured to:

[0194] Based on the first input mass and the first detection mass of each of the multiple quantum dot materials detected by the first candidate anomaly detection point, the mass ratio of each of the multiple quantum dot materials is determined.

[0195] The main source of contamination is determined based on the stated mass ratios.

[0196] In one possible implementation, the at least some candidate anomaly detection points include: a second candidate anomaly detection point, and the anomaly location and anomaly degree determination unit 24 is further configured to:

[0197] If the time series data of the target analysis index of at least one quantum dot material corresponding to the second candidate anomaly detection point meets the second preset condition, and the type of the deployment point corresponding to the at least one quantum dot material is the same as the type of the second candidate anomaly detection point, it is determined that a pipe rupture has occurred in the second pipe section between the deployment point corresponding to the at least one quantum dot material and the second candidate anomaly detection point, and the anomaly location includes: the second pipe section;

[0198] The degree of abnormality includes the degree of damage;

[0199] Based on the spectral detection device, the concentrations of various quantum dot materials at the second candidate anomaly detection point are determined, and time series data of multiple second quantum dot concentrations corresponding to the second candidate anomaly detection point are obtained.

[0200] Based on the flow rate, pipe diameter, time series data of multiple second quantum dot concentrations at the second candidate anomaly detection point, and the detection frequency of the spectral detection device, the second detection quality corresponding to the various quantum dot materials at the second candidate anomaly detection point is obtained;

[0201] Based on the second input mass and the second detection mass of each of the multiple quantum dot materials detected at each of the second candidate anomaly detection points, the degree of damage to each of the second pipe segments is determined.

[0202] In one possible implementation, the at least some candidate anomaly detection points include: a third candidate anomaly detection point, and the anomaly location and anomaly degree determination unit 24 is further configured to:

[0203] If the time series data of the target analysis index of at least one quantum dot material corresponding to the third candidate anomaly detection point meets the third preset condition, and the type of the deployment point corresponding to the at least one quantum dot material is the same as the type of the third candidate anomaly detection point, the first data of the target analysis index at the deployment point corresponding to the at least one quantum dot material is obtained.

[0204] If the first data of the target analysis index at the delivery point corresponding to the at least one quantum dot material and the time series data of the target analysis index of the at least one quantum dot material corresponding to the third candidate anomaly detection point satisfy the fourth preset condition, it is determined that a pipe rupture and / or rainwater and sewage mixing has occurred in the third pipe section between the third candidate anomaly detection point and the delivery point corresponding to the at least one quantum dot material, and the anomaly location includes: the third pipe section.

[0205] In one possible implementation, the candidate anomaly detection point determination unit 21 is further configured to:

[0206] When the pipe network type is a rainwater pipe network and the rainfall in the area where the rainwater pipe network is located does not meet the preset rainfall threshold within a preset time period, for any monitoring point, the median of the first target water quality index corresponding to the monitoring point is determined based on the time series data of the first target water quality index corresponding to the monitoring point.

[0207] If the median of the first target water quality index meets the fifth preset condition, the monitoring point is determined as a candidate anomaly detection point;

[0208] When the pipeline type is a sewage pipeline and the rainfall in the area where the sewage pipeline is located meets the preset rainfall threshold within a preset time period, for any monitoring point, based on the time series data of at least two correlated water quality indicators corresponding to the monitoring point, the trend analysis result of each water quality indicator time series data in the at least two correlated water quality indicator time series data is determined respectively.

[0209] If the trend analysis results of at least two correlated water quality index time series data corresponding to the monitoring point meet the sixth preset condition, the monitoring point is determined as a candidate anomaly detection point.

[0210] When the pipeline type is a sewage pipeline and the rainfall in the area where the sewage pipeline is located does not meet the preset rainfall threshold within a preset time period, for any monitoring point, the first target flow time series data corresponding to the monitoring point and the second target flow time series data corresponding to the monitoring point adjacent to the upstream of the monitoring point are determined.

[0211] If the first target traffic flow time series data and the second target traffic flow time series data meet the seventh preset condition, the monitoring point is determined as a candidate anomaly detection point;

[0212] When the pipe network type is a rainwater pipe network and the rainfall in the area where the rainwater pipe network is located meets the preset rainfall threshold within a preset time period, for any monitoring point, the third target flow time series data and the second target water quality index time series data corresponding to the monitoring point are determined, as well as the fourth target flow time series data and the third target water quality index time series data corresponding to the monitoring point adjacent to the upstream of the monitoring point.

[0213] If the time series data of the third target flow rate, the time series data of the second target water quality index, the time series data of the fourth target flow rate, and the time series data of the third target water quality index meet the eighth preset condition, the monitoring point is determined as a candidate anomaly detection point.

[0214] 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.

[0215] 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.

[0216] This disclosure also provides a non-volatile computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0217] This disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described method.

[0218] Figure 7 This is a schematic diagram of an electronic device for detecting anomalies in a drainage pipe network, provided in an embodiment of this disclosure. For example, device 1900 can be provided as a server or terminal device. (Refer to...) Figure 7 The apparatus 1900 includes a processing component 1922, which further includes one or more processors, and memory resources represented by memory 1932 for storing instructions, such as application programs, that can be executed by the processing component 1922. 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.

