Sewage pipe network defect screening and early warning method based on online monitoring data

Abstract

The invention relates to the technical field of sewage pipe network damage partition screening, and discloses a sewage pipe network defect screening and early warning method based on online monitoring data. According to the method, firstly, monitoring points are divided on a sewage pipe network, online flow, water quality and water depth data of each point are collected in real time, and a flow matrix and a water quality concentration matrix are obtained through Gaussian noise reduction preprocessing; calculating a pollutant load matrix and a daily weighted average concentration matrix of each monitoring point; determining a topological relation matrix, and calculating daily flow, pollutant load and weighted average concentration difference matrix of the pipe sections between the adjacent monitoring points in combination with the flow and pollutant load matrix; and finally, according to the difference value matrixes and daily average water depth data, the types of defects such as infiltration, exosmosis and sedimentation of the sewage pipe section are judged, early warning is performed, and rapid and accurate screening of the damage and sedimentation conditions of the sewage pipe network is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of sewage pipe network damage zoning screening, and in particular to a sewage pipe network defect screening and early warning method based on online monitoring data. Background Art

[0002] Drainage pipe networks constitute a key part of urban drainage systems, and their stable operation is crucial to ensuring urban public safety. However, due to aging pipes and environmental factors, drainage pipe networks often suffer from structural defects caused by damage and functional defects caused by siltation. This not only leads to large-scale groundwater infiltration, but also reduces the efficiency of sewage transportation and may even pose a threat to public safety. Therefore, urban drainage systems must be able to detect and repair defective points in a timely manner. Traditional closed-circuit television imaging detection methods, while effective, are limited by their high cost and the need to shut off water supply. Despite advances in new technologies such as robotics, their high cost and operational complexity make their popularization and application in practical work challenging.

[0003] Therefore, it is necessary to design a sewage pipe network defect screening and early warning method based on online monitoring data to solve the problems existing in current technology. Summary of the Invention

[0004] In view of this, the present invention proposes a sewage pipe network defect screening and early warning method based on online monitoring data, aiming to solve the problem that it is difficult to quickly and accurately screen sewage pipe network defects in current technology.

[0005] The present invention proposes a sewage pipe network defect screening and early warning method based on online monitoring data, which is characterized by comprising the following steps:

[0006] A number of monitoring points are divided on the target sewage pipe network, and online flow data, water quality data and water depth data of each monitoring point are collected in real time. After Gaussian noise reduction preprocessing, the online flow matrix Q, online water quality concentration matrix C and online water depth matrix H are obtained;

[0007] According to the online flow data and water quality data, the pollutant load matrix L and the daily weighted average concentration matrix sum (C j );

[0008] Determine the topological relationship matrix T of each monitoring point, combine the online flow matrix Q and the pollutant load matrix L, and calculate the daily flow difference matrix sum (ΔQ j ), daily pollutant load difference matrix sum(ΔL j ) and the daily weighted average concentration difference matrix sum(ΔC j );

[0009] According to the daily flow difference matrix sum(ΔQ j ), daily pollutant load difference matrix sum(ΔL j ) and the daily weighted average concentration difference matrix sum(ΔC j ), determining the defect type of the sewage pipe section, wherein the defect type includes infiltration, exfiltration, and siltation;

[0010] Combined with the average daily water depth Data can be used to determine the defect type of the sewage network and issue early warnings.

[0011] Furthermore, after Gaussian noise reduction preprocessing, the online flow matrix Q, the online water quality concentration matrix C and the online water depth matrix H are obtained, including: the online flow matrix Q is:

[0012]

[0013] The online water quality concentration matrix C is:

[0014]

[0015] The online water depth matrix H is:

[0016]

[0017] Where m represents the number of online monitoring data;

[0018] n is the number of monitoring points.

