Pipeline network comprehensive risk assessment method and device

Abstract

The present invention discloses a comprehensive risk assessment method and device for a pipe network, which belongs to the field of water environment protection and monitoring technology. The method includes collecting risk assessment data of a rainwater and sewage pipe network, including monitoring index data of the pipe network and rainfall data in the pipe network area; using an unsupervised clustering method to perform cluster analysis on the risk assessment data, and determining inflow discharge category, infiltration discharge category and dry day discharge category; taking sample points under each category as group units, statistically analyzing the average value of monitoring index data under each category, and taking the average value of monitoring index data under the dry day category as the background value, calculating the mixed connection index and infiltration index, overflow index and blockage index of the pipe network, thereby determining the risk index of the pipe network. The present invention effectively avoids the influence of insufficient or inaccurate basic data of the pipe network on the inflow and infiltration assessment, and improves the accuracy and reliability of the inflow and infiltration assessment.

Description

Technical Field

[0001] The present invention relates to the technical field of water environment protection and monitoring, and in particular to a method and device for comprehensive risk assessment of a pipe network. Background Art

[0002] As one of the important urban infrastructures, the rainwater and sewage pipe network system has many uncertainties in its operation, especially the inflow and infiltration, overflow, mixing of rainwater and sewage, and pipe blockage. The water environment pollution caused directly or indirectly will endanger human and environmental health.

[0003] The flow of municipal rainwater and sewage collection systems is mainly composed of dry season flow and inflow and infiltration. The dry season flow and water quality changes are relatively stable, while the inflow and infiltration process is relatively complex. The problems of pipeline inflow and infiltration have become the main concerns in rainwater and sewage collection systems. For example, inflow and infiltration of sewage pipe networks can aggravate the structural and functional defects of the pipe network, increase the cost of facility operation and maintenance, increase the flow of pipes, and add unnecessary loads to sewage treatment plants. When the flow in the pipe network exceeds the capacity of the pipe network, it will be reflected in the form of overflow. These overflowing sewage will flood the streets, pollute nearby rivers, and cause serious operational problems in sewage treatment plants. When the pipe network is blocked, the subsequent rainwater and sewage cannot be discharged in time. Over time, there will be problems of seepage and leakage, and even cause sewage in the pipe network to flow back, causing odor.

[0004] The drainage system is divided into rainwater drainage system and sewage drainage system. Ideally, the rainwater pipe network designed for rainwater and sewage separation should remain dry after water accumulates in the rainwater and sewage pipe network. However, the actual situation is that there are a large number of sewage discharge points or leakage points in the rainwater pipe network, which cannot completely drain the accumulated water for a long time, and the water quality is polluted or even black and smelly, resulting in rainwater pollution and mixing of water systems, polluting rivers, lakes and oceans.

[0005] As an emerging science with important practical value, risk analysis and assessment can evaluate the degree of engineering risk. The operation risk analysis and assessment of the rainwater and sewage pipe network system is a topic of practical significance. Traditional rainwater and sewage pipe networks are mainly evaluated by CCTV, manual inspection and water quality testing. These methods are time-consuming and require a lot of on-site work, such as pipeline inspection and opening the manhole cover for inspection. This method is time-consuming and labor-intensive, and is subject to greater on-site constraints. There are relatively few methods based on water volume monitoring, which are mainly evaluated by using different hydraulic models, such as SWMM. However, sufficient and accurate pipe network information data is required for model calculation. However, the current domestic sewage system generally has problems such as missing or inaccurate basic information data of pipelines and insufficient drainage capacity of pipeline design. Therefore, the model-based method has many limitations in the diagnosis and analysis of the inflow and infiltration process of the pipe network; there are also some methods based on water quality balance to diagnose the inflow and infiltration of the pipe network, such as isotope tracing, TN and COD balance, etc., but they all have problems such as expensive detection methods and difficulty in obtaining long-term continuous data, which are difficult to be applied in the diagnosis of inflow and infiltration problems of pipe networks in a large area.

[0006] In the related art, the invention patent application with patent number CN 113392523 A discloses a sewage pipe network health diagnosis model based on long-term multi-measurement points, which consists of the following parts: single-measurement point drainage law learning, single-measurement point sewage inflow and infiltration analysis based on drainage law, district sewage inflow and infiltration analysis based on multiple measurement points, sewage pipe network rainwater mixed flow analysis based on single measurement point, district sewage inflow and infiltration analysis based on multiple measurement points, and rainfall well risk inference warning based on single measurement point. The model can be used to effectively diagnose the health status of the district sewage pipe network, but the model still needs to rely on long-term sewage drainage parameter monitoring data to construct sewage drainage laws. The lack or inaccuracy of sewage drainage parameter monitoring data will directly lead to errors in the diagnosis of the health status of the sewage pipe network. Summary of the invention

[0007] The technical problem to be solved by the present invention is to effectively avoid the impact of insufficient or inaccurate basic data of the pipeline network on the risk assessment of the rainwater and sewage pipeline network.

[0008] The present invention solves the above technical problems through the following technical means:

[0009] In one aspect, the present invention provides a method for comprehensive risk assessment of a pipeline network, the method comprising:

[0010] Collect risk assessment data of the rainwater and sewage pipe network, wherein the risk assessment data includes monitoring index data of the rainwater and sewage pipe network and rainfall data in the pipe network area;

[0011] The risk assessment data were clustered using an unsupervised clustering method, and combined with the rainfall data under different categories, the inflow discharge category, the infiltration discharge category, and the dry day discharge category were determined;

[0012] Taking the sample points under each category as group units, the average values ​​of the monitoring index data in the inflow discharge category, the infiltration discharge category and the dry day discharge category are counted, and the average value of the monitoring index data in the dry day discharge category is used as the background value to calculate the mixed connection index and infiltration index of the rainwater and sewage pipe network;

[0013] When it is determined that the rainwater and sewage pipe network has overflow based on the monitoring index data and the well depth data, an overflow index is calculated;

[0014] Based on the monitoring index data and the well depth data, when it is determined that the flow rate of the rainwater and sewage pipe network is less than a set threshold, a blockage index is calculated;

[0015] Based on the mixing index, the infiltration index, the overflow index and the blockage index, the risk index of the rainwater and sewage pipe network is calculated.

[0016] The present invention is based on the monitoring index data of the rainwater and sewage pipe network and the rainfall information in the pipe network area, and analyzes the inflow and infiltration process in the rainwater and sewage pipe network based on an unsupervised clustering algorithm, and diagnoses the comprehensive risk index of the rainwater and sewage pipe network operation. Compared with the existing methods based on hydraulic models and water quality balance, the present invention effectively avoids the impact of insufficient or inaccurate basic pipe network data on inflow and infiltration assessment, improves the accuracy and reliability of inflow and infiltration assessment, and provides a data basis for pipe network repair and reconstruction decisions.

[0017] Furthermore, after collecting the risk assessment data of the rainwater and sewage pipe network, the method further includes:

[0018] Preprocessing the risk assessment data to obtain preprocessed data, wherein the preprocessing method includes missing value processing and normalization processing;

[0019] Accordingly, the unsupervised clustering method is used to perform cluster analysis on the risk assessment data, and combined with the rainfall data under different categories, the inflow discharge category, the infiltration discharge category and the dry day discharge category are determined, specifically:

[0020] An unsupervised clustering method is used to perform cluster analysis on the preprocessed data, and the rainfall data under different categories are combined to determine the inflow discharge category, the infiltration discharge category and the dry day discharge category.

[0021] Furthermore, the monitoring index data includes flow velocity, flow rate and liquid level, and the calculation formula of the mixed connection index of the rainwater and sewage pipe network is:

[0022]

[0023] The calculation formula of the infiltration index is:

[0024]

[0025] Among them, F 混接 is the mixing index, Q 入流 is the mean inflow flow rate of the sample point, Q 旱天 is the mean flow rate of the sample point on a dry day, L 入渗 The average liquid level of the inflow category at the sample point, L 旱天 The mean liquid level of the sample point on a dry day, u 旱天 is the mean flow velocity of the sample point on dry days, r is the pipe diameter of the sample point, and h is the well depth of the sample point; F 入渗 is the infiltration index, Q 入渗 is the mean infiltration flow rate of the sample point.

[0026] Furthermore, the overflow index is calculated based on the monitoring indicator data and the well depth data, including:

[0027] Based on the monitoring index data and the well depth data, it is determined that the rainwater and sewage pipe network has overflow, and the overflow index is calculated as:

[0028]

[0029] Among them, F 溢流 is the overflow index, f 溢流 is the overflow frequency, that is, the data sample size when the liquid level data is greater than the well depth, f 监测 is the monitoring frequency, that is, the sample size of liquid level monitoring data.

[0030] Furthermore, when it is determined based on the monitoring index data and the well depth data that the flow rate of the rainwater and sewage pipe network is less than the flow rate threshold, the blockage index is calculated as:

[0031]

[0032] Among them, F 堵塞 is the blocking index, t 低流速 That is, the running time with a flow rate less than 0.6 m / s for 24 hours, t 监测 The total test time.

