Urban sewage pipe network inspection path planning method based on risk level

Abstract

The invention discloses a town sewage pipe network inspection path planning method based on risk levels, and belongs to the technical field of town sewage pipe network inspection path planning. The operation risk levels of pipe sections of a sewage pipe network are obtained through an analytic hierarchy process and fuzzy comprehensive evaluation, and inspection periods corresponding to the risk levels are combined; clustering the pipe sections with various risk levels, combining the pipe sections with close distances to obtain a planned inspection pipe section set, and applying a path planning method to obtain an optimal inspection route of the planned inspection pipe sections; according to the method, the operation risk level of the pipe section can be obtained according to the sewage pipe network pipe section feature evaluation, clustering and combination are performed in combination with the risk level of the pipe section and the corresponding inspection period, the planned inspection pipe section is efficiently allocated, and the inspection task is effectively optimized through reasonable planning of the inspection route, so that the inspection efficiency is improved, and the inspection cost is saved.

Description

Technical Field

[0001] The present invention relates to the technical field of urban sewage pipe network inspection route planning, and in particular to an urban sewage pipe network inspection route planning method based on risk level. Background Art

[0002] Urban sewage pipe networks are responsible for collecting, transporting and treating sewage, and are of great significance for protecting residents' lives and maintaining urban environmental sanitation. However, with the increase in the operation time of sewage pipe networks and the influence of the surrounding environment, sewage pipe networks are prone to damage, blockage, collapse and other problems, which affect the normal drainage function and easily cause public safety accidents and environmental pollution. Therefore, it is necessary to conduct regular inspections of sewage pipe networks to promptly discover and solve problems in sewage pipe networks and ensure the normal operation of sewage pipe networks.

[0003] At present, sewage pipe network inspection work often stipulates that a sewage pipe network inspection of a designated area or line must be completed within a certain period of time. The inspection frequency will be increased accordingly in some key areas such as commercial centers, construction sites, and stations. The division of key areas and pipe sections relies on the experience of inspectors, and the judgment is relatively simple and subjective, which can easily lead to incorrect division of key areas and high-risk pipe sections and missed or insufficient inspections. At the same time, the selection of inspection pipe sections and the arrangement of inspection routes lack reasonable planning, resulting in low inspection efficiency, high time cost and inspection material consumption, and other problems.

[0004] Therefore, it is necessary to design a risk-level-based urban sewage pipe network inspection route planning method that can solve the above problems. Summary of the invention

[0005] Purpose of the invention: A method for planning inspection routes for urban sewage pipe networks based on risk levels to solve the above-mentioned problems existing in the prior art.

[0006] In order to solve the above technical problems, the present invention provides a method for planning inspection paths for urban sewage pipe networks based on risk levels, comprising:

[0007] S1: Applying the analytic hierarchy process and fuzzy comprehensive evaluation, the operation risk level of all pipe sections in the inspection area sewage pipe network is determined;

[0008] S2: For the set of pipe sections with different risk levels, the k-means++ clustering algorithm is applied to obtain the clustering results of pipe sections with different risk levels;

[0009] S3: Based on the clustering results in S2, and according to the inspection cycles corresponding to the pipe sections of different risk levels, calculate the inspection pipe section sets of different risk levels;

[0010] S4: combining the inspection pipe section set in S3 to obtain the planned inspection pipe section set on the inspection working day; applying the path planning method to obtain the optimal inspection path of the planned inspection pipe section.

[0011] As a preferred solution, the step S1 is specifically as follows:

[0012] Establish a sewage pipe network operation risk assessment index system based on the evaluation indicators of pipe age, pipe diameter, pipe material, pipe burial depth, pipe length, pipe type, pipe interface, pipe foundation, soil type, road grade, construction status, occupation status, regional type, traffic load, and maintenance frequency;

[0013] The 15 basic indicators in the sewage network operation risk assessment index system are subjectively weighted by the analytic hierarchy process, and the weight vector of each basic indicator is calculated;

[0014] A membership evaluation matrix is ​​established, the evaluation results are calculated using fuzzy comprehensive evaluation, and the level of the evaluation results is determined based on the maximum membership principle.

[0015] As a preferred solution, the pipe age, pipe diameter, pipe material, pipe burial depth, pipe length, pipe type, pipe interface and pipe foundation are collectively classified as pipe factors, the soil type, road grade, construction situation, occupation situation, regional type and traffic load are collectively classified as environmental factors, the maintenance frequency is a management factor, the sewage pipe network operation risk is taken as the target layer, the pipe factors, environmental factors and management factors are taken as the criterion layer, and the basic indicators are taken as the sub-criterion layer, and a judgment matrix of the criterion layer indicators and the sub-criterion layer indicators is constructed, which is recorded as a judgment matrix A;

[0016] Performing consistency check on the obtained judgment matrix A, and judging whether the construction of the judgment matrix is ​​reasonable by calculating the consistency index and the consistency ratio;

[0017] After the judgment matrix A passes the consistency check, the maximum eigenvalue and the corresponding weight vector of the judgment matrix A are obtained; according to the above method, the weight vector Wn of the sub-criteria layer index to the criterion layer to which it belongs and the weight vector W of the criterion layer index to the target layer can be obtained;

[0018] The weight vector Wn and the weight vector W are used to perform a fuzzy comprehensive evaluation on the membership evaluation matrix to obtain the risk levels corresponding to all pipe sections of the sewage pipe network in the inspection area.

