[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN111680374A - Method for checking and repairing topological relation of pipe network - Google Patents

Method for checking and repairing topological relation of pipe network Download PDF

Info

Publication number
CN111680374A
CN111680374A CN202010434121.2A CN202010434121A CN111680374A CN 111680374 A CN111680374 A CN 111680374A CN 202010434121 A CN202010434121 A CN 202010434121A CN 111680374 A CN111680374 A CN 111680374A
Authority
CN
China
Prior art keywords
node
pipe network
abnormal
individual
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202010434121.2A
Other languages
Chinese (zh)
Other versions
CN111680374B (en
Inventor
凡伟伟
郑宝中
董毓良
付明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hefei Zezhong City Intelligent Technology Co ltd
Hefei Institute for Public Safety Research Tsinghua University
Original Assignee
Hefei Zezhong City Intelligent Technology Co ltd
Hefei Institute for Public Safety Research Tsinghua University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hefei Zezhong City Intelligent Technology Co ltd, Hefei Institute for Public Safety Research Tsinghua University filed Critical Hefei Zezhong City Intelligent Technology Co ltd
Priority to CN202010434121.2A priority Critical patent/CN111680374B/en
Publication of CN111680374A publication Critical patent/CN111680374A/en
Application granted granted Critical
Publication of CN111680374B publication Critical patent/CN111680374B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/04—Constraint-based CAD
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/14—Pipes

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Geometry (AREA)
  • Computer Hardware Design (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Molecular Biology (AREA)
  • Genetics & Genomics (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Computational Mathematics (AREA)
  • Computing Systems (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Physiology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a method for checking and repairing a pipe network topological relation, which comprises the steps of selecting a pipe network path with a known flow direction, and measuring initial inner bottom elevation values of all nodes of the pipe network according to the sequence of the flow direction; sequentially traversing all the pipe sections along the flow direction of the pipe network path, and calculating the gradient of each pipe section; checking whether a negative value exists in the gradient data; removing negative value data, forming data set with the remaining non-negative value gradient data, identifying abnormal gradient data, counting normal gradient data, and obtaining normal gradient interval range [ s ]min,smax](ii) a Identifying slope data as negativeAnd forming an abnormal node set by the slope and the starting and stopping nodes of the pipe section corresponding to the abnormal slope data, and adjusting the inner bottom elevation value of the abnormal nodes in the abnormal node set, wherein the abnormal nodes with the abnormal inner bottom elevation exist in the abnormal node set. The method has the advantages of realizing automatic identification, automatic modification and optimization of the elevation of the inner bottom of the abnormal node of the pipe network, along with convenience, rapidness, high efficiency and accuracy.

