Leak source positioning method, device and equipment of buried oil pipeline and storage medium

Abstract

The application provides a buried oil pipeline leakage source positioning method, device and equipment and storage medium, and relates to the technical field of pipeline leakage. The method comprises the following steps: obtaining a leakage area of a buried oil pipeline; generating a plurality of random leakage source points of the leakage area according to a genetic algorithm; establishing a leakage diffusion model of the buried oil pipeline, simulating pollution diffusion of the random leakage source points to obtain fitness of the random leakage source points, and determining a predicted leakage point among the plurality of random leakage source points; generating a candidate leakage point set of the buried oil pipeline by using a Markov chain Monte Carlo algorithm and through a self-adaptive step constraint mechanism; performing probability sampling processing to obtain a leakage search space of the buried oil pipeline; and determining a leakage source coordinate of the buried oil pipeline based on a particle swarm dynamic iteration mechanism. The application solves the problem of low efficiency of leakage source positioning of the buried oil pipeline caused by long time consumption, low positioning accuracy and high calculation complexity of the leakage positioning method.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pipeline leakage, in particular to a buried oil pipeline leakage source positioning method, device, equipment and storage medium. BACKGROUND

[0002] The rapid economic growth drives the continuous rise of oil consumption, and the complexity of the pipeline network system is increasing, and the buried oil pipeline leakage source positioning is facing increasingly severe challenges, such as the concealment of leakage signals, environmental interference factors, and the stringent requirements of emergency response timeliness. The traditional leakage positioning method usually relies on pressure monitoring and flow analysis to determine whether there is leakage by comparing the flow difference between the inlet and outlet of the pipeline. However, with the complication of the pipeline network and the diversification of environmental factors, the accuracy of this method is limited.

[0003] At present, new detection technologies, intelligent monitoring methods and crowd intelligence algorithms are mainly used for optimization. However, the introduction of intelligent monitoring technology improves the sensitivity and accuracy of detection, but requires relevant personnel not only to have traditional pipeline knowledge, but also to master advanced technical means to effectively cope with these new challenges. In the crowd intelligence algorithm, a single optimization algorithm is limited by the inherent defects of the algorithm and is highly sensitive to parameters, and the improvement is limited. The hybrid optimization model breaks through the limitations of single method through algorithm complementation, and significantly improves the accuracy and robustness.

[0004] The existing leakage positioning method is time-consuming, low in positioning accuracy, and high in computational complexity, resulting in low efficiency of buried oil pipeline leakage source positioning. SUMMARY

[0005] The present application provides a buried oil pipeline leakage source positioning method, device, equipment and storage medium to solve the problem of low efficiency of buried oil pipeline leakage source positioning caused by long time-consuming, low positioning accuracy and high computational complexity of the leakage positioning method.

[0006] In a first aspect, the present application provides a buried oil pipeline leakage source positioning method, comprising:

[0007] Obtaining a leakage area of a buried oil pipeline;

[0008] According to the genetic algorithm, a plurality of random leakage source points of the leakage area are generated;

[0009] Establishing a leakage diffusion model of the buried oil pipeline;

[0010] According to the leakage diffusion model, the pollution diffusion simulation is performed on the random leakage source points to obtain the fitness of the random leakage source points;

[0011] According to the fitness of the random leakage source points, a predicted leakage point is determined from the plurality of random leakage source points.

[0012] Adopt Markov chain Monte Carlo algorithm, with the predicted leakage point as the benchmark, generate a candidate leakage point set of the buried oil pipeline through an adaptive step constraint mechanism;

[0013] Probability sampling processing is performed on the candidate leakage point set to obtain a leakage search space of the buried oil pipeline;

[0014] Based on the dynamic iteration mechanism of the particle swarm, the candidate leakage points in the leakage search space are dynamically tracked to determine the leakage source coordinates of the buried oil pipeline.

[0015] In one possible design, according to the leakage diffusion model, pollution diffusion simulation is performed on the random leakage source point to obtain the fitness of the random leakage source point, including:

[0016] Determine a plurality of data collection points;

[0017] Calculate the axial weighted distance between the data collection points and the random leakage source point;

[0018] Obtain sensor collection data of the data sampling points;

[0019] According to the leakage diffusion model and the data collection points, pollution diffusion simulation is performed on the random leakage source point to obtain pollution simulation data;

[0020] According to the axial weighted distance, the pollution simulation data and the sensor sampling data, calculate the weighted error;

[0021] According to the pollution simulation data and the weighted error, determine the fitness of the random leakage source point.

[0022] In one possible design, probability sampling processing is performed on the candidate leakage point set to obtain a leakage search space of the buried oil pipeline, including:

[0023] Calculate the fitness of each candidate leakage point in the candidate leakage point set;

[0024] Calculate the fitness difference between each candidate leakage point and the predicted leakage point;

[0025] According to the fitness difference, filter out candidate leakage points meeting the fitness difference requirement and candidate leakage points not meeting the fitness difference requirement;

[0026] For candidate leakage points not meeting the fitness difference requirement, calculate the leakage acceptance probability, and according to the leakage acceptance probability, determine candidate leakage points meeting the leakage acceptance probability requirement;

[0027] According to the candidate leakage points meeting the leakage acceptance probability requirement and the candidate leakage points meeting the fitness difference requirement, construct a leakage search space of the buried oil pipeline.

[0028] In a possible design, based on a particle swarm dynamic iteration mechanism, a candidate leakage point in a leakage search space is dynamically tracked to determine the leakage source coordinates of the buried oil pipeline, comprising:

[0029] Based on the Sobol index sequence, an initial particle swarm in the leakage search space is constructed;

[0030] The particle position in the initial particle swarm is preliminarily updated to generate an intermediate particle swarm;

[0031] The particle position coordinates, the particle individual optimal fitness position coordinates, and the intermediate particle swarm group optimal fitness position coordinates in the intermediate particle swarm are nonlinearly weighted and fused to update the current speed of the particles in the intermediate particle swarm;

[0032] Based on the updated particle current speed and the current position coordinates of the particles in the intermediate particle swarm, the intermediate particle swarm is iteratively updated;

[0033] The group optimal fitness position coordinates of the iteratively updated intermediate particle swarm are determined as the leakage source coordinates of the buried oil pipeline.

[0034] In a possible design, the leakage area of the buried oil pipeline is obtained, comprising:

[0035] The elastic wave signal of the sensor is received;

[0036] According to the elastic wave signal, the time difference positioning method is combined to determine the leakage area of the buried oil pipeline.

[0037] In a possible design, according to the genetic algorithm, a plurality of random leakage source points of the leakage area are generated, comprising:

[0038] A plurality of random candidate positions are generated in the leakage area through a multi-objective genetic algorithm;

[0039] The random candidate positions are determined as the random leakage source points.

[0040] In a possible design, a leakage diffusion model of the buried oil pipeline is established, comprising:

[0041] The environmental parameters and pollution source characteristics of the buried oil pipeline are obtained;

[0042] The environmental parameters and pollution source characteristics are preprocessed to obtain preprocessed data;

[0043] An original non-steady-state Domenic model is obtained;

[0044] According to the preprocessed data and the original non-steady-state Domenic model, a leakage diffusion model of the buried oil pipeline is trained.