[0219] Device 1900 may also include a power supply component 1926 configured to perform power management of device 1900, a wired or wireless network interface 1950 configured to connect device 1900 to a network, and an input / output interface 1958 (I / O interface). Device 1900 can operate on an operating system, such as Windows Server, stored in memory 1932. TM macOS X TM Unix TM Linux TM FreeBSD TM Or similar.

[0220] 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 the device 1900 to perform the above-described method.

[0221] 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.

[0222] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, and are not 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 detecting anomalies in a drainage pipe network, characterized in that, The method includes: Based on the type of drainage network, the rainfall in the area where the drainage network is located, and the time series data of at least one water quality indicator or flow rate corresponding to multiple monitoring points in the drainage network, at least one candidate anomaly detection point is determined. Multiple delivery points are determined within a preset range upstream of each candidate anomaly detection point, and different types of quantum dot materials are delivered to each delivery point corresponding to each candidate anomaly detection point, wherein the spectral information of the different types of quantum dot materials delivered to each delivery point is different. Using spectral detection equipment deployed at at least some of the candidate anomaly detection points, the target analysis index of the quantum dot material deployed at each of the deployment points is obtained, and time series data of the target analysis index of each quantum dot material corresponding to each of the at least some candidate anomaly detection points are obtained; wherein, the target analysis index includes at least one of concentration, mass and spectral information; Based on the type of at least one delivery point corresponding to each of the at least some candidate anomaly detection points and the time series data of the target analysis index of at least one quantum dot material corresponding to each candidate anomaly detection point, the location and degree of anomaly of the drainage network are determined.

2. The method according to claim 1, characterized in that, The method of utilizing spectral detection equipment deployed at at least some candidate anomaly detection points includes: When multiple candidate anomaly detection points have an upstream and downstream adjacent position relationship, the spectral detection device is deployed at the upstream candidate anomaly detection point among the multiple candidate anomaly detection points; wherein, the upstream and downstream adjacent position relationship means that, based on the water flow direction in the drainage pipe network, any candidate anomaly detection point is located upstream or downstream of another candidate anomaly detection point, and the two candidate anomaly detection points are directly adjacent to each other, with no other candidate anomaly detection points between them.

3. The method according to claim 2, characterized in that, The at least some candidate anomaly detection points include: a first candidate anomaly detection point. The step of determining the anomaly location of the drainage network based on the type of at least one delivery point corresponding to each of the at least some candidate anomaly detection points and the time series data of the target analysis indicators of at least one quantum dot material corresponding to each of the at least some candidate anomaly detection points includes: If the time series data of the target analysis index of at least one quantum dot material corresponding to the first candidate anomaly detection point meets the first preset condition, and the type of the deployment point corresponding to the at least one quantum dot material is different from the type of the first candidate anomaly detection point, it is determined that a first pipe section between the first candidate anomaly detection point and the monitoring point adjacent to the first candidate anomaly detection point upstream has a rainwater and sewage mixing, and the anomaly location includes: the first pipe section.

4. The method according to claim 3, characterized in that, In the first candidate anomaly detection point, the time series data of the target analysis index of various quantum dot materials all meet the first preset condition, wherein the target analysis index is concentration, and the method further includes: Based on the spectral detection device, the concentration of the various quantum dot materials at the first candidate anomaly detection point is determined, and time series data of the concentration of multiple first quantum dots corresponding to the first candidate anomaly detection point are obtained. Based on the flow rate, pipe diameter, time series data of multiple first quantum dot concentrations at the first candidate anomaly detection point, and the detection frequency of the spectral detection device, the first detection quality corresponding to the various quantum dot materials at the first candidate anomaly detection point is obtained; Based on the first detection quality, the main source of rainwater and sewage mixing is determined from each of the various quantum dot materials at their respective delivery points.

5. The method according to claim 4, characterized in that, The degree of abnormality includes the degree of cross-connection. Determining the degree of abnormality of the drainage network includes: Based on the first detection quality, determine the quantum dot detection ratio corresponding to each first candidate abnormal detection point; Based on the first detection quality and the time series data of the first quantum dot concentration, the absolute pollution load corresponding to each first candidate anomaly detection point is determined. The absolute pollution load characterizes the pollution intensity of the mixed connection on the first candidate anomaly detection point. Obtain the environmental sensitivity coefficient corresponding to each of the first candidate anomaly detection points; Based on the quantum dot detection rate, the absolute pollution load, and the environmental sensitivity coefficient, the cross-connection severity index corresponding to each of the first candidate anomaly detection points is determined; Based on the severity index of the cross-connection, the degree of cross-connection in each of the first pipe segments is determined.

6. The method according to claim 4, characterized in that, The step of determining the main source of rainwater and sewage mixing from each of the various quantum dot materials' application points based on the first detection quality includes: Based on the first input mass and the first detection mass of each of the multiple quantum dot materials detected by the first candidate anomaly detection point, the mass ratio of each of the multiple quantum dot materials is determined. The main source of contamination is determined based on the stated mass ratios.