Description

Method for checking and repairing topological relation of pipe network
Technical Field
The invention relates to the technical field of drainage pipe networks, in particular to a method for checking and repairing a topological relation of a pipe network.
Background
The urban underground drainage pipe network has the characteristics of large system, strong concealment, outstanding safety problems and the like, and in recent years, urban managers attach more and more importance to the general investigation work of the basic information of the urban underground drainage pipe network so as to solve the problems of incomplete and unclear information control of the urban underground drainage pipe network by management departments and provide guarantee for the safe operation and the quality improvement and efficiency enhancement work of the urban drainage system. The general investigation of the basic information of the drainage pipe network mainly comprises the general investigation of the basic information of the positions, the connections, the elevations, the burial depths, the lengths and the like of drainage facilities such as drainage pipes, underdrains, inspection wells, rainwater grates and the like. The elevation data of pipe network nodes such as inspection wells, inspection wells and the like comprises ground elevation and inner bottom elevation, and is used as one of key basic information of a drainage pipe network, the accuracy of the elevation data is very critical, and the hydraulic working condition analysis, the operation scheduling and the later-stage transformation plan of a manager on the drainage pipe network are directly influenced.
The number of nodes such as inspection wells and inspection wells of the urban underground drainage pipe network is large, partial abnormal data generally exist in general investigation results due to the fact that problems such as accuracy of measuring tools and negligence of measuring personnel exist in the pipe network detection process, if the elevation of inner bottoms of pipe network nodes is abnormal, the problem that the pipe network is in a reverse slope in a topological relation is caused, and serious influences are caused on hydraulic modeling and operation scheduling of the pipe network, so that after general investigation of the drainage pipe network is finished, the topology of the drainage pipe network needs to be inspected, repaired or re-measured. In 2012, the city pipe network spatial data quality inspection system design and implementation of the yaoyao and the like in the major thesis of city pipe network spatial data quality inspection system design and implementation of the yaoyao in the ministry of our university studies on city pipe network spatial data as a main research object, researches on a city pipe network spatial data quality model of the system according to specifications and standards of a large amount of spatial data, analyzes a rule model and a method for city pipe network spatial data quality inspection in detail, obtains a rule base for city pipe network spatial data quality inspection based on the rule base and an evaluation software result, but does not specifically provide a method for automatically inspecting pipe network data. At present, topology inspection and modification of a drainage pipe network mainly depend on manual work to carry out section-by-section and point-by-point inspection on all pipe sections and all nodes, data of upstream and downstream nodes are combined to judge whether a problem of adverse slope exists, and if the problem of adverse slope exists, the elevation of an inner bottom of each node is manually modified by referring to the gradient of upstream and downstream pipe sections. The method for manually checking and modifying the topology of the pipe network has the disadvantages of huge workload, low efficiency and high time cost.
Disclosure of Invention
The invention aims to solve the technical problems of large workload, low efficiency and high time cost in pipe network inspection in the prior art.
The invention solves the technical problems by the following technical means: a method for checking and repairing a pipe network topological relation comprises the following steps:
s1, selecting a pipe network path with a known flow direction from the pipe network to be inspected, marking n nodes according to the front-back sequence of the flow direction, measuring the initial inner bottom elevation values of all nodes of the pipe network, and ensuring the accuracy of the initial inner bottom elevation values of the nodes at the initial position;
the node comprises an inspection well and a water outlet according to the flow direction of a pipe network to be inspected;
s2, forming a pipe section by the pipelines between adjacent nodes, sequentially traversing all the pipe sections along the flow direction of the pipe network path, and calculating the gradient of each section of pipe section to obtain gradient data of the pipe section;
s3, checking whether the gradient data has a negative value; removing negative value data, forming a data set by the remaining non-negative value gradient data, performing statistical analysis on the data set, identifying abnormal gradient data in the data set, performing statistical analysis on normal gradient data, and obtaining the interval range [ s ] of the normal gradientmin,smax]；
S4, recognitionThe abnormal gradient data is a negative gradient and a starting node and a stopping node of a pipe section corresponding to the abnormal gradient data to form an abnormal node set J; and other nodes (i.e., node numbers)
Figure BDA0002501599530000021
Node(s) is then a normal node having a normal inner bottom elevation.
And S5, adjusting the initial inner bottom elevation value of the abnormal nodes in the abnormal node set, wherein the abnormal nodes with abnormal inner bottom elevations exist in the abnormal node set.
For a pipe network path capable of clearly judging the flow direction, the method calculates the gradient of all pipe sections, automatically identifies the gradient data of the abnormal pipe sections and the corresponding starting and ending nodes of the abnormal pipe sections through a box diagram algorithm, and automatically modifies and optimizes the elevation of the inner bottom of the abnormal node of the abnormal pipe section in the abnormal pipe sections by establishing a fitness function and constraint conditions. The intelligent inspection method for the drainage pipe network topology realizes automatic identification, automatic modification and optimization of the elevation of the inner bottom of the abnormal node of the pipe network, and is convenient, rapid, efficient and accurate.
Preferably, the slope data of the pipe section in S2 is obtained by using the following model:
Figure BDA0002501599530000022
wherein i is the ith node of the pipe network path, n nodes are all provided, i is 1, the node of the starting position of the pipe network path from the upstream, and L is the node of the starting position of the pipe network path from the upstreami,i+1Representing the length of the pipe section between the starting node i and the ending node i +1,
Figure BDA0002501599530000023
represents the initial insole height value of the ith node, the following table i represents the ith node, the superscript 0 represents the initial value,
Figure BDA0002501599530000024
representing the initial insole height value of the (i + 1) th node.
Preferably, in S3, statistical analysis is performed on the data set by using a boxplot algorithm-based abnormal gradient data identification method;
