CN117993306B - Method, system and medium for calibrating simulation parameters of pipe network - Google Patents
Method, system and medium for calibrating simulation parameters of pipe network Download PDFInfo
- Publication number
- CN117993306B CN117993306B CN202410396911.4A CN202410396911A CN117993306B CN 117993306 B CN117993306 B CN 117993306B CN 202410396911 A CN202410396911 A CN 202410396911A CN 117993306 B CN117993306 B CN 117993306B
- Authority
- CN
- China
- Prior art keywords
- pressure
- coefficient
- flow
- pipe
- node
- 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
Links
- 238000004088 simulation Methods 0.000 title claims abstract description 104
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000012544 monitoring process Methods 0.000 claims abstract description 167
- 238000013528 artificial neural network Methods 0.000 claims abstract description 25
- 238000012937 correction Methods 0.000 claims abstract description 13
- 238000004364 calculation method Methods 0.000 claims description 30
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000010586 diagram Methods 0.000 claims description 6
- 230000001133 acceleration Effects 0.000 claims description 4
- 230000006835 compression Effects 0.000 claims description 4
- 238000007906 compression Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract description 10
- 238000012545 processing Methods 0.000 description 7
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 4
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 4
- 238000005303 weighing Methods 0.000 description 3
- 238000002940 Newton-Raphson method Methods 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000011478 gradient descent method Methods 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Classifications
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/14—Pipes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Pure & Applied Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Optimization (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Databases & Information Systems (AREA)
- Computational Mathematics (AREA)
- Evolutionary Biology (AREA)
- Algebra (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a method, a system and a medium for calibrating simulation parameters of a pipeline network. The method comprises the steps that a central node is determined in monitoring nodes in a pipe network through clustering; based on the measured data of the flow or the pressure of the central node, the flow or the pressure of other monitoring nodes is calculated in a simulation mode by utilizing a pipe section pressure drop equation and a flow balance equation of each node; when the error ratio of the simulated calculated flow or pressure of other monitoring nodes to the actual measurement result is not greater than a preset threshold, determining that the flow or pressure meets the engineering requirements, otherwise, not meeting the engineering requirements; preliminarily calibrating a first coefficient, a second coefficient and a third coefficient; correcting the first coefficient, the second coefficient and the third coefficient which are initially set by using the trained neural network to obtain the first coefficient, the second coefficient and the third coefficient which are corrected; and traversing each pipe section in turn based on the actually measured flow and pressure of the monitoring node in the pipe network to determine the flow and pressure information of the correction simulation of the non-monitoring node.
Description
Technical Field
The application relates to a simulation method for a pipe network, in particular to a method, a system and a medium for calibrating simulation parameters of the pipe network.
Background
Along with the operation of the pipe network, on one hand, corrosion and abrasion can occur on the inner wall of the pipeline along with the increase of the operation time, but the influence of the corrosion and abrasion on the friction resistance coefficient of the pipeline is difficult to estimate, and on the other hand, the local resistance of an elbow, a tee joint and the like in the gas pipe network is difficult to calculate accurately. The relative error brought by the method is eliminated by means of resistance identification, so that technical support can be provided for the scenes such as intelligent regulation and control of a pipe network, leakage detection and the like. Errors of actual conditions and design working conditions of the pipe network system are often reflected by data of pipe network simulation and equipment monitoring, and meanwhile, the accuracy of pipe network simulation is greatly limited due to dynamic fluctuation of pipe network working conditions along with time.
At present, two methods are available for simulating errors of a pipe network. The first approach is to classify and evaluate simulation errors by using the MAPE method. Specifically, according to SCADA system center data and online simulation system data, accuracy errors caused by factors such as data quality, noise level, parameter conditions and the like in an actual environment are compared and analyzed. N for the same time layerMeasurement data and NSimulation data are classified and evaluated for simulation errors by adopting the following MAPE method:
wherein MAPE is the mean absolute percentage error, Is an arbitrary measured value,/>Is the corresponding simulation value.
The calculation mode error calculation is rough, and the essence is that the threshold value is calculated by using the idea of the difference value.
The second approach is to identify the resistance of the pipeline model. However, as the pipe network scale increases and ages, the traditional numerical algorithm gradually fails in terms of resistance identification.
Disclosure of Invention
The present application is proposed to solve the problems in the prior art.
The application aims to provide a method, a system and a medium for calibrating simulation parameters of a pipe network, which can efficiently introduce AI into the simulation of the pipe network, simulate the flow or the pressure of non-monitoring nodes in the pipe network by using the flow or the pressure actual measurement data of the monitoring nodes, enable the AI algorithm to be excessively called when the simulation result is reasonable, and enable the flow or the pressure of the non-monitoring nodes to be balanced and comprehensively corrected by using the AI when the simulation result is deviated from reasonable, so that good balance is realized between calculation load and the dynamic accuracy of the simulation.
According to a first aspect of the present application there is provided a method of calibrating pipeline network simulation parameters, the method comprising the steps of. And determining a central node through clustering among a plurality of monitoring nodes with flow or pressure measured data in the pipe network, wherein the pipe network comprises non-monitoring nodes without flow or pressure measured data besides the monitoring nodes. Based on the measured data of the flow or the pressure of the central node, the flow or the pressure of other monitoring nodes and the flow or the pressure of non-monitoring nodes are calculated in a simulation mode by utilizing a pipe section pressure drop equation and a flow balance equation of each node. When the error ratio of the simulated calculated flow or pressure of other monitoring nodes to the measured flow or pressure of the other monitoring nodes is not greater than a preset threshold value, determining that the simulated calculated flow or pressure of the non-monitoring nodes meets the engineering requirements and directly using the non-monitoring nodes. And when the error ratio of the simulated calculated flow or pressure of the other monitoring nodes to the measured flow or pressure of the other monitoring nodes is larger than a preset threshold value, determining that the simulated calculated flow or pressure of the non-monitoring nodes does not meet the engineering requirements. For each pipe section in the pipe network, preliminarily calibrating a first coefficient, a second coefficient and a third coefficient according to the starting pressure, the ending pressure and the flow in the pipe section by using a formula (1),
Formula (1)
Wherein,Represents the starting point pressure,/>The end point pressure is represented, Q represents the flow in the pipe section, A is a first coefficient, B is a second coefficient, and C is a third coefficient. And under the conditions that the starting point or the end point of each pipe section is a non-monitoring node and the simulation calculation flow or the pressure does not meet the engineering requirement, correcting the preliminarily calibrated first coefficient, second coefficient and third coefficient by using the trained neural network to obtain the corrected first coefficient, second coefficient and third coefficient. And based on the actually measured flow and pressure of the monitoring nodes in the pipe network, sequentially traversing and applying the formula (1) to each pipe section formed by connecting the monitoring nodes and the non-monitoring nodes and each pipe section formed by connecting the non-monitoring nodes to each other to determine the flow and pressure information of the correction simulation of the non-monitoring nodes.