7. The method according to claim 1, characterized in that, The at least some candidate anomaly detection points include: second candidate anomaly detection points. The step of determining the anomaly location and degree of anomaly in the drainage network based on the type of at least one delivery point corresponding to each of the at least some candidate anomaly detection points and the time series data of the target analysis indicators of at least one quantum dot material corresponding to each of the at least some candidate anomaly detection points includes: If the time series data of the target analysis index of at least one quantum dot material corresponding to the second candidate anomaly detection point meets the second preset condition, and the type of the deployment point corresponding to the at least one quantum dot material is the same as the type of the second candidate anomaly detection point, it is determined that a pipe rupture has occurred in the second pipe section between the deployment point corresponding to the at least one quantum dot material and the second candidate anomaly detection point, and the anomaly location includes: the second pipe section; The degree of abnormality includes the degree of damage; Based on the spectral detection device, the concentrations of various quantum dot materials at the second candidate anomaly detection point are determined, and time series data of multiple second quantum dot concentrations corresponding to the second candidate anomaly detection point are obtained. Based on the flow rate, pipe diameter, time series data of multiple second quantum dot concentrations at the second candidate anomaly detection point, and the detection frequency of the spectral detection device, the second detection quality corresponding to the various quantum dot materials at the second candidate anomaly detection point is obtained; Based on the second input mass and the second detection mass of each of the multiple quantum dot materials detected at each of the second candidate anomaly detection points, the degree of damage to each of the second pipe segments is determined.

8. The method according to claim 1, characterized in that, The at least some candidate anomaly detection points include: a third candidate anomaly detection point. The step of determining the anomaly location of the drainage network based on the type of at least one delivery point corresponding to each of the at least some candidate anomaly detection points and the time series data of the target analysis indicators of at least one quantum dot material corresponding to each of the at least some candidate anomaly detection points includes: If the time series data of the target analysis index of at least one quantum dot material corresponding to the third candidate anomaly detection point meets the third preset condition, and the type of the deployment point corresponding to the at least one quantum dot material is the same as the type of the third candidate anomaly detection point, the first data of the target analysis index at the deployment point corresponding to the at least one quantum dot material is obtained. If the first data of the target analysis index at the delivery point corresponding to the at least one quantum dot material and the time series data of the target analysis index of the at least one quantum dot material corresponding to the third candidate anomaly detection point satisfy the fourth preset condition, it is determined that a pipe rupture and / or rainwater and sewage mixing has occurred in the third pipe section between the third candidate anomaly detection point and the delivery point corresponding to the at least one quantum dot material, and the anomaly location includes: the third pipe section.

9. The method according to claim 1, characterized in that, The step of determining at least one candidate anomaly detection point based on the drainage network type, the rainfall conditions in the area where the drainage network is located, and time series data of at least one water quality indicator or flow rate corresponding to multiple monitoring points in the drainage network includes: When the pipe network type is a rainwater pipe network and the rainfall in the area where the rainwater pipe network is located does not meet the preset rainfall threshold within a preset time period, for any monitoring point, the median of the first target water quality index corresponding to the monitoring point is determined based on the time series data of the first target water quality index corresponding to the monitoring point. If the median of the first target water quality index meets the fifth preset condition, the monitoring point is determined as a candidate anomaly detection point; When the pipeline type is a sewage pipeline and the rainfall in the area where the sewage pipeline is located meets the preset rainfall threshold within a preset time period, for any monitoring point, based on the time series data of at least two correlated water quality indicators corresponding to the monitoring point, the trend analysis result of each water quality indicator time series data in the at least two correlated water quality indicator time series data is determined respectively. If the trend analysis results of at least two correlated water quality index time series data corresponding to the monitoring point meet the sixth preset condition, the monitoring point is determined as a candidate anomaly detection point. When the pipeline type is a sewage pipeline and the rainfall in the area where the sewage pipeline is located does not meet the preset rainfall threshold within a preset time period, for any monitoring point, the first target flow time series data corresponding to the monitoring point and the second target flow time series data corresponding to the monitoring point adjacent to the upstream of the monitoring point are determined. If the first target traffic flow time series data and the second target traffic flow time series data meet the seventh preset condition, the monitoring point is determined as a candidate anomaly detection point; When the pipe network type is a rainwater pipe network and the rainfall in the area where the rainwater pipe network is located meets the preset rainfall threshold within a preset time period, for any monitoring point, the third target flow time series data and the second target water quality index time series data corresponding to the monitoring point are determined, as well as the fourth target flow time series data and the third target water quality index time series data corresponding to the monitoring point adjacent to the upstream of the monitoring point. If the time series data of the third target flow rate, the time series data of the second target water quality index, the time series data of the fourth target flow rate, and the time series data of the third target water quality index meet the eighth preset condition, the monitoring point is determined as a candidate anomaly detection point.

10. 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 9.

Images