CN108591836A

CN108591836A - The detection method and device of pipe leakage

Info

Publication number: CN108591836A
Application number: CN201810329471.5A
Authority: CN
Inventors: 张万; 梁永图; 聂四明; 徐宁; 张浩然
Original assignee: China University of Petroleum Beijing
Current assignee: China University of Petroleum Beijing
Priority date: 2018-04-13
Filing date: 2018-04-13
Publication date: 2018-09-28
Anticipated expiration: 2038-04-13
Also published as: CN108591836B

Abstract

The embodiment of the present application provides a kind of detection method and device of pipe leakage, wherein this method includes：Obtain data on flows and pressure data, the data on flows in the pipe under test final position and pressure data of pipe under test start position；According to the data on flows and pressure data of the pipe under test start position, the data on flows and pressure data in the pipe under test final position, the hydrodynamics and thermodynamics transient model of pipe under test are solved by particle swarm optimization, to obtain result parameter, the result parameter is for determining whether the pipe under test leaks, since the program is by the way that particle swarm optimization to be combined with hydrodynamics and thermodynamics transient analysis, above-mentioned transient model is solved to determine conduit running situation by particle swarm optimization, to solve restricted application present in existing method, the poor technical problem of leak detection accuracy, reach the technique effect for effectively improving leak detection precision.

Description

Method and device for detecting pipeline leakage

Technical Field

The application relates to the technical field of oil and gas storage and transportation management, in particular to a method and a device for detecting pipeline leakage.

Background

In the industrial transportation process, many chemicals are transported to their corresponding destinations through pipelines. For example, crude oil is typically transported via an oil and gas transport pipeline to a distribution station along the pipeline, from which the crude oil is supplied to a surrounding area for use. During the transportation process, if chemical substances in the pipeline leak, economic loss can be caused, and environmental pollution can also be caused.

At present, most of the existing methods utilize a negative pressure wave method to detect the pipeline and discover the pipeline leakage in time. However, the method is relatively simple, is not sensitive enough to some leakage conditions (such as micropore leakage and transport liquid with large elastic coefficient, density or viscosity), and has relatively large error in leakage detection. Namely, the existing method is often limited in application range and poor in detection accuracy when implemented.

In view of the above problems, no effective solution has been proposed.

Disclosure of Invention

The embodiment of the application provides a method and a device for detecting pipeline leakage, which are used for solving the technical problems of limited application range and poor leakage detection accuracy in the existing method and achieving the technical effect of effectively improving the pipeline leakage detection precision.

The embodiment of the application provides a method for detecting pipeline leakage, which comprises the following steps:

acquiring flow data and pressure data of a starting position of a pipeline to be detected and flow data and pressure data of an end position of the pipeline to be detected;

and solving a hydrodynamic and thermodynamic transient model of the pipeline to be detected through a particle swarm algorithm according to the flow data and the pressure data of the starting position of the pipeline to be detected and the flow data and the pressure data of the end position of the pipeline to be detected to obtain a result parameter, wherein the result parameter is used for determining whether the pipeline to be detected leaks.

In one embodiment, the hydrodynamic and thermodynamic transient models of the pipe under test are established as follows:

acquiring characteristic parameters of a pipeline to be tested, wherein the characteristic parameters of the pipeline to be tested at least comprise: the starting position of the pipeline to be tested, the end position of the pipeline to be tested and the diameter of the pipeline to be tested;

establishing an initial model of the pipeline to be tested according to the characteristic parameters of the pipeline to be tested;

and preprocessing the initial model of the pipeline to be tested by a finite volume method of a staggered grid to obtain a hydrodynamics and thermodynamic transient model of the pipeline to be tested.

In one embodiment, solving a hydrodynamic and thermodynamic transient model of a pipeline to be measured by a particle swarm algorithm according to flow data and pressure data of a starting position of the pipeline to be measured and flow data and pressure data of an ending position of the pipeline to be measured to obtain a result parameter includes:

performing iterative solution on the hydrodynamic and thermodynamic transient model of the pipeline to be tested for multiple times through a particle swarm algorithm according to the flow data and the pressure data of the starting position of the pipeline to be tested and the flow data and the pressure data of the end position of the pipeline to be tested to obtain a simulated flow and a simulated pressure; stopping iteration until the adaptive function based on the simulation flow and the simulation pressure meets a preset condition, and recording a result parameter solved when the iteration is stopped;

and determining whether the pipeline to be detected leaks or not according to the result parameters.

In one embodiment, the hydrodynamic and thermodynamic transient models of the pipeline to be measured are solved by a particle swarm algorithm in a plurality of iterations, including:

the iterative solution is performed in the following manner:

v_k(τ+1)＝v_k(τ)+c₁r₁(p_k(τ)-x_k(τ))+c₂r₂(p_k(τ)-x_k(τ))

x_k(τ+1)＝x_k(τ)+v_k(τ+1)

wherein v is_k(τ +1) particle velocity after τ +1 th iteration of particle numbered k, v_k(τ) is the particle velocity, x, of the particle numbered k after the τ th iteration_k(τ +1) is the particle position, x, after τ +1 iterations of particle number k_k(τ) is the position of the particle after the τ th iteration for the particle numbered k, τ is the number of iterations, k is the particle number, c₁Is a first acceleration parameter, c₂Is the second acceleration parameter, r₁Is a first random parameter, r₂Is a second random parameter, p_gIs the highest position of the bee colony in the search interval, p_k(τ) is the highest position after the τ -th iteration of particle number k.

In one embodiment, the fitness function is established as follows:

wherein Fitness is an adaptive function value, Q_imi,jFor measuring flow, Q_iei,jTo simulate flow, Q_immaxi,jFor maximum measured flow, H_imi,jFor measuring pressure, H_iei,jTo simulate pressure, H_immaxi,jFor the maximum measured pressure, i is the number of the discrete rear pipe section, J is the number of the discrete time, and J is the detection time set and is used for representing the total detection time.

In one embodiment, the particle swarm algorithm comprises at least one of: GPSO algorithm, LPSO algorithm, MCPSO algorithm, SIPSO algorithm.

In one embodiment, the result parameters include: leakage coefficient, time parameter, location parameter.

In one embodiment, determining whether the pipe to be tested leaks according to the result parameter includes:

determining whether the leakage coefficient is equal to 0;

and under the condition that the leakage coefficient is equal to 0, determining that the pipeline to be detected does not leak.

In one embodiment, when the leakage coefficient is not equal to 0, it is determined that the pipe to be tested leaks, the time indicated by the time parameter is determined as the leakage time, and the position indicated by the position parameter is determined as the leakage position.

In an embodiment, a position parameter in the result parameter may also be used as an index parameter to determine whether the pipe to be tested leaks, and the specific implementation may include:

determining whether the position indicated by the position parameter is the same as the starting position or the end position of the pipeline to be detected;

and under the condition that the position indicated by the position parameter is the same as the starting position or the end position of the pipeline to be detected, determining that the pipeline to be detected does not leak.

In one embodiment, when the position indicated by the position parameter is different from the starting position or the end position of the pipe to be tested, it is determined that the pipe to be tested leaks, the time parameter is determined as the leakage time, and the position indicated by the position parameter is determined as the leakage position.

In one embodiment, the pipe under test comprises a transport pipe for transporting crude oil.

The embodiment of the present application further provides a device for detecting pipeline leakage, including:

the acquisition module is used for acquiring flow data and pressure data of a starting position of the pipeline to be detected and flow data and pressure data of an end position of the pipeline to be detected;

and the determining module is used for solving a hydrodynamic and thermodynamic transient model of the pipeline to be detected through a particle swarm algorithm according to the flow data and the pressure data of the starting position of the pipeline to be detected and the flow data and the pressure data of the end position of the pipeline to be detected so as to obtain a result parameter, and the result parameter is used for determining whether the pipeline to be detected leaks.

In the embodiment of the application, the particle swarm algorithm is combined with hydrodynamic and thermodynamic transient analysis, and the particle swarm algorithm is used for solving the corresponding hydrodynamic and thermodynamic transient models to accurately determine the specific operation condition of the pipeline, so that the technical problems of limited application range and poor leakage detection accuracy in the existing method are solved, and the technical effect of effectively improving the pipeline leakage detection precision is achieved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.

FIG. 1 is a process flow diagram of a method for detecting a pipeline leak according to an embodiment of the present application;

FIG. 2 is a block diagram of a device for detecting a leakage in a pipe according to an embodiment of the present disclosure;

FIG. 3 is a schematic structural diagram of an electronic device according to a method for detecting a pipeline leakage provided by an embodiment of the present application;

fig. 4 is a schematic diagram of a limited volume method of a staggered grid for preprocessing in a scene example, to which the pipeline leakage detection method and apparatus provided by the embodiments of the present application are applied.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

In consideration of the fact that the conventional method mostly uses a negative pressure wave method, that is, a leakage position is found by calculating a time difference of arrival of a negative pressure wave at both ends of a pipeline according to characteristics of the negative pressure wave generated at the time of leakage. However, the method is relatively simple, and is often not sensitive enough to leakage of some transport liquids, such as micro-pores or those with large elastic coefficients, densities or viscosities, which results in specific implementation, effective application range, relatively large error in leakage detection, and relatively poor accuracy. Aiming at the root cause of the technical problems, the method considers that a more accurate pipeline model can be established through hydrodynamic and thermodynamic transient analysis, and the specific operation condition in the pipeline is accurately determined by combining an improved Particle Swarm Optimization (PSO) algorithm to solve the technical problems of limited application range and poor leakage detection accuracy in the existing method, so that the technical effect of effectively improving the pipeline leakage detection precision is achieved.

Based on the thought, the embodiment of the application provides a method for detecting pipeline leakage. Specifically, please refer to fig. 1. The method for detecting the pipeline leakage provided by the embodiment of the application can comprise the following steps in specific implementation.

S11: and acquiring flow data and pressure data of the starting position of the pipeline to be detected and flow data and pressure data of the end position of the pipeline to be detected.

In one embodiment, the pipeline to be tested may be, but is not limited to, a transportation pipeline for transporting crude oil. Specifically, for example, the transport pipeline may be a transport pipeline for transporting natural gas, water, or the like.

In one embodiment, in specific implementation, pressure detectors may be respectively disposed at a starting position and an end position of a pipeline to be measured, so as to collect pressure data of the starting position and the end position of the pipeline to be measured; the flow detection devices are respectively arranged at the starting position (or upstream position) and the end position (or downstream position) of the pipeline to be detected so as to collect flow data of the starting position and the end position of the pipeline to be detected, so that further analysis and processing can be carried out subsequently.

S12: and solving a hydrodynamic and thermodynamic transient model of the pipeline to be detected through a particle swarm algorithm according to the flow data and the pressure data of the starting position of the pipeline to be detected and the flow data and the pressure data of the end position of the pipeline to be detected to obtain a result parameter, wherein the result parameter is used for determining whether the pipeline to be detected leaks.

In one embodiment, in order to accurately and quickly determine whether leakage occurs in a complex pipeline transport network to be detected, a hydrodynamics and thermodynamic transient model of the pipeline to be detected, which can finely describe the running condition of the pipeline to be detected, can be established based on a continuity equation, a momentum equation and an energy equation of fluid in the pipeline to be detected; and then, carrying out repeated iterative solution on the hydrodynamic and thermodynamic transient models of the pipeline to be detected by utilizing a particle swarm algorithm which aims at a complex transport network of the pipeline to be detected and has fast convergence, so as to quickly and efficiently obtain a convergence result and determine whether the pipeline to be detected leaks.

In one embodiment, when implemented, the hydrodynamic and thermodynamic transient models of the pipe under test may be established as follows:

s1: acquiring characteristic parameters of a pipeline to be tested, wherein the characteristic parameters of the pipeline to be tested at least comprise: the starting point position of the pipeline to be measured, the end point position of the pipeline to be measured, the diameter of the pipeline to be measured and the like.

In one embodiment, in order to further more accurately analyze the operation state of the pipeline to be tested, other physical parameters of the pipeline to be tested may also be collected, such as: the length of the pipeline to be measured, the wall thickness of the pipeline to be measured and the like are taken as characteristic parameters of the pipeline to be measured. Of course, it should be noted that the above-mentioned characteristic parameters of the pipe to be tested are only for better illustration of the embodiments of the present application. In specific implementation, other physical parameters of the pipeline to be tested can be introduced as characteristic parameters of the pipeline to be tested according to specific conditions and construction requirements. The present application is not limited thereto.

S2: and establishing an initial model of the pipeline to be tested according to the characteristic parameters of the pipeline to be tested.

In an embodiment, in specific implementation, an initial model of the pipe to be tested may be established according to characteristic parameters of the pipe to be tested and in combination with a continuity equation, a momentum equation and an energy equation of an internal transport fluid of the pipe to be tested.

In one embodiment, the continuity equation, the momentum equation and the energy equation of the inner transport fluid of the pipe to be measured can be specifically established in the following manner.

Establishing a continuity equation based on the pipeline to be measured according to the following formula:

wherein H can be expressed as the pressure head in the pipeline to be tested, t_pIt can be expressed in particular as the time of movement, x, of the fluid in the pipe_pSpecifically, the motion distance of the fluid in the pipeline is represented, g specifically may be a gravity acceleration, w specifically may be a cross-sectional area of the pipeline to be detected, Q specifically may be a flow rate in the pipeline to be detected, and v specifically may be an average flow velocity of the fluid in the pipeline to be detected.

Wherein the value of w can be calculated according to the following formula:

wherein D may be specifically represented as the inner diameter of the pipe to be measured.

Establishing a momentum equation based on the pipeline to be measured according to the following formula:

wherein, f can be specifically expressed as an on-way friction coefficient in the pipeline to be detected, and m can be specifically expressed as a coefficient related to the flow state in the pipeline to be detected.

Establishing an energy equation based on the pipeline to be measured according to the following formula:

wherein λ may be specifically expressed as darcy friction coefficient, c may be specifically expressed as heat capacity of fluid in the pipe to be measured, T may be specifically expressed as temperature in the pipe to be measured, and T is₀And may particularly be expressed as the ambient temperature around the pipe to be measured.

After the continuity equation based on the pipeline to be tested, the momentum equation based on the pipeline to be tested and the energy equation based on the pipeline to be tested are established, the initial hydrodynamic and thermodynamic transient models of the pipeline to be tested, namely the initial models, are equivalently established. In fact, the initial model can be directly used as a hydrodynamic and thermodynamic transient model of the pipeline to be tested to perform subsequent data processing, so as to determine whether the pipeline to be tested leaks.

S3: and preprocessing the initial model of the pipeline to be tested by a finite volume method of a staggered grid to obtain a hydrodynamics and thermodynamic transient model of the pipeline to be tested.

In an embodiment, after the initial model is established, when a specific iterative solution is performed by using the model, it is often necessary to perform a difference processing on the initial model first, that is, the difference between the continuity equation based on the pipeline to be measured, the momentum equation based on the pipeline to be measured, and the energy equation based on the pipeline to be measured is converted into a difference term, so as to perform a subsequent mathematical solution.

In one embodiment, in order to avoid the failure of coupling between the pressure data and the flow data due to the conventional differential processing, which results in the reduction of the accuracy of the solution result, in specific implementation, the initial model of the pipeline to be measured may be preprocessed by a finite volume method of an interleaved network, so as to obtain a hydrodynamic and thermodynamic transient model of the pipeline to be measured, which may have higher accuracy and is suitable for mathematical solution.

In this embodiment, the preprocessing the initial model of the pipeline to be measured by the finite volume method of the traffic crossing network may specifically be understood as: and respectively storing the pressure data and the flow data in the model in two different grid systems. In specific implementation, the pipeline to be tested can be divided into a series of control bodies, and then the numerical value of the pipeline to be tested is dispersed by adopting a Finite Volume Method (FVM). In order to avoid the pressure and temperature field of the vibrating chessboard, the flow and pressure in the center of the control body and the phase velocity on the surface of the control body are stored by adopting an interlaced grid method. In this way, decoupling of the pressure field caused by storing pressure (related to pressure data) and velocity (related to flow data) at the same node as processed by prior methods can be eliminated by the staggered grid arrangement.

In an embodiment, the preprocessing the initial model of the pipe to be measured by the finite volume method with the staggered grids to obtain a hydrodynamic and thermodynamic transient model of the pipe to be measured specifically includes: and preprocessing the initial model of the pipeline to be detected by a finite volume method of a staggered grid, and respectively carrying out differential processing on a continuity equation based on the pipeline to be detected, a momentum equation based on the pipeline to be detected and an energy equation based on the pipeline to be detected to obtain a discrete continuity equation, a discrete momentum equation and a discrete energy equation.

Specifically, the finite volume method of the staggered grid is used for preprocessing, so that a discrete continuity equation based on the pipeline to be measured in the following form can be obtained:

wherein i and j may be specifically represented as grid numbers.

The discrete momentum equation based on the pipeline to be measured in the following form can be obtained by preprocessing the finite volume method of the staggered grids:

the energy equation based on the pipeline to be measured after the dispersion in the following form can be obtained by preprocessing the finite volume method of the staggered grid:

according to the discrete continuity equation, momentum equation and energy equation, the leakage coefficient and leakage flow can be further deduced in the following formula form:

wherein,and may be specifically expressed as the pre-leak line flow,specifically expressed as post-leak pipeline flow, Q_LjWhich may be expressed specifically as a pipe leakage flow, C_vIt can be expressed in particular as the leakage coefficient, H_i,jIt can be expressed as the pressure head, H, of the pipe section i to be measured corresponding to the leakage point_LIt can be expressed in particular as the pressure head, H, in the leak point of the pipe to be tested_eAnd can be specifically expressed as a pressure head outside the leakage point of the pipeline to be measured. The leakage coefficient is generally related to, among other things, the orifice shape, area of the leak, and the leakage empirical coefficient.

Through the steps, the hydrodynamics and thermodynamic transient model of the pipeline to be measured can be considered to be relatively accurate.

In one embodiment, in order to improve the solution efficiency, a particle swarm algorithm having a relatively good convergence effect and suitable for a pipeline network may be used to iteratively solve the hydrodynamic and thermodynamic transient models of the pipeline to be measured, so as to quickly obtain a solution result.

In one embodiment, the particle swarm algorithm described above is specifically understood as an improved algorithm based on the particle swarm algorithm in order to be applied to the scenario problem to be solved by the embodiments of the present application. The Particle Swarm algorithm, also called Particle Swarm algorithm, Particle Swarm Optimization algorithm or bird Swarm Optimization (PSO) is a new evolutionary algorithm developed by j.kennedy and r.c. eberhart, etc. When the algorithm is specifically implemented, the optimal solution is searched through iteration starting from a random solution, and the quality of the solution is evaluated through fitness. Compared with a genetic algorithm, the PSO rule is simpler, the operation of crossing (Crossover) and Mutation (Mutation) of the genetic algorithm is avoided, the global optimal solution is found by following the currently searched optimal value, the method has the advantages of easiness in implementation, high precision, quickness in convergence and the like, and is suitable for processing the complex scene of state analysis in the transport pipeline network. In this embodiment, the coupled transient hydrodynamic and thermodynamic analysis is combined with a particle swarm algorithm (i.e., a PSO algorithm) to arrive at the particle swarm algorithm, taking into account the application scenario of the particular pipeline network being processed.

In an embodiment, the above-mentioned performing multiple iterative solutions on the hydrodynamic and thermodynamic transient models of the pipeline to be measured by using the particle swarm optimization algorithm may include the following steps:

carrying out iterative solution according to the following mode to carry out repeated iterative update on the particle speed and the particle position until the iterative result meets the preset requirement:

v_k(τ+1)＝v_k(τ)+c₁r₁(p_k(τ)-x_k(τ))+c₂r₂(p_k(τ)-x_k(τ))

x_k(τ+1)＝x_k(τ)+v_k(τ+1)

wherein v is_k(τ +1) can be expressed in particular as the particle velocity, v, after τ +1 th iteration of the particle numbered k_k(τ) can be expressed in particular as the particle velocity, x, after the τ th iteration of the particle numbered k_k(τ +1) can be expressed in particular as the position, x, of the particle after τ +1 th iteration of the particle numbered k_k(τ) can be expressed in particular after the τ th iteration of the particle numbered kτ may be specifically represented as the number of iterations, k may be specifically represented as the particle number, c₁Which may be expressed in particular as a first acceleration parameter, c₂In particular, as a second acceleration parameter, r₁It can be expressed in particular as a first random parameter, r₂It can be expressed in particular as a second random parameter, p_gWhich may be expressed in particular as the highest position of the colony in the search interval, p_k(τ) may be specifically represented as the highest position after the τ -th iteration of the particle numbered k.

In an embodiment, the above-mentioned performing multiple iterative solutions on the hydrodynamic and thermodynamic transient models of the pipeline to be tested through a particle swarm algorithm according to the flow data and the pressure data of the starting position of the pipeline to be tested and the flow data and the pressure data of the ending position of the pipeline to be tested to determine whether the pipeline to be tested leaks, in a specific implementation, the following contents may be included:

s1: performing iterative solution on the hydrodynamic and thermodynamic transient model of the pipeline to be tested for multiple times through a particle swarm algorithm according to the flow data and the pressure data of the starting position of the pipeline to be tested and the flow data and the pressure data of the end position of the pipeline to be tested to obtain a simulated flow and a simulated pressure; stopping iteration until the adaptive function based on the simulation flow and the simulation pressure meets a preset condition (namely, an iteration result meets a preset requirement), and recording a result parameter solved when the iteration is stopped;

s2: and determining whether the pipeline to be detected leaks or not according to the result parameters.

In one embodiment, the adaptive function may be established as follows:

wherein Fitness may be specifically expressed as an adaptive function value, Q_imi,jMay particularly be expressed asMeasuring the flow rate, Q_iei,jIt can be expressed in particular as an analog flow, Q_immaxi,jIt can be expressed in particular as the maximum measured flow, H_imi,jCan be expressed in particular as the measured pressure, H_iei,jIt can be expressed in particular as a simulated pressure, H_immaxi,jSpecifically, the measured pressure may be represented as a maximum measured pressure, i may be represented as a discrete rear pipe section number, J may be represented as a discrete time index, and J may be represented as a leak detection time set, that is, may be used to represent a leak detection total time.

In one embodiment, the result parameter may specifically include: leakage coefficient, time parameter, location parameter, etc. It should be understood that the above-mentioned result parameters are only for better illustration of the embodiments of the present application, and in the case of concrete implementation, other data may be selected as the result parameters according to the construction requirements.

In an embodiment, the determining, according to the result parameter, whether the pipe to be tested leaks may be performed, and in a specific implementation, the determining, by using a leakage parameter in the result parameter as an index parameter, whether the pipe to be tested leaks may include:

s1: determining whether the leakage coefficient is equal to 0;

s2: and under the condition that the leakage coefficient is equal to 0, determining that the pipeline to be detected does not leak.

In one embodiment, in the case that the leakage coefficient is not equal to 0, it is determined that the pipe to be tested leaks, and the time parameter may also be determined as a leakage time, and a position indicated by the position parameter may be determined as a leakage position. Therefore, the position and time of leakage can be accurately positioned, so that the pipeline leakage can be timely treated, and the loss is reduced.

s1: determining whether the position indicated by the position parameter is the same as the starting position or the end position of the pipeline to be detected;

s2: and under the condition that the position indicated by the position parameter is the same as the starting position or the end position of the pipeline to be detected, determining that the pipeline to be detected does not leak.

In one embodiment, when the position indicated by the position parameter is different from the starting position or the end position of the pipe to be tested, it is determined that the pipe to be tested leaks, the time parameter is determined as the leakage time, and the position indicated by the position parameter is determined as the leakage position. Therefore, the position and time of leakage can be accurately positioned, so that the pipeline leakage can be timely treated, and the loss is reduced.

Of course, other parameters in the result parameters, or data obtained by combining the position parameters and the leakage parameters may also be used as index parameters to determine whether the pipeline to be tested leaks. The present application is not limited thereto.

In the embodiment of the application, compared with the existing method, the particle swarm algorithm is combined with hydrodynamic and thermodynamic transient analysis, and the transient model is solved by the particle swarm algorithm to accurately determine the specific operation condition of the pipeline, so that the technical problems of limited application range and poor leakage detection accuracy existing in the existing method are solved, and the technical effect of effectively improving the pipeline leakage detection precision is achieved.

In one embodiment, the particle swarm algorithm may specifically include at least one of: GPSO algorithm, LPSO algorithm, MCPSO algorithm, SIPSO algorithm, etc. The GPSO (Global PSO) algorithm may specifically refer to a Global version of a particle swarm algorithm, and a topology structure of its neighbor is called All type. The LPSO (Local PSO) algorithm may specifically refer to a Local version of the particle swarm algorithm, whose topology is usually Ring type, Four Cluster type, Pyramid type and Square type. The MCPSO (Multi-Swarm Cooperative PSO) algorithm may specifically refer to a Multi-population coevolution particle Swarm algorithm, in which the evolution of an individual is not only affected by its own population but also affected by the symbiotic population information, thereby avoiding the possibility of falling into a locally optimal solution due to misjudgment of the individual information to a certain extent. The SIPSO (selective information swarm algorithm) algorithm may specifically refer to a selective information transfer particle swarm algorithm, wherein the SIPSO has an advantage that a scale-free network is introduced as a particle structure in consideration of example heterogeneity, and different learning strategies are used as example information interaction modes, so that an obtained result is relatively better. The multiple algorithms have respective advantages, and a corresponding PSO algorithm can be selected as a particle swarm algorithm used in the embodiment of the application according to specific conditions and construction requirements during specific implementation.

In an embodiment, after it is determined that the pipeline to be detected does not leak and the operation state is normal by the pipeline leakage detection method provided in the embodiment of the present application, the pipeline leakage detection method may be used to perform leakage detection in the next period.

In one embodiment, the pipeline to be tested may specifically include, but is not limited to, a transportation pipeline for transporting crude oil, and the like. For example, the pipeline leakage detection device provided by the embodiment of the application can also be applied to a conveying pipeline for conveying natural gas, water and other substances. The application is not limited to the specific type of transport conduit described above.

From the above description, it can be seen that, in the method for detecting pipeline leakage provided in the embodiment of the present application, because the particle swarm algorithm is combined with hydrodynamic and thermodynamic transient analyses, and the transient model is solved by using the particle swarm algorithm to accurately determine the specific operation condition of the pipeline, the technical problems of limited application range and poor leakage detection accuracy existing in the existing method are solved, and the technical effect of effectively improving the pipeline leakage detection precision is achieved; and the initial model of the pipeline to be tested is preprocessed by a finite volume method of a staggered grid, so that decoupling of a pressure field is avoided, and the accuracy of the established hydrodynamics and thermodynamic transient model of the pipeline to be tested is improved.

Based on the same inventive concept, the embodiment of the present invention further provides a device for detecting pipeline leakage, as described in the following embodiments. Because the principle of solving the problem of the pipeline leakage detection device is similar to that of the pipeline leakage detection method, the implementation of the pipeline leakage detection device can refer to the implementation of the pipeline leakage detection method, and repeated parts are not described again. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated. Referring to fig. 2, a structural diagram of a device for detecting pipeline leakage according to an embodiment of the present application is shown, where the device may specifically include: the acquisition module 21 and the determination module 22 will be described in detail below.

The obtaining module 21 may be specifically configured to obtain flow data and pressure data of a starting position of the pipeline to be detected and flow data and pressure data of an ending position of the pipeline to be detected;

the determining module 22 may be specifically configured to solve a hydrodynamics and thermodynamic transient model of the pipeline to be detected by using a particle swarm algorithm according to the flow data and the pressure data of the starting position of the pipeline to be detected and the flow data and the pressure data of the ending position of the pipeline to be detected, so as to obtain a result parameter, where the result parameter is used to determine whether the pipeline to be detected leaks.

In one embodiment, the apparatus may specifically include a modeling module for establishing a hydrodynamic and thermodynamic transient model of the pipe under test used by the determination module 22. Specifically, the modeling module may include the following structural units:

the characteristic parameter obtaining unit may be specifically configured to obtain a characteristic parameter of the pipe to be tested, where the characteristic parameter of the pipe to be tested at least includes: the starting position of the pipeline to be tested, the end position of the pipeline to be tested and the diameter of the pipeline to be tested;

the initial model establishing unit is specifically used for establishing an initial model of the pipeline to be tested according to the characteristic parameters of the pipeline to be tested;

the model processing unit may be specifically configured to perform preprocessing on the initial model of the pipe to be measured by using a finite volume method of a staggered grid, so as to obtain a hydrodynamic and thermodynamic transient model of the pipe to be measured.

In one embodiment, when the determining module 22 is implemented, the iterative solution may be performed as follows:

v_k(τ+1)＝v_k(τ)+c₁r₁(p_k(τ)-x_k(τ))+c₂r₂(p_k(τ)-x_k(τ))

x_k(τ+1)＝x_k(τ)+v_k(τ+1)

wherein v is_k(τ +1) can be expressed in particular as the particle velocity, v, after τ +1 th iteration of the particle numbered k_k(τ) can be expressed in particular as the particle velocity, x, after the τ th iteration of the particle numbered k_k(τ +1) can be expressed in particular as the position, x, of the particle after τ +1 th iteration of the particle numbered k_k(τ) may specifically be represented as the position of the particle after the τ th iteration of the particle with number k, τ may specifically be represented as the number of iterations, k may specifically be represented as the particle number, c₁Which may be expressed in particular as a first acceleration parameter, c₂In particular, as a second acceleration parameter, r₁It can be expressed in particular as a first random parameter, r₂It can be expressed in particular as a second random parameter, p_gWhich may be expressed in particular as the highest position of the colony in the search interval, p_k(τ) may be specifically represented as the highest position after the τ -th iteration of the particle numbered k.

In an embodiment, in order to perform multiple iterative solutions on the hydrodynamic and thermodynamic transient models of the pipeline to be tested according to the flow data and the pressure data of the starting position of the pipeline to be tested and the flow data and the pressure data of the ending position of the pipeline to be tested by using a particle swarm algorithm to determine whether the pipeline to be tested leaks, the determining module 22 may specifically include the following structural units:

the iteration unit is specifically used for carrying out repeated iteration solving on the hydrodynamic and thermodynamic transient models of the pipeline to be tested through a particle swarm algorithm according to the flow data and the pressure data of the starting position of the pipeline to be tested and the flow data and the pressure data of the ending position of the pipeline to be tested to obtain a simulated flow and a simulated pressure; stopping iteration until the adaptive function based on the simulation flow and the simulation pressure meets a preset condition, and recording a result parameter solved when the iteration is stopped;

and the determining unit is specifically configured to determine whether the pipe to be tested leaks according to the result parameter.

In an embodiment, when the iteration unit is implemented, the adaptive function may be established as follows:

wherein Fitness may be specifically expressed as an adaptive function value, Q_imi,jIt can be expressed in particular as a measured flow, Q_iei,jIt can be expressed in particular as an analog flow, Q_immaxi,jIt can be expressed in particular as the maximum measured flow, H_imi,jCan be expressed in particular as the measured pressure, H_iei,jIt can be expressed in particular as a simulated pressure, H_immaxi,jSpecifically, the measured pressure may be represented as a maximum measured pressure, i may be represented as a discrete rear pipe section number, J may be represented as a discrete time index, and J may be represented as a leak detection time set, that is, may be used to represent a leak detection time.

In one embodiment, when implemented, the particle swarm algorithm may include at least one of: GPSO algorithm, LPSO algorithm, MCPSO algorithm, SIPSO algorithm, etc. Of course, it should be noted that the particle swarm algorithm listed above is only an exemplary one. In specific implementation, other types of particle swarm algorithms can be introduced according to specific situations and construction requirements. The present application is not limited thereto.

In one embodiment, the result parameter may specifically include: leakage coefficient, time parameter, location parameter, etc. Of course, it should be noted that the above-mentioned various parameters are only for better illustration of the embodiments of the present application. In specific implementation, other parameters can be introduced as the result parameters according to specific situations and precision requirements.

In an embodiment, when the determining unit is implemented, it may determine that the pipe to be tested leaks when the leakage coefficient is not equal to 0 and/or the position indicated by the position parameter is different from a starting position of the pipe to be tested or an ending position of the pipe to be tested, determine the time parameter as the leakage time, and determine the position indicated by the position parameter as the leakage position. And then can reach the effect of finding the pipeline and in time fixing a position the concrete position of pipeline leakage.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

It should be noted that, the systems, devices, modules or units described in the above embodiments may be implemented by a computer chip or an entity, or implemented by a product with certain functions. For convenience of description, in the present specification, the above devices are described as being divided into various units by functions, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.

Moreover, in the subject specification, adjectives such as first and second may only be used to distinguish one element or action from another element or action without necessarily requiring or implying any actual such relationship or order. References to an element or component or step (etc.) should not be construed as limited to only one of the element, component, or step, but rather to one or more of the element, component, or step, etc., where the context permits.

From the above description, it can be seen that, in the device for detecting pipeline leakage provided in the embodiment of the present application, because the particle swarm algorithm is combined with hydrodynamic and thermodynamic transient analyses, and the transient model is solved by using the particle swarm algorithm to accurately determine the specific operation condition of the pipeline, the technical problems of limited application range and poor leakage detection accuracy existing in the existing method are solved, and the technical effect of effectively improving the pipeline leakage detection precision is achieved; and the initial model of the pipeline to be tested is preprocessed by a finite volume method of a staggered grid, so that decoupling of a pressure field is avoided, and the accuracy of the established hydrodynamics and thermodynamic transient model of the pipeline to be tested is improved.

The embodiment of the present application further provides an electronic device, which may specifically refer to a schematic structural diagram of the electronic device based on the method for detecting the pipeline leakage provided in the embodiment of the present application, shown in fig. 3, where the electronic device may specifically include an input device 31, a processor 32, and a memory 33. The input device 31 may be specifically configured to input flow data and pressure data of a starting position of the pipeline to be tested, and flow data and pressure data of an ending position of the pipeline to be tested. The processor 32 may be specifically configured to perform multiple iterative solutions on the hydrodynamic and thermodynamic transient models of the pipeline to be detected through a particle swarm algorithm according to the flow data and the pressure data of the starting position of the pipeline to be detected and the flow data and the pressure data of the ending position of the pipeline to be detected, so as to determine whether the pipeline to be detected leaks. The memory 33 may be specifically configured to store the input flow data and pressure data of the starting position of the pipe to be measured, the input flow data and pressure data of the ending position of the pipe to be measured, and the intermediate data generated by the processor 32.

In this embodiment, the input device may be one of the main apparatuses for information exchange between a user and a computer system. The input device may include a keyboard, a mouse, a camera, a scanner, a light pen, a handwriting input board, a voice input device, etc.; the input device is used to input raw data and a program for processing the data into the computer. The input device can also acquire and receive data transmitted by other modules, units and devices. The processor may be implemented in any suitable way. For example, the processor may take the form of, for example, a microprocessor or processor and a computer-readable medium that stores computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, an embedded microcontroller, and so forth. The memory may in particular be a memory device used in modern information technology for storing information. The memory may include multiple levels, and in a digital system, the memory may be any memory as long as it can store binary data; in an integrated circuit, a circuit without a physical form and with a storage function is also called a memory, such as a RAM, a FIFO and the like; in the system, the storage device in physical form is also called a memory, such as a memory bank, a TF card and the like.

In this embodiment, the functions and effects specifically realized by the electronic device can be explained by comparing with other embodiments, and are not described herein again.

The present application also provides a computer storage medium based on a pipeline leakage detection method, where the computer storage medium stores computer program instructions that, when executed, implement: acquiring flow data and pressure data of a starting position of a pipeline to be detected and flow data and pressure data of an end position of the pipeline to be detected; and carrying out repeated iterative solution on the hydrodynamic and thermodynamic transient models of the pipeline to be detected through a particle swarm algorithm according to the flow data and the pressure data of the starting position of the pipeline to be detected and the flow data and the pressure data of the end position of the pipeline to be detected so as to determine whether the pipeline to be detected leaks.

In the present embodiment, the storage medium includes, but is not limited to, a Random Access Memory (RAM), a Read-Only Memory (ROM), a Cache (Cache), a Hard disk (HDD), or a Memory Card (Memory Card). The memory may be used to store computer program instructions. The network communication unit may be an interface for performing network connection communication, which is set in accordance with a standard prescribed by a communication protocol.

In this embodiment, the functions and effects specifically realized by the program instructions stored in the computer storage medium can be explained by comparing with other embodiments, and are not described herein again.

In a specific implementation scenario example, the method and the device for detecting pipeline leakage according to the embodiments of the present application are applied to perform leakage detection on a crude oil transportation pipeline in a certain area. The following can be referred to as a specific implementation process.

S1: and establishing hydrodynamic and thermodynamic transient models.

In the embodiment, the fluid flow in the crude oil transportation pipeline to be measured can be regarded as one-dimensional flow, and the conservation of mass, momentum and energy is met. An in-pipe fluid flow model may be built from fluid mechanics, including continuity, momentum, and energy equations, to describe the relationship between pressure, temperature, and flow in a pipe.

The continuity equation (i.e., the continuity equation based on the pipe under test) can be expressed as:

wherein,

the momentum equation (i.e., based on the momentum equation of the pipe under test) can be expressed as:

the energy equation (i.e., based on the energy equation of the pipe under test) can be expressed as:

the differential terms in the above equations are further converted into differential terms. In particular, a staggered grid approach may be used to avoid coupling failures between pressure and flow. Where the above-mentioned staggered grids mean that pressure and flow will be stored in two different grid systems. In specific implementation, the pipeline can be divided into a series of control bodies, and then the numerical value dispersion is carried out by adopting a Finite Volume Method (FVM). Fig. 4 is a schematic diagram illustrating a schematic diagram of a limited volume method of a staggered grid for preprocessing in a scenario example to which the pipeline leakage detection method and apparatus provided by the embodiment of the present application are applied. In order to avoid the oscillating chessboard pressure and temperature fields, scalar variables and pressure values at the center of the control body and the phase velocity of the surface of the control body are stored by adopting an interlaced grid method. The staggered grid arrangement described above may eliminate decoupling of the pressure field when pressure and velocity are stored at the same node. After processing in the above manner, the final discrete form of each equation is as follows:

continuity equation:

the momentum equation:

energy equation:

further, the leak flow rate can be derived from the leak coefficient according to equation (7) and equation (8). Wherein, C_vThe leakage coefficient may be expressed and is typically related to the shape and area of the leakage hole and the leakage empirical coefficient.

The flow behind the leak hole equals the flow before the leak hole minus the flow at the leak hole:

s2: and solving the hydrodynamic and thermodynamic transient models by using a Particle Swarm Optimization (PSO) algorithm to determine whether the pipeline leaks or not and locate the leakage position.

In the embodiment, a hybrid method (namely, a particle swarm algorithm) for coupling inverse transient hydrodynamic and thermodynamic analysis and a PSO algorithm based on the swarm intelligence proposed by Kennedy and Eberhart is provided for model solution. The PSO algorithm is a research hotspot in the engineering field due to the fact that the PSO algorithm has high convergence precision and can effectively avoid local optimization. With this algorithm, each member of the set, called a particle, represents a viable solution, updating their velocity and position in iterations for the purpose of iterative solution, in particular according to equations (9) and (10) below.

v_k(τ+1)＝v_k(τ)+c₁r₁(p_k(τ)-x_k(τ))+c₂r₂(p_g(τ)-x_k(τ)) formula (9)

x_k(τ+1)＝x_k(τ)+v_k(τ +1) formula (10)

Wherein v is_kAnd x_kRespectively the velocity and position of the particle, c₁And c₂Is the acceleration parameter, r₁And r₂Is in the range of [0,1]Two randomly generated numbers of (1), p_gRepresenting the best position of the entire colony, p, during the entire search_kIs the particle k to^thThe historically optimal position after the sub-iteration.

At present, combining the characteristics of various PSO algorithms, although many improved algorithms are effective in computing convergence and efficiency, the computational efficiency of different models is quite different. To prove the applicability and reliability of the method, the embodiment selects four improved PSO algorithms: two classical algorithms (GPSO, LPSO), a widely used algorithm (MCPSO) and an advanced algorithm (SIPSO) were tested and compared.

In particular, if the leakage coefficient C is included_vThe location x of the leak, the time t at which the leak started, and any two of the four sets of hydrokinetic measurements (flow and pressure at the beginning and end of the pipeline) are known. Two other sets of hydrodynamic data may also be calculated. This means thatIf any leakage variable is given (C)_vX and t). Based on any two of these four sets of hydrokinetic measurement data, two additional sets of simulated operational data may be obtained. Having obtained the actual hydrokinetic measurement data, the deviation between the simulated data and the actual data (the comparative data) can be solved. Generally, the more accurate the leakage variable, the smaller the error. Thus, the problem of leak detection and localization is translated into a large-scale nonlinear mathematical optimization problem, i.e., finding the best leak variables (decision variables) to reduce the error between the calculated and compared data (targets).

Specifically, the fitness function of the PSO is shown in equation (11). C_vX and t are decision variables with the goal of minimizing the deviation between the simulated and the compared data of pressure and flow between the starting and ending points of the pipeline. Q_imAnd H_imRepresenting measured flow and pressure data (comparative data). Q_ieAnd H_ieThe results of the model calculations are shown. Maximum value Q of measurement data taking into account different sequences of different pressure and flow parameters_immaxAnd H_immaxIt can be used to non-dimensionalize the comparison data to ensure that the calculated results are of the same order of magnitude, which has the same effect on the objective function and ensures the minimum deviation of the calculation.

When the fitness function satisfies the output condition, the improved PSO will stop the iteration, and the randomly generated parameter is C_vX and t are the final results.

The specific solution may include: data are extracted from an SCADA (Supervisory Control And Data Acquisition) system to carry out transient fluid mechanics thermodynamic analysis, And improved PSO And leakage alarm judgment are utilized. Specifically, first, the operation data (flow rate and pressure) at the start and end of the pipeline at certain periods are extracted and divided into two parts. One part is used for solving the thermodynamics of fluid mechanicsThe model (the required data), and the other part to solve the fitness function (the contrast data). Wherein the desired data and the comparison data are interchangeable. Then, the fluid mechanics thermodynamic model can be solved by combining the initial leakage variable, and the value of the fitness function is also obtained. According to the improved PSO solution principle, new leakage variables are traversed, and the steps of the fluid mechanics thermodynamic model are returned until the convergence condition of the PSO algorithm is met. Finally, it is determined whether the PSO calculation result meets a leak alarm condition (X ≠ 0 or X ≠ X)_imOr C_v0,). If yes, outputting the required C_vX and t to determine the location of the leak and the time of the leak. If not, the next cycle data is read from the SCADA system for a new calculation.

After the result is determined by the above method, verification can be performed in the following manner. Specifically, the following may be included.

A. Initialization of simulation parameters

The simulated test pipeline has a length of 20 km and the specific parameters of the pipeline are shown in the pipeline parameters and leakage data table in table 1. The simulated pipe will begin to leak after 180s, 16.5 km from the beginning of the pipe. Actual leakage coefficient C_vThe value was 3.0X 10^-4. To verify the adaptability of the method, since the virtual data of the leaking pipe section is affected by the upstream and downstream hydraulic devices, frequent fluctuations may be introduced into the virtual hydrodynamic measurement data during the simulation initialization process to determine the hydraulic device and operational effects. With the above information, pipeline transient processes, steady/transient calculations and automatic control simulations of long distance oil and gas pipelines can be simulated by pipeline simulation software (e.g., SPS, a high precision software for design).

TABLE 1 pipeline parameters and leak data sheet

B. Accuracy testing

Four improved PSO algorithms are utilized to respectively calculate simulation parameters x and C_vAnd t50 times. 50 test results of 4 improved PSOs were processed. The comparative analysis shows that: the error of x calculated based on GPSO, MCPSO and SIPSO compared with the true value is small, and the falling points of experimental data are relatively concentrated; the experimental data based on LPSO are relatively dispersed, and the relative error is larger. Likewise, comparative analysis reveals that: the degree of scattering of the data points may determine that the effect of GPSO and SIPSO is superior to LPSO calculated/and based on the results. Calculation of C based on GPSO and SIPSO can be determined by the scatter range of the data points_vAnd t is superior to LPSO. In particular, the relative error of t calculated on the basis of GPSO, MCPSO, SIPSO is less than 0.5%.

C. Stability test

The procedure was calculated 50 iterations using four modified PSO algorithms. The optimum value set by the PSO (adaptation value ═ 0) is the smallest deviation between the calculation result and the actual measurement. Thus, the model can converge to the optimum quickly, but the optimum obtained with the least amount of computation deviates most. Compared with the MCPSO model, the GPSO model and the SIPSO model have higher calculation accuracy and convergence speed and can converge to an optimal value in 50 calculations. Compared with the convergence process of the four algorithms, the GPSO, the MCPSO and the SIPSO algorithms can be found to be converged to a global optimal solution all the time. Meanwhile, the SIPSO and GPSO algorithms have high speed of converging to the optimal solution and better convergence effect.

D. False alarm rate testing

Since the collected data may be disturbed, x, C should be calculated when a pipe leak does not occur_vAnd t. If at least one variable meets the required error, the pipeline is considered to be leak-free; otherwise, if all three variables satisfy the required error, it is considered a false alarm. In the false alarm experiment, false alarm data can be added for 50 times in the calculation, and the ratio of the false alarm number to the total experiment number is defined as the false alarm rate. If the calculated point is not at t-0 or t-300 or C_vOn the plane of 0, the experiment will be carried outAnd (4) determining as a false alarm. Further, from the 50 sets of data, the probability of false alarms occurring in LPSO averages about 2.00% while the probability of GPSO, MCPSO and SIPSO is almost 0.

E. Robustness testing

Considering equipment considerations, environmental uncertainties and fluid non-uniformities, there may be noise effects in the actual hydrodynamic measurement data, which play an important role in the accuracy of leak detection and localization. Therefore, in the present embodiment, the influence of the Noise Ratio (NR) on the leak detection and localization is also analyzed and analyzed. Specifically, the noise can be regarded as white noise, and NRs in the test is set to 10%, 20%, 30%, 40%, and 50%, respectively.

At the same time, the flow and pressure sensing devices in the monitoring and data logging may deviate significantly from the actual data. The point when the input-independent response reaches the saturation threshold, or the point where the response value is significantly higher or lower than the average value, is defined as a bad point of leak detection. However, the Bad Point Rate (BPR) refers to the proportion of input data that is significantly higher or lower than the average. Given the robustness of the pipeline leak detection and position model in the presence of a dead pixel in the input data, the BPRs are 0.5%, 1.0%, 1.5%, and 2.0%, respectively, in calculating the test pipelines x, C_vAnd t, the number of dead spots is 1.5-2.5 times higher than the original data.

It can be seen from the sensitivity analysis of the calculation error that the calculation error has much greater sensitivity to BPR than to NR. That is, when using this method, the measurement data is first processed to reduce the BPR of the data. The calculated error of the leak location is less sensitive to BPR and NR than other variables, i.e. when there is noise and bad spots in the data, the relative error of the leak location should also be a relatively small value if the hydrothermal model is correct. C_vIs more sensitive to BPR and NR. However, by simply performing leak characteristic analysis using this value, the actual demand can be satisfied. At the same time, from the results, it was found that the MCPSO performed better than the other algorithms.