According to a second aspect of the present application, there is provided a system for calibrating pipeline network simulation parameters, the system comprising a processor and a memory. The processor is configured to perform a method of calibrating pipeline network simulation parameters in accordance with various embodiments of the application. The memory is configured to: and storing a trained neural network, wherein the trained neural network is used for correcting the first coefficient, the second coefficient and the third coefficient which are initially set.
According to a third aspect of the present application, there is provided a computer storage medium having stored thereon executable instructions. When the executable instructions are executed by a processor, a method for calibrating pipeline simulation parameters according to various embodiments of the application is realized.
According to the method, the system and the medium for calibrating the simulation parameters of the pipe network, disclosed by the embodiment of the application, AI can be efficiently introduced into the simulation of the pipe network, the flow or the pressure of the non-monitoring node in the pipe network is simulated by using the actually measured data of the flow or the pressure of the monitoring node, so that an AI algorithm is not excessively called when a simulation result is reasonable, and the flow or the pressure of the non-monitoring node can be weighed and comprehensively corrected by using the AI when the simulation result deviates from reasonable, so that good weighing is realized between the calculation load and the dynamic accuracy of the simulation. Therefore, even if the working condition of the pipe network dynamically fluctuates with time, the accuracy of pipe network simulation can be ensured under the condition of considering the calculation speed.
Drawings
In the drawings, which are not necessarily drawn to scale, like numerals may describe similar components in different views. The accompanying drawings illustrate various embodiments by way of example in general and not by way of limitation, and together with the description and claims serve to explain the disclosed embodiments. Such embodiments are illustrative and not intended to be exhaustive or exclusive of the present apparatus or method.
FIG. 1 illustrates a flow chart of a method of calibrating pipeline network simulation parameters in accordance with an embodiment of the present application.
Fig. 2 shows a schematic diagram of a pipe network topology according to an embodiment of the application.
FIG. 3 illustrates a flow chart of determining flow and pressure information for a modified simulation of a non-monitoring node based on measured flow and pressure of a monitoring node in the pipe network, according to an embodiment of the application.
FIG. 4 illustrates a frame diagram of a system for calibrating pipeline network simulation parameters in accordance with an embodiment of the present application.
FIG. 5 shows a flow chart of a method of performing simulation analysis of a pipeline network in accordance with an embodiment of the present application.
Detailed Description
The terms "first," "second," and the like, as used herein do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises" and the like means that elements preceding the word encompass the elements recited after the word, and not exclude the possibility of also encompassing other elements. The term "a or more" used in the present application includes a and a number larger than a, and the term "B or less" used herein includes not B but only a number smaller than B. The order in which the steps of the methods described in connection with the figures are performed is not intended to be limiting. As long as the logical relationship between the steps is not affected, several steps may be integrated into a single step, the single step may be decomposed into multiple steps, or the execution order of the steps may be exchanged according to specific requirements.
FIG. 1 illustrates a flow chart of a method of calibrating pipeline network simulation parameters in accordance with an embodiment of the present application. As shown in fig. 1, the method includes the following steps.
In step 101, a central node is determined by clustering among a plurality of monitoring nodes having measured data of flow or pressure in a pipe network, where the pipe network includes non-monitoring nodes not having measured data of flow or pressure in addition to the monitoring nodes. Specifically, the network to be rated, i.e., the target network, and the central node obtained by clustering can be selected based on a k-means clustering algorithm. The so-called hub node topology is connected to a large number of monitoring nodes and non-monitoring nodes. Thus, the central node may serve as a starting point for the simulation calculation.
In step 102, based on the measured data of the flow or pressure of the central node, the flow or pressure of other monitoring nodes and the flow or pressure of non-monitoring nodes are calculated in a simulation manner by using the pipe segment pressure drop equation and the flow balance equation of each node. The central point of the cluster is a node in a pipe network with known flow or pressure data and monitoring data, and the node does not contain an air source node and a tail end branch transmission node. Therefore, the clustered simulation calculation data is derived from actual measurement real data, and the flow and pressure of different nodes can be calculated through the adjacency matrix connection relation and the pipe section pressure drop equation. The pressure and flow calculated here depend on the impedance information of the pipe section. Based on the pipe network topological structure, node parameters and pipe section information are extracted, wherein the information comprises pipe diameter, material, wall thickness, roughness, node pressure, flow and the like. And combining a pipe section pressure drop equation, and additionally adding a flow balance equation of each node to form a pipe network equation set. For example, the Newton-Raphson method can be used to solve for the pressure, flow, pressure drop, etc. of each other monitoring node or non-monitoring node.
In step 103, when the error ratio of the simulated calculated flow or pressure of the other monitoring nodes and the measured flow or pressure of the other monitoring nodes is not greater than a predetermined threshold, determining that the simulated calculated flow or pressure of the non-monitoring nodes meets the engineering requirements and directly using the simulated calculated flow or pressure. Note that the monitoring node itself also has actually measured flow or pressure, and the flow or pressure of other monitoring nodes in the simulation calculation may deviate from the actually measured flow or pressure, and the magnitude of the deviation can verify whether the overall simulation calculation result is reasonable or not, and whether the overall simulation calculation result meets the engineering requirements or not. That is, the simulated calculated flow or pressure of the other monitoring nodes is used as a sampling sample in all the simulated calculation results, and compared with the measured flow or pressure of the other monitoring nodes, whether the simulated calculated flow or pressure of the non-monitoring nodes meets the engineering requirements can be verified, and whether the simulated calculated flow or pressure of each node including the non-monitoring nodes meets the engineering requirements is further estimated. In some embodiments, the predetermined threshold is 4% to 8%. For example, if the error rate does not exceed 5%, it is considered that the engineering requirements are met, and the simulated calculated flow or pressure of the non-monitoring node meets the engineering requirements and can be directly used without further processing.
In step 104, when the error ratio of the simulated calculated flow or pressure of the other monitoring nodes to the measured flow or pressure of the other monitoring nodes is greater than a predetermined threshold, it is determined that the simulated calculated flow or pressure of the non-monitoring nodes does not meet the engineering requirements. Under the condition of not meeting engineering requirements, the simulation calculation flow or pressure of the non-monitoring node can be used only after the adjustment and correction of the steps 105-107 are needed.
In step 105, for each pipe segment in the pipe network, initially calibrating a first coefficient, a second coefficient, and a third coefficient according to a starting pressure, an ending pressure, and a flow in the pipe segment using equation (1),
Formula (1)
Wherein,Represents the starting point pressure,/>The end point pressure is represented, Q represents the flow in the pipe section, A is a first coefficient, B is a second coefficient, and C is a third coefficient.
In the application, the starting point pressure isEndpoint pressure/>The influencing parameters between the flows Q in the pipe segments are carded and refined into three coefficients A, B and C, which are described in detail below in connection with the schematic diagram of the exemplary pipe network topology shown in fig. 2.
Taking the sub-network composed of nodes 1,2, 3,4 and 5 as an example, if the nodes 1 and 2 are monitoring nodes with measured pressure and flow, selecting a pipe section between the nodes 1 and 2, wherein the volume flow under the engineering standard condition is as follows:
formula (2)
Wherein Q, D is a,、/>Is known.
Representing the sequence number of segments in a pipe segment, H representing the number of segments in a pipe segment,/>Is the difference between the end point and the start point of the last segment in the gas pipe (the difference between the start point and the last segment is 0, then/>) Influence on the delivery capacity of the gas delivery pipe.The influence of the relative elevation of each point (namely each segment) in the middle of the pipe section on the air conveying capacity is considered, namely the influence of the longitudinal section characteristics of the pipe section on the air conveying capacity.
，/>The value of (2) is a constant depending on the unit used for each parameter,/>Gravitational acceleration, R represents molar gas constant.
Represents the diameter of the pipe section, T represents the temperature,/>Representing sequence numbers of segments in a pipe segment,/>Representing the relative difference in height between the end and start of the ith segment in the pipe segment,/>Representing the difference in elevation between the end point and the start point of the last segment in a pipe segment,/>Representing the length of projection of the ith segment in the pipe section in the horizontal direction, Z represents the compression factor related to node pressure and temperature T,/>Representing the roughness of the wall surface of a pipe section,/>The friction coefficient of the pipe section is represented, and L represents the pipe section length.
Equation (2) can be converted into equation (3):
Formula (3)
Wherein,In practice, the algebraic sum of the areas included between the longitudinal section line of the pipe section and the horizontal line drawn from the start point can be considered.
The first coefficient, the second coefficient and the third coefficient A, B and C of each pipe section are extracted by utilizing the attribute of each pipe section in the pipe network and are respectively as follows:
Formula (a)
Formula (b)
Formula (c)
Wherein,Represents the diameter of the pipe section, T represents the temperature,/>Representing the sequence number of segments in a pipe segment, H representing the number of segments in a pipe segment,/>Representing the relative difference in height between the end point and the start point of the last segment in a pipe segment,/>，/>Representing the effect of the difference in elevation between the end point and the start point of the last segment in a pipe segment on the pipe transport capacity,/>Representing the length of projection of the ith segment in the pipe section in the horizontal direction, Z represents the compression factor related to node pressure and temperature T,/>Indicating the roughness of the wall surface of the pipe section,Represents the friction coefficient of the pipe section, L represents the pipe length,/>The value of (2) is a constant depending on the unit used for each parameter,/>Gravitational acceleration, R represents molar gas constant.
Thus, equation (3) can be reduced to equation (1) above:
Formula (1)
That is, for each pipe segment formed by the connection of the monitoring node and the non-monitoring node, the monitoring node has the measured pressure and flow, if A, B and C of the pipe segment are known, the pressure and flow of the non-monitoring node at the other end of the pipe segment can be calculated in a simulation manner; starting from the non-monitoring node, the pressure and flow of the other non-monitoring node at the other end of the pipe section can be calculated in a simulation mode based on the calculated pressure and flow of the non-monitoring node, if A, B and C of the pipe section are known, the pipe section is traversed in a simulation mode, and if A, B and C of each pipe section are accurate and reasonable, the pressure and flow of each pipe section can be calculated in a simulation mode, as described in the following step 107. In transient simulation, the network topology is often fixed,、/>Q is the dynamic variable.
If it is determined that the calculated flow or pressure of the simulation of the non-monitoring node does not meet the engineering requirements in step 104, the first coefficient a, the second coefficient B, and the third coefficient C may be initially defined in step 105 according to the starting pressure, the ending pressure, and the flow in the pipe segment for each pipe segment in the pipe network by using the formula (1). The first coefficient a, the second coefficient B, and the third coefficient C here are preliminary calibrations and are not always necessarily accurate and reasonable. In some embodiments, for each pipe segment, initially calibrating the first, second, and third coefficients using equation (1) based on the starting pressure, the ending pressure, and the flow in the pipe segment specifically includes: and (3) preliminarily calibrating a first coefficient, a second coefficient and a third coefficient by utilizing a formula (1) according to the starting point pressure, the end point pressure and the flow in the pipe section at 3 moments calculated or actually measured by the pipe section simulation.
Returning to the pipe network topology of FIG. 2, for the pipe segment between nodes 2, 3, the starting pressure, ending pressure and flow at time t1 are respectively、/>And/>Starting pressure, ending pressure and flow at time t2 are/>, respectively、/>And/>Starting pressure, ending pressure and flow at time t3 are/>, respectively、/>And/>Equation (1) can be extended to the following 3 equations:
At least 3 sets of data can be obtained A, B, C, and the 3 sets of data are measured data to obtain reliable A, B and C, but if the 3 sets of data are mixed with simulation calculation data and the simulation calculation flow or pressure of a non-monitoring node does not meet engineering requirements, the reliability of A, B and C obtained by the method is insufficient, the calculated A, B and C cannot be directly used for calculating the starting pressure, the end pressure and the flow at other moments, but can be used as the basis for preliminary calibration A, B and C, namely, correction by the neural network trained in the following step 106.
In step 106, under the condition that the starting point or the end point of each pipe section is a non-monitoring node and the simulation calculation flow or the pressure does not meet the engineering requirement, the first coefficient, the second coefficient and the third coefficient which are initially set are corrected by using the trained neural network, and the first coefficient, the second coefficient and the third coefficient which are corrected are obtained. The trained neural network herein may be configured to learn how to map preliminary scaled A, B and C for each pipe segment of the pipe network to accurate and rational modified A, B and C.
The neural network can be used to solve many of the problems of complex nonlinear systems. Specifically, the neural network includes an input layer configured to receive a first coefficient, a second coefficient, and a third coefficient for each pipe segment to be calibrated, a number of intermediate layers, and an output layer configured to output the first coefficient, the second coefficient, and the third coefficient for each pipe segment to be calibrated.
Each layer of the neural network is provided with a plurality of neuron elements, and a unidirectional input layer is arranged between elements of adjacent layers to transfer information to the next layer by layer, and can be expressed as a formula (4):
Formula (4)
Wherein,And j both represent the sequence number of the pipe segment,/>First coefficient, second coefficient and third coefficient/>, which are rated for the to-be-corrected corresponding to the mth pipe section，/>Represents the j-th pipe section to the j-th pipe sectionPipe section amount to be corrected/>Impact weight (also called weight coefficient),/>，/>First, second and third coefficients representing correction factors for an mth pipe segment/>。
In some embodiments, the neural network is trained as follows.
And determining ground truth values of a first coefficient, a second coefficient and a third coefficient of each pipe section by using time sequence data of the measured pressure of the starting point, the measured pressure of the ending point and the measured flow of each pipe section in the pipe network.
Determining the first coefficient, the second coefficient and the third coefficient to be corrected rate fixed values of each pipe section according to the formula (a) -formula (b) by utilizing the attribute of each pipe section in the pipe network:
Formula (a)
Formula (b)
Formula (c)
Wherein,Represents the diameter of the pipe section, T represents the temperature,/>Representing the sequence number of segments in a pipe segment, H representing the number of segments in a pipe segment,/>Representing the relative difference in height between the end and start of the ith segment in the pipe segment,/>Representing the relative difference in height between the end point and the start point of the last segment in a pipe segment,/>，/>Representing the effect of the difference in elevation between the end point and the start point of the last segment in a pipe segment on the pipe transport capacity,/>Representing the length of projection of the ith segment in the pipe section in the horizontal direction, Z represents the compression factor related to node pressure and temperature T,/>Representing the roughness of the wall surface of a pipe section,/>Represents the friction coefficient of the pipe section, L represents the length of the pipe section,The value of (2) is a constant depending on the unit used for each parameter,/>Gravitational acceleration, R represents molar gas constant.
And correcting the weight coefficient of each middle layer by using the fixed value of the to-be-corrected rate and the ground true value of the first coefficient, the second coefficient and the third coefficient of each pipe section. The loss function may be calculated based on the deviation of the to-be-corrected rate set value and the ground truth value, and the weight coefficients of each intermediate layer may be adjusted based on the value of the loss function, such as, but not limited to, a random gradient descent method, a batch gradient descent method, and the like, until training is completed.
In step 107, based on the measured flow and pressure of the monitoring node in the pipe network, the flow and pressure information of the correction simulation of the non-monitoring node is determined by sequentially traversing and applying the formula (1) to each pipe segment formed by connecting the monitoring node with the non-monitoring node and each pipe segment formed by connecting the non-monitoring nodes with each other.
By using the method for calibrating the simulation parameters of the pipe network, the neural network can be efficiently introduced into the simulation of the pipe network, the flow or pressure of the non-monitoring node in the pipe network is simulated by using the flow or pressure actual measurement data of the monitoring node, whether the simulation result is reasonable or not is intuitively and objectively and efficiently estimated by fully using the accurate flow or pressure actual measurement data of the monitoring node, the method is directly applicable when the simulation result is reasonable, and the first coefficient A, the second coefficient B and the third coefficient C of each pipe section can be weighed and comprehensively corrected by using the trained neural network when the simulation result is deviated from reasonable, so that the flow or pressure of each non-monitoring node is comprehensively corrected according to the simulation result, and good weighing is realized between the calculation load and the simulation dynamic accuracy. Therefore, even if the working condition of the pipe network dynamically fluctuates with time, the accuracy of pipe network simulation can be ensured under the condition of considering the calculation speed.
FIG. 3 illustrates a flow chart of determining flow and pressure information for a modified simulation of a non-monitoring node based on measured flow and pressure of a monitoring node in the pipe network, according to an embodiment of the application.