[0019] Furthermore, during the Gaussian noise reduction preprocessing, the following steps are performed: selecting an appropriate kernel width σ to calculate the Gaussian weight ω ij , use Gaussian weights to perform weighted averaging on each data point to obtain a new denoised matrix value.

[0020] Furthermore, the pollutant load matrix L and the daily weighted average concentration matrix sum(C j ), including:

[0021] The pollutant load matrix L is composed of L ij =Q ij ·C ij Calculated;

[0022] The pollutant load matrix L is:

[0023]

[0024] Where m represents the number of online monitoring data;

[0025] n is the number of monitoring points;

[0026] Daily weighted average concentration matrix sum(C j ),Depend on Calculated;

[0027] Wherein, j represents the jth monitoring point, j = 1, 2,…, n.

[0028] Furthermore, when determining the topological relationship matrix T of each monitoring point, the topological relationship matrix T is obtained according to the actual topological relationship between the monitoring points, and the element T ij The values ​​are:

[0029]

[0030] The dimension of the topological relationship matrix T is (n, n-1).

[0031] Furthermore, the daily flow difference matrix sum(ΔQ j ), daily pollutant load difference matrix sum(ΔL j ) and the daily weighted average concentration difference matrix sum(ΔC j ), including:

[0032] The flow difference matrix ΔQ is calculated by ΔQ=Q·T;

[0033] The pollutant load difference matrix ΔL is calculated by ΔL=L·T;

[0034] The weighted average concentration difference matrix sum(ΔC j ) is calculated from sum(ΔC j )=sum(C j )·T is calculated;

[0035] The daily flow difference matrix, daily pollutant load difference matrix and daily pollutant concentration difference matrix are sum(ΔQ j )、sum(ΔL j )、sum(ΔC j );

[0036] Where j = 1, 2,…, n-1.

[0037] Furthermore, when judging the defect type of the sewage pipe section, it includes: presetting the defect threshold of the sewage pipe section as D j ;

[0038] When sum(ΔQ j )>0,sum(ΔL j )>0 and sum(ΔC j)≥0, it means that the daily pollution load and the daily weighted average concentration of pollutants in the sewage pipe section between two adjacent monitoring points increase, and it is judged that the sewage pipe section is operating normally. The defect threshold value D of the sewage pipe section is j is 0;

[0039] When sum(ΔQ j )>0,sum(ΔL j )>0 and sum(ΔC j )<0, it means that the daily pollution load of the sewage pipe section between two adjacent monitoring points increases while the daily weighted average concentration of pollutants decreases, and it is judged that the sewage pipe section has the risk of external water inflow and infiltration caused by damage. The defect threshold value D of the sewage pipe section is j is -1;

[0040] When sum(ΔQ j )<0, it is judged that the sewage pipe section between two adjacent monitoring points has the risk of sewage leakage caused by damage, and the defect threshold value D of the sewage pipe section is j is -2.

[0041] Furthermore, when the daily pollution load of the sewage pipe section between the two adjacent monitoring points decreases, it includes: when sum(ΔQ j )>0 and sum(ΔL j )<0, it means that there is a risk of functional defects caused by siltation in the sewage pipe section between two adjacent monitoring points. j Indicated by -3.

[0042] Furthermore, combined with the daily average water depth Data, to determine the type of defects in the sewage network and issue early warnings, including: the average daily water depth where j = 1, 2, ..., n;

[0043] When the water depth in the pipeline When the pipeline is blocked, it is determined that there are functional defects caused by siltation, an early warning is issued, and an instruction to dredge the pipeline is issued;

[0044] When the pipeline appears When the risk of external water inflow and infiltration due to damage is determined, an early warning prompt is issued and an instruction for damage detection is issued;

[0045] When the water depth in the pipeline is lower than the water depth at the upstream point When a damage occurs, it is determined that there is a risk of sewage leakage, an early warning is issued, and an instruction to conduct damage detection is issued.