[0033] Furthermore, the risk index F of the rainwater and sewage pipe network is calculated as follows:

[0034] F=w 混接 F 混接 +w 入渗 F 入渗 +w 溢流 F 溢流+w 堵塞 F 堵塞 .

[0035] Among them, w 混接 , w 入渗 , w 溢流 , w 堵塞 They are the weights of each situation, which can be allocated according to actual conditions using expert scoring method.

[0036] In addition, the present invention also proposes a pipeline network comprehensive risk assessment device, the device comprising:

[0037] A data collection module, used to collect risk assessment data of the rainwater and sewage pipe network, wherein the risk assessment data includes monitoring index data of the rainwater and sewage pipe network and rainfall data in the pipe network area;

[0038] A cluster analysis module, for performing cluster analysis on the risk assessment data using an unsupervised clustering method, and combining the rainfall data under different categories to determine the inflow discharge category, the infiltration discharge category, and the dry day discharge category;

[0039] The first index calculation module is used to calculate the average value of the monitoring index data in the inflow discharge category, the infiltration discharge category and the dry day discharge category by taking the sample points under each category as group units, and taking the average value of the monitoring index data in the dry day discharge category as the background value to calculate the mixed connection index and infiltration index of the rainwater and sewage pipe network;

[0040] A second index calculation module is used to calculate an overflow index when it is determined that the rainwater and sewage pipe network has overflow based on the monitoring index data and the well depth data;

[0041] A third index calculation module is used to calculate a blockage index when it is determined that the flow rate of the rainwater and sewage pipe network is less than a set threshold based on the monitoring index data and the well depth data;

[0042] The risk index calculation module is used to calculate the risk index of the rainwater and sewage pipe network based on the mixing index, the infiltration index and the overflow.

[0043] Furthermore, the device also includes:

[0044] A preprocessing module, used to preprocess the risk assessment data to obtain preprocessed data, wherein the preprocessing method includes missing value processing and normalization processing;

[0045] Accordingly, the cluster analysis module is specifically used for:

[0046] An unsupervised clustering method is used to perform cluster analysis on the preprocessed data, and the rainfall data under different categories are combined to determine the inflow discharge category, the infiltration discharge category and the dry day discharge category.

[0047] Furthermore, the monitoring index data includes flow velocity, flow rate and liquid level. The first index calculation module is used to calculate the mixing index and the infiltration index. The calculation formula of the mixing index of the rainwater and sewage pipe network is:

[0048]

[0049] The calculation formula of the infiltration index is:

[0050]

[0051] Among them, F 混接 is the mixing index, Q 入流 is the mean inflow flow rate of the sample point, Q 旱天 is the mean flow rate of the sample point on a dry day, L 入渗 The average liquid level of the inflow category at the sample point, L 旱天 The mean liquid level of the sample point on a dry day, u 旱天 is the mean flow velocity of the sample point on dry days, r is the pipe diameter of the sample point, and h is the well depth of the sample point; F 入渗 is the infiltration index, Q 入渗 is the mean infiltration flow rate of the sample point.

[0052] Furthermore, the second index calculation module is used to calculate the overflow index when it is determined that the rainwater and sewage pipe network has overflow based on the monitoring indicator data and the well depth data:

[0053]

[0054] Among them, F 溢流 is the overflow index, f 溢流 is the overflow frequency, that is, the data sample size when the liquid level data is greater than the well depth, f 监测 is the monitoring frequency, that is, the sample size of liquid level monitoring data.

[0055] Furthermore, the third index calculation module is used to calculate the blockage index when it is determined that the flow rate of the rainwater and sewage pipe network is less than the flow rate threshold based on the monitoring index data and the well depth data:

[0056]

[0057] Among them, F 堵塞 is the blocking index, t 低流速 That is, the running time with a flow rate less than 0.6 m / s for 24 hours, t 监测 The total test time.

[0058] Furthermore, the risk index F of the rainwater and sewage pipe network is calculated as follows:

[0059] F=w 混接 F 混接 +w 入渗 F 入渗 +w 溢流 F 溢流 +w 堵塞 F 堵塞 .

[0060] Among them, w 混接 , w 入渗 , w 溢流 , w 堵塞 They are the weights of each situation, which can be allocated according to actual conditions using expert scoring method.

[0061] The advantages of the present invention are:

[0062] (1) Based on the monitoring index data of the rainwater and sewage pipe network and the rainfall information in the pipe network area, the present invention analyzes the inflow and infiltration process in the rainwater and sewage pipe network based on an unsupervised clustering algorithm, and diagnoses the comprehensive risk index of the rainwater and sewage pipe network operation. Compared with the existing methods based on hydraulic models and water quality balance, the present invention effectively avoids the impact of insufficient or inaccurate basic pipe network data on inflow and infiltration assessment, improves the accuracy and reliability of inflow and infiltration assessment, and provides a data basis for pipe network repair and reconstruction decisions.

[0063] (2) The comprehensive risk assessment method for inflow and infiltration of rainwater and sewage pipe networks and pipe network operation of the present invention has the characteristics of low cost and real-time dynamic assessment, and can achieve long-term stable real-time online operation.

[0064] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 is a flow chart of the comprehensive risk assessment method for pipe network in the present invention;

[0066] Figure 2 It is a structural diagram of the comprehensive risk assessment device for the pipeline network in the present invention. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described in combination with the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0068] Reference Figure 1 The embodiment of the present invention provides a method for comprehensive risk assessment of a pipeline network, the method comprising the following steps:

[0069] S10, collecting risk assessment data of the rainwater and sewage pipe network, wherein the risk assessment data includes monitoring index data of the rainwater and sewage pipe network and rainfall data in the pipe network area;

[0070] It should be noted that the risk assessment data in this embodiment includes online monitoring index data of the rainwater and sewage pipe network and real-time rainfall data in the pipe network area, which can be obtained through the automated online monitoring system of the rainwater and sewage pipe network.

[0071] S20, performing cluster analysis on the risk assessment data using an unsupervised clustering method, and combining the rainfall data under different categories to determine the inflow discharge category, the infiltration discharge category, and the dry day discharge category;

[0072] It should be noted that cluster analysis is the process of grouping data objects into multiple classes or clusters, and making the data objects in the same group have a high degree of similarity, while the data objects in different groups are dissimilar. Clustering algorithms are divided into two categories according to different learning methods: supervised clustering algorithms and unsupervised clustering algorithms. Supervised clustering algorithms must classify all learning samples, which usually requires a large number of learning samples. Unsupervised clustering algorithms are an automatic learning method that does not rely on predefined classes or training samples with class labels. Clustering can be used as an independent tool to obtain the distribution of data, observe the characteristics of each cluster of data, and focus on further analysis of specific clusters.

[0073] This embodiment uses an unsupervised clustering method to perform objective and scientific cluster analysis on the risk assessment data, and combines the rainfall conditions under different categories to determine the inflow category, infiltration category, and dry day discharge category.

[0074] S30, taking the sample points under each category as a group unit, calculating the average value of the monitoring index data in the inflow discharge category, the infiltration discharge category and the dry day discharge category, and taking the average value of the monitoring index data in the dry day discharge category as the background value, and calculating the mixed connection index and infiltration index of the rainwater and sewage pipe network;

[0075] S40, based on the monitoring index data and the well depth data, when it is determined that the rainwater and sewage pipe network has overflow, calculate the overflow index;

[0076] S50, based on the monitoring index data and the well depth data, when it is determined that the flow rate of the rainwater and sewage pipe network is less than a set threshold, a blockage index is calculated;

[0077] S60. Calculate the risk index of the rainwater and sewage pipe network based on the mixing index, the infiltration index, the overflow index and the blockage index.

[0078] This embodiment uses an unsupervised clustering algorithm to analyze the inflow and infiltration process in the rainwater and sewage pipe network for the collected risk assessment data, and diagnoses the comprehensive risk index of the rainwater and sewage pipe network operation. There is no need to rely on the historical basic data of the pipeline, which effectively avoids the impact of insufficient or inaccurate basic data of the pipe network on the inflow and infiltration assessment, improves the accuracy and reliability of the inflow and infiltration assessment, provides a data basis for pipe network repair and renovation decisions, can achieve long-term stable real-time online operation, and reduce operating costs.

[0079] In one embodiment, after step S10, the method further includes:

[0080] Preprocessing the risk assessment data to obtain preprocessed data, wherein the preprocessing method includes missing value processing and normalization processing;

[0081] Accordingly, the unsupervised clustering method is used to perform cluster analysis on the risk assessment data, and combined with the rainfall data under different categories, the inflow discharge category, the infiltration discharge category and the dry day discharge category are determined, specifically:

[0082] An unsupervised clustering method is used to perform cluster analysis on the preprocessed data, and the rainfall data under different categories are combined to determine the inflow discharge category, the infiltration discharge category and the dry day discharge category.