[0045] In a second aspect, the present application provides a leakage source positioning device for a buried oil pipeline, comprising:

[0046] a obtaining module, configured to obtain a leakage area of the buried oil pipeline;

[0047] a first generating module, configured to generate a plurality of random leakage source points in the leakage area according to a genetic algorithm;

[0048] a establishing module, configured to establish a leakage diffusion model of the buried oil pipeline;

[0049] a simulating module, configured to perform pollution diffusion simulation on the random leakage source points according to the leakage diffusion model, to obtain fitness of the random leakage source points;

[0050] a first determining module, configured to determine a predicted leakage point from the plurality of random leakage source points according to the fitness of the random leakage source points;

[0051] a second generating module, configured to generate a candidate leakage point set of the buried oil pipeline by using a Markov chain Monte Carlo algorithm, taking the predicted leakage point as a reference, and through an adaptive step constraint mechanism;

[0052] a first processing module, configured to perform probability sampling processing on the candidate leakage point set, to obtain a leakage search space of the buried oil pipeline;

[0053] a second processing module, configured to perform dynamic tracking processing on the candidate leakage points in the leakage search space based on a particle swarm dynamic iteration mechanism, to determine a leakage source coordinate of the buried oil pipeline.

[0054] In a third aspect, the present application provides a leakage source positioning device for a buried oil pipeline, comprising a memory and a processor.

[0055] The memory stores computer execution instructions;

[0056] The processor executes the computer execution instructions stored in the memory, so that the processor executes the leakage source positioning method for the buried oil pipeline according to the summary of the first aspect.

[0057] In a fourth aspect, the present application provides a computer readable storage medium, which stores computer execution instructions, and the computer execution instructions are executed by a processor to implement the leakage source positioning method for the buried oil pipeline according to the summary of the first aspect.

[0058] In a fifth aspect, the present application provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the leakage source positioning method for the buried oil pipeline according to the summary of the first aspect.

[0059] The application provides a leakage source positioning method, device and equipment of a buried oil pipeline and a storage medium. The method comprises the following steps: obtaining a leakage area of the buried oil pipeline; generating a plurality of random leakage source points of the leakage area according to a genetic algorithm; establishing a leakage diffusion model of the buried oil pipeline, simulating pollution diffusion of the random leakage source points, obtaining fitness of the random leakage source points, and determining a predicted leakage point in the plurality of random leakage source points; using a Markov chain Monte Carlo algorithm, taking the predicted leakage point as a benchmark, generating a candidate leakage point set of the buried oil pipeline through an adaptive step constraint mechanism; performing probability sampling processing to obtain a leakage search space of the buried oil pipeline; and based on a particle swarm dynamic iteration mechanism, performing dynamic tracking processing on the candidate leakage points to determine a leakage source coordinate of the buried oil pipeline. Compared with the prior art, the leakage positioning method has the problems of long time consumption, low positioning accuracy and high calculation complexity, which result in low efficiency of the leakage source positioning of the buried oil pipeline. The application determines the predicted leakage point based on the genetic algorithm and the leakage diffusion model, determines the candidate leakage point through the adaptive step constraint mechanism, determines the leakage search space through the probability sampling, and determines the leakage source coordinate by performing dynamic tracking on the candidate leakage points in the leakage search space based on the particle swarm dynamic iteration mechanism. The local extreme value interference can be avoided, accurate positioning can be performed, and the efficiency of the leakage source positioning of the buried oil pipeline is improved. BRIEF DESCRIPTION OF DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without any creative effort.

[0061] Figure 1 The system architecture schematic diagram of the leakage source positioning method of the buried oil pipeline provided by the embodiments of the present application is shown in the figure.

[0062] Figure 2 The leakage source positioning method flowchart of the buried oil pipeline provided by the embodiments of the present application is shown in the figure. Figure 1

[0063] Figure 3 The leakage source positioning method flowchart of the buried oil pipeline provided by the embodiments of the present application is shown in the figure. Figure 2

[0064] Figure 4 The leakage source positioning method flowchart of the buried oil pipeline provided by the embodiments of the present application is shown in the figure. Figure 3

[0065] Figure 4 ​​​A schematic diagram of a leakage source positioning method of a buried oil pipeline provided by an embodiment of the present application Figure 5 ;

[0066] Figure 5 A schematic diagram of a leakage source positioning method of a buried oil pipeline provided by an embodiment of the present application Figure 6 ;

[0067] Figure 6 A schematic diagram of a leakage source positioning device of a buried oil pipeline provided by an embodiment of the present application

[0068] Figure 7 A schematic diagram of a leakage source positioning device of a buried oil pipeline provided by an embodiment of the present application

[0069] Figure 8 A schematic diagram of a pollution diffusion state in a buried oil pipeline provided by an embodiment of the present application

[0070] Figure 9 A schematic diagram of fitness change with iteration number of a random leakage source provided by an embodiment of the present application

[0071] Figure 10 A schematic diagram of a search space determined based on a Markov chain Monte Carlo algorithm provided by an embodiment of the present application

[0072] Figure 11 A schematic diagram of leakage source coordinates of a buried oil pipeline determined based on a particle swarm dynamic iteration mechanism provided by an embodiment of the present application. DETAILED DESCRIPTION

[0073] The exemplary embodiments will be described in detail herein with reference to the attached drawings. In the following description, the same numbers are used to indicate the same elements throughout the several views. The following detailed description is not intended to represent all embodiments in accordance with the present application. Rather, the following description is intended only to represent example embodiments in accordance with a subset of embodiments of the present application as detailed and described in the claims hereafter.

[0074] In the embodiments of the present application, the same items or similar items with basically same functions and effects are distinguished by using "first", "second", etc. It can be understood by those skilled in the art that "first", "second", etc. do not limit the quantity and execution order, and "first", "second", etc. do not necessarily mean different. It should be noted that in the embodiments of the present application, "exemplary" or "for example" is used to represent an example, illustration or description. Any embodiment or design scheme described as "exemplary" or "for example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the use of "exemplary" or "for example" is intended to present the relevant concept in a specific manner. In the embodiments of the present application, "at least one" means one or more, and "multiple" means two or more.

[0075] It should be noted that "at" in the embodiments of the present application can be at the moment when a certain condition occurs, or within a period of time after a certain condition occurs, which is not limited in the embodiments of the present application. In addition, the method for locating the leakage source of the buried oil pipeline provided in the embodiments of the present application is only an example, and the method for locating the leakage source of the buried oil pipeline can include more or less content.

[0076] In order to clearly describe the technical solutions of the embodiments of the present application, the following briefly introduces some terms and technologies involved in the embodiments of the present application:

[0077] Markov Chain Monte Carlo algorithm: a statistical sampling technique combining Markov chain and Monte Carlo method, which constructs a Markov chain to approximate the target probability distribution and generates samples from it. These samples can be used to estimate various statistics of the target distribution, such as expected value. Markov chain is a stochastic process in which each state only depends on the previous state, with "no memory" property.

[0078] Specifically, the core idea of Markov Chain Monte Carlo algorithm is to construct a Markov chain, whose stationary distribution is the posterior distribution of the parameter to be estimated. Samples of the posterior distribution are generated through this Markov chain, and Monte Carlo integration is performed based on the samples (effective samples) when the Markov chain reaches the stationary distribution. The key of the algorithm is the acceptance-rejection mechanism, that is, only when the new sample meets certain conditions will it be accepted, so as to ensure that the generated samples are subject to the target distribution.