s31, forming a data set by the remaining non-negative gradient data, and arranging the elements of the data set in a descending order;
s32, calculating the first quartile Q of all non-negative gradient data in the descending data set1＝min{[1+(k-1)·0.25]，(k+1)·0.25}；
Calculating a third quartile Q of all non-negative slope data in the descending order data set3＝max{[1+(k-1)·0.75]，(k+1)·0.75}；
Calculating the interquartile range IQR ═ Q3-Q1；
k is the number of all non-negative gradient data;
s33, calculating abnormal value cut-off point (Q)3+1.5IQR) and (Q)1-1.5IQR), non-negative values of slope data greater than (Q)3+1.5IQR) or less than (Q)1-1.5IQR) is abnormal gradient data.
Preferably, in S5, the height value of the inner bottom of the abnormal node in the abnormal node set is adjusted in the following manner;
s51, taking the insole elevation values of all nodes on the pipe network path as variables to be optimized, constructing an objective function according to the initial insole elevation values of all the nodes, and taking the reciprocal of the objective function as a fitness function;
the construction of the objective function is:
Figure BDA0002501599530000031
constructing a fitness function as follows:
Figure BDA0002501599530000032
Eithe adjusted inner bottom elevation value of the ith node is obtained;
the following conditions are used as constraints of the fitness function:
(a) the gradient data of the pipe section, which is calculated by the adjusted inner bottom elevation value of the node, is within the interval range of the normal gradient:
Figure BDA0002501599530000033
(b) the adjusted inner bottom elevation value of the node is set at a depth below the ground:
Figure BDA0002501599530000034
Figure BDA0002501599530000035
deep is the minimum depth of the inspection well specified by the engineering design specification for the ground elevation of the ith node;
(c) the nodes with normal initial insole height values,
Figure BDA0002501599530000036
the inner bottom elevation value does not need to be modified, and the initial inner bottom elevation value is directly taken:
Figure BDA0002501599530000037
setting the abnormal node set as a set J, and setting other nodes as normal nodes with normal inner bottom elevation values;
converting the constraint conditions into matrix forms respectively as follows:
Figure BDA0002501599530000041
Figure BDA0002501599530000042
Figure BDA0002501599530000043
in the formula, E1Indicating the adjusted insole height, E, of the 1 st node2Indicating the adjusted insole height, E, of the 2 nd nodenRepresents the adjusted inner bottom elevation value, L, of the nth node1-2Represents the length of the pipe segment between a starting node of 1 and a terminating node of 2, L2-3Indicating the length of the pipe segment between a start node of 2 and an end node of 3, Ln-1-nRepresenting the length of the pipe segment between the start node n-1 and the end node n, sminInterval range of normal gradient [ smin,smax]Lower limit of (d), smaxInterval range of normal gradient [ smin,smax]The upper limit of (a) is,
Figure BDA0002501599530000044
is the ground elevation of the 1 st node,
Figure BDA0002501599530000045
is the ground elevation of the 2 nd node,
Figure BDA0002501599530000046
the ground elevation of the nth node and deep is the minimum depth of the inspection well specified by the engineering design specification,
Figure BDA0002501599530000047
represents adjusted insole elevation values for nodes outside abnormal node set J,
Figure BDA0002501599530000048
representing the initial insole height values of nodes outside the abnormal node set J.
S52, encoding the inner bottom elevation variables of each node by using a floating point number encoding mode, wherein the encoding length is n and is the same as the number of the variables;
s53, arranging the floating point numbers in n designated ranges into an individual, and randomly generating a plurality of individuals as an initial population;
s54, calculating the fitness function value f of each individual of the initial populationiCalculating the selection of each individual into the next generation populationProbability P ofi(ii) a In the individual selection process, two individuals are selected each time according to a roulette selection mechanism, wherein the individuals with high fitness enter a next generation population;
where f isiSpecifically representing the fitness function value of the ith individual in the initial population; piRepresenting the probability that the ith individual is selected into the next generation population;
s55, randomly pairing the new population individuals in pairs for the new population generated by the selection operation, and calculating the cross probability P of each paircCarrying out non-uniform arithmetic crossing on the two paired individuals according to the crossing probability; wherein the cross probability PcDynamically changing with individual fitness:
s56, according to the mutation probability PmPerforming basic potential variation operation on the population individuals after the cross operation; wherein the mutation probability PmDynamically changing with individual fitness:
s57, obtaining a progeny population after mutation operation, calculating fitness function values of each individual of the progeny population, and outputting an individual with the highest fitness, namely an optimal fitness individual; comparing the optimal fitness individual with the optimal fitness individual of the parent population, and taking whether the Euclidean distance of the two individuals is smaller than the allowable residual error as a convergence condition of population evolution;
s58, if the convergence condition is met, the optimal fitness individual is the optimal individual, and the individual gene value is the optimal pipe network node inner bottom elevation value which is the adjusted pipe network node inner bottom elevation value; if the convergence condition is not met, returning to the step S54, and continuing to perform selection, crossing and mutation operations of the offspring population until the offspring population meets the convergence condition;
or setting the maximum evolution algebra of the population, stopping calculation when the maximum evolution algebra is reached, and outputting the optimal fitness individual as the optimal individual.
Preferably, in said S54
Figure BDA0002501599530000051
Preferably, in said S55
Figure BDA0002501599530000052
fmax、favgRespectively representing the maximum fitness and the average fitness, k, of the new population generated by the selection operation1、k2Is a constant number, k1<k2。
Preferably, in S55, the genes to be crossed in two individuals are set as x and y, and the new genes formed after crossing are x 'and y':
Figure BDA0002501599530000061
in the formula, alpha is a random number which accords with uniform probability distribution in the range of (0, r), r is more than 0 and less than or equal to 1, and r changes along with evolution algebra.
Preferably, in said S56
Figure BDA0002501599530000062
f’max、f’avgRespectively representing the maximum fitness and the average fitness, k, of the new population generated by the cross operation3、k4Is a constant number, k3<k4。
Preferably, in S56, the gene to be mutated in the individual is designated as z, and the new gene after mutation z' is:
z'＝z+(R-L)·γ
gamma is a random number which accords with uniform probability distribution in the range of [0,1], L and R are respectively the left boundary and the right boundary of the value range of the corresponding gene, z is more than or equal to L and less than or equal to R, and L and R are respectively solved according to the constraint condition of the fitness function.