F. Algorithmic parameter analysis

Through comparative analysis, the calculation parameters of the MCPSO and the SIPSO have certain influence on the final result. In order to improve the calculation stability, the MCPSO is used for repeated calculation, and the optimization result is used as a final solution. It is based on a master-slave model in which a population consists of a master and several slaves (N)_S) And (4) forming. Slave populations perform a single PSO or its variants independently maintaining particle diversity, whereas master populations evolve based on their own knowledge and learning of slave populations. Whereas for SIPSO, the particles select different learning strategies depending on their connection: a tightly connected central particle gets complete information from all its neighbors, while a rarely connected non-central particle can only follow a single, best performing neighbor. Thus, a threshold parameter (k) may be introduced_c) As an important parameter for determining the connection structure of the particle group. Calculation of optimal Algorithm parameter settings (N)_SAnd k_c) Further analysis is required. When NR and BPR are equal to 0, the false alarm rate is 0 regardless of the value of the algorithm parameter. To further compare this algorithm, NR and BPR values can be set to 20% and 5%, respectively, when calculating the false positive rate.

Specifically, N is set respectively_S2, 3, 4, 5, 6, 7 and solving the test model using the MCPSO algorithm based on the above rules. The accuracy and the false alarm rate are shown in a parameter analysis table of the MCPSO algorithm in the table 2. It can be seen that when N is_SWhen the value is more than 4, the calculation result tends to be stable. Are respectively provided with k_c2, 3, 4, 5, 6, 7 and solves the test model with SIPSO algorithm based on the above rules. The accuracy and false alarm rates are shown in table 3. The results show that when k is_cWhen the number is equal to 3, the calculation result is the best.

Hundreds of groups of data are tested and analyzed, and x and C can be judged_vAnd the accuracy, stability and robustness of t. The results show that the method is based on k in SIPSO_c3 leakage detection and location method compares its basisThe method is used for GPSO, LPSO and MCPSO calculation, and has the advantages of high calculation accuracy, good stability, low false alarm rate, strong noise resistance and the like. Therefore, the SIPSO-based method, which may be preferred, is applied to experimental verification and comparison in an actual field.

TABLE 2 parameter analysis Table of the MCPSO Algorithm

TABLE 3 parameter analysis table of SIPSO algorithm

Through the scene example, the method and the device for detecting the pipeline leakage provided by the embodiment of the application are verified, and the particle swarm algorithm is combined with hydrodynamic and thermodynamic transient analysis, so that the transient model is solved by the particle swarm algorithm to accurately determine the specific operation condition of the pipeline, the technical problems of limited application range and poor leakage detection accuracy in the existing method are really solved, and the technical effect of effectively improving the pipeline leakage detection precision is achieved.

Although various specific embodiments are mentioned in the disclosure of the present application, the present application is not limited to the cases described in the industry standards or the examples, and the like, and some industry standards or the embodiments slightly modified based on the implementation described in the custom manner or the examples can also achieve the same, equivalent or similar, or the expected implementation effects after the modifications. Embodiments employing such modified or transformed data acquisition, processing, output, determination, etc., may still fall within the scope of alternative embodiments of the present application.

Although the present application provides method steps as described in an embodiment or flowchart, more or fewer steps may be included based on conventional or non-inventive means. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an apparatus or client product in practice executes, it may execute sequentially or in parallel (e.g., in a parallel processor or multithreaded processing environment, or even in a distributed data processing environment) according to the embodiments or methods shown in the figures. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, the presence of additional identical or equivalent elements in a process, method, article, or apparatus that comprises the recited elements is not excluded.

The devices or modules and the like explained in the above embodiments may be specifically implemented by a computer chip or an entity, or implemented by a product with certain functions. For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, in implementing the present application, the functions of each module may be implemented in one or more pieces of software and/or hardware, or a module that implements the same function may be implemented by a combination of a plurality of sub-modules, and the like. The above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and other divisions may be realized in practice, for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed.

Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may therefore be considered as a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, classes, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

From the above description of the embodiments, it is clear to those skilled in the art that the present application can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, or the like, and includes several instructions for enabling a computer device (which may be a personal computer, a mobile terminal, a server, or a network device) to execute the method according to the embodiments or some parts of the embodiments of the present application.

The embodiments in the present specification are described in a progressive manner, and the same or similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. The application is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.

While the present application has been described by way of examples, those of ordinary skill in the art will appreciate that there are numerous variations and permutations of the present application without departing from the spirit thereof and that the appended embodiments include such variations and permutations without departing from the present application.

Claims

1. A method of detecting a leak in a pipe, comprising:

2. The method according to claim 1, characterized in that the hydrodynamic and thermodynamic transient models of the pipe under test are established in the following way:

3. The method of claim 1, wherein solving hydrodynamic and thermodynamic transient models of the pipeline under test by a particle swarm algorithm based on the flow and pressure data at the starting location of the pipeline under test and the flow and pressure data at the ending location of the pipeline under test to obtain resulting parameters comprises:

performing iterative solution on the hydrodynamic and thermodynamic transient model of the pipeline to be tested for multiple times through a particle swarm algorithm according to the flow data and the pressure data of the starting position of the pipeline to be tested and the flow data and the pressure data of the end position of the pipeline to be tested to obtain a simulated flow and a simulated pressure; stopping iteration until the adaptive function based on the simulation flow and the simulation pressure meets a preset condition, and recording result parameters solved when the iteration is stopped.

4. The method of claim 3, wherein the hydrodynamic and thermodynamic transient models of the pipeline under test are solved for a plurality of iterations through a particle swarm algorithm, comprising:

the iterative solution is performed in the following manner:

v_k(τ+1)＝v_k(τ)+c₁r₁(p_k(τ)-x_k(τ))+c₂r₂(p_k(τ)-x_k(τ))

x_k(τ+1)＝x_k(τ)+v_k(τ+1)

5. The method of claim 3, wherein the adaptive function is established as follows:

wherein Fitness is an adaptive function value, Q_imi,jFor measuring flow, Q_iei,jTo simulate flow, Q_immaxi,jFor maximum measured flow, H_imi,jFor measuring pressure, H_iei,jTo simulate pressure, H_immaxi,jFor the maximum measured pressure, i is the number of the discrete rear pipe section, J is the number of the discrete time, and J is the leak detection time set.

6. The method of claim 3, wherein the particle swarm algorithm comprises at least one of: GPSO algorithm, LPSO algorithm, MCPSO algorithm, SIPSO algorithm.

7. The method of claim 3, wherein the result parameters comprise: leakage coefficient, time parameter, location parameter.

8. The method of claim 7, wherein determining whether the pipe under test is leaking according to the result parameter comprises:

determining whether the leakage coefficient is equal to 0;

9. The method according to claim 8, characterized in that, in the case that the leakage coefficient is not equal to 0, it is determined that the pipe under test is leaking, and the time indicated by the time parameter is determined as the leakage time, and the location indicated by the location parameter is determined as the leakage location.

10. A device for detecting a leak in a pipe, comprising: