CN116127671B - Water supply network parameter optimization method, system, equipment and storage medium - Google Patents

Water supply network parameter optimization method, system, equipment and storage medium Download PDF

Info

Publication number
CN116127671B
CN116127671B CN202310401777.8A CN202310401777A CN116127671B CN 116127671 B CN116127671 B CN 116127671B CN 202310401777 A CN202310401777 A CN 202310401777A CN 116127671 B CN116127671 B CN 116127671B
Authority
CN
China
Prior art keywords
pipe network
network parameter
parameter
parameter optimization
unconstrained
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.)
Active
Application number
CN202310401777.8A
Other languages
Chinese (zh)
Other versions
CN116127671A (en
Inventor
王嘉
夏泽鑫
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.)
Rongwan Technology Shanghai Co ltd
Original Assignee
Sichuan Aoconvex Environmental Protection Technology Co ltd
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 Sichuan Aoconvex Environmental Protection Technology Co ltd filed Critical Sichuan Aoconvex Environmental Protection Technology Co ltd
Priority to CN202310401777.8A priority Critical patent/CN116127671B/en
Publication of CN116127671A publication Critical patent/CN116127671A/en
Application granted granted Critical
Publication of CN116127671B publication Critical patent/CN116127671B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00Computer-aided design [CAD]
    • G06F30/10Geometric CAD
    • G06F30/18Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00Computer-aided design [CAD]
    • G06F30/20Design optimisation, verification or simulation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00Details relating to CAD techniques
    • G06F2111/04Constraint-based CAD

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Geometry (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Computational Mathematics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a method, a system, equipment and a storage medium for optimizing parameters of a water supply network, and belongs to the technical field of water power of the network. The optimization method of the invention comprises the following steps: acquiring pipe network GIS information through a pipe network GIS system, and acquiring a pipe network topological structure according to the pipe network GIS information; establishing a pipe network parameter optimization model based on the pipe network topological structure, wherein the pipe network parameter optimization model comprises an objective function and constraint conditions; converting the optimization problem of the pipe network parameter optimization model into an unconstrained extremum problem; and solving the unconstrained extremum problem by adopting a gradient flow method to obtain the optimal value of the pipe network parameter. According to the invention, the optimization problem of the pipe network parameter optimization model is converted into the unconstrained extremum problem, and the unconstrained extremum problem is solved iteratively by adopting a gradient flow method, so that the optimal value of the pipe network parameter can be obtained rapidly and accurately, and more reliable data support and technical support are provided for subsequent pipe network fault monitoring.