[0046] Compared with the existing technology, the beneficial effect of the present invention is that the present invention provides a sewage pipe network defect screening and early warning method based on online monitoring data, which effectively improves the accuracy and reliability of the data by real-time monitoring of the water volume and water quality data of each monitoring point in the sewage pipe network, combined with Gaussian noise reduction preprocessing technology. By calculating the pollutant load matrix L, we can quantify the pollutant load of each monitoring point, providing a basis for further analysis. At the same time, using the topological relationship matrix T, we consider the actual connection between the monitoring points, making the analysis closer to reality. When calculating the daily flow difference matrix sum (ΔQ j ), daily pollutant load difference matrix sum(ΔL j ) and the daily weighted average concentration difference matrix sum(ΔC j ), the changes in sewage flow, pollutant load and concentration are comprehensively considered, so as to more accurately reflect the structural defects caused by damage and functional defects caused by siltation in the pipe network. This method not only improves the accuracy and efficiency of damage and siltation screening, but also reduces costs and provides a strong guarantee for the safe operation of urban drainage systems.

[0047] The present invention provides a sewage pipe network defect screening and early warning method based on online monitoring data. Through real-time monitoring, data preprocessing, matrix calculation and risk assessment, it can achieve rapid and accurate screening of sewage pipe network damage and siltation.

[0048] The foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

[0049] Other features and aspects of the present disclosure will become more apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0051] Figure 1 A flow chart of a sewage pipe network defect screening and early warning method based on online monitoring data provided by an embodiment of the present invention;

[0052] Figure 2 This is a sewage pipe network defect distribution diagram according to an embodiment of the present invention. DETAILED DESCRIPTION

[0053] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, unless there is a conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0054] Reference Figure 1 and Figure 2 In some embodiments of the present application, a sewage pipe network defect screening and early warning method based on online monitoring data is characterized by comprising the following steps:

[0055] Step S1: A number of monitoring points are divided on the target sewage network. The online flow data, water quality data, and water depth data of each monitoring point are collected in real time. After Gaussian noise reduction preprocessing, the online flow matrix Q, the online water quality concentration matrix C, and the online water depth matrix H are obtained.

[0056] Step S2: Calculate the pollutant load matrix L and the daily weighted average concentration matrix sum(C j );

[0057] Step S3: Determine the topological relationship matrix T of each monitoring point, combine the online flow matrix Q and the pollutant load matrix L, and calculate the daily flow difference matrix sum (ΔQ j ), daily pollutant load difference matrix sum(ΔL j ) and the daily weighted average concentration difference matrix sum(ΔC j );

[0058] Step S4: According to the daily flow difference matrix sum(ΔQ j ), daily pollutant load difference matrix sum(ΔL j ) and the daily weighted average concentration difference matrix sum(ΔC j ) to determine the defect type of the sewage pipe section, including infiltration, exfiltration, and siltation;

[0059] Step S5: Combined with the daily average water depth Data can be used to determine the defect type of the sewage network and issue early warnings.

[0060] In this embodiment, the online flow matrix Q and the online water quality concentration matrix C in step S1 are updated in real time by the online flow Q of the six monitoring points. ijand COD concentration C ij Data composition: Online data is collected every 5 minutes and pre-processed with Gaussian noise reduction. Assuming that the collection time is 24 hours, the dimension is (288, 6).

[0061] The online traffic matrix Q is:

[0062]

[0063] The online COD water quality concentration matrix C is:

[0064]

[0065] The online water depth matrix H is:

[0066]

[0067] Specifically, after Gaussian noise reduction preprocessing, the online flow matrix Q, online water quality concentration matrix C, and online water depth matrix H are obtained, including: the online flow matrix Q is:

[0068]

[0069] The online water quality concentration matrix C is:

[0070]

[0071] The online water depth matrix H is:

[0072]

[0073] Where m represents the number of online monitoring data;

[0074] n is the number of monitoring points.