As shown in fig. 3, at step 301, an adjacency matrix of pipe network nodes is generated. In step 302, the monitoring nodes in the adjacency matrix are numbered. Take nodes 1,2,3, 4 and 5 in fig. 2 as examples, where node 2 is the monitoring node.
In step 303, from the monitoring node as a searching start point, a traversing algorithm is adopted to sequentially traverse adjacent nodes, edges and rings in the adjacency matrix and obtain sequentially adjacent pipe sections. For example, referring to FIG. 2, if node 2 is a monitoring node, traversing it as a search starting point may result in neighboring nodes of 1, 3, 4, and 5, with adjoining pipe segments comprising 2-1, 2-3, 2-4, 2-5.
In step 304, for each numbered monitoring node, based on its measured flow and pressure, equation (1) is sequentially traversed and applied to each pipe segment (2-1, 2-3, 2-4, 2-5) formed by connecting the monitoring node with a non-monitoring node and each pipe segment formed by connecting the connected non-monitoring nodes with each other to determine flow and pressure information of the correction simulation of the non-monitoring node. Here, the first coefficient a, the second coefficient B, and the third coefficient C of the corresponding pipe section have been corrected comprehensively when the formula (1) is applied, so the calculated flow and pressure information of the correction simulation of the non-monitoring node is accurate and reasonable.
In the above example, the pipe sections are formed by connecting the monitoring nodes with the non-monitoring nodes, which is only used as an example, and can be further extended to each pipe section formed by connecting the non-monitoring nodes with each other, if the nodes 3 and 5 are both non-monitoring nodes, the pipe sections 3-5 are pipe sections formed by connecting the non-monitoring nodes with each other, and by comprehensively correcting the first coefficient a, the second coefficient B and the third coefficient C of the corresponding pipe section (for example but not limited to the pipe sections 3-5), the accurate and reasonable pressure and flow information of the node 5 can be calculated based on the flow and pressure information corrected by the simulation of the node 3, which is not described herein.
In some embodiments, based on the measured data of the flow or pressure of the central node, the flow or pressure of other monitoring nodes and the flow or pressure of non-monitoring nodes can be calculated in a similar manner by using the pipe segment pressure drop equation and the flow balance equation of each node. Specifically, the following is described.
Generating an adjacency matrix of pipe network nodes according to the node and edge connection relation formed by the pipe network topology structure diagram; numbering monitoring nodes in the adjacent matrix; and traversing adjacent nodes, edges and rings in the adjacent matrix by adopting a traversing algorithm from the monitoring node to a searching starting point, and determining the flow and pressure information of the non-monitoring node by applying a one-dimensional Newton node method or a one-dimensional Newton loop method.
FIG. 4 is a block diagram of a system for calibrating pipeline network simulation parameters in accordance with an embodiment of the present application
As shown in fig. 4, the system includes a processor 401 and a memory 402.
The processor 401 is configured to: the method for calibrating the simulation parameters of the pipeline network according to the various embodiments of the application is executed. The method specifically comprises the following steps.
In step 101, a central node is determined by clustering among a plurality of monitoring nodes having measured data of flow or pressure in a pipe network, where the pipe network includes non-monitoring nodes not having measured data of flow or pressure in addition to the monitoring nodes. Specifically, the network to be rated, i.e., the target network, and the central node obtained by clustering can be selected based on a k-means clustering algorithm. The so-called hub node topology is connected to a large number of monitoring nodes and non-monitoring nodes. Thus, the central node may serve as a starting point for the simulation calculation.
In step 102, based on the measured data of the flow or pressure of the central node, the flow or pressure of other monitoring nodes and the flow or pressure of non-monitoring nodes are calculated in a simulation manner by using the pipe segment pressure drop equation and the flow balance equation of each node. The central point of the cluster is a node in a pipe network with known flow or pressure data and monitoring data, and the node does not contain an air source node and a tail end branch transmission node. Therefore, the clustered simulation calculation data is derived from actual measurement real data, and the flow and pressure of different nodes can be calculated through the adjacency matrix connection relation and the pipe section pressure drop equation. The pressure and flow calculated here depend on the impedance information of the pipe section. Based on the pipe network topological structure, node parameters and pipe section information are extracted, wherein the information comprises pipe diameter, material, wall thickness, roughness, node pressure, flow and the like. And combining a pipe section pressure drop equation, and additionally adding a flow balance equation of each node to form a pipe network equation set. The Newton-Raphson method is adopted to solve, and the pressure, flow, pressure drop and the like of each other monitoring node or non-monitoring node can be obtained.
In step 103, when the error ratio of the simulated calculated flow or pressure of the other monitoring nodes and the measured flow or pressure of the other monitoring nodes is not greater than a predetermined threshold, determining that the simulated calculated flow or pressure of the non-monitoring nodes meets the engineering requirements and directly using the simulated calculated flow or pressure. Note that the monitoring node itself also has actually measured flow or pressure, and the flow or pressure of other monitoring nodes in the simulation calculation may deviate from the actually measured flow or pressure, and the magnitude of the deviation can verify whether the overall simulation calculation result is reasonable or not, and whether the overall simulation calculation result meets the engineering requirements or not. That is, the simulated calculated flow or pressure of the other monitoring nodes is used as a sampling sample in all the simulated calculation results, and compared with the measured flow or pressure of the other monitoring nodes, whether the simulated calculated flow or pressure of the non-monitoring nodes meets the engineering requirements can be verified, and whether the simulated calculated flow or pressure of each node including the non-monitoring nodes meets the engineering requirements is further estimated. In some embodiments, the predetermined threshold is 4% to 8%. For example, if the error rate does not exceed 5%, it is considered that the engineering requirements are met, and the simulated calculated flow or pressure of the non-monitoring node meets the engineering requirements and can be directly used without further processing.
In step 104, when the error ratio of the simulated calculated flow or pressure of the other monitoring nodes to the measured flow or pressure of the other monitoring nodes is greater than a predetermined threshold, it is determined that the simulated calculated flow or pressure of the non-monitoring nodes does not meet the engineering requirements. Under the condition of not meeting engineering requirements, the simulation calculation flow or pressure of the non-monitoring node can be used only after the adjustment and correction of the steps 105-107 are needed.
In step 105, for each pipe segment in the pipe network, initially calibrating a first coefficient, a second coefficient, and a third coefficient according to a starting pressure, an ending pressure, and a flow in the pipe segment using equation (1),
Formula (1)
Wherein,Represents the starting point pressure,/>The end point pressure is represented, Q represents the flow in the pipe section, A is a first coefficient, B is a second coefficient, and C is a third coefficient.
If it is determined that the calculated flow or pressure of the simulation of the non-monitoring node does not meet the engineering requirements in step 104, the first coefficient a, the second coefficient B, and the third coefficient C may be initially defined in step 105 according to the starting pressure, the ending pressure, and the flow in the pipe segment for each pipe segment in the pipe network by using the formula (1). The first coefficient a, the second coefficient B, and the third coefficient C here are preliminary calibrations and are not always necessarily accurate and reasonable. In some embodiments, for each pipe segment, initially calibrating the first, second, and third coefficients using equation (1) based on the starting pressure, the ending pressure, and the flow in the pipe segment specifically includes: and (3) preliminarily calibrating a first coefficient, a second coefficient and a third coefficient by utilizing a formula (1) according to the starting point pressure, the end point pressure and the flow in the pipe section at 3 moments calculated or actually measured by the pipe section simulation.
In step 106, under the condition that the starting point or the end point of each pipe section is a non-monitoring node and the simulation calculation flow or the pressure does not meet the engineering requirement, the first coefficient, the second coefficient and the third coefficient which are initially set are corrected by using the trained neural network, and the first coefficient, the second coefficient and the third coefficient which are corrected are obtained. The trained neural network herein may be configured to learn how to map preliminary scaled A, B and C for each pipe segment of the pipe network to accurate and rational modified A, B and C.
In step 107, based on the measured flow and pressure of the monitoring node in the pipe network, the flow and pressure information of the correction simulation of the non-monitoring node is determined by sequentially traversing and applying the formula (1) to each pipe segment formed by connecting the monitoring node with the non-monitoring node and each pipe segment formed by connecting the non-monitoring nodes with each other.
By using the method for calibrating the simulation parameters of the pipe network, the neural network can be efficiently introduced into the simulation of the pipe network, the flow or pressure of the non-monitoring node in the pipe network is simulated by using the flow or pressure actual measurement data of the monitoring node, whether the simulation result is reasonable or not is intuitively and objectively and efficiently estimated by fully using the accurate flow or pressure actual measurement data of the monitoring node, the method is directly applicable when the simulation result is reasonable, and the first coefficient A, the second coefficient B and the third coefficient C of each pipe section can be weighed and comprehensively corrected by using the trained neural network when the simulation result is deviated from reasonable, so that the flow or pressure of each non-monitoring node is comprehensively corrected according to the simulation result, and good weighing is realized between the calculation load and the simulation dynamic accuracy. Therefore, even if the working condition of the pipe network dynamically fluctuates with time, the accuracy of pipe network simulation can be ensured under the condition of considering the calculation speed.
The memory 402 is configured to: and storing a trained neural network, wherein the trained neural network is used for correcting the first coefficient, the second coefficient and the third coefficient which are initially set.
In some embodiments, the present application also provides a computer storage medium having stored thereon executable instructions which when executed by a processor implement a method of calibrating pipeline simulation parameters according to any of the embodiments of the present application, or the steps of a method of performing simulation analysis of a pipeline according to any of the embodiments of the present application, or a combination thereof.
FIG. 5 shows a flow chart of a method of performing simulation analysis of a pipeline network in accordance with an embodiment of the present application. As shown in FIG. 5, the data at both ends can be extracted for each individual pipe segment to check whether the pipe segment has the actual measurementAnd Q, if all the 3 variables are provided, AI training is not performed, and the values in the adjacent matrix are directly calculated, so that the pressure and the flow of the adjacent nodes are calculated in a simulation mode. If the simulation parameters of the pipeline network are only 2 variables, the method for calibrating the simulation parameters of the pipeline network is executed, the neural network is trained, errors of simulation data and measured data of the monitoring nodes are identified, if the errors are less than 5%, MAPE method is directly adopted for correction or not, otherwise, the errors of A, B and C are sequentially corrected. The following steps may be performed with reference to other embodiments of the present application and are not described in detail herein.
The processor 401 in the present application may be a processing device including one or more general-purpose processing devices, such as a microprocessor, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), or the like. More specifically, the processor 401 may be a Complex Instruction Set Computing (CISC) microprocessor, a Reduced Instruction Set Computing (RISC) microprocessor, a Very Long Instruction Word (VLIW) microprocessor, a processor running other instruction sets, or a processor running a combination of instruction sets. The processor 401 may also be one or more special purpose processing devices such as an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), a system on a chip (SoC), etc. The processor 401 may be communicatively coupled to a memory and configured to execute computer-executable instructions stored thereon.
Furthermore, although exemplary embodiments have been described herein, the scope thereof includes any and all embodiments having equivalent elements, modifications, omissions, combinations (e.g., of the various embodiments across), adaptations or alterations as pertains to the present application. The elements in the claims are to be construed broadly based on the language employed in the claims and are not limited to examples described in the present specification or during the practice of the application, which examples are to be construed as non-exclusive. It is intended, therefore, that the specification and examples be considered as exemplary only, with a true scope and spirit being indicated by the following claims and their full scope of equivalents.
The above description is intended to be illustrative and not restrictive. For example, the above-described examples (or one or more aspects thereof) may be used in combination with each other. For example, other embodiments may be used by those of ordinary skill in the art upon reading the above description. In addition, in the above detailed description, various features may be grouped together to streamline the application. This is not to be interpreted as an intention that the disclosed features not being claimed are essential to any claim. Rather, inventive subject matter may lie in less than all features of a particular disclosed embodiment. Thus, the following claims are hereby incorporated into the detailed description as examples or embodiments, with each claim standing on its own as a separate embodiment, and it is contemplated that these embodiments may be combined with one another in various combinations or permutations. The scope of the application should be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.
The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application, the scope of which is defined by the claims. Various modifications and equivalent arrangements of this application will occur to those skilled in the art, and are intended to be within the spirit and scope of the application.
Claims (10)
1. A method of calibrating a pipeline network simulation parameter, the method comprising:
the method comprises the steps that among a plurality of monitoring nodes with flow or pressure measured data in a pipe network, a central node is determined through clustering, and the pipe network comprises non-monitoring nodes without flow or pressure measured data besides the monitoring nodes;
Based on the measured data of the flow or the pressure of the central node, the flow or the pressure of other monitoring nodes and the flow or the pressure of non-monitoring nodes are calculated in a simulation mode by utilizing a pipe section pressure drop equation and a flow balance equation of each node;
when the error ratio of the simulated calculated flow or pressure of other monitoring nodes to the measured flow or pressure of the other monitoring nodes is not greater than a preset threshold value, determining that the simulated calculated flow or pressure of the non-monitoring nodes meets the engineering requirements and directly using the non-monitoring nodes;
when the error ratio of the simulated calculated flow or pressure of other monitoring nodes to the measured flow or pressure of the other monitoring nodes is larger than a preset threshold value, determining that the simulated calculated flow or pressure of the non-monitoring nodes does not meet the engineering requirements;
For each pipe section in the pipe network, preliminarily calibrating a first coefficient, a second coefficient and a third coefficient according to the starting pressure, the ending pressure and the flow in the pipe section by using a formula (1),
Formula (1)
Wherein,Represents the starting point pressure,/>The end point pressure is represented, Q represents the flow in the pipe section, A is a first coefficient, B is a second coefficient, and C is a third coefficient;
Under the conditions that the starting point or the end point of each pipe section is a non-monitoring node and the simulation calculation flow or the pressure does not meet the engineering requirement, the first coefficient, the second coefficient and the third coefficient which are initially set are corrected by using the trained neural network, so that the first coefficient, the second coefficient and the third coefficient which are corrected are obtained; and
Based on the actually measured flow and pressure of the monitoring nodes in the pipe network, the formula (1) is sequentially traversed and applied to each pipe section formed by connecting the monitoring nodes with the non-monitoring nodes and each pipe section formed by connecting the non-monitoring nodes with each other, so that the flow and pressure information of the correction simulation of the non-monitoring nodes is determined.
2. The method of claim 1, wherein the central node does not include an air source node or an end branching node.
3. The method of claim 1, wherein determining corrected simulated flow and pressure information for non-monitoring nodes based on measured flow and pressure for monitoring nodes in the pipe network comprises: generating an adjacency matrix of pipe network nodes; numbering monitoring nodes in the adjacent matrix; using the monitoring node as a searching starting point, adopting a traversing algorithm to sequentially traverse adjacent nodes, edges and rings in the adjacent matrix and obtain sequentially adjacent pipe sections; for each numbered monitoring node, based on the actually measured flow and pressure of the monitoring node, sequentially traversing and applying the formula (1) to each pipe section formed by connecting the monitoring node with the non-monitoring node and each pipe section formed by connecting the communicated non-monitoring nodes with each other to determine the flow and pressure information of the correction simulation of the non-monitoring node.
4. The method of claim 1, wherein the neural network comprises an input layer configured to receive the first, second, and third coefficients for each pipe segment to be modified, a number of intermediate layers, and an output layer configured to output the first, second, and third coefficients for each pipe segment to be modified.
5. The method of claim 4, wherein the neural network is trained by:
determining ground truth values of a first coefficient, a second coefficient and a third coefficient of each pipe section by using time sequence data of measured pressure of a starting point, measured pressure of a finishing point and measured flow of each pipe section in the pipe network;
Determining the first coefficient, the second coefficient and the third coefficient to be corrected rate fixed values of each pipe section according to the formula (a) -formula (c) by utilizing the attribute of each pipe section in the pipe network:
Formula (a)
Formula (b)
Formula (c)
Wherein,Represents the diameter of the pipe section, T represents the temperature,/>Representing sequence numbers of segments in a pipe segment,/>Representing the relative height difference between the end point and the start point of the ith segment in the pipe section, H representing the number of segments in the pipe section,/>Representing the relative difference in height between the end point and the start point of the last segment in a pipe segment,/>，/>Representing the effect of the difference in elevation between the end point and the start point of the last segment in a pipe segment on the pipe transport capacity,/>Representing the length of projection of the ith segment in the pipe section in the horizontal direction, Z represents the compression factor related to node pressure and temperature T,/>Representing the roughness of the wall surface of a pipe section,/>Represents the friction coefficient of the pipe section, L represents the pipe length,/>The value of (2) is a constant depending on the unit used for each parameter,/>Gravitational acceleration, R represents molar gas constant;
and correcting the weight coefficient of each middle layer by using the fixed value of the to-be-corrected rate and the ground true value of the first coefficient, the second coefficient and the third coefficient of each pipe section.
6. The method of claim 1, wherein the predetermined threshold is 4% to 8%.
7. The method of claim 1, wherein the simulating calculation of the flow or pressure of other monitoring nodes and the flow or pressure of non-monitoring nodes based on the measured flow or pressure data of the central node by using a pipe segment pressure drop equation and a flow balance equation of each node specifically comprises: generating an adjacency matrix of pipe network nodes according to the node and edge connection relation formed by the pipe network topology structure diagram; numbering monitoring nodes in the adjacent matrix; and traversing adjacent nodes, edges and rings in the adjacent matrix by adopting a traversing algorithm from the monitoring node to a searching starting point, and determining the flow and pressure information of the non-monitoring node by applying a one-dimensional Newton node method or a one-dimensional Newton loop method.
8. The method of claim 1, wherein initially plotting the first, second and third coefficients using equation (1) based on the starting pressure, the ending pressure and the flow in the pipe segment for each pipe segment comprises:
And (3) preliminarily calibrating a first coefficient, a second coefficient and a third coefficient by utilizing a formula (1) according to the starting point pressure, the end point pressure and the flow in the pipe section at 3 moments calculated or actually measured by the pipe section simulation.
9. A system for calibrating network simulation parameters, comprising:
A processor configured to: performing the method of calibrating pipeline network simulation parameters according to any of claims 1-8; and
A memory configured to: and storing a trained neural network, wherein the trained neural network is used for correcting the first coefficient, the second coefficient and the third coefficient which are initially set.
10. A computer storage medium having stored thereon executable instructions which when executed by a processor implement a method of calibrating pipeline simulation parameters according to any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410396911.4A CN117993306B (en) | 2024-04-03 | 2024-04-03 | Method, system and medium for calibrating simulation parameters of pipe network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410396911.4A CN117993306B (en) | 2024-04-03 | 2024-04-03 | Method, system and medium for calibrating simulation parameters of pipe network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117993306A CN117993306A (en) | 2024-05-07 |
| CN117993306B true CN117993306B (en) | 2024-06-04 |
Family
ID=90900849
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410396911.4A Active CN117993306B (en) | 2024-04-03 | 2024-04-03 | Method, system and medium for calibrating simulation parameters of pipe network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117993306B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118171500B (en) * | 2024-05-14 | 2024-07-16 | 上海叁零肆零科技有限公司 | Steady state tracing monitoring analysis method, device, equipment and medium for natural gas pipe network |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682369A (en) * | 2017-02-27 | 2017-05-17 | 常州英集动力科技有限公司 | Heating pipe network hydraulic simulation model identification correction method and system, method of operation |
| CN112818495A (en) * | 2021-02-22 | 2021-05-18 | 成都四为电子信息股份有限公司 | Novel dynamic correction method for pipeline pressure drop measurement and calculation algorithm parameters |
| CN116305489A (en) * | 2023-04-11 | 2023-06-23 | 北京云庐科技有限公司 | Method, system and medium for monitoring structural damage of building |
| CN116611309A (en) * | 2023-04-04 | 2023-08-18 | 华为技术有限公司 | Physical field simulation method, system, medium and electronic equipment |
| CN117521313A (en) * | 2024-01-08 | 2024-02-06 | 北京云庐科技有限公司 | Method and device for leak detection of a pipeline network |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR3088463A1 (en) * | 2018-11-09 | 2020-05-15 | Adagos | METHOD OF CONSTRUCTING A NEURON ARRAY FOR THE SIMULATION OF REAL SYSTEMS |
-
2024
- 2024-04-03 CN CN202410396911.4A patent/CN117993306B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682369A (en) * | 2017-02-27 | 2017-05-17 | 常州英集动力科技有限公司 | Heating pipe network hydraulic simulation model identification correction method and system, method of operation |
| CN112818495A (en) * | 2021-02-22 | 2021-05-18 | 成都四为电子信息股份有限公司 | Novel dynamic correction method for pipeline pressure drop measurement and calculation algorithm parameters |
| CN116611309A (en) * | 2023-04-04 | 2023-08-18 | 华为技术有限公司 | Physical field simulation method, system, medium and electronic equipment |
| CN116305489A (en) * | 2023-04-11 | 2023-06-23 | 北京云庐科技有限公司 | Method, system and medium for monitoring structural damage of building |
| CN117521313A (en) * | 2024-01-08 | 2024-02-06 | 北京云庐科技有限公司 | Method and device for leak detection of a pipeline network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117993306A (en) | 2024-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117993306B (en) | Method, system and medium for calibrating simulation parameters of pipe network | |
| US11709979B1 (en) | Bridge damage identification method considering uncertainty | |
| CN109145464B (en) | Structural damage identification method integrating multi-target ant lion optimization and trace sparse regularization | |
| CN115111537B (en) | Method, device and medium for determining the position of a leak in a gas pipeline network | |
| CN115166618B (en) | Current transformer error evaluation method for non-stable output | |
| CN110502277A (en) | A kind of bad taste detection method of code based on BP neural network | |
| CN108846200B (en) | Quasi-static bridge influence line identification method based on iteration method | |
| CN111666684B (en) | Circumferential weld risk prediction method and device for conveying pipeline and readable storage medium | |
| CN109190901A (en) | The credible evaluation method of reliability assessment result based on multi objective measurement | |
| CN109272217A (en) | A kind of data processing method and relevant device | |
| CN115047064A (en) | Pipeline defect quantification method, processor and pipeline defect quantification device | |
| CN114626769A (en) | Operation and maintenance method and system for capacitor voltage transformer | |
| CN104111887A (en) | Software fault prediction system and method based on Logistic model | |
| CN113607601A (en) | Intelligent detection method for ore pulp concentration based on combination of identification model and deep learning | |
| CN117748481A (en) | Real-time dynamic partitioning-based power system inertia online evaluation method and device | |
| CN117494555A (en) | Training method and device for pipeline stress prediction model and computing equipment | |
| CN112241808A (en) | Road surface technical condition prediction method, device, electronic equipment and storage medium | |
| CN117034808A (en) | Natural gas pipe network pressure estimation method based on graph attention network | |
| CN110411721A (en) | A kind of marine riser damage positioning method and system | |
| CN115878986A (en) | Degradation trend evaluation method for variable working condition bearing | |
| CN115481461A (en) | Structural wind pressure statistic prediction method based on deep learning | |
| CN104331775A (en) | Quality analysis method for metering asset lifecycles | |
| CN115754875A (en) | Voltage transformer error evaluation method and device | |
| CN109101759A (en) | A kind of parameter identification method based on forward and reverse response phase method | |
| CN111859744B (en) | Method, device and equipment for identifying node rigid domain based on monitoring data |
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 |