Description

Water supply network parameter optimization method, system, equipment and storage medium
Technical Field
The invention belongs to the technical field of pipe network waterpower, and particularly relates to a method, a system, equipment and a storage medium for optimizing parameters of a water supply pipe network.
Background
With the development of digital twinning, the traditional digital model can not meet the requirements of the pipe network industry scene. The digital model is used for not only describing the water supply network, but also training by depending on real-time data, so that the prediction of the water supply network is realized. Dynamic model checking is one of the important processes of optimization calculation, and the checked mathematical model can be abstracted into an optimization problem with constraint conditions.
The traditional thinking for solving the optimization problem is to find a local optimal point in European space, and the used methods comprise Newton's method, gradient descent method, ant colony algorithm or particle swarm algorithm and the like. The Newton method or gradient descent method relies on a Hessian matrix and an inverse matrix of the Hessian matrix for solving the problem, but when the obtained Hessian matrix is not positive, the value of an objective function on a newly found point is possibly larger than the original value, or the Hessian matrix is possibly singular, so that the inverse matrix does not exist, at the moment, the initial value or the step size is manually adjusted by manual intervention to achieve the purpose of final convergence, and the extremum can be obtained by solving for a plurality of times or only a suboptimal solution is output, so that the pipe network optimization efficiency is low or the pipe network optimization precision is not high.
The calculated amount of the ant colony algorithm is large, the convergence speed is low, and therefore the pipe network optimization efficiency is low; the particle swarm algorithm is easy to generate the problems of premature convergence and the like, so that the reliability of the pipe network optimization result is poor.
Disclosure of Invention
In order to solve the problems of poor reliability, low efficiency and the like in the conventional pipe network optimization technology, the invention provides a water supply pipe network parameter optimization method, a system, equipment and a storage medium. According to the invention, the pipe network hydraulic optimization solution based on the gradient flow method can be converged to the extremum faster, so that the optimization efficiency is improved; meanwhile, the physical parameters of each pipe network can be obtained rapidly and accurately, the prediction precision of the node water pressure and the pipe flow is improved, and technical support is provided for subsequent leakage detection and pipe explosion early warning.
The invention is realized by the following technical scheme:
a water supply network parameter optimization method, the method comprising:
acquiring pipe network GIS information through a pipe network GIS system, and acquiring a pipe network topological structure according to the pipe network GIS information;
establishing a pipe network parameter optimization model based on the pipe network topological structure, wherein the pipe network parameter optimization model comprises an objective function and constraint conditions;
converting the optimization problem of the pipe network parameter optimization model into an unconstrained extremum problem;
and solving the unconstrained extremum problem by adopting a gradient flow method to obtain the optimal value of the pipe network parameter.
According to the invention, the optimization problem of the pipe network parameter optimization model is converted into the unconstrained extremum problem, and the unconstrained extremum problem is solved iteratively by adopting a gradient flow method, so that the optimal value of the pipe network parameter can be obtained rapidly and accurately, and more reliable data support and technical support are provided for subsequent pipe network fault monitoring.
As a preferred embodiment, the pipe network GIS information of the present invention includes pipe network space data and pipe network attribute data;
obtaining a pipe network topological structure according to the pipe network GIS information, which specifically comprises the following steps:
and establishing pipelines, pipe points and equipment along the lines according to the pipe network space data and the pipe network attribute data to form a pipe network topological structure.
As a preferred embodiment, the objective function of the present invention is:
Figure SMS_1
in the method, in the process of the invention,
Figure SMS_2
and->
Figure SMS_3
Is weight(s)>
Figure SMS_4
And->
Figure SMS_5
Respectively nodesiMeasured and predicted values of pressure, +.>
Figure SMS_6