[0075] In this embodiment, Gaussian noise reduction preprocessing is used to construct an online flow matrix, water quality concentration matrix, and water depth matrix. This not only eliminates data noise to ensure the quality of basic data, but also integrates multi-dimensional operating parameters such as flow, water quality, and water depth in the form of a structured matrix. Combined with the topological relationship, the flow, load, and concentration differences between pipe sections can be accurately calculated, providing a quantitative basis for the subsequent qualitative analysis of defect types, and upgrading the sewage pipe network defect warning from empirical judgment to data-driven precise identification, effectively improving the efficiency and reliability of pipe network damage and siltation screening.

[0076] Specifically, the Gaussian noise reduction preprocessing includes: selecting an appropriate kernel width σ to calculate the Gaussian weight ω ij , use Gaussian weights to perform weighted averaging on each data point to obtain a new denoised matrix value.

[0077] In this embodiment, a Gaussian noise reduction preprocessing method is adopted in which an appropriate kernel width is selected to calculate the Gaussian weight and the data points are subjected to weighted averaging. This method can accurately assign different weights according to the spatial relationship between the data points, and perform targeted filtering on the noise data. While effectively removing random interference factors in the data, it retains the key features and change trends in the original data to the maximum extent, laying a solid foundation for the subsequent in-depth analysis of sewage network flow, water quality concentration, water depth and other data, ensuring that the pollutant load, concentration difference and other results calculated based on these data truly reflect the operation status of the network, thereby improving the accuracy and effectiveness of sewage network defect warning.

[0078] Specifically, the pollutant load matrix L and the daily weighted average concentration matrix sum(C j ), including:

[0079] The pollutant load matrix L is composed of L ij =Q ij ·C ij Calculated;

[0080] The pollutant load matrix L is:

[0081]

[0082] Where m represents the number of online monitoring data;

[0083] n is the number of monitoring points.

[0084] Daily weighted average concentration matrix sum(C j ),Depend on Calculated;

[0085] Wherein, j represents the jth monitoring point, j = 1, 2,…, n.

[0086] Specifically, the pollutant load matrix L is composed of L ij =Q ij ·C ij Calculated, where i represents 6 monitoring points, and the value range is i=1, 2,…, 6; j represents the 24h online monitoring data, and the value range is 1, 2,…, 288.

[0087] The pollutant load matrix L is:

[0088]

[0089] Daily weighted average concentration matrix sum(C j )for:

[0090]

[0091] Specifically, when determining the topological relationship matrix T of each monitoring point, the following steps are included: the topological relationship matrix T is obtained based on the actual topological relationship between the monitoring points, and the element T ij The values ​​are:

[0092]

[0093] Among them, the dimension of the topological relationship matrix T is (n, n-1).

[0094] In this embodiment, by constructing a topological relationship matrix T based on the actual topological relationships between monitoring points, and using clear value selection rules to intuitively reflect the connection status between each monitoring point, the complex spatial structure of the sewage network can be converted into a computer-processable matrix form, allowing topological information such as the connection logic and flow direction of each pipe segment in the network to be accurately quantified. This not only provides a spatial correlation basis for calculating flow rate differences and pollutant load differences between sewage pipe segments between adjacent monitoring points, but also enables rapid analysis of the overall operational status of the pipe network based on matrix operations, greatly improving the efficiency of pipe network defect analysis and facilitating systematic and accurate judgment and early warning of sewage network defect types.

[0095] Specifically, the daily flow difference matrix sum(ΔQ j ), daily pollutant load difference matrix sum(ΔL j ) and the daily weighted average concentration difference matrix sum(ΔC j ), including:

[0096] The flow difference matrix ΔQ is calculated by ΔQ = Q·T;

[0097] The pollutant load difference matrix ΔL is calculated by ΔL = L·T;

[0098] Weighted average concentration difference matrix sum(ΔC j ) is calculated from sum(ΔC j )=sum(C j )·T is calculated;

[0099] The daily flow difference matrix, daily pollutant load difference matrix and daily pollutant concentration difference matrix are sum(ΔQ j )、sum(ΔL j )、sum(ΔC j );

[0100] Where j = 1, 2,…, n-1.

[0101] In this embodiment, the topological relationship matrix T in step S3 is obtained according to the actual topological relationship between the monitoring points, and its dimension is (6, 5).

[0102] The topological relationship matrix T is:

[0103]

[0104] The flow difference matrix ΔQ is:

[0105]

[0106] The pollutant load difference matrix ΔL is:

[0107]

[0108] Specifically, the daily flow difference, daily pollutant load difference matrix and daily pollutant concentration difference are calculated as sum(ΔQ), sum(ΔL j )、sum(ΔC j ), whose dimension is (5,1);

[0109] sum(ΔQ j ) = [44.99 166.31 42.85 165.88 30.53]

[0110] sum(ΔL j ) = [5042.80 27728.26 6674.43 26155.69 -912.57]

[0111] sum(ΔC j )=[-56.13 36.13 33.23 6.51 -22.86].

[0112] Specifically, when judging the defect type of the sewage pipe section, it includes: presetting the defect threshold of the sewage pipe section as D j ;

[0113] When sum(ΔQ j )>0,sum(ΔL j )>0 and sum(ΔC j )≥0, it means that the daily pollution load and the daily weighted average concentration of pollutants in the sewage pipe section between two adjacent monitoring points increase, and the sewage pipe section is judged to be operating normally. The defect threshold value D of the sewage pipe section is j is 0;

[0114] When sum(ΔQ j )>0,sum(ΔL j )>0 and sum(ΔC j )<0, it means that the daily pollution load of the sewage pipe section between two adjacent monitoring points increases while the daily weighted average concentration of pollutants decreases. It is judged that there is a risk of external water inflow and infiltration caused by damage in the sewage pipe section. The defect threshold value of the sewage pipe section is D jis -1;

[0115] When sum(ΔQ j )<0, it is judged that the sewage pipe section between two adjacent monitoring points has the risk of sewage leakage caused by damage, and the defect threshold value D t is -2.

[0116] Specifically, when the daily pollution load of the sewage pipe section between two adjacent monitoring points decreases, it includes: when sum(ΔQ j )>0 and sum(ΔL j )<0, it means that there is a risk of functional defects caused by siltation in the sewage pipe section between two adjacent monitoring points. j Indicated by -3.

[0117] Specifically, for the sum(ΔL j )>0, and sum(ΔC j )<0, indicating that there is a risk of external water inflow and infiltration in the sewage pipe section between two adjacent monitoring points. j It is represented by -1; for the pipe section between monitoring points 5 and 6, the sum (ΔQ j )>0 and sum(ΔL j )<0, indicating that there is a risk of functional defects caused by siltation in the sewage pipe section between two adjacent monitoring points, D j It is represented by -3; the sum of the remaining sewage pipe sections (ΔL j )>0, and sum(ΔC j )>0, indicating that the sewage pipe section is operating normally, D j Indicated by 0.

[0118] Based on this, the defect risk matrix D of the sewage pipe network is obtained as follows:

[0119] D = [-1 0 0 0 -1&-3];

[0120] Specifically, combined with the average daily water depth Data, to determine the type of defects in the sewage network and issue early warnings, including: average daily water depth where j = 1, 2, ..., n;

[0121] When the water depth in the pipeline When the pipeline is blocked, it is determined that there are functional defects caused by siltation, an early warning is issued, and an instruction to dredge the pipeline is issued;

[0122] When the pipeline appears When the risk of external water inflow and infiltration due to damage is determined, an early warning prompt is issued and an instruction for damage detection is issued;

[0123] When the water depth in the pipeline is lower than the water depth at the upstream point When a damage occurs, it is determined that there is a risk of sewage leakage, an early warning is issued, and an instruction to conduct damage detection is issued.

[0124] Specifically, combined with the average daily water depth Determine the defects of each section of the sewage pipe network and the average daily water depth The matrix dimensions are (6,1):

[0125]

[0126] For the pipe sections 1-2 and 5-6 that are at risk of external water inflow and infiltration due to damage, the corresponding pipe sections Therefore, no infiltration warning will be issued for the time being; for pipe sections 5-6 that are determined to have siltation risk, the corresponding pipe sections Therefore, no sedimentation warning will be issued for the time being.

[0127] Compared with the existing technology, the beneficial effect of the present invention is that the present invention provides a sewage pipe network defect screening and early warning method based on online monitoring data, which effectively improves the accuracy and reliability of the data by real-time monitoring of the water volume and water quality data of each monitoring point in the sewage pipe network, combined with Gaussian noise reduction preprocessing technology. By calculating the pollutant load matrix L, we can quantify the pollutant load of each monitoring point, providing a basis for further analysis. At the same time, using the topological relationship matrix T, we consider the actual connection between the monitoring points, making the analysis closer to reality. When calculating the daily flow difference matrix sum (ΔQ j ), daily pollutant load difference matrix sum(ΔL j ) and the daily weighted average concentration difference matrix sum(ΔC j ), the changes in sewage flow, pollutant load and concentration are comprehensively considered, so as to more accurately reflect the structural defects caused by damage and functional defects caused by siltation in the pipe network. This method not only improves the accuracy and efficiency of damage and siltation screening, but also reduces costs and provides a strong guarantee for the safe operation of urban drainage systems.

[0128] The present invention provides a sewage pipe network defect screening and early warning method based on online monitoring data. Through real-time monitoring, data preprocessing, matrix calculation and risk assessment, it can achieve rapid and accurate screening of sewage pipe network damage and siltation.

[0129] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or a combination of software and hardware embodiments. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0130] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0131] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0132] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0133] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A sewage pipe network defect screening and early warning method based on online monitoring data, characterized in that: include: A number of monitoring points are divided on the target sewage pipe network, and online flow data, water quality data and water depth data of each monitoring point are collected in real time. After Gaussian noise reduction preprocessing, the online flow matrix Q, online water quality concentration matrix C and online water depth matrix H are obtained; According to the online flow data and water quality data, the pollutant load matrix L and the daily weighted average concentration matrix sum (C j ); Determine the topological relationship matrix T of each monitoring point, combine the online flow matrix Q and the pollutant load matrix L, and calculate the daily flow difference matrix sum (ΔQ j ), daily pollutant load difference matrix sum(ΔL j ) and the daily weighted average concentration difference matrix sum(ΔC j ); According to the daily flow difference matrix sum(ΔQ j ), daily pollutant load difference matrix sum(ΔL j ) and the daily weighted average concentration difference matrix sum(ΔC j ), determining the defect type of the sewage pipe section, wherein the defect type includes infiltration, exfiltration, and siltation; Combined with the average daily water depth Data can be used to determine the defect type of the sewage network and issue early warnings.

2. The sewage pipe network defect screening and early warning method based on online monitoring data according to claim 1 is characterized in that: After Gaussian noise reduction preprocessing, the online flow matrix Q, online water quality concentration matrix C, and online water depth matrix H are obtained, including: The online traffic matrix Q is: The online water quality concentration matrix C is: The online water depth matrix H is: Where m represents the number of online monitoring data; n is the number of monitoring points.

3. The sewage pipe network defect screening and early warning method based on online monitoring data according to claim 2 is characterized in that: The Gaussian noise reduction preprocessing includes: Choose an appropriate kernel width σ to calculate the Gaussian weight ω ij , use Gaussian weights to perform weighted averaging on each data point to obtain a new denoised matrix value.