[0019] As a preferred solution, the method for constructing the judgment matrix A is:

[0020] First, drainage network business experts judge the importance scale of sub-criteria layer indicators to the criterion layer indicators they belong to based on their professional knowledge and practical experience, and construct a judgment matrix of sub-criteria layer indicators to the criterion layer indicators they belong to; then, drainage network business experts judge the importance scale of criterion layer indicators to the target layer.

[0021] As a preferred solution, in the step S2, the distance between samples of the clustering algorithm adopts the distance between the longitude and latitude coordinates of the starting positions of the two pipe segments, which is calculated by the semi-vector formula to obtain the clustering algorithm parameters and sample distances corresponding to different pipe segment sets, and the k-means++ algorithm is used to cluster the pipe segment sets respectively.

[0022] As a preferred solution, the S3 step is specifically as follows: the preset length in the high-risk inspection pipe section set and its corresponding subset can be obtained through the number of high-risk pipe sections and the inspection cycle, and the inspection starting point is determined and traversed to obtain the minimum pipe section from the starting point and the cluster where the minimum pipe section is located, thereby obtaining the inspection pipe section sets of medium risk, general risk and low risk.

[0023] As a preferred solution, the step S4 is specifically as follows:

[0024] On the starting day of the inspection cycle corresponding to the inspection pipe sections of different risk levels, the set of pipe sections to be inspected is initialized to obtain a set of high-risk pipe sections to be inspected, a set of medium-risk pipe sections to be inspected, a set of general-risk pipe sections to be inspected, and a set of low-risk pipe sections to be inspected;

[0025] On the inspection working day, select a subset y that has not been inspected from the set of high-risk pipe sections to be inspected a , as the high-risk pipe section planned for inspection that day, and then traverse the uninspected subsets of the set of medium-risk pipe sections to be inspected, and calculate the same as y a The nearest medium-risk pipeline segment subset y b Then, traverse the uninspected sub-sets in the set of general risk pipe sections to be inspected, and calculate the a ,y b The subset y of the uninspected general risk pipe sections with the smallest sum of distances c Finally, traverse the uninspected sub-sets in the low-risk pipe section set to be inspected and calculate the a ,y b ,y c The subset y of uninspected low-risk pipe sections with the smallest sum of distances d ; From the above, we can get all the planned inspection sections combination y for the inspection working day;

[0026] Inspection is performed through all planned inspection pipe section combinations y on the inspection working day.

[0027] As a preferred solution, after the inspection plan is completed on weekdays, a ,y b ,y c ,y d Remove from the corresponding set of pipe sections to be inspected, and determine the number of remaining uninspected sub-sets in each set of pipe sections to be inspected. If the number of remaining uninspected sub-sets is 0, it is necessary to reinitialize the set of pipe sections to be inspected of the risk level.

[0028] As a preferred solution, the inspection workday planned inspection pipe section combination y can be planned for inspection route by one of inspection from high to low risk level and inspection according to the optimal route.

[0029] As a preferred solution, the inspection route planning is to solve the traveling salesman problem, and the solution method can be solved by using one of the ant colony algorithm, genetic algorithm, taboo search algorithm, simulated annealing algorithm and neural network.

[0030] Beneficial effect: The present invention relates to a method for planning inspection paths of urban sewage pipe networks based on risk levels. The present invention obtains the operating risk level of the sewage pipe network segments through analytic hierarchy process and fuzzy comprehensive evaluation, clusters the pipe segments of various risk levels in combination with the inspection cycles corresponding to the risk levels, and then combines the pipe segments with similar distances to obtain a set of planned inspection pipe segments, and applies the path planning method to obtain the optimal inspection route of the planned inspection pipe segments; the present invention can obtain the operating risk level of the pipe segment according to the characteristic assessment of the sewage pipe network segments, cluster and combine the risk level of the pipe segment and the corresponding inspection cycle, efficiently allocate the planned inspection pipe segments, and then effectively optimize the inspection tasks through reasonable planning of the inspection routes, which is beneficial to improving the inspection efficiency and saving the inspection cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a schematic diagram of the process of the present invention.

[0032] Figure 2 It is a schematic diagram of the calculation method of step S3 of the present invention.

[0033] Figure 3 It is a schematic diagram of establishing a sewage pipe network operation risk assessment index system according to the present invention. DETAILED DESCRIPTION

[0034] In the following description, a large number of specific details are provided to provide a more thorough understanding of the present invention. However, it is apparent to those skilled in the art that the present invention can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present invention, some technical features well known in the art are not described.