And (3) with
Figure SMS_7
Respectively pipe sectionsjActual measurement value and prediction value of flow;
the constraints include continuity equations, pressure drop equations, virtual ring equations, and energy equations.
As a preferred embodiment, the method converts the optimization problem of the pipe network parameter optimization model into an unconstrained extremum problem, specifically expressed as follows:
Figure SMS_8
wherein,,
Figure SMS_11
for +.>
Figure SMS_13
Dimension parameter->
Figure SMS_16
Is a parameter space, ++>
Figure SMS_9
Is the transformed equation, +.>
Figure SMS_15
Is an objective function->
Figure SMS_18
Is a pipe network parameter->
Figure SMS_20
,/>
Figure SMS_10
Is to->
Figure SMS_14
Head loss function as parameter, +.>
Figure SMS_17
For the actual measured value, +.>
Figure SMS_19
Is a constraint condition (JavaScript)>
Figure SMS_12
Is the lagrange multiplier.
As a preferred embodiment, the invention adopts a gradient flow method to solve the minimum value of the unconstrained problem in the parameter space, and the solving process specifically comprises the following steps:
initializing: setting an initial value and an initial time;
solving: solving a differential equation for the current point on the parameter curve;
updating: and determining an iteration step length, updating the current point, and returning to the solving step to continuously solve the differential equation until the iteration termination condition is met.
As a preferred embodiment, the iterative step of the present invention satisfies the following condition:
Figure SMS_21
wherein,,
Figure SMS_23
and->
Figure SMS_29
Is weight(s)>
Figure SMS_32
Is the parameter space->
Figure SMS_25
Gradient operator on->
Figure SMS_28
Is the parameter space->
Figure SMS_31
A curve on ∈ ->
Figure SMS_34
Is->
Figure SMS_22
Derivative of>
Figure SMS_26
Time of presentation->
Figure SMS_30
For similarity, ->
Figure SMS_33
,/>
Figure SMS_24
And
Figure SMS_27
As a preferred embodiment, the iteration termination conditions of the present invention include:
the iteration times are larger than a certain preset integer;
or the difference of the objective function before and after iteration is smaller than a difference preset value;
or, the updated time interval is greater than the time preset value.
In a second aspect, the present invention provides a water supply network parameter optimization system, which includes:
the data acquisition module acquires pipe network GIS information through a pipe network GIS system;
the topological structure construction module acquires a pipe network topological structure according to the pipe network GIS information;
the model construction module is used for constructing a pipe network parameter optimization model based on the pipe network topological structure, wherein the pipe network parameter optimization model comprises an objective function and constraint conditions;
the model conversion module is used for converting the optimization problem of the pipe network parameter optimization model into an unconstrained extremum problem;
and the solving module is used for solving the unconstrained extremum problem by adopting a gradient flow method to obtain the optimal value of the pipe network parameter.
In a third aspect, the present invention also proposes a computer device comprising a memory storing a computer program and a processor implementing the steps of the above-mentioned method of the present invention when said computer program is executed by said processor.
In a fourth aspect, the present invention also proposes a computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the above-mentioned method of the invention.
The invention has the following advantages and beneficial effects:
compared with the prior art, the method adopts the gradient flow method to solve the pipe network hydraulic optimization model, can converge to the extremum faster, and improves the pipe network optimization efficiency; meanwhile, the invention can avoid the problem of poor reliability caused by non-convergence or early termination when the objective function Hessian matrix is not positive or singular in the solving process, can obtain the optimal parameters more quickly and reliably, and provides technical support for pipe network leakage detection, pipe explosion early warning and the like.
Drawings
The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention. In the drawings:
FIG. 1 is a flow chart of a method according to an embodiment of the invention.
Fig. 2 is a schematic diagram of a model solving process according to an embodiment of the invention.
Fig. 3 is a system schematic block diagram of an embodiment of the present invention.
Detailed Description
For the purpose of making apparent the objects, technical solutions and advantages of the present invention, the present invention will be further described in detail with reference to the following examples and the accompanying drawings, wherein the exemplary embodiments of the present invention and the descriptions thereof are for illustrating the present invention only and are not to be construed as limiting the present invention.