4. The sewage pipe network defect screening and early warning method based on online monitoring data according to claim 3 is characterized in that: Calculate the pollutant load matrix L and the daily weighted average concentration matrix sum(C j ), including: The pollutant load matrix L is composed of L ij =Q ij ·C ij Calculated; The pollutant load matrix L is: Where m represents the number of online monitoring data; n is the number of monitoring points; Daily weighted average concentration matrix sum(C j ),Depend on Calculated; Wherein, j represents the jth monitoring point, j = 1, 2,…, n.

5. The sewage pipe network defect screening and early warning method based on online monitoring data according to claim 4 is characterized in that: Determining the topological relationship matrix T of each monitoring point includes: The topological relationship matrix T is obtained according to the actual topological relationship between the monitoring points, and the element T ij The values ​​are: The dimension of the topological relationship matrix T is (n, n-1).

6. The sewage pipe network defect screening and early warning method based on online monitoring data according to claim 5 is characterized in that: Calculate the daily flow difference matrix sum(ΔQ j ), daily pollutant load difference matrix sum(ΔL j ) and the daily weighted average concentration difference matrix sum(ΔC j ), including: The flow difference matrix ΔQ is calculated by ΔQ=Q·T; The pollutant load difference matrix ΔL is calculated by ΔL=L·T; The weighted average concentration difference matrix sum(ΔC j ) is calculated from sum(ΔC j )=sum(C j )·T is calculated; The daily flow difference matrix, daily pollutant load difference matrix and daily pollutant concentration difference matrix are sum(ΔQ j )、sum(ΔL j )、sum(ΔC j ); Where j = 1, 2,…, n-1.

7. The sewage pipe network defect screening and early warning method based on online monitoring data according to claim 6 is characterized in that: When determining the defect type of a sewage pipe section, the following are included: The default defect threshold of the sewage pipe section is D j ; When sum(ΔQ j )>0,sum(ΔL j )>0 and sum(ΔC j )≥0, it means that the daily pollution load and the daily weighted average concentration of pollutants in the sewage pipe section between two adjacent monitoring points increase, and it is judged that the sewage pipe section is operating normally. The defect threshold value D of the sewage pipe section is j is 0; When sum(ΔQ j )>0,sum(ΔL j )>0 and sum(ΔC j )<0, it means that the daily pollution load of the sewage pipe section between two adjacent monitoring points increases while the daily weighted average concentration of pollutants decreases, and it is judged that the sewage pipe section has the risk of external water inflow and infiltration caused by damage. The defect threshold value D of the sewage pipe section is j is -1; When sum(ΔQ j )<0, it is judged that the sewage pipe section between two adjacent monitoring points has the risk of sewage leakage caused by damage, and the defect threshold value D of the sewage pipe section is j is -2.

8. The sewage pipe network defect screening and early warning method based on online monitoring data according to claim 7 is characterized in that: When the daily pollution load of the sewage pipe section between the two adjacent monitoring points decreases, it includes: When sum(ΔQ j )>0 and sum(ΔL j )<0, it means that there is a risk of functional defects caused by siltation in the sewage pipe section between two adjacent monitoring points. j Indicated by -3.

9. The sewage pipe network defect screening and early warning method based on online monitoring data according to claim 8 is characterized in that: Combined with the daily average water depth Data, to determine the type of defects in the sewage network and issue early warnings, including: The average daily water depth where j = 1, 2, ..., n; When the water depth in the pipeline When the pipeline is blocked, it is determined that there are functional defects caused by siltation, an early warning is issued, and an instruction to dredge the pipeline is issued; When the pipeline appears When the risk of external water inflow and infiltration due to damage is determined, an early warning prompt is issued and an instruction for damage detection is issued; When the water depth in the pipeline is lower than the water depth at the upstream point When a damage occurs, it is determined that there is a risk of sewage leakage, an early warning is issued, and an instruction to conduct damage detection is issued.

Images