[0079] Metropolis criterion: A probability acceptance criterion used in optimization algorithms. It is based on a probabilistic judgment to accept new solutions, thereby avoiding the algorithm from getting stuck in local optima. It is a key component of optimization algorithms such as simulated annealing. Its core role is to compare the quality of new solutions with the current solution during the algorithm iteration process, and accept new solutions with a certain probability. Even if the new solution is worse than the current solution (i.e. "worse solution"), the criterion allows it to be accepted with a certain probability, thereby increasing the algorithm's exploration ability and helping to find the global optimal solution.

[0080] Sobol sequence: Sobol sequence is a method for generating low-discrepancy sequences, commonly used in numerical integration, Monte Carlo simulation, etc. Low-discrepancy sequences have better statistical properties, such as low two-dimensional discrepancy and four-dimensional discrepancy, which means that in multi-dimensional space, the difference between adjacent points is small, thereby avoiding the clustering phenomenon.

[0081] Sobol' indices: Sobol' indices is a method for global sensitivity analysis, used to quantify the degree of influence of model input parameters on output variables. It is based on the variance decomposition method, and is obtained by normalizing each component. It includes first-order Sobol' indices and total-order Sobol' indices. First-order Sobol' indices represent the independent contribution of a single input variable to the output variance, while total-order Sobol' indices represent the total contribution of input variables to the output variance after interacting with other variables.

[0082] Domenic model: A analytical model for simulating the migration of solutes in groundwater, especially suitable for simulating the natural attenuation and migration process of pollutants in aquifers.

[0083] Unsteady-state model: Also known as dynamic model, used to describe the transient characteristics of the process under various operating conditions. It is derived based on the conservation theorem and other basic principles, and can be described by ordinary differential equations. Compared with steady-state model, unsteady-state model considers the influence of time factor on system state, and can more accurately reflect the behavior of system at different time points.

[0084] The rapid economic growth drives the continuous rise of oil consumption, and the complexity of pipeline systems increases, making the positioning of buried oil pipeline leakage sources face increasingly severe challenges, such as the concealment of leakage signals, environmental interference factors and the strict requirements of emergency response timeliness. Due to the particularity of the environment in which buried pipelines are located, their leakage is not easy to detect and can easily cause serious safety accidents.

[0085] Traditional leak location methods usually rely on pressure monitoring and flow analysis by comparing the flow difference between the inlet and outlet of the pipeline to determine whether there is a leak. However, with the complexity of the pipeline network and the diversity of environmental factors, the accuracy of this method is limited. Therefore, the traditional positioning method has the limitations of long time-consuming and low positioning accuracy, which cannot effectively cope with the increasingly complex pipeline network and changing external conditions.

[0086] Currently, new detection technologies, intelligent monitoring methods, and swarm intelligence algorithms are mainly used for optimization, but in the face of increasing uncertainty and complexity of pipeline operation, the following technical problems are brought to the existing leak source positioning:

[0087] On the one hand, the introduction of intelligent monitoring technology (such as sensor networks and data analysis algorithms) has improved the sensitivity and accuracy of detection, but it has also increased the complexity of data processing, requiring relevant personnel not only to have traditional pipeline knowledge but also to master advanced technical means to effectively cope with these new challenges.

[0088] On the other hand, although swarm intelligence algorithms are widely used in complex optimization problems, single optimization algorithms are limited by inherent algorithm defects and strong parameter sensitivity, with limited improvement. While hybrid optimization models break through the limitations of single methods through algorithm complementation, significantly improving accuracy and robustness, the computational complexity of hybrid optimization algorithms is high, and it is difficult to optimize parameters reasonably in complex buried environments. Therefore, it is still difficult to accurately locate the leak source in the early stage of leakage.

[0089] Based on this, the embodiments of the present application provide a leak source positioning method, device, and equipment for buried oil pipelines and a storage medium, which can be used in the field of pipeline leakage technology and aims to solve the above technical problems of the prior art.

[0090] To solve the above problems, the inventors found that in the positioning process of the existing leak source positioning, the intelligent monitoring technology relied on by the existing leak source positioning has complex data processing. In the swarm intelligence algorithm responsible for complex optimization problems, single optimization algorithms are limited by inherent algorithm defects and strong parameter sensitivity, with limited improvement. The algorithm computational complexity of hybrid optimization models is high, and it is difficult to optimize parameters reasonably in complex buried environments, making it difficult to accurately locate the leak source in the early stage of leakage. These all lead to low efficiency of leak source positioning for buried oil pipelines. To solve the above problems, the inventors improve the timeliness and accuracy of leak source positioning by mixing multiple optimization algorithms, dynamically adjusting algorithm parameters, based on the constructed leak diffusion model of buried oil pipelines, and positioning the leak source according to multi-source data information, thereby improving the efficiency of leak source positioning for buried oil pipelines.

[0091] The technical solutions of the present application and how the technical solutions solve the above technical problems will be described in detail below with specific examples. The following specific examples can be combined with each other, and the same or similar concepts or processes can not be described again in some examples. The embodiments of the present application will be described below with reference to the drawings.

[0092] Figure 1 The system architecture schematic diagram of the leak source positioning method of the buried oil pipeline provided by the embodiments of the present application is shown in the figure. In the Figure 1 , the above architecture includes at least one of a data acquisition device 101, a processing device 102 and a display device 103.

[0093] It can be understood that the structure shown in the embodiments of the present application does not constitute a specific limitation on the system architecture of the leak source positioning method of the buried oil pipeline. In other feasible embodiments of the present application, the above architecture can include more or fewer components than the schematic diagram, or combine certain components, or split certain components, or different component arrangement, which can be determined according to the actual application scene, and is not limited here. Figure 1 The components shown can be realized in hardware, software, or a combination of software and hardware.

[0094] In the specific implementation process, the data acquisition device 101 can include an input / output interface and a communication interface. The data acquisition device 101 can be connected with the processing device through the input / output interface or the communication interface, and collect the data related to the leakage area through various sensors.

[0095] The processing device 102 can process the collected data, establish a leakage diffusion model, and determine a predicted leakage point based on the leakage diffusion model, and then determine the coordinates of the leakage source of the buried oil pipeline according to the predicted leakage point.

[0096] The display device 103 can also be a touch display screen or a screen of a terminal device, which is used to receive user instructions while displaying the above content, so as to realize the interaction with the user.

[0097] It should be understood that the above processing device can be realized by reading the instructions in the memory by the processor and executing the instructions, or by the chip circuit.

[0098] In addition, the network architecture and business scenarios described in the embodiments of the present application are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. It can be known by those skilled in the art that with the evolution of network architecture and the appearance of new business scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0099] The technical solutions of the present application will be described in detail below with specific embodiments.

[0100] Figure 2 A leakage source positioning method of a buried oil pipeline is provided for the embodiments of the present application Figure 1 , and the method comprises the following steps.

[0101] S201: Obtain a leakage area of the buried oil pipeline.

[0102] Specifically, the elastic wave signals of the sensors are received.

[0103] More specifically, the leakage area of the buried oil pipeline is determined based on acoustic emission technology. When the pipeline leaks, fluid generates high-frequency stress waves through the crack, and the sensors capture these elastic wave signals

[0104] Specifically, the leakage area of the buried oil pipeline is determined according to the elastic wave signals and in combination with the time difference positioning method.

[0105] More specifically, the time difference positioning method is used to calculate the coordinates of the leakage point through the time delay of the signals received by multiple sensors, and the potential leakage area is demarcated.

[0106] Further, the data of the pollution diffusion range in the potential leakage area is collected by laying sensors or using ground penetrating radar and the like.

[0107] S202: Generate multiple random leakage source points in the leakage area according to a genetic algorithm.

[0108] Specifically, multiple random candidate positions are generated in the leakage area through a multi-objective genetic algorithm.

[0109] Specifically, the random candidate positions are determined as random leakage source points.

[0110] More specifically, random candidate positions are generated in the potential leakage area of the buried oil pipeline through a multi-objective genetic algorithm, and each candidate position is assumed to be a potential leakage source position (i.e., a random leakage source point).

[0111] S203: Establish a leakage diffusion model of the buried oil pipeline.

[0112] S204: According to the leakage diffusion model, simulate the pollution diffusion of the random leakage source points to obtain the fitness of the random leakage source points.

[0113] S205: According to the fitness of the random leakage source points, determine a predicted leakage point from the multiple random leakage source points.

[0114] In the embodiment, the predicted value (pollution simulation data) of the field laying sensor position of the buried oil pipeline is calculated, and the predicted value is compared with the actual sensor collection data, the best individual of each generation is reserved and iteration is performed, and the candidate position with the best fitness is selected as the potential leakage source, i.e., the predicted leakage point.

[0115] Specifically, in the process, the leakage source is searched in the leakage area, global optimization is performed based on natural selection and genetic mechanism, and a population individual evaluation mechanism is introduced, similarity between individuals is judged based on a distance index to judge whether the trend of premature convergence occurs.

[0116] If the population diversity decreases, the difference between individuals decreases, and the probability of crossover and mutation operation is increased to promote the diversity of the population.

[0117] Further, an adaptive measurement strategy is adopted, the crossover and mutation probabilities are dynamically adjusted according to the current generation number and fitness distribution, the fitness of the random leakage source point is determined according to the error between the predicted value (pollution simulation data) and the actual sensor collection data, and the random leakage source point corresponding to the best fitness is selected as the predicted leakage point.

[0118] In a possible embodiment, Figure 10 The schematic diagram of the fitness of the random leakage source provided by the embodiment of the application changing with the iteration number is shown in FIG. 2. Figure 10 As shown in FIG. 2, the dynamic evolution of the fitness value with the iteration process is shown: in the early iteration, the fitness value is at a high level, then it rapidly decreases and is accompanied by obvious fluctuations. After about 200 iterations, the fitness value tends to be stable, the fluctuation amplitude is significantly reduced, and finally it is stabilized at about 2.3. Figure 10 The 200th iteration in FIG. 2 constitutes a key node, indicating that the fitness value reaches a relatively high point and enters a stable stage. The overall change trend shows that the algorithm experiences a large amplitude of exploration and adjustment in the early stage, gradually converges to a better solution as the iteration deepens, and the final stable state indicates that the algorithm has found a satisfactory leakage source positioning scheme.

[0119] S206, the Markov chain Monte Carlo algorithm is adopted to generate a candidate leakage point set of the buried oil pipeline by taking the predicted leakage point as a benchmark and through an adaptive step constraint mechanism.

[0120] Based on the Markov chain Monte Carlo algorithm, the adaptive sampling mechanism is introduced to dynamically adjust the sampling strategy, improve the sampling rate, avoid being trapped in local optimum at the boundary point, and realize the constraint on the candidate leakage point through the adaptive step constraint mechanism.

[0121] Specifically, in each iteration, the iteration step can be dynamically adjusted according to the current acceptance rate to keep the search within a reasonable range, such as determining the step adjustment parameter a to adjust the iteration step by the following formula:

[0122]

[0123]

[0124] wherein, is the predicted value at the corresponding position of the i th data collection point in the buried oil pipeline during the pollution diffusion simulation by the leakage diffusion model; is the sensor collection data (actual value) of the i th data collection point in the buried oil pipeline;d i is the predicted value and the sensor collection data ; e is the error tolerance parameter; n is the total number of data collection points in the buried oil pipeline; new is the candidate leakage point of the current iteration step; old is the candidate leakage point of the previous iteration step.

[0125] S207, probabilistic sampling processing is performed on the candidate leakage point set to obtain a leakage search space of the buried oil pipeline.

[0126] It should be noted that the three-dimensional global search framework is constructed by the multi-objective genetic algorithm, and the dynamic population evaluation and adaptive crossover and mutation strategy are used to effectively avoid the premature convergence problem and significantly improve the screening efficiency of the potential leakage area. At the same time, the probability focusing and adaptive step constraint mechanism of the Markov chain Monte Carlo algorithm, combined with the probability sampling of the Metropolis criterion, significantly reduces the local extreme value interference and forms a high-confidence spatial search path. Therefore, by combining the multi-objective genetic algorithm and the Markov chain Monte Carlo algorithm, a hybrid optimization framework with global search ability and local optimization characteristics is constructed, which can quickly and efficiently find the potential leakage source in a complex leakage environment.

[0127] In one possible embodiment, Figure 11 the search space determined based on the Markov chain Monte Carlo algorithm provided by the embodiments of the present application is shown in FIG. 8. Figure 11 As shown in FIG. 8, the search range and the distribution of the sampling points in the three-dimensional space are intuitively displayed.

[0128] wherein, the red box clearly indicates the boundary of the search space, which limits the search area on the X-axis, Y-axis and Z-axis, wherein the X-axis range extends from a certain starting value in the figure to 12, the Y-axis range extends from 0 to a certain end value in the figure, and the Z-axis range extends from -13 to -9.

[0129] The gray point set represents the points sampled by the Markov chain Monte Carlo algorithm, which are concentrated in a certain area in the search space, embodying the concentration trend of the algorithm in the exploration process, and reflecting the behavior of the Markov chain Monte Carlo algorithm in exploring the distribution area of sample points in the search space.

[0130] In addition, the coordinate axis label clearly shows the direction and range of the search space in the three-dimensional space, which helps to understand the geometric characteristics of the search space.

[0131] S208, based on the particle swarm dynamic iteration mechanism, the candidate leakage points in the leakage search space are dynamically tracked and processed to determine the leakage source coordinates of the buried oil pipeline.

[0132] It should be noted that the traditional single particle swarm optimization has the limitations of insufficient working condition generalization, easy to fall into local optimum, strong error volatility, etc. In this application, in the local area defined by the Markov chain Monte Carlo algorithm, the global exploration ability of the genetic algorithm and the local development characteristics of the particle swarm optimization algorithm are fused, and the multi-objective collaborative optimization is carried out through the dynamic inertia weight adjustment strategy, which effectively improves the global search and local optimization ability.

[0133] It should be noted that after completing the leakage source positioning, a leakage diffusion multi-scenario verification model can be constructed in a three-dimensional simulation environment to simulate the leakage scene, including noise interference, partial sensor failure and heterogeneous soil parameter disturbance and other complex factors, to evaluate the positioning accuracy and efficiency in complex scenarios, test, verify and dynamically adjust the leakage source positioning strategy. Through the establishment of a multi-scenario test environment, the optimized positioning strategy is comprehensively verified to ensure the robustness and practicality of the positioning method, so that it can effectively cope with various complex environmental factors in actual application, and provide reliable protection for the safe operation of the crude oil transportation system.

[0134] The embodiment provides a leakage source positioning method of a buried oil pipeline. Compared with the prior art, the leakage positioning method is time-consuming, low in positioning accuracy and high in calculation complexity, and these problems result in low leakage source positioning efficiency of the buried oil pipeline. The application determines a predicted leakage point based on a genetic algorithm and a leakage diffusion model, determines a candidate leakage point through an adaptive step length constraint mechanism, determines a leakage search space through probability sampling, and determines a leakage source coordinate of the buried oil pipeline through dynamic tracking of the candidate leakage point in the leakage search space based on a particle swarm dynamic iteration mechanism. Local extremum interference can be avoided, accurate positioning can be performed, and therefore the leakage source positioning efficiency of the buried oil pipeline is improved.

[0135] Figure 3 A leakage source positioning method of a buried oil pipeline provided by the embodiment of the application is shown in the flowchart Figure 2 As shown in Figure 3 , the specific implementation steps of S204 further include:

[0136] S301, a plurality of data collection points are determined.

[0137] S302, an axial weighted distance of the data collection point and the random leakage source point is calculated.

[0138] In the embodiment, the axial weighted distance of each data collection point of the leakage area of the buried oil pipeline and the i-th random leakage source point is calculated; wherein i is an element of N, and i and N are positive integers.

[0139] The axial weighted distance of each data collection point and the i-th random leakage source point reflects the diffusion characteristics of pollutants in different directions.

[0140] S303, sensor collection data of the data sampling point is acquired.

[0141] The data is collected through an on-site sensor.

[0142] S304, according to the leakage diffusion model and the data collection point, the random leakage source point is simulated for pollution diffusion to obtain pollution simulation data.

[0143] In the embodiment, according to the leakage diffusion model and the data collection points, the pollution diffusion simulation is performed on the random leakage source points to obtain the pollution simulation data. And the pollution diffusion trend diagram is generated according to the pollution simulation data.

[0144] In a possible embodiment, Figure 9 The pollution diffusion trend diagram in the buried oil pipeline provided in the embodiment of the application is shown in FIG. 1, which can show the diffusion of the pollutants in the area below the pipeline: the pollutants are mainly concentrated in the central area and diffuse to the surrounding areas from the source, and the pollutants are highly concentrated near the source and gradually diluted with the increase of the distance. Figure 9

[0145] In the embodiment, the diffusion range is approximately between -10m and 10m in the X-axis, Y-axis and Z-axis directions, forming an approximate cubic diffusion area.

[0146] In the embodiment, the color in the diagram represents the concentration change, the blue area has a lower concentration, and the yellow area has a higher concentration. The highest concentration is close to the source, and the concentration gradually decreases with the increase of the distance. The right color bar shows that the concentration range is approximately between 0.2 and 1.

[0147] S305, calculating the weighted error according to the axial weighted distance, the pollution simulation data and the sensor sampling data.

[0148] In the embodiment, the weighted error of the pollution simulation data generated when the pollution diffusion simulation is performed on the ith random leakage source point and the sensor sampling data of each data collection point is calculated according to the axial weighted distance.

[0149] For example, the weighted error of the pollution simulation data generated when the pollution diffusion simulation is performed on the ith random leakage source point and the sensor sampling data of each data collection point is calculated according to the axial weighted distance between the data collection point and the random leakage source point.

[0150] S306, determining the fitness of the random leakage source point according to the pollution simulation data and the weighted error.

[0151] In the embodiment, the fitness of the ith random leakage source point is determined by summing the weighted error of the pollution simulation data generated when the pollution diffusion simulation is performed on the ith random leakage source point and the sensor sampling data of each data collection point.

[0152] ​In this embodiment, based on the leakage diffusion model of the buried oil pipeline, N times of pollution diffusion simulation are performed on N random leakage source points respectively, and pollution simulation data of the leakage area in each pollution diffusion simulation is obtained to determine the fitness of the N random leakage source points. The random leakage source point is quantitatively matched with the real leakage source, the accuracy of the leakage source positioning is improved, the search process is optimized, the robustness of the positioning method is enhanced, and thus the efficiency of the leakage source positioning of the buried oil pipeline is improved.

[0153] Figure 4 A leakage source positioning method of a buried oil pipeline provided by the embodiment of the application Figure 3 As shown in Figure 4 The specific implementation steps of S207 include:

[0154] S401, calculate the fitness of each candidate leakage point in the candidate leakage point set.

[0155] S402, calculate the fitness difference between each candidate leakage point and the predicted leakage point.

[0156] S403, according to the fitness difference, screen out the candidate leakage points meeting the fitness difference requirement and the candidate leakage points not meeting the fitness difference requirement.

[0157] Wherein, in a complex buried environment, the leakage signal may be disturbed by various factors such as soil properties, pipeline layout, and leakage amount. The leakage search space determined by probability sampling can better adapt to these complex diffusion scenarios and reduce the influence of interference factors on the positioning result.

[0158] S404, for the candidate leakage points not meeting the fitness difference requirement, calculate the leakage acceptance probability, and according to the leakage acceptance probability, determine the candidate leakage points meeting the leakage acceptance probability requirement.

[0159] S405, according to the candidate leakage points meeting the leakage acceptance probability requirement and the candidate leakage points meeting the fitness difference requirement, construct the leakage search space of the buried oil pipeline.

[0160] Wherein, based on the Metropolis criterion, probability sampling is performed on multiple candidate leakage points, a high-confidence search space is established, and the leakage search space of the buried oil pipeline is generated.

[0161] Wherein, probability sampling can determine a smaller and more accurate search area, which is called a high-confidence search space. This greatly reduces the search range, making the leakage source positioning work more efficient and accurate.

[0162] Wherein, in the initial stage of the leakage accident, quickly locating the leakage source is crucial for implementing emergency response measures. Quickly determining the leakage search space through probability sampling helps to find the leakage source in a short time, meets the timeliness requirement of emergency response, and thus reduces the loss and impact caused by the accident.

[0163] For example, the fitness of the jth candidate leakage point is determined, and the fitness difference between the jth candidate leakage point and the predicted leakage point is calculated. Wherein, j is a positive integer.

[0164] Further, if the fitness difference between the jth candidate leakage point and the predicted leakage point is greater than 0, the ratio of the fitness difference between the jth candidate leakage point and the predicted leakage point to the fitness of the predicted leakage point is input into the natural exponential function to determine the leakage acceptance probability of the jth candidate leakage point.

[0165] Further, the leakage search space of the buried oil pipeline is constructed.

[0166] Specifically, the leakage search space of the buried oil pipeline is constructed through M1 candidate leakage points with a leakage acceptance probability greater than or equal to a random number generated based on a random generation algorithm, and M2 candidate leakage points with a fitness difference between the candidate leakage point and the predicted leakage point less than or equal to 0.

[0167] Wherein, M1 and M2 are positive integers.

[0168] In this embodiment, the multiple candidate leakage points are probability sampled based on the Metropolis criterion to generate the leakage search space of the buried oil pipeline, which narrows the search range, reduces the influence of interference factors on the positioning result, meets the timeliness requirement of emergency response, and thus improves the leakage source positioning efficiency of the buried oil pipeline.

[0169] Figure 5 A leakage source positioning method of a buried oil pipeline provided in this embodiment Figure 4 As shown in Figure 5 The specific implementation steps of the above S208 include:

[0170] S501, based on the Sobol index sequence, an initial particle group in the leakage search space is constructed.

[0171] Specifically, the initial particle group containing multiple particles in the leakage search space is generated based on the Sobol low-discrepancy sequence.

[0172] S502, the particle positions in the initial particle group are preliminarily updated to generate an intermediate particle group.

[0173] In this embodiment, the intermediate particle group is generated by preliminarily updating the particle positions in the initial particle group.

[0174] Specifically, the particle position in the initial particle swarm set is preliminarily updated according to the initial position coordinates of the particles in the initial particle swarm and the initial velocity of the particles, and the particles after the position is preliminarily updated are used to replace the corresponding particles in the initial particle swarm to generate an intermediate particle swarm.

[0175] S503, the particle current velocity in the intermediate particle swarm is updated by nonlinearly weighting and fusing the particle position coordinates in the intermediate particle swarm, the position coordinates of the particle individual optimal fitness, and the position coordinates of the intermediate particle swarm population optimal fitness.

[0176] S504, the intermediate particle swarm is iteratively updated based on the updated particle current velocity and the current position coordinates of the particles in the intermediate particle swarm.

[0177] In this embodiment, the particle position in the intermediate particle swarm is iteratively updated based on the updated particle current velocity and the current position coordinates of the particles in the intermediate particle swarm, so as to iteratively update the intermediate particle swarm.

[0178] Specifically, the multi-objective genetic algorithm and the particle swarm optimization algorithm are combined, the individual fitness function, i.e. the error between the sensor data and the model prediction value, is evaluated in the global search stage, the high-quality individual is selected according to the fitness, the cross operation is performed to generate a new individual, the mutation operation is performed on the new individual to increase the diversity of the population, the new individual is used to replace the old individual, and a new generation population is formed.

[0179] Further, in the local optimization stage, the optimal individual is selected as the initial position of the particle swarm, the velocity and position of the particle swarm are initialized, the fitness function is calculated, and the particle velocity and position are updated until the iteration stop condition is met: the fitness function converges or the maximum iteration number is reached, and the optimal solution is output.

[0180] Optionally, in the process of iteratively updating the intermediate particle swarm, the fitness between the particles and each candidate leakage point in the leakage search space before and after the particle position is updated is weighted and summed to obtain the corresponding particle individual fitness. The particle individual fitnesses of all particles in the intermediate particle swarm are compared to determine the position coordinates of the particle individual optimal fitness.

[0181] Optionally, the fitness between each particle in the intermediate particle swarm set and each candidate leakage point in the leakage search space is also calculated, and the particle coordinates with the best fitness in the intermediate particle swarm set are selected as the position coordinates of the population optimal fitness of the intermediate particle swarm.

[0182] S505, the position coordinates of the population optimal fitness of the iteratively updated intermediate particle swarm are determined as the leakage source coordinates of the buried oil pipeline.

[0183] It should be noted that the gradual transition from global coarse positioning to local precise positioning greatly reduces the operation amount of the model, and the particle swarm dynamic iteration mechanism is used to precisely position the leakage source coordinates, significantly improves the positioning efficiency in complex diffusion scenarios, effectively reduces the positioning error, realizes the precise positioning of the buried oil pipeline leakage source, improves the adaptability of the buried oil pipeline leakage source positioning in complex scenarios, greatly improves the emergency response rate after the accident, and provides favorable support for rapid plugging and rapid rescue operation.

[0184] In a possible embodiment, Figure 12 The buried oil pipeline leakage source coordinates determined based on the particle swarm dynamic iteration mechanism provided in the embodiments of the present application are shown in Figure 12 As shown, the dynamic iteration results of the particle swarm algorithm in the process of positioning the leakage source are intuitively presented.

[0185] Among them, the red dot clearly indicates the real coordinates or the coordinates of the algorithm finally determined of the leakage source. The blue trajectory depicts the dynamic search path of the particle swarm in the three-dimensional search space (composed of X axis, Y axis and N axis, N axis represents a certain normalization or specific physical quantity), and presents the process of gradually converging to the leakage source coordinates from the random initialization of the particle swarm through the continuous iteration of updating the position and speed.

[0186] It should be noted that this process embodies the core mechanism of the particle swarm algorithm: each particle adjusts its search direction according to the individual optimal position and global optimal position, and the speed update strategy balances the demand for exploring new areas and using known optimal information. Finally, when the particle swarm converges or reaches the preset iteration number, the leakage source coordinates are determined.

[0187] In the present embodiment, the particle swarm optimization algorithm is improved based on the genetic algorithm, and the candidate leakage points in the leakage search space are dynamically tracked to determine the leakage source coordinates of the buried oil pipeline. Dynamic tracking avoids the problem that the traditional single particle swarm optimization algorithm is easy to fall into local optimum, making the algorithm more flexible and adaptable. The gradual transition from global coarse positioning to local precise positioning greatly reduces the operation amount of the model, significantly improves the efficiency of leakage source positioning, helps to find the leakage source in a short time, and thus improves the efficiency of buried oil pipeline leakage source positioning.

[0188] Figure 6 A buried oil pipeline leakage source positioning method provided in the embodiments of the present application is shown in Figure 5 As shown in Figure 6 The specific implementation steps of the above S203 include:

[0189] S601, obtaining the environmental parameters and pollution source characteristics of the buried oil pipeline.

[0190] Among them, through the feature engineering method, the representative features are extracted from the collected raw data, which at least include time series analysis results, statistical data, and migration parameters of pollutants, etc.

[0191] Among them, in the model construction process, by introducing environmental parameters and pollution source characteristics, it is ensured that the model can effectively simulate the diffusion of pollutants in different scenarios. For example, various environmental data related to pollutant migration in the groundwater system are collected, including but not limited to water level, flow rate, soil properties, pollutant concentration, etc., to ensure that as many environmental factors as possible are covered in the simulation process, providing comprehensive data input for simulation.

[0192] S602, data preprocessing is performed on the environmental parameters and pollution source characteristics to obtain preprocessed data.

[0193] Optionally, the collected data is cleaned to remove outliers and noise to ensure the quality of the collected data.

[0194] Optionally, the collected data is normalized or standardized to enable data of different magnitudes to be compared and analyzed on the same scale.

[0195] Optionally, interpolation, average value method or median filling method is used to fill in missing values to ensure data integrity.

[0196] S603, an original non-steady-state Domenic model is obtained.

[0197] S604, according to the preprocessed data and the original non-steady-state Domenic model, a leakage diffusion model of the buried oil pipeline is trained.

[0198] In this embodiment, after processing the original data, the processed data is used to train the leakage diffusion model based on the non-steady-state Domenico model, the error is calculated by comparing the predicted value of the model with the field collected data through sensors, the prediction ability of the leakage diffusion model is evaluated, and the model parameters of the leakage diffusion model are optimized through back propagation.

[0199] Among them, the processed data is divided into a training set and a validation set to ensure that the trained model has good generalization ability.

[0200] Among them, in the model training process, the prediction performance of the model is monitored, and the root mean square error, the determination coefficient and other indicators are used to evaluate the performance of the model.

[0201] Optionally, the trained leakage diffusion model can analyze the input environmental data and output a diffusion state representation of the pollutant (i.e., pollution simulation data), including but not limited to a pollution concentration distribution, a pollution migration path, and a possible pollution impact range.

[0202] In the embodiment, the environmental parameters and pollution source features are obtained by a feature engineering method, and data preprocessing is performed, and a leakage diffusion model of the buried oil pipeline is trained based on the original non-steady-state Domenic model, thereby improving the prediction accuracy, reliability, and generalization ability of the model, and further improving the leakage source positioning efficiency of the buried oil pipeline.

[0203] Figure 7 A structure diagram of a leakage source positioning device for a buried oil pipeline provided in the embodiment of the present application is shown in Figure 7 As shown, the device includes an acquisition module 71, a first generation module 72, an establishment module 73, a simulation module 74, a first determination module 75, a second generation module 76, a first processing module 77, and a second processing module 78.

[0204] The acquisition module 71 is configured to acquire a leakage area of the buried oil pipeline.

[0205] The first generation module 72 is configured to generate a plurality of random leakage source points of the leakage area according to a genetic algorithm.

[0206] The establishment module 73 is configured to establish a leakage diffusion model of the buried oil pipeline.

[0207] The simulation module 74 is configured to perform pollution diffusion simulation on the random leakage source points according to the leakage diffusion model to obtain fitness of the random leakage source points.

[0208] The first determination module 75 is configured to determine a predicted leakage point from the plurality of random leakage source points according to the fitness of the random leakage source points.

[0209] The second generation module 76 is configured to generate a candidate leakage point set of the buried oil pipeline by using a Markov chain Monte Carlo algorithm, taking the predicted leakage point as a reference, and using a self-adaptive step constraint mechanism.

[0210] The first processing module 77 is configured to perform probability sampling processing on the candidate leakage point set to obtain a leakage search space of the buried oil pipeline.

[0211] The second processing module 78 is configured to perform dynamic tracking processing on the candidate leakage points in the leakage search space based on a particle swarm dynamic iteration mechanism to determine a leakage source coordinate of the buried oil pipeline.

[0212] In one possible design, based on a leakage diffusion model, pollution diffusion simulation is performed on random leakage sources to obtain the fitness of the random leakage sources, including:

[0213] Simulation module 74 is also used to determine multiple data acquisition points;

[0214] Calculate the axial weighted distance between data collection points and random leakage sources;

[0215] Acquire sensor data from data sampling points;

[0216] Based on the leakage diffusion model and data collection points, pollution diffusion simulation was performed on random leakage sources to obtain pollution simulation data;

[0217] The weighted error is calculated based on the axial weighted distance, pollution simulation data, and sensor sampling data.

[0218] The fitness of random leakage sources is determined based on pollution simulation data and weighted error.

[0219] In one possible design, the set of candidate leak points is probabilistically sampled to obtain the leak search space for the buried oil pipeline, including:

[0220] The first processing module 77 is also used to calculate the fitness of each candidate leak point in the candidate leak point set;

[0221] Calculate the fitness difference between each candidate leak point and the predicted leak point;

[0222] Based on fitness differences, candidate leak points that meet the fitness difference requirements and candidate leak points that do not meet the fitness difference requirements are selected.

[0223] For candidate leak points that do not meet the fitness difference requirement, calculate the leak acceptance probability, and determine the candidate leak points that meet the leak acceptance probability requirement based on the leak acceptance probability.

[0224] Based on candidate leak points that meet the leak acceptance probability requirement and candidate leak points that meet the fitness difference requirement, a leak search space for buried oil pipelines is constructed.

[0225] In one possible design, based on a particle swarm optimization dynamic iteration mechanism, candidate leak points within the leak search space are dynamically tracked to determine the coordinates of the leak source in the buried oil pipeline, including:

[0226] The second processing module 78 is used to construct an initial particle swarm in the leakage search space based on the Sobol index sequence.

[0227] The positions of particles in the initial particle swarm are initially updated to generate an intermediate particle swarm.

[0228] Nonlinearly weighting and fusing the particle position coordinates in the intermediate particle group, the particle individual optimal fitness position coordinates, and the intermediate particle group population optimal fitness position coordinates to update the current velocity of the particle in the intermediate particle group;

[0229] Iteratively updating the intermediate particle group based on the updated current velocity of the particle and the current position coordinates of the particle in the intermediate particle group;

[0230] Determining the group optimal fitness position coordinates of the iteratively updated intermediate particle group as the leakage source coordinates of the buried oil pipeline.

[0231] In a possible design, the leakage area of the buried oil pipeline is acquired, including:

[0232] The acquisition module 71 is further configured to receive the elastic wave signal of the sensor.

[0233] According to the elastic wave signal, the time difference positioning method is combined to determine the leakage area of the buried oil pipeline.

[0234] In a possible design, the multiple random leakage source points of the leakage area are generated according to a genetic algorithm, including:

[0235] The first generation module 72 is further configured to generate multiple random candidate positions in the leakage area by using a multi-objective genetic algorithm.

[0236] The random candidate positions are determined as the random leakage source points.

[0237] In a possible design, the leakage diffusion model of the buried oil pipeline is established, including:

[0238] The establishment module 73 is further configured to acquire environmental parameters and pollution source characteristics of the buried oil pipeline.

[0239] The environmental parameters and the pollution source characteristics are preprocessed to obtain preprocessed data.

[0240] An original non-steady-state Domenic model is acquired.

[0241] The leakage diffusion model of the buried oil pipeline is trained according to the preprocessed data and the original non-steady-state Domenic model.

[0242] The leakage source positioning device of the buried oil pipeline provided in this embodiment can execute the leakage source positioning method of the buried oil pipeline in the above embodiments, and has similar implementation principles and technical effects, which will not be described here again.

[0243] In the specific implementation of the method for locating a leakage source of a buried oil pipeline, each module can be implemented as a processor, and the processor can execute computer execution instructions stored in the memory, so that the processor executes the method for locating a leakage source of a buried oil pipeline.

[0244] Figure 8 A structural schematic diagram of a leakage source locating device of a buried oil pipeline is provided in the embodiments of the present application. As shown in the figure, the leakage source locating device 80 of the buried oil pipeline includes at least one processor 81 and a memory 82. The leakage source locating device 80 of the buried oil pipeline further includes a communication component 83. The processor 81, the memory 82, and the communication component 83 are connected through a second bus 84. Figure 8

[0245] In the specific implementation process, the at least one processor 81 executes the computer execution instructions stored in the memory 82, so that the at least one processor 81 executes the method for locating a leakage source of a buried oil pipeline as executed on the leakage source locating device side of the buried oil pipeline.

[0246] The specific implementation process of the processor 81 can refer to the method embodiments described above, which has similar implementation principles and technical effects, and will not be described here in detail.

[0247] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor, or the processor can also be any conventional processor, etc. The steps of the method disclosed in the application can be directly embodied as execution completed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

[0248] The memory can include a high-speed RAM memory, and can also include a non-volatile storage NVM, for example, at least one disk memory.

[0249] ​The second bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application does not limit to only one bus or one type of bus.

[0250] The functions realized by the leakage source positioning device and the master control device for the buried oil pipeline are introduced. It can be understood that the leakage source positioning device or the master control device for the buried oil pipeline includes the corresponding hardware structure and / or software module for executing each function. The units and algorithm steps of each example described in combination with the embodiments disclosed in the embodiments of the present application can be realized in the form of hardware or a combination of hardware and computer software. Whether a certain function is realized by hardware or computer software driven hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the technical solutions of the embodiments of the present application.

[0251] The present application also provides a computer readable storage medium, which stores computer execution instructions, and when the processor executes the computer execution instructions, a buried oil pipeline leakage source positioning method is realized.

[0252] The above readable storage medium can be realized by any type of volatile or non-volatile storage device or their combination, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0253] An example readable storage medium is coupled to the processor such that the processor can read information from, and can write information to, the readable storage medium. Of course, the readable storage medium can be a part of the processor. The processor and the readable storage medium can be located in an Application Specific Integrated Circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in the leak source positioning device or the master control device of the buried oil pipeline.

[0254] The application further provides a computer program product, which comprises a computer program stored in a readable storage medium, at least one processor of the leak source positioning device of the buried oil pipeline can read the computer program from the readable storage medium, and the at least one processor executes the computer program to enable the leak source positioning device of the buried oil pipeline to execute the scheme provided in any of the above embodiments.

[0255] Those skilled in the art can understand that all or part of the steps of the above method embodiments can be completed by program instruction related hardware. The foregoing program can be stored in a computer readable storage medium. When the program is executed, the steps of the above method embodiments are executed; and the foregoing storage medium includes ROM, RAM, magnetic disk or optical disk and various storage media that can store program codes.

[0256] So far, the technical scheme of the application has been described in combination with the preferred embodiments shown in the drawings, but those skilled in the art can easily understand that the protection scope of the application is obviously not limited to these specific embodiments, and the above embodiments are only used to illustrate the technical scheme of the application, but not to limit it; although the application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical scheme recorded in the above embodiments, or make equivalent replacement to part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical scheme deviate from the scope of the technical scheme of the embodiments of the application.

Claims

1. A method for locating the leakage source of a buried oil pipeline, characterized in that, include: Locate the leak area of ​​the buried oil pipeline; Based on a genetic algorithm, multiple random leakage source points are generated in the leakage area; Establish a leakage diffusion model for the buried oil pipeline; Based on the leakage diffusion model, pollution diffusion simulation is performed on the random leakage source points to obtain the fitness of the random leakage source points; Based on the fitness of the random leakage sources, a predicted leakage point is determined from the plurality of random leakage sources; The Markov chain Monte Carlo algorithm is used to generate a set of candidate leak points for the buried oil pipeline based on the predicted leak points and through an adaptive step size constraint mechanism. The candidate leak point set is subjected to probability sampling to obtain the leak search space of the buried oil pipeline; Based on the particle swarm dynamic iteration mechanism, candidate leak points in the leak search space are dynamically tracked to determine the coordinates of the leak source of the buried oil pipeline.

2. The method according to claim 1, characterized in that, The step of simulating pollution diffusion at the random leakage source point based on the leakage diffusion model to obtain the fitness of the random leakage source point includes: Identify multiple data collection points; Calculate the axial weighted distance between the data acquisition point and the random leakage source point; Acquire sensor data from the data sampling points; Based on the leakage diffusion model and the data collection points, pollution diffusion simulation is performed on the random leakage source points to obtain pollution simulation data; The weighted error is calculated based on the axial weighted distance, the pollution simulation data, and the sensor sampling data. The fitness of the random leakage source is determined based on the pollution simulation data and the weighted error.

3. The method according to claim 1, characterized in that, The step of performing probability sampling on the candidate leak point set to obtain the leak search space of the buried oil pipeline includes: Calculate the fitness of each candidate leak point in the candidate leak point set; Calculate the fitness difference between each candidate leak point and the predicted leak point; Based on the fitness difference, candidate leakage points that meet the fitness difference requirements and candidate leakage points that do not meet the fitness difference requirements are selected. For the candidate leak points that do not meet the fitness difference requirement, calculate the leak acceptance probability, and determine the candidate leak points that meet the leak acceptance probability requirement based on the leak acceptance probability. Based on the candidate leak points that meet the leak acceptance probability requirement and the candidate leak points that meet the fitness difference requirement, a leak search space for the buried oil pipeline is constructed.

4. The method according to any one of claims 1 to 3, characterized in that, The process of dynamically tracking candidate leak points within the leak search space based on a particle swarm optimization dynamic iteration mechanism to determine the coordinates of the leak source in the buried oil pipeline includes: Based on the Sobol index sequence, an initial particle swarm is constructed within the leakage search space; The positions of particles in the initial particle swarm are initially updated to generate an intermediate particle swarm. The position coordinates of the particles in the intermediate particle swarm, the position coordinates of the individual particles with the best fitness, and the position coordinates of the intermediate particle swarm with the best fitness are nonlinearly weighted and fused to update the current velocity of the particles in the intermediate particle swarm. The intermediate particle swarm is iteratively updated based on the updated current particle velocity and the current position coordinates of the particles in the intermediate particle swarm. The location coordinates of the optimal fitness of the intermediate particle swarm after iterative updates are determined as the coordinates of the leakage source of the buried oil pipeline.

5. The method according to any one of claims 1 to 3, characterized in that, The process of identifying the leakage area of ​​the buried oil pipeline includes: Receives elastic wave signals from the sensor; Based on the elastic wave signal and combined with the time difference positioning method, the leakage area of ​​the buried oil pipeline is determined.

6. The method according to claim 5, characterized in that, The step of generating multiple random leakage source points in the leakage area according to the genetic algorithm includes: A multi-objective genetic algorithm is used to generate multiple random candidate locations in the leak area; The random candidate locations are determined as the random leakage source points.

7. The method according to any one of claims 1 to 3, characterized in that, The establishment of the leakage diffusion model for the buried oil pipeline includes: Obtain the environmental parameters and pollution source characteristics of the buried oil pipeline; The environmental parameters and pollution source characteristics are preprocessed to obtain preprocessed data; Obtain the original unsteady Domenic model; Based on the preprocessed data and the original unsteady Domenic model, a leakage diffusion model for the buried oil pipeline is trained.

8. A leak source locating device for a buried oil pipeline, characterized in that, include: The acquisition module is used to acquire the leakage area of ​​buried oil pipelines; The first generation module is used to generate multiple random leakage source points in the leakage area according to a genetic algorithm; A module is established to create a leakage diffusion model for the buried oil pipeline; The simulation module is used to simulate the pollution diffusion of the random leakage source point according to the leakage diffusion model, so as to obtain the fitness of the random leakage source point; The first determining module is used to determine the predicted leakage point from the plurality of random leakage source points based on the fitness of the random leakage source points; The second generation module is used to generate a set of candidate leak points for the buried oil pipeline by using the Markov chain Monte Carlo algorithm, based on the predicted leak points, and through an adaptive step size constraint mechanism. The first processing module is used to perform probability sampling processing on the candidate leak point set to obtain the leak search space of the buried oil pipeline. The second processing module is used to dynamically track candidate leak points in the leak search space based on a particle swarm dynamic iteration mechanism in order to determine the coordinates of the leak source of the buried oil pipeline.

9. A leak source locating device for a buried oil pipeline, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

Images