Preferably, the euclidean distance of two individuals in S57 is:
Figure BDA0002501599530000063
Figure BDA0002501599530000064
respectively as the optimal fitness individuals of the parent population and the offspring population, and as the set allowable residual error, x1 iRepresents the individual X with the optimal fitness in the i generation filial population i1 gene of (2), xn iRepresents the individual X with the optimal fitness in the i generation filial populationiThe nth gene of (1), xn i+1Represents the individual X with the optimal fitness in the i +1 generation filial populationi+1The nth gene of (1).
The invention has the advantages that: for a pipe network path capable of clearly judging the flow direction, the method calculates the gradient of all pipe sections, automatically identifies the gradient data of the abnormal pipe sections and the corresponding starting and ending nodes of the abnormal pipe sections through a box diagram algorithm, and automatically modifies and optimizes the elevation of the inner bottom of the abnormal node of the abnormal pipe section in the abnormal pipe sections by establishing a fitness function and constraint conditions. The intelligent inspection method for the drainage pipe network topology realizes automatic identification, automatic modification and optimization of the elevation of the inner bottom of the abnormal node of the pipe network, and is convenient, rapid, efficient and accurate.
Drawings
Fig. 1 is a flowchart of a method for checking and repairing a topology relationship of a pipe network according to embodiment 1 of the present invention;
FIG. 2 is a flowchart illustrating the method of adjusting the initial insole height of abnormal nodes in the abnormal node set according to embodiment 1 of the present invention;
fig. 3 is a schematic view of a topology structure of a drainage pipe network in embodiment 2 of the present invention;
in the drawings, arrows indicate flow directions.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
A method for checking and repairing a pipe network topological relation comprises the following steps:
s1, selecting a pipe network path with a known flow direction from the pipe network to be inspected, marking n nodes according to the front-back sequence of the flow direction, measuring the initial inner bottom elevation values of all nodes of the pipe network, and ensuring the accuracy of the initial inner bottom elevation values of the nodes at the initial position;
s2, forming a pipe section by the pipelines between adjacent nodes, sequentially traversing all the pipe sections along the flow direction of the pipe network path, and calculating the gradient of each section of pipe section to obtain gradient data of the pipe section;
the gradient data of the pipe section in the S2 is obtained by adopting the following model:
Figure BDA0002501599530000071
wherein i is the ith node of the pipe network path, n nodes are all provided, i is 1, the node of the starting position of the pipe network path from the upstream, and L is the node of the starting position of the pipe network path from the upstreami,i+1Representing the length of the pipe section between the starting node i and the ending node i +1,
Figure BDA0002501599530000072
represents the initial insole height value of the ith node, the following table i represents the ith node, the superscript 0 represents the initial value,
Figure BDA0002501599530000073
representing the initial insole height value of the (i + 1) th node.
S3, checking whether the gradient data has a negative value; removing negative value data, forming a data set by the remaining non-negative value gradient data, performing statistical analysis on the data set, identifying abnormal gradient data in the data set, performing statistical analysis on normal gradient data, and obtaining the interval range [ s ] of the normal gradientmin,smax]；
Performing statistical analysis on the data set in the following manner in S3;
s31, forming a data set by the remaining non-negative gradient data, and arranging the elements of the data set in a descending order;
s32, calculating the first quartile Q of all non-negative gradient data in the descending data set1＝min{[1+(k-1)·0.25]，(k+1)·0.25}；
Calculating a third quartile Q of all non-negative slope data in the descending order data set3＝max{[1+(k-1)·0.75]，(k+1)·0.75}；
Calculating the interquartile range IQR ═ Q3-Q1；
k is the number of all non-negative gradient data;
s33, calculating abnormal value cut-off point (Q)3+1.5IQR) and (Q)1-1.5IQR), non-negative values of slope data greater than (Q)3+1.5IQR) or less than (Q)1-1.5IQR) is abnormal gradient data.
S4, identifying the slope data as a negative slope and the start and stop nodes of the pipe section corresponding to the abnormal slope data to form an abnormal node set J;
and S5, adjusting the initial inner bottom elevation value of the abnormal nodes in the abnormal node set, wherein the abnormal nodes with abnormal inner bottom elevations exist in the abnormal node set.
Adjusting the height value of the inner bottom of the abnormal node in the abnormal node set in the following mode;
s51, taking the insole elevation values of all nodes on the pipe network path as variables to be optimized, constructing an objective function according to the initial insole elevation values of all the nodes, and taking the reciprocal of the objective function as a fitness function;
the construction of the objective function is:
Figure BDA0002501599530000081
constructing a fitness function as follows:
Figure BDA0002501599530000082
Eithe adjusted inner bottom elevation value of the ith node is obtained;
the following conditions are used as constraints of the fitness function:
(a) the gradient data of the pipe section, which is calculated by the adjusted inner bottom elevation value of the node, is within the interval range of the normal gradient:
Figure BDA0002501599530000083
(b) the adjusted inner bottom elevation value of the node is set at a depth below the ground:
Figure BDA0002501599530000084
Figure BDA0002501599530000085
deep is the minimum depth of the inspection well specified by the engineering design specification for the ground elevation of the ith node;
(c) the nodes with normal initial insole height values,
Figure BDA0002501599530000086
the inner bottom elevation value does not need to be modified, and the initial inner bottom elevation value is directly taken:
Figure BDA0002501599530000091
setting the abnormal node set as a set J, and setting other nodes as normal nodes with normal inner bottom elevation values;
converting the constraint conditions into matrix forms respectively as follows:
Figure BDA0002501599530000092
Figure BDA0002501599530000093
Figure BDA0002501599530000094
in the formula, E1Indicating the adjusted insole height, E, of the 1 st node2Indicating the adjusted insole height, E, of the 2 nd nodenRepresents the adjusted inner bottom elevation value, L, of the nth node1-2Represents the length of the pipe segment between a starting node of 1 and a terminating node of 2, L2-3Indicating the length of the pipe segment between a start node of 2 and an end node of 3, Ln-1-nRepresenting the length of the pipe segment between the start node n-1 and the end node n, sminInterval range of normal gradient [ smin,smax]Lower limit of (d), smaxInterval range of normal gradient [ smin,smax]The upper limit of (a) is,
Figure BDA0002501599530000095
is the ground elevation of the 1 st node,
Figure BDA0002501599530000096
is the ground elevation of the 2 nd node,
Figure BDA0002501599530000097
the ground elevation of the nth node and deep is the minimum depth of the inspection well specified by the engineering design specification,
Figure BDA0002501599530000098
represents adjusted insole elevation values for nodes outside abnormal node set J,
Figure BDA0002501599530000099
representing the initial insole height values of nodes outside the abnormal node set J.
S52, encoding the inner bottom elevation variables of each node by using a floating point number encoding mode, wherein the encoding length is n and is the same as the number of the variables;
s53, arranging the floating point numbers in n designated ranges into an individual, and randomly generating a plurality of individuals as an initial population;
s54, calculating the fitness function value f of each individual of the initial populationiCalculating the probability P that each individual is selected to enter the next generation populationi(ii) a In the individual selection process, two individuals are selected each time according to a roulette selection mechanism, wherein the individuals with high fitness enter a next generation population;
s55, randomly pairing the new population individuals in pairs for the new population generated by the selection operation, and calculating the cross probability P of each paircCarrying out non-uniform arithmetic crossing on the two paired individuals according to the crossing probability; wherein the cross probability PcDynamically changing with individual fitness:
setting the genes to be crossed of two individuals as x and y, and setting the new genes formed after crossing as x 'and y':
Figure BDA0002501599530000101
in the formula, alpha is a random number which accords with uniform probability distribution in the range of (0, r), r is more than 0 and less than or equal to 1, and r changes along with evolution algebra;
s56, according to the mutation probability PmPerforming basic potential variation operation on the population individuals after the cross operation; wherein the mutation probability PmDynamically changing with individual fitness:
s57, obtaining a progeny population after mutation operation, calculating fitness function values of each individual of the progeny population, and outputting an individual with the highest fitness, namely an optimal fitness individual; comparing the optimal fitness individual with the optimal fitness individual of the parent population, and taking whether the Euclidean distance of the two individuals is smaller than the allowable residual error as a convergence condition of population evolution;
s58, if the convergence condition is met, the optimal fitness individual is the optimal individual, and the individual gene value is the optimal elevation value of the inner bottom of the pipe network node; if the convergence condition is not met, returning to the step S54, and continuing to perform selection, crossing and mutation operations of the offspring population until the offspring population meets the convergence condition;
or setting the maximum evolution algebra of the population, stopping calculation when the maximum evolution algebra is reached, and outputting the optimal fitness individual as the optimal individual.
In said S54
Figure BDA0002501599530000102
In said S55
Figure BDA0002501599530000103
fmax、favgRespectively representing the maximum fitness and the average fitness, k, of the new population generated by the selection operation1、k2Is a constant number, k1<k2。
Figure BDA0002501599530000111
f’max、f’avgRespectively representing the maximum fitness and the average fitness, k, of the new population generated by the cross operation3、k4Is a constant number, k3<k4。
In S56, the gene to be mutated in an individual is designated as z, and the new gene after mutation z' is:
z'＝z+(R-L)·γ
gamma is a random number which accords with uniform probability distribution in the range of [0,1], L and R are respectively the left boundary and the right boundary of the value range of the corresponding gene, z is more than or equal to L and less than or equal to R, and L and R are respectively solved according to the constraint condition of the fitness function.
Preferably, the euclidean distance of two individuals in S57 is:
Figure BDA0002501599530000112
Figure BDA0002501599530000113
respectively as the optimal fitness individuals of the parent population and the offspring population, and as the set allowable residual error, x1 iRepresents the individual X with the optimal fitness in the i generation filial population i1 gene of (2), xn iRepresents the individual X with the optimal fitness in the i generation filial populationiThe nth gene of (1), xn i+1Represents the individual X with the optimal fitness in the i +1 generation filial populationi+1The nth gene of (1).
Example 2
The embodiment discloses a method for checking and repairing the topological relation of the drainage pipe network by adopting the method for checking and repairing the topological relation of the pipe network.
As shown in fig. 3, the topology of the drainage network is shown, wherein the reference numbers of the "MH" prefix represent inspection well nodes, the reference numbers of the "O" prefix represent water gap nodes, and the reference numbers of the "CO" prefix represent pipe segments. According to the position of the water outlet of the pipe network, the elevation of urban terrain and the characteristics of a water system, the water flow direction of the pipe network can be determined, as shown by arrows in the figure. Table 1 shows the parameters associated with the inspection well and the water outlet nodes, and table 2 shows the parameters of each pipe section. Knowing that the insole height values of upstream initial nodes MH-1, MH-13, MH-19 and MH-25 of the pipe network are accurate values, the topological intelligent inspection method for the drainage pipe network is used for searching and modifying the insole height values of abnormal nodes.
TABLE 1 node parameters
Figure BDA0002501599530000121
TABLE 2 pipe section parameters
Figure BDA0002501599530000122
Figure BDA0002501599530000131
As shown in fig. 3, a pipe network path i (MH-1_ MH-2_ MH-3_ … _ MH-12_ O-1), a path ii (MH-13_ MH-14_ … _ MH-4_ … _ MH-7), a path iii (MH-19_ MH-20_ … _ MH-7_ … _ MH-10) and a path iv (MH-25_ MH-26_ … _ MH-10_ … _ O-1) are selected for inspection, and table 3 shows the results of automatic inspection and modification of the node insole elevation.
Table 3 node check results
Figure BDA0002501599530000132
Figure BDA0002501599530000141
In summary, for a pipe network path capable of clearly judging the flow direction, the invention firstly calculates the gradient of all pipe sections, then automatically identifies the gradient data of the abnormal pipe sections and the corresponding starting and ending nodes of the abnormal pipe sections by the box-line graph algorithm, and finally automatically modifies and optimizes the inner bottom elevation of the abnormal node of the abnormal pipe section in the abnormal pipe sections by establishing a fitness function and constraint conditions and utilizing a genetic algorithm. The intelligent inspection method for the drainage pipe network topology realizes automatic identification, automatic modification and optimization of the elevation of the inner bottom of the abnormal node of the pipe network, and is convenient, rapid, efficient and accurate.
It is noted that the presence of relational terms such as first and second, and the like, if any, are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (10)

1. A method for checking and repairing a pipe network topological relation is characterized by comprising the following steps:
s1, selecting a pipe network path with a known flow direction from the pipe network to be inspected, marking n nodes according to the front-back sequence of the flow direction, and measuring the initial inner bottom elevation values of all the nodes of the pipe network;
s2, forming a pipe section by the pipelines between adjacent nodes, sequentially traversing all the pipe sections along the flow direction of the pipe network path, and calculating the gradient of each section of pipe section to obtain gradient data of the pipe section;
s3, checking whether the gradient data has a negative value; removing negative value data, forming a data set by the remaining non-negative value gradient data, performing statistical analysis on the data set, identifying abnormal gradient data in the data set, performing statistical analysis on normal gradient data, and obtaining the interval range [ s ] of the normal gradientmin,smax]；
S4, identifying the slope data as a negative slope and the start and stop nodes of the pipe section corresponding to the abnormal slope data to form an abnormal node set J;
and S5, adjusting the initial insole height value of the abnormal nodes in the abnormal node set.
2. The method for checking and repairing the topological relation of the pipe network according to claim 1, wherein the gradient data of the pipe section in the step S2 is obtained by using the following model:
Figure FDA0002501599520000011
wherein i is the ith node of the pipe network path, n nodes are all provided, and i is 1 node of the starting position of the pipe network path from upstreamPoint, Li,i+1Representing the length of the pipe section between the starting node i and the ending node i +1,
Figure FDA0002501599520000012
represents the initial insole height value of the ith node, the following table i represents the ith node, the superscript 0 represents the initial value,
Figure FDA0002501599520000013
representing the initial insole height value of the (i + 1) th node.
3. The method for checking and repairing the topological relation of the pipe network according to claim 1, wherein in S3, the statistical analysis of the data set is implemented in the following manner;
s31, forming a data set by the remaining non-negative gradient data, and arranging the elements of the data set in a descending order;
s32, calculating the first quartile Q of all non-negative gradient data in the descending data set1＝min{[1+(k-1)·0.25]，(k+1)·0.25}；
Calculating a third quartile Q of all non-negative slope data in the descending order data set3＝max{[1+(k-1)·0.75]，(k+1)·0.75}；
Calculating the interquartile range IQR ═ Q3-Q1；
k is the number of all non-negative gradient data;
s33, calculating abnormal value cut-off point (Q)3+1.5IQR) and (Q)1-1.5IQR), non-negative values of slope data greater than (Q)3+1.5IQR) or less than (Q)1-1.5IQR) is abnormal gradient data.
4. The method for checking and repairing the topological relation of the pipe network according to claim 1, wherein in S5, the height value of the inner bottom of the abnormal node in the abnormal node set is adjusted in the following manner;
s51, taking the insole elevation values of all nodes on the pipe network path as variables to be optimized, constructing an objective function according to the initial insole elevation values of all the nodes, and taking the reciprocal of the objective function as a fitness function;
the construction of the objective function is:
Figure FDA0002501599520000021
constructing a fitness function as follows:
Figure FDA0002501599520000022
Eithe adjusted inner bottom elevation value of the ith node is obtained;
the following conditions are used as constraints of the fitness function:
(a) the gradient data of the pipe section, which is calculated by the adjusted inner bottom elevation value of the node, is within the interval range of the normal gradient:
Figure FDA0002501599520000023
(b) the adjusted inner bottom elevation value of the node is set at a depth below the ground:
Figure FDA0002501599520000024
Figure FDA0002501599520000025
deep is the minimum depth of the inspection well specified by the engineering design specification for the ground elevation of the ith node;
(c) the nodes with normal initial insole height values,
Figure FDA0002501599520000026
the height value of the inner bottom is directly obtained from the height value of the initial inner bottom:
Figure FDA0002501599520000027
setting the abnormal node set as a set J, and setting other nodes as normal nodes with normal inner bottom elevation values;
converting the constraint conditions into matrix forms respectively as follows:
Figure FDA0002501599520000031
Figure FDA0002501599520000032
Figure FDA0002501599520000033
in the formula, E1Indicating the adjusted insole height, E, of the 1 st node2Indicating the adjusted insole height, E, of the 2 nd nodenRepresents the adjusted inner bottom elevation value, L, of the nth node1-2Represents the length of the pipe segment between a starting node of 1 and a terminating node of 2, L2-3Indicating the length of the pipe segment between a start node of 2 and an end node of 3, Ln-1-nRepresenting the length of the pipe segment between the start node n-1 and the end node n, sminInterval range of normal gradient [ smin,smax]Lower limit of (d), smaxInterval range of normal gradient [ smin,smax]The upper limit of (a) is,
Figure FDA0002501599520000034
is the ground elevation of the 1 st node,
Figure FDA0002501599520000035
is the ground elevation of the 2 nd node,
Figure FDA0002501599520000036
deep is the engineering design specification for the ground elevation of the nth nodeThe minimum depth of the inspection well is specified,
Figure FDA0002501599520000037
represents adjusted insole elevation values for nodes outside abnormal node set J,
Figure FDA0002501599520000038
representing the initial insole height values of nodes outside the abnormal node set J.
S52, encoding the inner bottom elevation variables of each node by using a floating point number encoding mode, wherein the encoding length is n;
s53, arranging the floating point numbers in n designated ranges into an individual, and randomly generating a plurality of individuals as an initial population;
s54, calculating the fitness function value f of each individual of the initial populationiCalculating the probability P that each individual is selected to enter the next generation populationi(ii) a In the individual selection process, two individuals are selected each time according to a roulette selection mechanism, wherein the individuals with high fitness enter a next generation population;
s55, randomly pairing the new population individuals in pairs for the new population generated by the selection operation, and calculating the cross probability P of each paircCarrying out non-uniform arithmetic crossing on the two paired individuals according to the crossing probability; wherein the cross probability PcDynamically changing with individual fitness:
s56, according to the mutation probability PmPerforming basic potential variation operation on the population individuals after the cross operation; wherein the mutation probability PmDynamically changing with individual fitness:
s57, obtaining a progeny population after mutation operation, calculating fitness function values of each individual of the progeny population, and outputting an individual with the highest fitness, namely an optimal fitness individual; comparing the optimal fitness individual with the optimal fitness individual of the parent population, and taking whether the Euclidean distance of the two individuals is smaller than the allowable residual error as a convergence condition of population evolution;
s58, if the convergence condition is met, the optimal fitness individual is the optimal individual, and the individual gene value is the optimal elevation value of the inner bottom of the pipe network node; if the convergence condition is not met, returning to the step S54, and continuing to perform selection, crossing and mutation operations of the offspring population until the offspring population meets the convergence condition;
or setting the maximum evolution algebra of the population, stopping calculation when the maximum evolution algebra is reached, and outputting the optimal fitness individual as the optimal individual.
5. The method for checking and repairing the topological relation of the pipe network according to claim 4, wherein the step S54 is
Figure FDA0002501599520000041
6. The method for checking and repairing the topological relation of the pipe network according to claim 4, wherein in the step S55
Figure FDA0002501599520000042
fmax、favgRespectively representing the maximum fitness and the average fitness, k, of the new population generated by the selection operation1、k2Is a constant number, k1<k2。
7. The method for checking and repairing the topological relation of the pipe network according to claim 4, wherein in S55, the genes to be crossed of two individuals are set as x and y, and the new genes formed after crossing are x 'and y':
Figure FDA0002501599520000043
in the formula, alpha is a random number which accords with uniform probability distribution in the range of (0, r), r is more than 0 and less than or equal to 1, and r changes along with evolution algebra.
8. The method for checking and repairing the topological relation of the pipe network according to claim 4, wherein in the step S56
Figure FDA0002501599520000044
f'max、f'avgRespectively representing the maximum fitness and the average fitness, k, of the new population generated by the cross operation3、k4Is a constant number, k3<k4。
9. The method for checking and repairing the topological relation of the pipe network according to claim 4, wherein in S56, the gene to be mutated in an individual is set to be z, and the new gene z' after mutation is:
z'＝z+(R-L)·γ
gamma is a random number which accords with uniform probability distribution in the range of [0,1], L and R are respectively the left boundary and the right boundary of the value range of the corresponding gene, and Z is more than or equal to L and less than or equal to R.
10. The method for checking and repairing the topological relation of the pipe network according to claim 4, wherein the Euclidean distance between two individuals in S57 is as follows:
Figure FDA0002501599520000051
Figure FDA0002501599520000052
respectively as the optimal fitness individuals of the parent population and the offspring population, and as the set allowable residual error, x1 iRepresents the individual X with the optimal fitness in the i generation filial populationiThe 1 st gene of (1); x is the number ofn iRepresents the individual X with the optimal fitness in the i generation filial populationiThe nth gene of (1), xn i+1Represents the individual X with the optimal fitness in the i +1 generation filial populationi+1The nth gene of (1).
CN202010434121.2A 2020-05-21 2020-05-21 Pipe network topology relation checking and repairing method Active CN111680374B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010434121.2A CN111680374B (en) 2020-05-21 2020-05-21 Pipe network topology relation checking and repairing method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010434121.2A CN111680374B (en) 2020-05-21 2020-05-21 Pipe network topology relation checking and repairing method