Examples:
the traditional pipe network optimization technology generally adopts Newton method, gradient descent method, ant colony algorithm or particle swarm algorithm to solve the optimization problem; however, the Newton method or the gradient descent method requires that the Hessian matrix is positive and is a non-singular matrix, and if the Hessian matrix is non-positive or is a singular matrix, the optimization reliability of the pipe network is poor or the optimization efficiency is low; the ant colony algorithm has larger calculated amount and slower convergence speed, so that the pipe network optimization efficiency is lower; the particle swarm algorithm is easy to generate premature convergence, so that the reliability of pipe network optimization is poor, and the like. Based on this, the embodiment provides a water supply network optimization method.
As shown in fig. 1, the method provided in this embodiment includes the following steps:
step 1, acquiring pipe network GIS information and acquiring a pipe network topological structure according to the pipe network GIS information.
The embodiment obtains pipe network GIS information through a pipe network GIS system, wherein the pipe network GIS information comprises: pipe network space data and pipe network attribute data; the pipe network space data comprise information such as the geographical position of the pipe network, and the pipe network attribute data comprise pipe network material, valve, reducing, tee joint, four-way and other pipe network and equipment data.
In the embodiment, the spatial data and the attribute data of the pipe network are integrated, and the pipeline, the pipe point and the equipment along the line are established to form a topological structure diagram of the pipe network.
Step 2: and establishing a pipe network parameter optimization model based on the pipe network topological structure.
According to the pipe network topological structure obtained in the steps, constraint conditions such as a continuity equation, a pressure drop equation, a virtual ring equation and an energy equation are established. Wherein the continuity equation is
Figure SMS_52
, />
Figure SMS_54
Is the node number,/->
Figure SMS_57
For the traffic of the node, +.>
Figure SMS_36
Is +.>
Figure SMS_41
Flow of connected pipe section,/">
Figure SMS_45
Respectively inflow and outflow. The pressure drop equation is
Figure SMS_49
Wherein->
Figure SMS_50
For node->
Figure SMS_55
Pressure of->
Figure SMS_58
For slave node->
Figure SMS_60
To node->
Figure SMS_51
Head loss function of pipe section
Figure SMS_53
,/>
Figure SMS_56
For length of pipe section->
Figure SMS_59
Is pipe diameter (I)>
Figure SMS_38
For Hazen-Williams coefficients, or equivalently, let
Figure SMS_40
, />
Figure SMS_44
Is friction coefficient>
Figure SMS_48
Is a pending parameter. The energy equation (including the virtual ring) is +.>
Figure SMS_35
Wherein
Figure SMS_39
Is a ring->
Figure SMS_43
Is provided. We's handle->
Figure SMS_47
?>
Figure SMS_37
Value, friction coefficient->
Figure SMS_42
And +.>
Figure SMS_46
Etc. as parameters to be solved. The constraints define the variation of the required parametersThe range (boundary condition), i.e. each equation in the constraint, gives the feasible fields for these parameters.
According to pipe network optimization targets, for example, for each node pressure and pipe section flow, an optimization target function is established:
Figure SMS_61
in the method, in the process of the invention,
Figure SMS_62
and->
Figure SMS_63
Is weight(s)>
Figure SMS_64
And->
Figure SMS_65
Respectively nodesiMeasured and predicted values of pressure, +.>
Figure SMS_66
And (3) with
Figure SMS_67
Respectively pipe sectionsjThe measured and predicted values of flow, the predicted values of node pressure and the predicted values of pipe section flow are functions of parameters, and by changing these parameters, such as friction coefficients used in pressure drop equations, virtual loop equations, and energy equation constraints, and the like, and the values of node flow used in continuity equations, and the like, the predicted values of node pressure and pipe section flow will be changed. For ease of description, these parameters may be collectively represented by a vector C.
Based on the above, the objective optimization function and the constraint condition together form a pipe network parameter optimization model.
Step 3: and converting the optimization problem of the pipe network parameter optimization model into an unconstrained extremum problem.
The model optimization problem can be converted into an unconstrained extremum problem by using, but not limited to, an outlier method:
Figure SMS_68
wherein,,
Figure SMS_69
for +.>
Figure SMS_70
Dimension parameter->
Figure SMS_71
Can be European space, or general Riemann manifold>
Figure SMS_72
Is the converted equation.
Figure SMS_73
Wherein,,
Figure SMS_76
is an optimized objective function, in particular the mean square error between the measured value and the predicted value obtained from the head loss function, pipe network parameter ∈ ->
Figure SMS_78
May be Hazen-Williams friction coefficient of pipe section, etc, +.>
Figure SMS_81
Is a parameter requiring optimization, +.>
Figure SMS_75
Is the actual measurement value, as in step 2 above +.>
Figure SMS_77
And->
Figure SMS_80
,/>
Figure SMS_83
Is to->
Figure SMS_74
The head loss function, etc. as parameters are vectors. />
Figure SMS_79
Is a continuity equation which the hydraulic pipe network system must satisfy, and constraint equations such as a pressure drop equation, a virtual ring equation, an energy equation and the like, < >>
Figure SMS_82
Is the lagrange multiplier.
And 4, solving an unconstrained extremum problem by adopting a gradient flow method, namely solving a minimum value of the unconstrained problem in a parameter space.
As shown in fig. 2, the solving process includes the following steps:
step 41, setting an initial value
Figure SMS_84
Is +.>
Figure SMS_85
Suppose that solution in parameter space is required
Figure SMS_86
Objective function->
Figure SMS_87
Is a minimum value of (2). The corresponding start position->
Figure SMS_88
The gradient flow of (2) satisfies the following equation>
Figure SMS_89
Parameter curves in space:
Figure SMS_90
wherein,,
Figure SMS_91
is the parameter space->
Figure SMS_92
Gradient operator on, defined as +.>
Figure SMS_93
Figure SMS_94
,/>
Figure SMS_95
Representing the inner product on the Riemann manifold, when the Riemann manifold is +.>
Figure SMS_96
When (I)>
Figure SMS_97
Which is the usual vector inner product.
Step 42, for the current point on the parameter curve, solve the differential equation:
Figure SMS_98
(1)
wherein,,
Figure SMS_101
is the parameter space->
Figure SMS_103
A curve in>
Figure SMS_106
Starting from, is an approximation of the gradient flow described above, i.e. +.>
Figure SMS_100
,/>
Figure SMS_104
Representation (Alexandrov) Hessian operator, < >>
Figure SMS_107
Is a curve->
Figure SMS_108
Is a derivative of (a). The approximation is adopted because only +_ at the current point can be obtained>
Figure SMS_99
While the gradient of equation (1) is solved, it is not known in advance when +.>
Figure SMS_102
Time gradient flow->
Figure SMS_105
A gradient thereat.
Step 43, determining iteration step length and updating
Figure SMS_109
And update->
Figure SMS_110
Is->
Figure SMS_111
Solving the equation (1) to obtain the following time
Figure SMS_112
Is a gradient flow curve. And when the current position on a given curve +.>
Figure SMS_113
At the next place +.>
Figure SMS_114
Is important, firstly, to ensure that +.>
Figure SMS_115
The value of the objective function is smaller than +.>
Figure SMS_116
Where, let->
Figure SMS_117
And->
Figure SMS_118
As large as possible to ensure a fast convergence speed.
For this purpose, first consider vectors
Figure SMS_119
And->
Figure SMS_120
In a certain period of time->
Figure SMS_121
Similarity of interior, i.e. define +.>
Figure SMS_122
The following are provided:
Figure SMS_123
wherein,,
Figure SMS_124
,/>
Figure SMS_125
representing the inner product on the Riemann manifold. If in time period->
Figure SMS_126
Any time->
Figure SMS_127
All have->
Figure SMS_128
It is easy to know
Figure SMS_129
From this, it can be seen that the objective function satisfies
Figure SMS_130
I.e. guaranteed to be +.>
Figure SMS_131
The value of the objective function is less than +.>
Figure SMS_132
A value at.
To determine iteration steps, i.e.
Figure SMS_133
Or equivalent, +.>
Figure SMS_134
Is of such a size that
Figure SMS_135
The value of (2) cannot be too small nor too large, and at the same time +.>
Figure SMS_136
And->
Figure SMS_137
The cosine similarity of (c) cannot be too small or too large. For this purpose, the parameter +.>
Figure SMS_138
And +.>
Figure SMS_139
So that
Figure SMS_140
(2)
Obviously, when
Figure SMS_142
When (I)>
Figure SMS_145
. Thus->
Figure SMS_147
When it is sufficiently small, the first formula in the formula (2) must be satisfied, but the second formula must not be satisfied. But is followed by->
Figure SMS_143
Gradually satisfying both of the above equations. If there is more than one +.>
Figure SMS_146
If the above conditions are satisfied, any +.>
Figure SMS_148
. It can be demonstrated when->
Figure SMS_149
I.e. +.>
Figure SMS_141
When converging to the extremum of the objective function. />
Figure SMS_144
The value of (2) is empirically set in the concrete implementation and can be obtained from a smaller valueABeginning and then followingnA,n=1,2, … to satisfy the formula (2).
Step 44, looping according to steps 42-43 until the iteration termination condition is met. The termination conditions include:
1) The iteration times are larger than a certain preset integer;
2) Or the difference of the objective functions before and after iteration is smaller than a certain preset small amount;
3) Or the updated time interval is greater than some preset value.
And 5, outputting an optimal result obtained by solving to realize pipe network parameter optimization.
According to the embodiment, through the optimization process, more accurate pipe network parameters, such as friction coefficient of each network segment and the like, can be obtained, on one hand, more accurate predicted values of the water pressure and the flow of the pipe network node can be obtained, and meanwhile, data support can be provided for pipe network leakage detection and pipe explosion early warning.
The embodiment also provides a water supply network optimization system, specifically as shown in fig. 3, the system includes:
the data acquisition module is used for acquiring the GIS information of the pipe network;
the topological structure construction module acquires a pipe network topological structure according to the GIS information of the pipe network;
the model construction module is used for constructing a pipe network parameter optimization model based on the pipe network topological structure, wherein the pipe network parameter optimization model comprises an objective function and corresponding constraint conditions;
the model conversion module is used for converting the optimization problem of the pipe network parameter optimization model into an unconstrained extremum problem;
the solving module adopts a gradient flow method to solve the unconstrained extremum problem, namely, the minimum value of the unconstrained problem on the manifold;
and the output module outputs an optimal result obtained by solving to realize the optimization of pipe network parameters.
The embodiment also provides a computer device for executing the method of the embodiment.
The computer device includes a processor, an internal memory, and a system bus; various device components, including internal memory and processors, are connected to the system bus. A processor is a piece of hardware used to execute computer program instructions by basic arithmetic and logical operations in a computer system. Internal memory is a physical device used to temporarily or permanently store computing programs or data (e.g., program state information). The system bus may be any of several types of bus structures including a memory bus or memory controller, a peripheral bus, and a local bus. The processor and the internal memory may communicate data via a system bus. Where internal memory includes Read Only Memory (ROM) or flash memory, and Random Access Memory (RAM), which generally refers to the main memory loaded with an operating system and computer programs.
Computer devices typically include an external storage device. The external storage device may be selected from a variety of computer readable media, which refers to any available media that can be accessed by a computer device, including both removable and fixed media. For example, computer-readable media includes, but is not limited to, flash memory (micro-SD card), CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer device.
The computer device may be logically connected to one or more network terminals in a network environment. The network terminal may be a personal computer, server, router, smart phone, tablet computer, or other public network node. The computer device is connected to a network terminal through a network interface (local area network LAN interface). Local Area Networks (LANs) refer to computer networks of interconnected networks within a limited area, such as a home, school, computer laboratory, or office building using network media. WiFi and twisted pair wired ethernet are the two most common technologies used to construct local area networks.
It should be noted that other computer systems including more or fewer subsystems than computer devices may also be suitable for use with the invention.
As described in detail above, the computer device suitable for the present embodiment can perform the designated operation of the water supply network optimization method. The computer device performs these operations in the form of software instructions that are executed by a processor in a computer-readable medium. The software instructions may be read into memory from a storage device or from another device via a lan interface. The software instructions stored in the memory cause the processor to perform the method of processing group member information described above. Furthermore, the invention may be implemented by means of hardware circuitry or by means of combination of hardware circuitry and software instructions. Thus, implementation of the present embodiments is not limited to any specific combination of hardware circuitry and software.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.