[0035] The applicant's research found that the current sewage pipe network inspection work often stipulates that a sewage pipe network inspection of a designated area or line must be completed within a certain period of time. The inspection frequency will be increased accordingly in key areas such as commercial centers, construction sites, and stations. The division of key areas and pipe sections relies on the experience of inspectors, and the judgment is relatively simple and subjective, which can easily lead to incorrect division of key areas and high-risk pipe sections and missed or insufficient inspections. At the same time, the selection of inspection sections and the arrangement of inspection routes lack reasonable planning, resulting in low inspection efficiency, high time cost and consumption of inspection materials.

[0036] To this end, the present invention provides a method for planning inspection routes for urban sewage pipe networks based on risk levels. Figure 1 , the method includes:

[0037] S1: Applying the analytic hierarchy process and fuzzy comprehensive evaluation, the operation risk level of all pipe sections in the inspection area sewage pipe network is determined;

[0038] S2: For the set of pipe sections with different risk levels, the k-means++ clustering algorithm is applied to obtain the clustering results of pipe sections with different risk levels;

[0039] S3: Based on the clustering results in S2, and according to the inspection cycles corresponding to the pipe sections of different risk levels, calculate the inspection pipe section sets of different risk levels;

[0040] S4: combining the inspection pipe section set in S3 to obtain the planned inspection pipe section set on the inspection working day; applying the path planning method to obtain the optimal inspection path of the planned inspection pipe section.

[0041] Preferably, the step S1 specifically comprises:

[0042] Establish a sewage pipe network operation risk assessment index system based on the evaluation indicators of pipe age, pipe diameter, pipe material, pipe burial depth, pipe length, pipe type, pipe interface, pipe foundation, soil type, road grade, construction status, occupation status, regional type, traffic load, and maintenance frequency;

[0043] The 15 basic indicators in the sewage network operation risk assessment index system are subjectively weighted by the analytic hierarchy process, and the weight vector of each basic indicator is calculated;

[0044] A membership evaluation matrix is ​​established, the evaluation results are calculated using fuzzy comprehensive evaluation, and the level of the evaluation results is determined based on the maximum membership principle.

[0045] Preferably, the pipe age, pipe diameter, pipe material, pipe burial depth, pipe length, pipe type, pipe interface and pipe foundation are collectively classified as pipe factors, the soil type, road grade, construction situation, occupation situation, regional type and traffic load are collectively classified as environmental factors, the maintenance frequency is a management factor, the sewage pipe network operation risk is taken as the target layer, the pipe factors, environmental factors and management factors are taken as the criterion layer, and the basic indicators are taken as the sub-criterion layer, and a judgment matrix of the criterion layer indicators and the sub-criterion layer indicators is constructed, which is recorded as a judgment matrix A;

[0046] Performing consistency check on the obtained judgment matrix A, and judging whether the construction of the judgment matrix is ​​reasonable by calculating the consistency index and the consistency ratio;

[0047] After the judgment matrix A passes the consistency check, the maximum eigenvalue and the corresponding weight vector of the judgment matrix A are obtained; according to the above method, the weight vector Wn of the sub-criteria layer index to the criterion layer to which it belongs and the weight vector W of the criterion layer index to the target layer can be obtained;

[0048] The weight vector Wn and the weight vector W are used to perform a fuzzy comprehensive evaluation on the membership evaluation matrix to obtain the risk levels corresponding to all pipe sections of the sewage pipe network in the inspection area.

[0049] Preferably, the judgment matrix A is constructed as follows:

[0050] First, drainage network business experts judge the importance scale of sub-criteria layer indicators to the criterion layer indicators they belong to based on their professional knowledge and practical experience, and construct a judgment matrix of sub-criteria layer indicators to the criterion layer indicators they belong to; then, drainage network business experts judge the importance scale of criterion layer indicators to the target layer.

[0051] Furthermore, in step S2, the distance between samples of the clustering algorithm is the distance between the longitude and latitude coordinates of the starting positions of the two pipe segments, which is calculated by the semi-vector formula to obtain the clustering algorithm parameters and sample distances corresponding to different pipe segment sets, and the k-means++ algorithm is used to cluster the pipe segment sets respectively.

[0052] Furthermore, the S3 step is specifically as follows: the preset length in the high-risk inspection pipe section set and its corresponding subset can be obtained through the number of high-risk pipe sections and the inspection cycle, and the inspection starting point is determined to obtain the minimum pipe section from the starting point and the cluster where the minimum pipe section is located through traversal, thereby obtaining the inspection pipe section sets of medium risk, general risk and low risk.

[0053] According to the determined inspection starting point, the clustering results of the pipe sections with different risk levels obtained in step S2, and the corresponding inspection cycles, the inspection pipe section sets corresponding to the four risk level pipe sections are calculated respectively. The calculation of the high-risk inspection pipe section set is described below as an example. The calculation process of the medium-risk inspection pipe section set, the general-risk inspection pipe section set, and the low-risk inspection pipe section set are the same:

[0054] First, the number of elements is initialized to the number of days in the inspection cycle of the high-risk pipe section T 高 The high-risk inspection pipeline section set L 高 , calculate the number of high-risk pipe sections planned for inspection on each day during the high-risk pipe section inspection cycle, preset to the length of the sub-set in the high-risk inspection pipe section set, the sub-set is the pipe section set planned for inspection on each day, and the sub-set is initialized to an empty set;

[0055] Randomly take out an empty subset l i , traverse the high-risk pipe segment clustering results C 高 The pipe section s closest to the inspection starting point s0 i , the pipe segment s i Add to subcollection l i The pipe segment is removed from the clustering results, and the high-risk pipe segment clustering results c are traversed repeatedly. 高 In and sub-set l i The nearest pipe segment s to all elements in j , the pipe segment s j Add to the subset and remove pipe segment s from the clustering result j , until the length of the subset reaches its preset length, the calculation stops;

[0056] Then, all empty subsets in the high-risk inspection pipe section set are taken out in turn, and the above calculation process is repeated until all subsets reach their preset lengths, and the calculation is stopped to obtain the high-risk inspection pipe section set.

[0057] Furthermore, the S4 step is specifically as follows:

[0058] On the starting day of the inspection cycle corresponding to the inspection pipe sections of different risk levels, the set of pipe sections to be inspected is initialized to obtain a set of high-risk pipe sections to be inspected, a set of medium-risk pipe sections to be inspected, a set of general-risk pipe sections to be inspected, and a set of low-risk pipe sections to be inspected;

[0059] On the inspection working day, select a subset y that has not been inspected from the set of high-risk pipe sections to be inspected a , as the high-risk pipe section planned for inspection that day, and then traverse the uninspected subsets of the set of medium-risk pipe sections to be inspected, and calculate the same as y a The nearest medium-risk pipeline segment subset y bThen, traverse the uninspected sub-sets in the set of general risk pipe sections to be inspected, and calculate the a ,y b The subset y of the uninspected general risk pipe sections with the smallest sum of distances c Finally, traverse the uninspected sub-sets in the low-risk pipe section set to be inspected and calculate the a ,y b ,y c The subset y of uninspected low-risk pipe sections with the smallest sum of distances d ; From the above, we can get all the planned inspection sections combination y for the inspection working day;

[0060] Inspection is performed through all planned inspection pipe section combinations y on the inspection working day.

[0061] Furthermore, after the workday inspection plan is completed, a ,y b ,y c ,y d Remove from the corresponding set of pipe sections to be inspected, and determine the number of remaining uninspected sub-sets in each set of pipe sections to be inspected. If the number of remaining uninspected sub-sets is 0, it is necessary to reinitialize the set of pipe sections to be inspected of the risk level.

[0062] Preferably, the inspection workday planned inspection pipe section combination y can be planned for inspection route by one of inspection from high to low risk level and inspection according to the optimal route.

[0063] Preferably, the inspection route planning is to solve the traveling salesman problem, and the solution method thereof can be solved by using one of an ant colony algorithm, a genetic algorithm, a taboo search algorithm, a simulated annealing algorithm and a neural network.

[0064] According to the above-mentioned risk-level-based urban sewage pipe network inspection route planning method, the following embodiments are listed for illustration:

[0065] 1. Construct a sewage network operation risk assessment index system, and apply the analytic hierarchy process and fuzzy comprehensive evaluation to evaluate all pipe sections in the inspection area to obtain a set of pipe sections with various risk levels.

[0066] 1.1. Establish a sewage pipe network operation risk assessment index system based on the evaluation indicators of pipe age, pipe diameter, pipe material, pipe burial depth, pipe length, pipe type, pipe interface, pipe foundation, soil type, road grade, construction status, occupation status, regional type, traffic load, and maintenance frequency, as shown in the figure below. The index system is divided into target layer, criterion layer, and sub-criterion layer. Please refer to Figure 3 .

[0067] 1.2. The 15 basic indicators in the sewage network operation risk assessment index system are subjectively weighted through the hierarchical analysis method, and the weight vector of each basic indicator is calculated.

[0068] 1.2.1. Taking the sewage pipe network operation risk as the target layer, the pipeline factors, environmental factors, and management factors as the criterion layer, and the basic indicators as the sub-criterion layer, a judgment matrix of the criterion layer indicators and the sub-criterion layer indicators is constructed: First, drainage pipe network business experts judge the importance of the sub-criterion layer indicators to the criterion layer indicators based on professional knowledge and practical experience, and construct a judgment matrix of the sub-criterion layer indicators to the criterion layer indicators; then, drainage pipe network business experts judge the importance of the criterion layer indicators to the target layer, and construct a judgment matrix of the criterion layer indicators to the target layer. The judgment matrix uses an element of the previous level as a comparison criterion, a ij It indicates the relative importance ratio of the i-th element to the j-th element at this level. The importance scale adopts the nine-level scale method, which is set according to the actual situation. The reference table of the nine-level scale method is as follows:

[0069]

[0070]

[0071] The constructed judgment matrix

[0072] The element a ij Represents the relative importance ratio of element i and element j, α ij >0,a ii =1,

[0073] 1.2.2. Perform consistency check on the obtained judgment matrix A, and judge whether the judgment matrix construction is reasonable by calculating the consistency index CI and consistency ratio CR.

[0074] where λ max is the maximum eigenvalue of the judgment matrix, n is the order of the judgment matrix, R is the average random consistency index, and the average random consistency index can be obtained through the query table, as shown in the following table:

[0075] n 1 2 3 4 5 6 7 8 9 10 RI 0 0 0.52 0.89 1.12 1.26 1.36 1.41 1.45 1.49

[0076] where λ max The solution steps are:

[0077] Normalize the column vectors of the judgment matrix A g ij is the normalized value of the judgment matrix column, i, j = (1, 2, .... n),

[0078] u ij is the judgment matrix element.

[0079] The normalized result matrix of the column vector is

[0080] Sum the normalized result matrix G by row, and the row summation result is Then Normalized, the processing result is:

[0081] The weight vector W of the judgment matrix A can be obtained as follows: n ) T , the maximum eigenvalue is Substitute the calculated CR value. When CR<0.1, it can be considered that the judgment matrix meets the consistency requirements. Otherwise, the importance scales of each indicator should be adjusted until the consistency test is passed.

[0082] 1.2.3. After the judgment matrix A passes the consistency check, the maximum eigenvalue and corresponding weight vector of A are obtained. According to the above method, the weight vector W of the sub-criteria layer indicator to the criterion layer to which it belongs can be obtained: n , the weight vector W of the criterion layer indicator to the target layer.

[0083] 1.3. Establish a membership evaluation matrix, use fuzzy comprehensive evaluation to calculate the evaluation results, and judge the level of the evaluation results according to the maximum membership principle.

[0084] 1.3.1. Establish an evaluation set. The evaluation set represents the set of all possible evaluation results. According to the risk characteristics of sewage pipe network operation, the evaluation set V is established:

[0085] V = {v1, v2, v3, v4} = {low risk, general risk, medium risk, high risk}.

[0086] 1.3.2. Determine the division criteria for each basic indicator at the sub-criteria layer, divide the operation risk level of each risk assessment basic indicator of the pipe section according to the actual measurement data, and obtain the risk level to which the basic indicator of the pipe section belongs. The division rules are as follows:

[0087]

[0088] 1.3.3. According to the data characteristics of the basic indicators, the membership functions such as triangular distribution and trapezoidal distribution are selected, and the measured data of the basic indicators of the pipe section are substituted into the membership function to obtain the membership results of the basic indicators of the pipe section, forming a membership matrix:

[0089]

[0090] Where Ri represents the membership matrix of the ith indicator in the criterion layer, r ijk It represents the membership of the jth sub-criterion layer indicator under the i-th criterion layer indicator to the kth evaluation factor in the evaluation set.

[0091] 1.3.4 Fuzzy comprehensive evaluation

[0092] Using the membership matrix R of a single indicator in the criterion layer i , and the weight vector W of the sub-criteria layer indicators under this indicator i , calculate the fuzzy comprehensive evaluation vector P of a single indicator at the criterion layer i ,

[0093] The obtained single index membership matrix of the criterion layer is combined to obtain the criterion layer fuzzy relationship matrix P, P = (P1, P2, ..., P n ) T .

[0094] The fuzzy relationship matrix P of the criterion layer and the weight vector W of the criterion layer are calculated to obtain the overall evaluation result vector Q

[0095]

[0096] The maximum membership principle is used to obtain the final evaluation risk level for the overall evaluation result Q. According to the above method, the risk level corresponding to all pipe sections in the inspection area sewage pipe network is obtained, and the pipe sections of the same type of risk level are combined into the same set to obtain the high-risk level pipe section set S 高 , medium risk level pipeline segment set S 中 , General risk level pipe section set S 一般 , low risk level pipe segment set S 低 .

[0097] 2. Inspection route planning

[0098] 2.1. Use the k-means++ clustering algorithm to cluster the four risk level pipe section sets obtained in Section 1.

[0099] 2.1.1. Assume that the inspection cycle days of high-risk pipe section, medium-risk pipe section, general-risk pipe section and low-risk pipe section are T respectively. 高 、T 中 、T -般 、T 低, the higher the risk level, the shorter the inspection cycle. The inspection cycle should be less than or equal to the number of pipe sections of the corresponding risk level, ensuring that at least one pipe section is inspected every day during the inspection cycle of each risk level pipe section. The element type in the pipe section set is (id, (longitude, latitude)), id is the unique number of the pipe section, longitude and latitude are the longitude and latitude data of the starting position of the pipe section respectively. Set the parameters of the k-means++ algorithm, set S 高 The initial number of centroids k of the clustering algorithm 高 , k 高 =T 高 . According to the above rules, we can get S 中 The initial number of centroids k of the clustering algorithm 中 , k 中 =T 中 , S 一般 The initial number of centroids k of the clustering algorithm 一般 , k 一般 =T 一般 , S 低 The initial number of centroids k of the clustering algorithm 低 , k 低 =T 低 The distance between samples of the clustering algorithm is the distance between the longitude and latitude coordinates of the starting positions of the two pipe segments, and the calculation method is the Haversine formula:

[0100]

[0101] Where d is the distance between two longitude and latitude coordinate points, r is the radius of the earth, which is set here as r = 6378137 meters, lng1 and lng2 are the longitudes of the two coordinate points, and lat1 and lat2 are the latitudes of the two coordinate points.

[0102] 2.1.2. Based on the clustering algorithm parameters and sample distance calculation methods corresponding to different pipe segment sets obtained in 2.1.1, the k-means++ algorithm is used to cluster the pipe segment sets S 高 , S 中 , S 一般 , S 低 Perform clustering to obtain the high-risk level pipe segment clustering result C 高 , Clustering results of medium risk level pipeline segments C 中 , Clustering results of pipeline sections with general risk level C 一般 , Clustering results of low risk pipe segments C 低 ,

[0103] 2.2. For the clustering results of the various risk level pipe sections obtained in 2.1, they are combined according to the inspection cycle to obtain the inspection pipe section sets of different risk levels. The following steps are performed in sequence. The process can be referred to Figure 2 .

[0104] 2.2.1. Assume that the maximum number of high-risk pipeline sections to be inspected daily is a positive integer m. 高 , calculated as:

[0105] T 高 (m 高 -1) <N 高 ≤T 高 m 高 (2)

[0106] Where N 高 is the number of high-risk pipeline sections, T 高 It is the inspection cycle for high-risk pipe sections.

[0107] For the high-risk pipe segment clustering result C 高 , initialize the high-risk inspection section set L 高 , L 高 ={l1,l2,...,l i , l t}, where the subset l i Initialize to an empty set, preset l i The length is n i , there are n1+...+n i +n t =N 高 , n i ∈(m 高 m 高 -1), i=(1, 2,...,t), t=T 高 .

[0108] First L 高 Randomly select N 高 -T 高 (m 高 -1) subsets, with a default length of m 高 , then select L 高 The remaining T 高 m 高 -N 高 subsets, whose length is preset to m 高 -1, assign the obtained preset length to n iFor example, if there are 40 high-risk pipeline sections and the inspection cycle is 7 days, then it can be found that there are 5 subsets with a preset length of 6 in the high-risk inspection pipeline section set, and there are 2 subsets with a preset length of 5, that is, there are 5 days in the inspection cycle where 6 high-risk pipeline sections are planned to be inspected every day, and there are 2 days where 5 high-risk pipeline sections are planned to be inspected every day.

[0109] 2.2.2, let the inspection starting point be s0, and randomly take out L 高 The empty subset l in i , traverse C 高 For each cluster in the cluster, calculate the distance between the elements in the cluster and s0, and find the pipe segment s with the minimum distance to s0 i , and s i The cluster c i , c i ∈C 声 ,s i ∈c i . i Put in t and from c i Remove i , where the distance between two pipe sections is calculated as formula (1); if L 高 If there is no empty subset in the, then all calculations are terminated, and the high-risk inspection pipe section set L is obtained. 高 .

[0110] 2.2.3, when l i When it changes, judge l i The number of elements p and their preset length n i Relationship, when p≠n i When p=n, execute step 2.3.4; when p=n, set l i Put in L 高 In, l i =[s1,s2,...,s p ],(p=n i ), and repeat step 2.2.2.

[0111] 2.2.4. Determine c i The number of elements in c is q. When q≠0, traverse c i The remaining elements in the calculation are the same as l i The nearest element s k And add l i In, k From c i Remove. Repeat step 2.2.3. i Element s i With the collection l i The distance calculation formula is:

[0112]

[0113] m j for l i Number of elements, s j for l i Any element in ||s i -s j || is element s i and j distance.

[0114] 2.2.5, when c in step 2.2.4 i When the number of elements q = 0, c i From C 高 Remove, judge C 高 Is the number of remaining clusters v in 0? If v = 0, end all calculations and set l i Put in L 高 In the above example, we get the high-risk inspection section set L 高 ; When v≠0, re-traverse C 高 For the remaining clusters in the i The closest cluster c j , c j ∈C 高 , for c j Repeat step 2.2.3. i With cluster c j The distance calculation formula is:

[0115]

[0116] d avg (c i , c j ) is cluster c i 、c j Distance, m i 、m j Cluster c i 、c j The number of elements, s i c i Any element in s j c j Any element in ||s i -s j || is element s i and j distance.

[0117] 2.2.6. According to steps 2.2.1-2.2.5, the set of medium-risk inspection sections L can be calculated. 中 , L 中 ={l1,l2,...,lh}, h = T 中 , general risk inspection section set L 一般 , L 一般 ={l1,l2,...,l r}, r = T 一般 , low-risk inspection section set L 低 , L 低 ={l1,l2,...,l u},u=T 低 .

[0118] 2.3. Based on the inspection pipeline sections of different risk levels obtained in 2.2, plan the inspection route on the inspection working day according to the following steps.

[0119] 2.3.1. On the starting day of the inspection cycle corresponding to the inspection pipe sections of different risk levels, initialize the set of pipe sections to be inspected, and obtain the set of high-risk pipe sections to be inspected Y 高 , Y 高 =L 高 , the set of risk pipe sections to be inspected is Y 中 , Y 中 =L 中 , the set of general risk pipe sections to be inspected is Y 一般 , Y 一般 =L 一般 , low-risk pipe section collection to be inspected Y 低 , Y 低 =L 低 .

[0120] 2.3.2. On inspection days, from Y 高 Take any uninspected subset y a ,y a ∈Y 高 , as the high-risk pipe section planned for inspection that day, and then traverse Y 中 The uninspected subset of a The nearest medium-risk pipeline segment subset y b ,y b ∈Y 中 , then traverse Y 一般 The uninspected subset in the calculation is the same as y a ,y b The subset y of the uninspected general risk pipe sections with the smallest sum of distances c ,y c ∈Y 一般 , and finally traverse Y 低 The uninspected subset in the calculation is the same as y a ,y b ,y cThe subset y of uninspected low-risk pipe sections with the smallest sum of distances d ,y d ∈Y 低 , where the distance between the two sets is calculated as formula (4). From the above, we can get the combination y of all the planned inspection sections on this inspection working day, y = {y a ,y b ,y c ,y d}. After the workday inspection plan is completed, a ,y b ,y c ,y d Remove from the corresponding set of pipe sections to be inspected, and determine the number of remaining uninspected sub-sets in each set of pipe sections to be inspected. If the number of remaining uninspected sub-sets is 0, it is necessary to reinitialize the set of pipe sections to be inspected of the risk level.

[0121] 2.3.3. For the inspection workday planned inspection pipe section combination y obtained in step 2.3.2, there are two inspection route planning methods: the first method is to inspect from high to low risk level, that is, to inspect the planned inspection pipe sections of various risk levels in the order of high risk, medium risk, general risk, and low risk. In this case, set the inspection starting point s0, and apply the path planning method to solve y a Optimal inspection path R a , then R a The end point of the path is taken as the starting point, and y is obtained. b The optimal inspection path R b According to this method, the end point of the optimal inspection path is used as the starting point of the next inspection path planning, and y c ,y d The optimal inspection paths are R c , R d The optimal inspection route for the inspection workday is obtained by summarizing the inspection route according to s0-R a -R b -R c -R d The first method is to inspect the routes in sequence; the second method is to inspect according to the optimal route, that is, to mix all the pipe sections with different risk levels in y, take the inspection starting point s0 as the starting point, apply the path planning method to solve the optimal inspection path, and then conduct inspection according to the optimal inspection path.

[0122] 2.3.4 The path planning method in step 2.3.3 is to solve the traveling salesman problem (TSP). Its solution methods include ant colony algorithm, genetic algorithm, taboo search algorithm, simulated annealing algorithm, neural network, etc., which are well-known technologies that are widely studied and applied at present, and will not be discussed in detail here.

[0123] It should also be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0124] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0125] The above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for planning inspection routes for urban sewage pipe networks based on risk levels, characterized in that: include: S1: Applying the analytic hierarchy process and fuzzy comprehensive evaluation, the operation risk level of all pipe sections in the inspection area sewage pipe network is determined; S2: For the set of pipe sections with different risk levels, the k-means++ clustering algorithm is applied to obtain the clustering results of pipe sections with different risk levels; S3: Based on the clustering results in S2, and according to the inspection cycles corresponding to the pipe sections of different risk levels, calculate the inspection pipe section sets of different risk levels; S4: combining the inspection pipe section set in S3 to obtain the planned inspection pipe section set on the inspection working day; applying the path planning method to obtain the optimal inspection path of the planned inspection pipe section.

2. The method for planning inspection routes of urban sewage pipe networks based on risk levels according to claim 1 is characterized in that: The S1 step is specifically as follows: Establish a sewage pipe network operation risk assessment index system based on the evaluation indicators of pipe age, pipe diameter, pipe material, pipe burial depth, pipe length, pipe type, pipe interface, pipe foundation, soil type, road grade, construction status, occupation status, regional type, traffic load, and maintenance frequency; The 15 basic indicators in the sewage network operation risk assessment index system are subjectively weighted by the analytic hierarchy process, and the weight vector of each basic indicator is calculated; A membership evaluation matrix is ​​established, the evaluation results are calculated using fuzzy comprehensive evaluation, and the level of the evaluation results is determined based on the maximum membership principle.

3. The method for planning inspection routes of urban sewage pipe networks based on risk levels according to claim 2 is characterized in that: The pipe age, pipe diameter, pipe material, pipe burial depth, pipe length, pipe type, pipe interface and pipe foundation are collectively classified as pipe factors, the soil type, road grade, construction situation, occupation situation, regional type and traffic load are collectively classified as environmental factors, the maintenance frequency is a management factor, the sewage pipe network operation risk is taken as the target layer, the pipe factors, environmental factors and management factors are taken as the criterion layer, and the basic indicators are taken as the sub-criterion layer, and a judgment matrix of the criterion layer indicators and the sub-criterion layer indicators is constructed, which is recorded as a judgment matrix A; Performing consistency check on the obtained judgment matrix A, and judging whether the construction of the judgment matrix is ​​reasonable by calculating the consistency index and the consistency ratio; After the judgment matrix A passes the consistency check, the maximum eigenvalue and the corresponding weight vector of the judgment matrix A are obtained; according to the above method, the weight vector Wn of the sub-criteria layer index to the criterion layer to which it belongs and the weight vector W of the criterion layer index to the target layer can be obtained; The weight vector Wn and the weight vector W are used to perform a fuzzy comprehensive evaluation on the membership evaluation matrix to obtain the risk levels corresponding to all pipe sections of the sewage pipe network in the inspection area.

4. The method for planning inspection routes of urban sewage pipe networks based on risk levels according to claim 3 is characterized in that: The construction method of the judgment matrix A is: First, drainage network business experts judge the importance scale of sub-criteria layer indicators to the criterion layer indicators they belong to based on their professional knowledge and practical experience, and construct a judgment matrix of sub-criteria layer indicators to the criterion layer indicators they belong to; then, drainage network business experts judge the importance scale of criterion layer indicators to the target layer.

5. The method for planning inspection routes of urban sewage pipe networks based on risk levels according to claim 1 is characterized in that: In step S2, the distance between samples of the clustering algorithm is the distance between the longitude and latitude coordinates of the starting positions of two pipe segments. The clustering algorithm parameters and sample distances corresponding to different pipe segment sets are calculated by the haversine formula, and the k-means++ algorithm is used to cluster the pipe segment sets respectively.

6. A method for planning inspection routes for urban sewage pipe networks based on risk levels according to claim 1, characterized in that: The S3 step is specifically as follows: The preset length of the high-risk inspection pipe section set and its corresponding subset can be obtained through the number of high-risk pipe sections and the inspection cycle. The inspection starting point is determined and the minimum pipe section from the starting point and the cluster where the minimum pipe section is located are obtained through traversal, thereby obtaining the inspection pipe section sets with medium risk, general risk and low risk.

7. A method for planning inspection routes for urban sewage pipe networks based on risk levels according to claim 1, characterized in that: The S4 step is specifically as follows: On the starting day of the inspection cycle corresponding to the inspection pipe sections of different risk levels, the set of pipe sections to be inspected is initialized to obtain a set of high-risk pipe sections to be inspected, a set of medium-risk pipe sections to be inspected, a set of general-risk pipe sections to be inspected, and a set of low-risk pipe sections to be inspected; On the inspection working day, randomly select a subset ya from the set of high-risk pipe sections to be inspected as the high-risk pipe section to be inspected on that day, then traverse the subsets of the medium-risk pipe sections to be inspected that have not been inspected, calculate the subset of medium-risk pipe sections yb that is closest to ya, then traverse the subsets of the medium-risk pipe sections to be inspected that have not been inspected, and calculate the subset of medium-risk pipe sections yb that is closest to y. a ,y b The subset y of the uninspected general risk pipe sections with the smallest sum of distances c Finally, traverse the uninspected sub-sets in the low-risk pipe section set to be inspected and calculate the a ,y b ,y c The subset of uninspected low-risk pipe sections yd with the smallest sum of distances; from the above, the combination y of all planned inspection pipe sections on the inspection working day is obtained; Inspection is performed through all planned inspection pipe section combinations y on the inspection working day.

8. The method for planning inspection routes of urban sewage pipe networks based on risk levels according to claim 7 is characterized in that: After the workday inspection plan is completed, a ,y b ,y c ,y d Remove from the corresponding set of pipe sections to be inspected, and determine the number of remaining uninspected sub-sets in each set of pipe sections to be inspected. If the number of remaining uninspected sub-sets is 0, it is necessary to reinitialize the set of pipe sections to be inspected of the risk level.

9. The method for planning inspection routes of urban sewage pipe networks based on risk levels according to claim 7 is characterized in that: The inspection workday planned inspection pipe section combination y can be used to plan the inspection route by one of the following methods: inspection from high to low risk level and inspection according to the optimal route.

10. A method for planning inspection routes for urban sewage pipe networks based on risk levels according to claim 9, characterized in that: The inspection route planning is to solve the traveling salesman problem, and the solution method thereof can be solved by using one of an ant colony algorithm, a genetic algorithm, a taboo search algorithm, a simulated annealing algorithm and a neural network.

Images