Publications (2)

Publication Number Publication Date
CN111680374A true CN111680374A (en) 2020-09-18
CN111680374B CN111680374B (en) 2023-04-28

Family

ID=72433750

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010434121.2A Active CN111680374B (en) 2020-05-21 2020-05-21 Pipe network topology relation checking and repairing method

Country Status (1)

Country Link
CN (1) CN111680374B (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112036553A (en) * 2020-10-20 2020-12-04 江苏其厚智能电气设备有限公司 Non-signal injection type user-phase topological relation identification method based on genetic algorithm
CN112035991A (en) * 2020-09-23 2020-12-04 中冶赛迪技术研究中心有限公司 Steam optimization calculation method and system based on pipe network conveying path
CN112132283A (en) * 2020-10-20 2020-12-25 江苏其厚智能电气设备有限公司 Non-signal injection type user variable topological relation identification method based on genetic algorithm
CN114117946A (en) * 2022-01-26 2022-03-01 浙江大学 Method and device for preprocessing drainage pipe network data
CN114840905A (en) * 2022-05-24 2022-08-02 安徽富煌钢构股份有限公司 BIM technology-based outdoor pipe network and inspection well building and adjusting method
CN115883439A (en) * 2022-11-25 2023-03-31 中国联合网络通信集团有限公司 Network transmission path processing method, device and storage medium
CN117408007A (en) * 2023-12-15 2024-01-16 华东交通大学 Three-dimensional pipe network initial flow distribution method, system, storage medium and electronic equipment