Claims (8)

1. The water supply network parameter optimization method is characterized by comprising the following steps:
acquiring pipe network GIS information through a pipe network GIS system, and acquiring a pipe network topological structure according to the pipe network GIS information;
establishing a pipe network parameter optimization model based on the pipe network topological structure, wherein the pipe network parameter optimization model comprises an objective function and constraint conditions; the objective function is:
Figure FDA0004243917930000011
wherein alpha is i And beta j As weight, mP i With PP i Respectively an actual measurement value and a predicted value of the pressure of the node i, and mQ j With PQ j Respectively an actual measurement value and a predicted value of the flow of the pipe section j;
the constraint conditions comprise a continuity equation, a pressure drop equation, a virtual ring equation and an energy equation;
converting the optimization problem of the pipe network parameter optimization model into an unconstrained extremum problem; converting the optimization problem of the pipe network parameter optimization model into an unconstrained extremum problem, which is specifically expressed as follows:
Figure FDA0004243917930000012
Figure FDA0004243917930000013
wherein,,
Figure FDA0004243917930000014
for the n+1-dimensional parameter to be solved, < ->
Figure FDA0004243917930000015
Is a parameter space, ++>
Figure FDA0004243917930000016
Is the equation after transformation, f is the objective function, C is the pipe network parameter, +.>
Figure FDA0004243917930000017
p (C) is a head loss function with C as a parameter, m is an actual measured value, g i Is a constraint, λ is the lagrange multiplier;
and solving the unconstrained extremum problem by adopting a gradient flow method to obtain the optimal value of the pipe network parameter.
2. The water supply network parameter optimization method according to claim 1, wherein the network GIS information comprises network space data and network attribute data;
obtaining a pipe network topological structure according to the pipe network GIS information, which specifically comprises the following steps:
and establishing pipelines, pipe points and equipment along the lines according to the pipe network space data and the pipe network attribute data to form a pipe network topological structure.
3. The water supply network parameter optimization method according to claim 1, wherein the minimum value of the unconstrained problem in the parameter space is solved by adopting a gradient flow method, and the solving process specifically comprises the following steps:
initializing: setting an initial value and an initial time;
solving: solving a differential equation for the current point on the parameter curve;
updating: and determining an iteration step length, updating the current point, and returning to the solving step to continuously solve the differential equation until the iteration termination condition is met.
4. A water supply network parameter optimization method according to claim 3, wherein the iterative step satisfies the following conditions:
Figure FDA0004243917930000021
wherein alpha is i And beta j As the weight of the material to be weighed,
Figure FDA0004243917930000022
is the parameter space->
Figure FDA0004243917930000023
Gradient operator on gamma i (t) is the parameter space->
Figure FDA0004243917930000024
A curve of gamma' i Is gamma i T represents time, S is similarity, 0 < alpha 1 <1,α 2 > 0 and 0 < beta 2 <β 1 <1。
5. A water supply network parameter optimization method as claimed in claim 3, wherein the iteration termination condition comprises:
the iteration times are larger than a certain preset integer;
or the difference of the objective function before and after iteration is smaller than a difference preset value;
or, the updated time interval is greater than the time preset value.
6. A water supply network parameter optimization system, the system comprising:
the data acquisition module acquires pipe network GIS information through a pipe network GIS system;
the topological structure construction module acquires a pipe network topological structure according to the pipe network GIS information;
the model construction module is used for constructing a pipe network parameter optimization model based on the pipe network topological structure, wherein the pipe network parameter optimization model comprises an objective function and constraint conditions; the objective function is:
Figure FDA0004243917930000031
wherein alpha is i And beta j As weight, mP i With PP i Respectively an actual measurement value and a predicted value of the pressure of the node i, and mQ j With PQ j Respectively an actual measurement value and a predicted value of the flow of the pipe section j;
the constraint conditions comprise a continuity equation, a pressure drop equation, a virtual ring equation and an energy equation;
the model conversion module is used for converting the optimization problem of the pipe network parameter optimization model into an unconstrained extremum problem; converting the optimization problem of the pipe network parameter optimization model into an unconstrained extremum problem, which is specifically expressed as follows:
Figure FDA0004243917930000032
Figure FDA0004243917930000033
wherein,,
Figure FDA0004243917930000034
for the n+1-dimensional parameter to be solved, < ->
Figure FDA0004243917930000035
Is a parameter space, ++>
Figure FDA0004243917930000036
Is the equation after transformation, f is the objective function, C is the pipe network parameter, +.>
Figure FDA0004243917930000037
p (C) is C as a referenceA head loss function of a number, m is an actual measured value, g i Is a constraint, λ is the lagrange multiplier;
and the solving module is used for solving the unconstrained extremum problem by adopting a gradient flow method to obtain the optimal value of the pipe network parameter.
7. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1-5 when the computer program is executed.
8. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any of claims 1-5.
CN202310401777.8A 2023-04-17 2023-04-17 Water supply network parameter optimization method, system, equipment and storage medium Active CN116127671B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310401777.8A CN116127671B (en) 2023-04-17 2023-04-17 Water supply network parameter optimization method, system, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310401777.8A CN116127671B (en) 2023-04-17 2023-04-17 Water supply network parameter optimization method, system, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN116127671A CN116127671A (en) 2023-05-16
CN116127671B true CN116127671B (en) 2023-06-23

Family

ID=86304899

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310401777.8A Active CN116127671B (en) 2023-04-17 2023-04-17 Water supply network parameter optimization method, system, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN116127671B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112330020A (en) * 2020-11-05 2021-02-05 东方电子股份有限公司 Collaborative optimization method for electricity-gas comprehensive energy system
CN115495857A (en) * 2022-08-22 2022-12-20 华能新华发电有限责任公司 Heat supply pipe network planning method

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2003077062A2 (en) * 2002-03-06 2003-09-18 Trustees Of Boston University Systems and methods for reverse engineering models of biological networks
BR112021016896A2 (en) * 2019-03-08 2021-11-03 Huawei Tech Co Ltd Encoder, decoder and corresponding methods for inter-prediction
CN114429034A (en) * 2021-12-27 2022-05-03 同济大学 Pressure monitoring point moving arrangement method for water supply network hydraulic model water quantity checking
CN115062764B (en) * 2022-06-17 2023-07-11 淮阴工学院 Intelligent illuminance adjustment and environmental parameter Internet of things big data system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112330020A (en) * 2020-11-05 2021-02-05 东方电子股份有限公司 Collaborative optimization method for electricity-gas comprehensive energy system
CN115495857A (en) * 2022-08-22 2022-12-20 华能新华发电有限责任公司 Heat supply pipe network planning method

Also Published As

Publication number Publication date
CN116127671A (en) 2023-05-16

Similar Documents

Publication Publication Date Title
Li et al. High‐order k‐exact WENO finite volume schemes for solving gas dynamic Euler equations on unstructured grids
WO2017084505A1 (en) Method and device for obtaining capacity of application cluster
JP7090734B2 (en) Control system, control method and storage medium
CN112000001B (en) PID parameter setting optimization method based on improved Bayesian model
CN104463381A (en) Building energy consumption predication method based on KPCA and WLSSVM
CN116127671B (en) Water supply network parameter optimization method, system, equipment and storage medium
CN110502842B (en) Thermal model modeling method of power semiconductor module and application method and device thereof
Wang et al. Research on digital twin modeling method of transformer temperature field based on POD
CN117040338B (en) Permanent magnet synchronous motor control method, system, device, equipment and storage medium
CN112487644A (en) Research platform and method for flow heat transfer and automatic control
CN115935566A (en) Simulation method and system for natural gas pipeline network, storage medium and electronic equipment
CN115422808A (en) Transformer temperature field model order reduction method based on Krylov subspace
CN113031435B (en) Digital double-frequency extended state observer and disturbance observation method
CN110705066A (en) Projection integral-based dynamic simulation method for integrated energy system of gas-electricity coupling park
CN109002419B (en) Dynamic analysis method and device for natural gas pipe network
Tai et al. Optimal PMU placement for power system state estimation with random communication packet losses
WO2023124893A1 (en) Torque estimation method and apparatus based on neural network, and device and storage medium
LU502802B1 (en) Numerical solution system for partial differential equation
CN113283200B (en) Wind turbine generator dynamic wake modeling method based on measurable parameters
CN110083877A (en) A kind of fluctuation heat power engineering system transfer function modeling method
TOUIL et al. Real-time fractional order system identification using recursive least squares method
CN112989497B (en) Tight branch radial basis function data transfer method based on geometric space main feature extraction
JP7460873B2 (en) Adaptive state estimation of power systems.
CN116401974B (en) Engine cooling performance evaluation method, device and equipment based on multidimensional
CN116111895B (en) Motor model predictive control method and device, storage medium and electronic equipment

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
TR01 Transfer of patent right

Effective date of registration: 20231110

Address after: 201109 floor 1, building 5, No. 951, Jianchuan Road, Minhang District, Shanghai

Patentee after: Rongwan Technology (Shanghai) Co.,Ltd.

Address before: No. 2 Futoushan Road, Chenghua District, Chengdu, Sichuan Province, 610000

Patentee before: Sichuan aoconvex Environmental Protection Technology Co.,Ltd.

TR01 Transfer of patent right