[0083] Specifically, the formula for normalization is as follows:

[0084]

[0085] Among them, x, x n0rmalization Respectively represent the values ​​before and after normalization, x max 、x min Represent the maximum and minimum values ​​in the sample data respectively.

[0086] This embodiment improves data precision and further improves the accuracy of data clustering analysis results by performing missing value processing and normalization processing on risk assessment data.

[0087] In one embodiment, in step S20, the K-means clustering algorithm is specifically used to perform cluster analysis on the risk assessment data. The K-means algorithm is a hard clustering algorithm and a representative of a typical prototype-based objective function clustering method. It uses a certain distance from the data point to the prototype as the optimized objective function, and uses the method of finding the extreme value of the function to obtain the adjustment rule of the iterative operation. The K-means algorithm uses the Euclidean distance as the similarity measure. It seeks the optimal classification corresponding to a certain initial cluster center vector V so that the evaluation index J is minimized. The algorithm uses the error square sum criterion function as the clustering criterion function. The K-means algorithm is a very typical distance-based clustering algorithm, which uses distance as an evaluation index of similarity, that is, it believes that the closer the distance between two objects, the greater their similarity. The algorithm believes that the cluster is composed of objects that are close in distance, so obtaining compact and independent clusters is the ultimate goal.

[0088] The K-means algorithm divides all samples into c groups of sample clusters and can find the location of the center points of these clusters. The specific process is as follows:

[0089] The n vectors X(t)=[x 1 (t),x 2 (t),…,x n (t)] is divided into c groups G i (i=1,2,…,c), and find the cluster center of each group so that the objective function of the non-similarity index reaches the minimum value. i The vector x k With cluster center c i When the non-similar indicators are used, the objective function can be defined as:

[0090]

[0091] A general distance function d(x k ,c i ), replacing group G i The vector x k and the dissimilarity between the corresponding cluster centers, the corresponding overall objective function can be expressed as:

[0092]

[0093] The divided groups are generally defined by a c×n two-dimensional membership matrix. If the jth data point x j belongs to group i, then the element u in this group ij is 1; otherwise, the element is 0. Once the cluster center is determined, the minimum u in formula (2) can be derived ij :

[0094]

[0095] If c i is x j The nearest cluster center, then x j Belongs to group i. Since a given data can only belong to one group, the membership matrix U has the following properties:

[0096]

[0097] Furthermore, if u is fixed jj , then the best cluster center that minimizes equation (1) is the mean of all vectors in group i.

[0098]

[0099] Here | G i |It is G i The scale or

[0100] Furthermore, in this embodiment, the data set x consisting of risk assessment data i (i=1,2,…,n) Using K-means algorithm, the clustering steps are as follows:

[0101] (1) Initialize the cluster center c i (i=1,2,…,n);

[0102] (2) Determine the membership matrix U according to formula (3);

[0103] (3) Calculate the objective function according to formula (1). If it is less than a certain threshold, or the change in the value function value relative to the last time is less than a certain threshold, stop the operation;

[0104] (4) Update the cluster center according to formula (6) and return to step (2).

[0105] K-means clustering is more effective in processing massive databases, especially when processing numerical attributes. Since it is very sensitive to abnormal data and has the characteristics of simple algorithm and fast convergence speed, this embodiment uses K-means clustering algorithm to perform cluster analysis on risk assessment data.

[0106] In one embodiment, the monitoring index data includes flow velocity, flow rate and liquid level, and the calculation formula of the mixed connection index of the rainwater and sewage pipe network is:

[0107]

[0108] The calculation formula of the infiltration index is:

[0109]

[0110] Among them, F 混接 is the mixing index, Q 入流 is the mean inflow flow rate of the sample point, Q 旱天 is the mean flow rate of the sample point on a dry day, L 入渗 The average liquid level of the inflow category at the sample point, L 旱天 The mean liquid level of the sample point on a dry day, u 旱天 is the mean flow velocity of the sample point on dry days, r is the pipe diameter of the sample point, and h is the well depth of the sample point; F 入渗 is the infiltration index, Q 入渗 is the mean infiltration flow rate of the sample point.

[0111] When calculating the hybrid index and the infiltration index in this embodiment, the index values ​​are unified into the same dimension range, so that the comprehensive evaluation index is more objective.

[0112] In one embodiment, the step S40 includes:

[0113] Based on the monitoring index data and the well depth data, it is determined that the rainwater and sewage pipe network has overflow, and the overflow index is calculated as:

[0114]

[0115] Among them, F 溢流 is the overflow index, f 溢流 is the overflow frequency, that is, the data sample size when the liquid level data is greater than the well depth, f 监测 is the monitoring frequency, that is, the sample size of liquid level monitoring data.

[0116] Specifically, if the real-time monitoring data of the pipeline network liquid level in the monitoring index data is greater than the well depth, it is determined that the pipeline network has overflow; otherwise, it is determined that the pipeline network does not have overflow.

[0117] In one embodiment, in step S50, when it is determined based on the monitoring index data and the well depth data that the flow rate of the rainwater and sewage pipe network is less than 0.6, the blockage index is calculated as:

[0118]

[0119] Among them, F 堵塞 is the blocking index, t 低流速 That is, the running time with a flow rate less than 0.6 m / s for 24 hours, t 监测 The total test time.

[0120] In one embodiment, in step S60, the risk index F of the rainwater and sewage pipe network is calculated as follows:

[0121] F=w 混接 F 混接 +w 入渗 F 入渗 +w 溢流 F 溢流 +w 堵塞 F 堵塞 .

[0122] w 混接 , w 入渗 , w 溢流 , w 堵塞 They are the weights of each situation, which can be allocated according to actual conditions using expert scoring method.

[0123] The embodiment provides a comprehensive risk method for inflow and infiltration of rainwater and sewage pipe networks and operation of the pipe network. Such water volume indicators mainly include data such as flow rate, flow velocity, liquid level, etc., and there are many types of testing equipment for such indicators at present, which have the characteristics of low cost and real-time dynamic evaluation, and can achieve long-term stable real-time online operation.

[0124] According to the assessed pipe network risk index, the operation risk of the rainwater and sewage pipe network system can be analyzed and evaluated, see Table 1:

[0125] Table 1

[0126]

[0127]

[0128] In addition, refer to Figure 2 The embodiment of the present invention further provides a device for comprehensive risk assessment of a pipe network, the device comprising:

[0129] The data collection module 10 is used to collect risk assessment data of the rainwater and sewage pipe network, wherein the risk assessment data includes monitoring index data of the rainwater and sewage pipe network and rainfall data in the pipe network area;

[0130] The cluster analysis module 20 is used to perform cluster analysis on the risk assessment data using an unsupervised clustering method, and determine the inflow discharge category, the infiltration discharge category and the dry day discharge category by combining the rainfall data under different categories;

[0131] The first index calculation module 30 is used to calculate the average value of the monitoring index data in the inflow discharge category, the infiltration discharge category and the dry day discharge category by taking the sample points under each category as group units, and taking the average value of the monitoring index data in the dry day discharge category as the background value to calculate the mixed connection index and the infiltration index of the rainwater and sewage pipe network;

[0132] A second index calculation module 40 is used to calculate an overflow index when it is determined that the rainwater and sewage pipe network has overflow based on the monitoring index data and the well depth data;

[0133] The third index calculation module 50 calculates the blockage index when it is determined that the flow rate of the rainwater and sewage pipe network is less than a set threshold value based on the monitoring index data and the well depth data;

[0134] The risk index calculation module 60 is used to calculate the risk index of the rainwater and sewage pipe network based on the mixing index, the infiltration index and the overflow index.

[0135] This embodiment uses an unsupervised clustering algorithm to analyze the inflow and infiltration process in the rainwater and sewage pipe network for the collected risk assessment data, and diagnoses the comprehensive risk index of the rainwater and sewage pipe network operation. There is no need to rely on the historical basic data of the pipeline, which effectively avoids the impact of insufficient or inaccurate basic data of the pipe network on the inflow and infiltration assessment, improves the accuracy and reliability of the inflow and infiltration assessment, provides a data basis for pipe network repair and renovation decisions, can achieve long-term stable real-time online operation, and reduce operating costs.

[0136] In one embodiment, the device further comprises:

[0137] A preprocessing module, used to preprocess the risk assessment data to obtain preprocessed data, wherein the preprocessing method includes missing value processing and normalization processing;

[0138] Accordingly, the cluster analysis module is specifically used for:

[0139] An unsupervised clustering method is used to perform cluster analysis on the preprocessed data, and the rainfall data under different categories are combined to determine the inflow discharge category, the infiltration discharge category and the dry day discharge category.

[0140] In one embodiment, the monitoring index data includes flow velocity, flow rate and liquid level. The first index calculation module 30 is used to calculate the mixing index and the infiltration index. The calculation formula of the mixing index of the rainwater and sewage pipe network is:

[0141]

[0142] The calculation formula of the infiltration index is:

[0143]

[0144] Among them, F 混接 is the mixing index, Q 入流 is the mean inflow flow rate of the sample point, Q 旱天 is the mean flow rate of the sample point on dry days, L 入渗 The average liquid level of the inflow category at the sample point, L旱天 The mean liquid level of the sample point on a dry day, u 旱天 is the mean flow velocity of the sample point on dry days, r is the pipe diameter of the sample point, and h is the well depth of the sample point; F 入渗 is the infiltration index, Q 入渗 is the mean infiltration flow rate of the sample point.

[0145] In one embodiment, the second index calculation module 40 is used to calculate the overflow index when it is determined that the rainwater and sewage pipe network has overflow based on the monitoring indicator data and the well depth data:

[0146]

[0147] Among them, F 溢流 is the overflow index, f 溢流 is the overflow frequency, that is, the data sample size when the liquid level data is greater than the well depth, f 监测 is the monitoring frequency, that is, the sample size of liquid level monitoring data.

[0148] In one embodiment, the third index calculation module 50 is used to calculate the blockage index as follows:

[0149]

[0150] Among them, F 堵塞 is the blocking index, t 低流速 That is, the running time with a flow rate less than 0.6 m / s for 24 hours, t 监测 The total test time.

[0151] In one embodiment, the risk index F of the rainwater and sewage pipe network is calculated as follows:

[0152] F=w 混接 F 混接 +w 入渗 F 入渗 +w 溢流 F 溢流 +w 堵塞 F 堵塞 .

[0153] Among them, w 混接 , w 入渗 , w 溢流 , w 堵塞 They are the weights of each situation, which can be allocated according to actual conditions using expert scoring method.

[0154] The method for comprehensive risk assessment of rainwater and sewage pipe network inflow and infiltration and pipe network operation provided in this embodiment has the characteristics of low cost and real-time dynamic assessment, and can achieve long-term stable real-time online operation.

[0155] It should be noted that other embodiments of the pipeline network comprehensive risk assessment device of the present invention or implementation methods can refer to the above-mentioned method embodiments, which are not repeated here.

[0156] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0157] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0158] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for comprehensive risk assessment of a pipeline network, characterized in that: The method comprises: Collect risk assessment data of the rainwater and sewage pipe network, wherein the risk assessment data includes monitoring index data of the rainwater and sewage pipe network and rainfall data in the pipe network area; The risk assessment data were clustered using an unsupervised clustering method, and combined with the rainfall data under different categories, the inflow discharge category, the infiltration discharge category, and the dry day discharge category were determined; Taking the sample points under each category as group units, the average values ​​of the monitoring index data in the inflow discharge category, the infiltration discharge category and the dry day discharge category are counted, and the average value of the monitoring index data in the dry day discharge category is used as the background value to calculate the mixed connection index and infiltration index of the rainwater and sewage pipe network; When it is determined that the rainwater and sewage pipe network has overflow based on the monitoring index data and the well depth data, an overflow index is calculated; Based on the monitoring index data and the well depth data, when it is determined that the flow rate of the rainwater and sewage pipe network is less than a set threshold, a blockage index is calculated; Calculating a risk index of the rainwater and sewage pipe network based on the mixing index, the infiltration index, the overflow index and the blockage index; The monitoring index data include flow velocity, flow rate and liquid level, and the calculation formula of the mixed connection index of the rainwater and sewage pipe network is: The calculation formula of the infiltration index is: Among them, F 混接 is the mixing index, Q 入流 is the mean inflow flow rate of the sample point, Q 旱天 is the mean flow rate of the sample point on dry days, L 入渗 The average liquid level of the inflow category at the sample point, L 旱天 The mean liquid level of the sample point on a dry day, u 旱天 is the mean flow velocity of the sample point on dry days, r is the pipe diameter of the sample point, and h is the well depth of the sample point; F 入渗 is the infiltration index, Q 入渗 is the mean infiltration flow rate of the sample point.

2. The method for comprehensive risk assessment of a pipeline network according to claim 1, characterized in that: After collecting risk assessment data on the stormwater and sewage pipe network, it also includes: Preprocessing the risk assessment data to obtain preprocessed data, wherein the preprocessing method includes missing value processing and normalization processing; Accordingly, the unsupervised clustering method is used to perform cluster analysis on the risk assessment data, and combined with the rainfall data under different categories, the inflow discharge category, the infiltration discharge category and the dry day discharge category are determined, specifically: An unsupervised clustering method is used to perform cluster analysis on the preprocessed data, and the rainfall data under different categories are combined to determine the inflow discharge category, the infiltration discharge category and the dry day discharge category.

3. The method for comprehensive risk assessment of a pipeline network according to claim 1, characterized in that: When it is determined that the rainwater and sewage pipe network has overflow based on the monitoring index data and the well depth data, the overflow index is calculated, including: Based on the monitoring index data and the well depth data, it is determined that the rainwater and sewage pipe network has overflow, and the overflow index is calculated as: Among them, F 溢流 is the overflow index, f 溢流 is the overflow frequency, that is, the data sample size when the liquid level data is greater than the well depth, f 监测 is the monitoring frequency, that is, the sample size of liquid level monitoring data.

4. The method for comprehensive risk assessment of a pipeline network according to claim 1, characterized in that: The calculation formula of the blocking index is: Among them, F 堵塞 is the blocking index, t 低流速 That is, the running time with a flow rate less than 0.6 m / s for 24 hours, t 监测 The total test time.

5. The method for comprehensive risk assessment of a pipeline network according to claim 1, characterized in that: The risk index F of the rainwater and sewage pipe network is calculated as follows: F=w 混接 F 混接 +w 入渗 F 入渗 +w 溢流 F 溢流 +w 堵塞 F 堵塞 ; Among them, w 混接 , w 入渗 , w 溢流 , w 堵塞 are the weights of each case.

6. A comprehensive risk assessment device for a pipeline network, characterized in that: The device comprises: A data collection module, used to collect risk assessment data of the rainwater and sewage pipe network, wherein the risk assessment data includes monitoring index data of the rainwater and sewage pipe network and rainfall data in the pipe network area; A cluster analysis module, for performing cluster analysis on the risk assessment data using an unsupervised clustering method, and combining the rainfall data under different categories to determine the inflow discharge category, the infiltration discharge category, and the dry day discharge category; The first index calculation module is used to calculate the average value of the monitoring index data in the inflow discharge category, the infiltration discharge category and the dry day discharge category by taking the sample points under each category as group units, and taking the average value of the monitoring index data in the dry day discharge category as the background value to calculate the mixed connection index and infiltration index of the rainwater and sewage pipe network; A second index calculation module is used to calculate an overflow index when it is determined that the rainwater and sewage pipe network has overflow based on the monitoring index data and the well depth data; A third index calculation module is used to calculate a blockage index when it is determined that the flow rate of the rainwater and sewage pipe network is less than a set threshold based on the monitoring index data and the well depth data; A risk index calculation module, used to calculate the risk index of the rainwater and sewage pipe network based on the mixing index, the infiltration index, and the overflow; The monitoring index data include flow velocity, flow rate and liquid level, and the calculation formula of the mixed connection index of the rainwater and sewage pipe network is: The calculation formula of the infiltration index is: Among them, F 混接 is the mixing index, Q 入流 is the mean inflow flow rate of the sample point, Q 旱天 is the mean flow rate of the sample point on a dry day, L 入渗 The average liquid level of the inflow category at the sample point, L 旱天 The mean liquid level of the sample point on a dry day, u 旱天 is the mean flow velocity of the sample point on dry days, r is the pipe diameter of the sample point, and h is the well depth of the sample point; F 入渗 is the infiltration index, Q 入渗 is the mean infiltration flow rate of the sample point.

7. The comprehensive risk assessment device for a pipe network as claimed in claim 6, characterized in that: The device also includes: A preprocessing module, used to preprocess the risk assessment data to obtain preprocessed data, wherein the preprocessing method includes missing value processing and normalization processing; Accordingly, the cluster analysis module is specifically used for: An unsupervised clustering method is used to perform cluster analysis on the preprocessed data, and the rainfall data under different categories are combined to determine the inflow discharge category, the infiltration discharge category and the dry day discharge category.

8. The pipe network comprehensive risk assessment device according to claim 6, characterized in that: The overflow index is: Among them, F 溢流 is the overflow index, f 溢流 is the overflow frequency, that is, the data sample size when the liquid level data is greater than the well depth, f 监测 is the monitoring frequency, i.e. the sample size of liquid level monitoring data; The calculation formula of the blocking index is: Among them, F 堵塞 is the blocking index, t 低流速 That is, the running time with a flow rate less than 0.6 m / s for 24 hours, t 监测 The total test time.

9. The pipe network comprehensive risk assessment device according to claim 6, characterized in that: The risk index F of the rainwater and sewage pipe network is calculated as follows: F=w 混接 F 混接 +w 入渗 F 入渗 +w 溢流 F 溢流 +w 堵塞 F 堵塞 ; Among them, w 混接 , w 入渗 , w 溢流 , w 堵塞 are the weights of each case.

Images