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015124988A1 (en) * 2014-02-19 2015-08-27 Tata Consultancy Services Limited Leak localization in water distribution networks
CN109726259A (en) * 2018-12-27 2019-05-07 中冶京诚工程技术有限公司 Drainage pipe network design optimization system and method based on GIS technology

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015124988A1 (en) * 2014-02-19 2015-08-27 Tata Consultancy Services Limited Leak localization in water distribution networks
CN109726259A (en) * 2018-12-27 2019-05-07 中冶京诚工程技术有限公司 Drainage pipe network design optimization system and method based on GIS technology

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
李小曼;徐梦洁;: "城市三维地下管网信息系统设计初探", 供水技术 *
郝沙;魏连雨;王丽娟;陈爱武;: "自适应遗传算法在排水管网优化设计中的应用", 天津建设科技 *

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112035991A (en) * 2020-09-23 2020-12-04 中冶赛迪技术研究中心有限公司 Steam optimization calculation method and system based on pipe network conveying path
CN112035991B (en) * 2020-09-23 2024-02-27 中冶赛迪技术研究中心有限公司 Steam optimization calculation method and system based on pipe network conveying path
CN112036553A (en) * 2020-10-20 2020-12-04 江苏其厚智能电气设备有限公司 Non-signal injection type user-phase topological relation identification method based on genetic algorithm
CN112132283A (en) * 2020-10-20 2020-12-25 江苏其厚智能电气设备有限公司 Non-signal injection type user variable topological relation identification method based on genetic algorithm
CN112132283B (en) * 2020-10-20 2024-04-05 江苏其厚智能电气设备有限公司 Genetic algorithm-based non-signal injection type household transformer topological relation identification method
CN112036553B (en) * 2020-10-20 2024-04-09 江苏其厚智能电气设备有限公司 Genetic algorithm-based non-signal injection type household phase topological relation identification method
CN114117946A (en) * 2022-01-26 2022-03-01 浙江大学 Method and device for preprocessing drainage pipe network data
CN114840905A (en) * 2022-05-24 2022-08-02 安徽富煌钢构股份有限公司 BIM technology-based outdoor pipe network and inspection well building and adjusting method
CN115883439A (en) * 2022-11-25 2023-03-31 中国联合网络通信集团有限公司 Network transmission path processing method, device and storage medium
CN117408007A (en) * 2023-12-15 2024-01-16 华东交通大学 Three-dimensional pipe network initial flow distribution method, system, storage medium and electronic equipment
CN117408007B (en) * 2023-12-15 2024-08-30 华东交通大学 Three-dimensional pipe network initial flow distribution method, system, storage medium and electronic equipment

Also Published As

Publication number Publication date
CN111680374B (en) 2023-04-28

Similar Documents

Publication Publication Date Title
CN111680374A (en) Method for checking and repairing topological relation of pipe network
KR102031714B1 (en) system for leakage detection based on hydraulic analysis in water supply networks
CN110929359B (en) Pipe network siltation risk prediction modeling method based on PNN neural network and SWMM technology
CN109117985B (en) Pipe network pressure monitoring point optimal arrangement method based on matrix and genetic algorithm
CN111625988A (en) Bridge health management analysis and prediction system and method based on deep learning
CN114548680B (en) Automatic calibration method and system for urban storm flood management model parameters
CN117540329B (en) Online early warning method and system for defects of drainage pipe network based on machine learning
CN114219334A (en) Bayesian network natural gas pipeline leakage probability calculation method based on genetic algorithm
Jenkins et al. Comparison of pipeline failure prediction models for water distribution networks with uncertain and limited data
CN104332051B (en) Urban road RFID detector optimizes distribution method
CN105975678B (en) A kind of oil-gas pipeline Prediction model for residual strength method based on parameterized model
CN115495857A (en) Heat supply pipe network planning method
Ferraro et al. Use of evolutionary algorithms in single and multi-objective optimization techniques for assisted history matching
Parvizsedghy et al. Deterioration assessment models for water pipelines
CN116307352A (en) Engineering quantity index estimation method and system based on machine learning
Morosini et al. Identification of leakages by calibration of WDS models
WO2024148660A1 (en) Indirect liquid level monitoring and analysis method for urban drainage system based on directed topological network
CN114491890A (en) Urban drainage system topology flow direction analysis method based on inspection well weight classification
Hajibabaei et al. Reconstruction of missing information in water distribution networks based on graph theory
CN118332745B (en) Water supply network repairing method and device, electronic equipment and computer storage medium
CN114493243A (en) Mountain torrent disaster easiness evaluation method based on ridge model tree algorithm
CN114324800A (en) Drainage pipeline water inflow monitoring method and system and storage medium
A Tantele et al. Integration of probabilistic effectiveness with a two-stage genetic algorithm methodology to develop optimum maintenance strategies for bridges
US7302372B1 (en) Technique for optimization of a simplified network model
CN118095606B (en) Urban drainage pipe network monitoring point optimal arrangement method based on graph theory and machine learning

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant