An oil and gas pipeline rerouting route optimization method, device and medium

Abstract

The application discloses an oil and gas pipeline rerouting optimization method and device, and a medium, relates to the technical field of oil and gas pipeline rerouting planning and design, and comprises the following steps: segmenting an active oil and gas pipeline to obtain a plurality of pipe sections, determining a to-be-rerouted pipe section needing to be rerouted based on operation data of the pipe sections, taking a starting point and an ending point of the to-be-rerouted pipe section as input, solving a rerouting optimization model to obtain a rerouting optimization scheme, and the objective function of the rerouting optimization model is the sum of a minimum suitable laying comprehensive evaluation value and a pipeline rerouting construction cost conversion value, the constraint conditions include pipeline node position constraints, pipeline node quantity constraints, pipeline turning angle constraints and pipeline node layout feasibility constraints. The application can automatically determine the optimal rerouting optimization scheme, effectively avoids problems, such as large pipeline routing layout engineering quantity, high construction cost and no avoidance of laying area risks, caused by artificial decision uncertainty.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of oil and gas pipeline rerouting planning and design, and particularly relates to an oil and gas pipeline rerouting optimization method, device and medium. BACKGROUND

[0002] In the process of laying a submarine pipeline, in the face of complex geological conditions and deep sea environment, when a service oil and gas pipeline has a problem, it is more economical and feasible to directly reroute the service oil and gas pipeline than to build a new oil and gas pipeline. However, at present, rerouting of the service oil and gas pipeline is mostly completed by manual experience, and there are problems such as large pipeline routing layout engineering quantity, high construction cost, and no risk avoidance of laying area due to uncertainty of manual decision. SUMMARY

[0003] The purpose of the present application is to provide an oil and gas pipeline rerouting optimization method, device and medium, which can effectively avoid problems such as large pipeline routing layout engineering quantity, high construction cost, and no risk avoidance of laying area due to uncertainty of manual decision.

[0004] To achieve the above purpose, the present application provides the following solutions.

[0005] In a first aspect, the present application provides an oil and gas pipeline rerouting optimization method, which comprises:

[0006] segmenting a service oil and gas pipeline to obtain a plurality of pipe segments, for each pipe segment, determining whether the pipe segment needs to be rerouted based on operation data of the pipe segment, and recording a pipe segment that needs to be rerouted as a pipe segment to be rerouted;

[0007] for each pipe segment to be rerouted, taking a starting point and an ending point of the pipe segment to be rerouted as input, solving a rerouting optimization model to obtain a rerouting optimization scheme; a target function of the rerouting optimization model is to minimize a sum of a suitable laying comprehensive evaluation value and a pipeline rerouting construction cost conversion value, and constraint conditions include pipeline node position constraints, pipeline node quantity constraints, pipeline turning angle constraints, and pipeline node layout feasibility constraints; the rerouting optimization scheme includes a position of each pipeline node, a connection relationship between pipeline nodes, and a pipeline specification between two connected pipeline nodes, and the pipeline nodes include the starting point, a routing node between the starting point and the ending point, and the ending point.

[0008] In a second aspect, the present application provides a computer device, which comprises a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor executes the computer program to implement the above-mentioned oil and gas pipeline rerouting optimization method.

[0009] In a third aspect, the present application provides a computer readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the oil and gas pipeline rerouting optimization method described above.

[0010] According to the specific embodiments provided in the present application, the present application has the following technical effects:

[0011] The present application provides an oil and gas pipeline rerouting optimization method, device and medium, which segments the active oil and gas pipeline to obtain a plurality of pipe sections, determines whether each pipe section needs to be rerouted based on the operation data of the pipe section, and records the pipe sections that need to be rerouted as to-be-rerouted pipe sections, and for each to-be-rerouted pipe section, takes the starting point and the end point of the to-be-rerouted pipe section as input, solves the rerouting optimization model to obtain a rerouting optimization scheme, the objective function of the rerouting optimization model is to minimize the sum of the optimal laying comprehensive evaluation value and the pipeline rerouting construction cost conversion value, the constraint conditions include pipeline node position constraint, pipeline node number constraint, pipeline turning angle constraint and pipeline node layout feasibility constraint, without human intervention, and by designing the objective function and constraint conditions of the rerouting optimization model, the optimal rerouting optimization scheme can be automatically determined, effectively avoiding the problems of large pipeline layout engineering quantity, high construction cost and no avoidance of laying area risk caused by human decision uncertainty, and assisting the oilfield gathering pipeline network manager to obtain the optimal rerouting optimization scheme for optimal laying, and realizing cost reduction and benefit increase optimization design. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0013] Figure 1 An application environment diagram of an oil and gas pipeline rerouting optimization method provided for Embodiment 1 of the present application.

[0014] Figure 2 A flowchart of an oil and gas pipeline rerouting optimization method provided for Embodiment 1 of the present application.

[0015] Figure 3 A technical route diagram of an oil and gas pipeline rerouting optimization method provided for Embodiment 1 of the present application.

[0016] Figure 4 A method flowchart of decision tree method 1 provided for Embodiment 1 of the present application.

[0017] Figure 5 Method flow chart of the decision tree method 2 provided for Embodiment 1 of the present application.

[0018] Figure 6 Result schematic diagram of the pipeline suitable laying comprehensive evaluation method provided for Embodiment 1 of the present application.

[0019] Figure 7 Method flow chart of the improved grey wolf algorithm provided for Embodiment 1 of the present application.

[0020] Figure 8 Schematic diagram of the rank mean value column chart provided for Embodiment 1 of the present application.

[0021] Figure 9 Effect comparison diagram of the artificial decision and the improved grey wolf algorithm provided for Embodiment 1 of the present application.

[0022] Figure 10 Structure schematic diagram of a computer device provided for Embodiment 2 of the present application. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the present application will be described clearly and completely below with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0024] Embodiment 1.

[0025] The oil and gas pipeline rerouting optimization method provided by the embodiments of the present application can be applied to an application environment as shown in the figure. Figure 1 As shown in the figure, the terminal communicates with the server through the network. The data storage system can store the data required to be processed by the server. The data storage system can be separately arranged, or integrated on the server, or placed on the cloud or other servers. The terminal can send a rerouting request to be processed to the server. After receiving the rerouting request to be processed, the server segments the active oil and gas pipeline to obtain a plurality of pipe sections. For each pipe section, it is determined whether the pipe section needs to be rerouted based on the operation data of the pipe section, and the pipe section that needs to be rerouted is recorded as a pipe section to be rerouted. For each pipe section to be rerouted, the starting point and the ending point of the pipe section to be rerouted are taken as inputs to solve the rerouting optimization model to obtain a rerouting optimization scheme. The server can feed back the rerouting result of the rerouting optimization scheme of each pipe section to be rerouted to the terminal.

[0026] In addition, in some embodiments, the oil and gas pipeline rerouting optimization method can also be implemented by a server or a terminal alone, such as being processed by a terminal directly for a to-be-processed rerouting request, or being processed by a server for a to-be-processed rerouting request obtained from a data storage system.

[0027] In one exemplary embodiment, as shown in Figure 2 , an oil and gas pipeline rerouting optimization method is provided, which is executed by a computer device, specifically, can be executed by a terminal or a server alone or by a terminal and a server together. In the embodiments of the present application, the method is applied to a server in Figure 1 , and includes the following steps.

[0028] Step S1: Segmenting active oil and gas pipelines to obtain a plurality of pipe segments. For each pipe segment, determining whether the pipe segment needs to be rerouted based on operation data of the pipe segment, and recording a pipe segment that needs to be rerouted as a to-be-rerouted pipe segment.

[0029] Step S2: For each to-be-rerouted pipe segment, solving a rerouting optimization model with a starting point and an ending point of the to-be-rerouted pipe segment as inputs to obtain a rerouting optimization scheme. A target function of the rerouting optimization model is to minimize a sum of a suitable laying comprehensive evaluation value and a pipeline rerouting construction cost conversion value. Constraint conditions include a pipeline node position constraint, a pipeline node quantity constraint, a pipeline turning angle constraint, and a pipeline node layout feasibility constraint. The rerouting optimization scheme includes a position of each pipeline node, a connection relationship between pipeline nodes, and a pipeline specification between two connected pipeline nodes. The pipeline nodes include the starting point, a routing node between the starting point and the ending point, and the ending point.

[0030] By implementing the above steps S1 to S2, in the present embodiment, the to-be-rerouted pipe segments that need to be rerouted are determined through operation data of each pipe segment in active oil and gas pipelines, and the rerouting optimization scheme of each to-be-rerouted pipe segment is determined by solving the rerouting optimization model, without human intervention. By designing the target function and the constraint conditions of the rerouting optimization model, the optimal rerouting optimization scheme can be automatically determined, effectively avoiding problems such as a large amount of pipeline layout engineering, high construction cost, and no avoidance of laying area risks caused by human decision uncertainty.

[0031] The oil and gas pipeline rerouting optimization method of the embodiment is used to find the optimal oil and gas pipeline (which can be a submarine oil and gas pipeline or other oil and gas pipeline) rerouting layout and determine the optimal rerouting optimization scheme of each pipeline segment to be rerouted of the oil and gas pipeline by using the active pipeline rerouting evaluation method, the pipeline suitable laying comprehensive evaluation method, and the hybrid grey wolf-goat algorithm (i.e., the improved grey wolf algorithm). By using this method, the pipeline laying path can be optimized, the oil and gas pipeline after rerouting can be ensured to be in a relatively stable area, so as to reduce the laying difficulty, reduce the construction cost, and avoid the problems of excessive engineering quantity caused by manual decision and failure to avoid laying area risks.

[0032] Hereinafter, the oil and gas pipeline rerouting optimization method of the embodiment will be described in detail. Figure 3 The oil and gas pipeline rerouting optimization method of the embodiment includes the following steps.

[0033] (1) Rerouting evaluation.

[0034] In the embodiment, the active oil and gas pipeline is segmented to obtain a plurality of pipeline segments. For each pipeline segment, whether the pipeline segment needs to be rerouted is determined based on the operation data of the pipeline segment, and the pipeline segment that needs to be rerouted is recorded as a pipeline segment to be rerouted.

[0035] In the embodiment, the active pipeline rerouting evaluation method is used to evaluate each pipeline segment of the active oil and gas pipeline, and the pipeline segment with the evaluation result of "suggested to be rerouted" is recorded as a pipeline segment to be rerouted for rerouting and new construction. The active pipeline rerouting evaluation method uses the pipeline suggested rerouting non-parametric test method. The process of the active pipeline rerouting evaluation method includes: processing the collected operation data of the pipeline segment by using the decision tree method, and then using the non-parametric test method to determine whether the pipeline segment needs to be rerouted. Specifically, the actual values of three types of operation data, i.e., the number of corrosion points, the number of historical leaks, and the number of third-party damage repairs, are collected, and each type of operation data is taken as a root node to branch. The actual value of the operation data is compared with the preset value under the ideal state of the pipeline segment. If the actual value is less than or equal to the preset value, the branch output is 0, otherwise, the branch output is the actual value, and the first pipeline data is obtained, as shown in Figure 4 Meanwhile, any type of operation data is taken as a root node, and branching is continued according to whether there is a problem corresponding to the type of operation data. The number of branches marked as "yes" is counted to obtain the second pipeline data, as shown in Figure 5 After obtaining the first pipeline data and the second pipeline data according to the above method, the Friedman test method is used to test the first pipeline data and the second pipeline data to obtain the chi-square value, The rank average values of the pipe sections and the rank average values of each pipe section are obtained based on the Friedman test method. The rank average value column chart is drawn by using the Bonferroni-Dunn test method, the threshold values when the significance levels are 5% and 10% are calculated, the threshold value is the sum of the minimum rank average value (i.e. the minimum value of the rank average values of each pipe section) and the critical difference value when the significance levels are 5% and 10%, and the pipe section with the rank average value greater than the threshold value when the significance level is 5% is recommended to be relocated.

[0036] The calculation formula of the critical difference value is:

[0037] ;

[0038] Wherein, is the critical difference value when the significance level is ; is the critical value when the significance level is , the critical value when the significance level is is determined according to the number of pipe evaluation methods and the number of pipe sections of the active oil and gas pipeline . is the number of pipe evaluation methods, since the first pipe data and the second pipe data are obtained by using the two decision tree methods in the embodiment, therefore, is 2; is the number of pipe sections of the active oil and gas pipeline.

[0039] Since the artificial decision is strongly subjective and is easily affected by artificial experience, it is impossible to objectively evaluate whether the pipe section needs to be relocated, the embodiment adopts the non-parametric test method to judge whether the pipe section needs to be relocated, which can avoid the interference of artificial subjective consciousness and improve the accuracy of pipe evaluation.

[0040] At this time, in the embodiment, the operation data of the pipe section includes the actual corrosion point number, the actual historical leakage times and the actual third-party damage repair times of the pipe section, at this time, for each pipe section, whether the pipe section needs to be relocated is determined based on the operation data of the pipe section, which specifically includes the following steps.

[0041] (1) For each pipe segment, if the actual corrosion point number is greater than the preset corrosion point number, set the corrosion point number equal to the actual corrosion point number, otherwise, set the corrosion point number equal to 0; if the actual historical leakage number is greater than the preset historical leakage number, set the historical leakage number equal to the actual historical leakage number, otherwise, set the historical leakage number equal to 0; if the actual third-party damage and maintenance number is greater than the preset third-party damage and maintenance number, set the third-party damage and maintenance number equal to the actual third-party damage and maintenance number, otherwise, set the third-party damage and maintenance number equal to 0; the corrosion point number, the historical leakage number and the third-party damage and maintenance number of all pipe segments are combined to form the first pipeline data.

[0042] (2) For each pipe segment, if the corrosion point number is greater than 0, set the corrosion judgment result to yes, otherwise, set the corrosion judgment result to no; if the historical leakage number is greater than 0, set the leakage judgment result to yes, otherwise, set the leakage judgment result to no; if the third-party damage and maintenance number is greater than 0, set the third-party damage judgment result to yes, otherwise, set the third-party damage judgment result to no; the corrosion judgment result, the leakage judgment result and the third-party damage judgment result of all pipe segments are combined to form the second pipeline data.

[0043] (3) The Friedman test method is used to test the first pipeline data and the second pipeline data, and the rank average value of each pipe segment is obtained.

[0044] (4) The rank average value of each pipe segment is taken as input, and the Bonferroni-Dunn test method is used to draw a rank average value bar chart.

[0045] (5) Based on the rank average value bar chart, it is determined whether each pipe segment needs to be rerouted.

[0046] (II) Rerouting route optimization model construction and solution.

[0047] For each pipe segment to be rerouted, the starting point and the ending point of the pipe segment to be rerouted are taken as input, the rerouting route optimization model is solved, and a rerouting route optimization scheme is obtained. The objective function of the rerouting route optimization model is to minimize the sum of the suitable laying comprehensive evaluation value and the pipeline rerouting construction cost conversion value. The constraint conditions include pipeline node position constraint, pipeline node number constraint, pipeline turning angle constraint and pipeline node layout feasibility constraint. The rerouting route optimization scheme includes the position of each pipeline node, the connection relationship between pipeline nodes, and the pipeline specification between the two connected pipeline nodes. The pipeline nodes include the starting point, the route nodes (need to be replanned) located between the starting point and the ending point, and the ending point.

[0048] The embodiment takes the minimum sum value of the comprehensive evaluation value of suitable laying and the converted value of pipeline reline construction cost as the objective function, establishes the reline route optimization model of the oil and gas pipeline, and considers the evaluation results of the reline evaluation method of the existing pipeline and the comprehensive evaluation results of the pipeline suitable laying comprehensive evaluation method in the reline route optimization model.

[0049] The objective function is:

[0050] ;

[0051] Wherein, is the sum value of the comprehensive evaluation value of suitable laying and the converted value of pipeline reline construction cost; is a pipeline node set, including the starting point, the ending point and the route nodes needed to pass from the starting point to the ending point, and the position of each route node needs to be determined in the embodiment; is a pipeline specification set; is a pipeline node and a pipeline node The comprehensive evaluation value of suitable laying of the pipeline between the pipeline node and the pipeline node is a constant between 0 and 1, and is dimensionless. is the converted value of pipeline reline construction cost when the pipeline specification is selected between the pipeline node and the pipeline node

[0052] The comprehensive evaluation value of suitable laying of the pipeline between the pipeline node and the pipeline node is determined based on the comprehensive evaluation value set of the pipeline laying area corresponding to the pipeline to be reline, and the comprehensive evaluation value set is obtained by comprehensively evaluating the pipeline laying area based on the soil corrosion condition, the geological disaster condition and the elevation of each grid in the pipeline laying area by using the pipeline suitable laying comprehensive evaluation method. The comprehensive evaluation value set includes the comprehensive evaluation value of each grid in the pipeline laying area. At this time, the comprehensive evaluation value of suitable laying of the pipeline between the pipeline node and the pipeline node is the maximum value of the comprehensive evaluation values of all the grids of the pipeline passing between the pipeline node and the pipeline node .

[0053] The embodiment utilizes the pipeline suitable laying comprehensive evaluation method to perform comprehensive evaluation on a pipeline laying area (including an area of a to-be-realigned pipe section, and the size and shape of which are defined by a user), to generate a comprehensive evaluation value set and a comprehensive evaluation result set, and subsequently, a grid with a comprehensive evaluation value less than a suitable laying comprehensive evaluation permission value is taken as an available grid, and a pipeline node is allowed to be arranged. The pipeline suitable laying comprehensive evaluation method includes the following steps. Firstly, the pipeline laying area is divided into a plurality of grids, and the number and size of the grids are determined according to the start point and end point of the to-be-realigned pipe section and the distribution of surrounding obstacles. For example, a 30*30m grid size can be selected to divide the pipeline laying area. Secondly, a factor set and a membership function of each influencing factor are established. Specifically, the factor set is established from three influencing factors of soil corrosion, geological disasters and elevation that are most concerned by decision-makers in pipeline laying planning wherein is the soil corrosion factor, is the geological disaster factor, is the elevation factor, and for each influencing factor, a membership function of the influencing factor is established. Finally, each grid is comprehensively evaluated by using the membership function of each influencing factor, and a comprehensive evaluation value set and a comprehensive evaluation result set are established. Specifically, for each grid, the membership function value of each influencing factor is calculated by using the membership function of each influencing factor, the membership function values of the three influencing factors are averaged to obtain the comprehensive evaluation value of the grid, and meanwhile, the evaluation result of each influencing factor is determined based on the membership function value of each influencing factor, the evaluation results of the three influencing factors are combined to obtain the comprehensive evaluation result of the grid, all the comprehensive evaluation values of the grids are combined to form the comprehensive evaluation value set, and all the comprehensive evaluation results of the grids are combined to form the comprehensive evaluation result set, as shown in Figure 6 .

[0054] For the soil corrosion factor, the membership function is established as follows:

[0055] ;

[0056] wherein is the membership function value of the soil corrosion factor; is the PH value of the grid; , , , The values of a, b, c and d can be set as 5, 6, 8 and 9 respectively. The pH value of any grid in the pipeline laying area is brought into the membership function of the soil corrosion factor. When the output membership function value is 0, it indicates that the grid belongs to “weakly acidic or weakly alkaline soil corrosion”. When the output membership function value is between 0 and 1, it indicates that the grid belongs to “moderately acidic or moderately alkaline soil corrosion”. When the output membership function value is 1, it indicates that the grid belongs to “strongly acidic or strongly alkaline soil corrosion”, and the evaluation result of the soil corrosion factor is obtained.

[0057] For the geological disaster factor, the membership function is established as:

[0058] ;

[0059] wherein, is the membership function value of the geological disaster factor; is the number of geological disaster history of the grid (i.e. the number of past geological disasters); , The values of a and b can be set as 1 and 3 respectively. The number of geological disaster history of any grid in the pipeline laying area is brought into the membership function of the geological disaster factor. When the output membership function value is 0, it indicates that the grid belongs to “not prone to geological disasters”. When the output membership function value is between 0 and 1, it indicates that the grid belongs to “relatively prone to geological disasters”. When the output membership function value is 1, it indicates that the grid belongs to “prone to geological disasters”, and the evaluation result of the geological disaster factor is obtained.

[0060] For the elevation factor, the membership function is established as:

[0061] ;

[0062] wherein, is the membership function value of the elevation factor; is the elevation difference of the grid (i.e. the absolute value of the difference between the elevation of the grid and the elevation of any adjacent grid of the grid); , The values of a and b can be set as 20 and 50 respectively. The elevation difference of any grid in the pipeline laying area is brought into the membership function of the elevation factor. When the output membership function value is 0, it indicates that the grid belongs to “moderate elevation”. When the output membership function value is between 0 and 1, it indicates that the grid belongs to “elevation is too high or too low”. When the output membership function value is 1, it indicates that the grid belongs to “elevation is too high or too low”, and the evaluation result of the elevation factor is obtained.

[0063] When the total budget of pipeline construction is sufficient, the pipeline relocation construction cost conversion value is between 0 and 1, and when the total budget value is constant, the pipeline relocation construction cost conversion value gradually decreases with the decrease of the pipeline relocation construction cost. At the same time, the suitable laying comprehensive evaluation value is also between 0 and 1, and when the membership function value of each influencing factor is small, it means that it is more suitable to lay the pipeline. Therefore, the smaller the sum of the suitable laying comprehensive evaluation value and the pipeline relocation construction cost conversion value, the higher the comprehensive performance ratio of the new pipeline, and the more reasonable and optimized the construction scheme. Therefore, this method can effectively evaluate the advantages and disadvantages of each construction scheme and select the most suitable construction scheme.

[0064] The calculation formula of the pipeline relocation construction cost conversion value is:

[0065] ;

[0066] wherein, is a binary variable representing whether the pipeline node and the pipeline node are connected, if the pipeline node and the pipeline node are connected, then is 1, otherwise, is 0, based on which the connection relationship between the pipeline nodes is determined; is a binary variable representing whether the pipeline between the pipeline node and the pipeline node selects the pipeline specification , if the pipeline between the pipeline node and the pipeline node selects the pipeline specification , then is 1, otherwise, is 0, based on which the pipeline specification of the pipeline between the two connected pipeline nodes is determined; is the length of the pipeline between the pipeline node and the pipeline node ; is the material procurement cost when the pipeline between the pipeline node and the pipeline node selects the pipeline specification ; is the labor cost when the pipeline between the pipeline node and the pipeline node selects the pipeline specification ; is a cost conversion coefficient for normalizing the pipeline relocation construction cost .

[0067] The length of the pipeline is calculated by the following formula:

[0068] ;

[0069] wherein, are the x coordinate, y coordinate and z coordinate of the pipeline node respectively; are the x coordinate, y coordinate and z coordinate of the pipeline node respectively.

[0070] In the calculation of the material procurement cost, the pipe cost is mainly considered, and the pipe specification is selected when the material procurement cost of the pipeline is calculated.

[0071] ;

[0072] wherein, is the pi; is the pipe material cost fitting coefficient when the pipeline specification is selected between the pipeline node and the pipeline node ; is the pipe wall thickness when the pipeline specification is selected between the pipeline node and the pipeline node ; is the pipe diameter when the pipeline specification is selected between the pipeline node and the pipeline node , and the pipe diameter is consistent with the original pipe diameter in the active oil and gas pipeline.

[0073] The calculation formula of the cost conversion coefficient is as follows:

[0074] ;

[0075] wherein, is the total budget of the construction pipeline cost.

[0076] The pipeline node position constraint is as follows:

[0077] ;

[0078] ;

[0079] wherein, is the suitable laying comprehensive evaluation value of the pipeline between the pipeline node and the pipeline node ; is the suitable laying comprehensive evaluation allowable value. is a set of pipeline nodes; is a set of routing nodes in the pipe segment to be re-routed; is an empty set.

[0080] The pipeline node number constraint is:

[0081] ;

[0082] wherein, is the minimum value of the number of pipeline nodes; is a set of pipeline nodes in the pipe segment to be re-routed; is the maximum value of the number of pipeline nodes.

[0083] The pipeline turning angle constraint is:

[0084] ;

[0085] wherein, is a binary variable representing whether the pipeline node is connected to the pipeline node , if the pipeline node is connected to the pipeline node , then is 1, otherwise, is 0; is a binary variable representing whether the pipeline node is connected to the pipeline node , if the pipeline node is connected to the pipeline node , then is 1, otherwise, is 0; is the turning angle (i.e. the included angle) between the pipeline between the pipeline node and the pipeline node and the pipeline between the pipeline node and the pipeline node , in °; is the maximum value of the turning angle, in °.

[0086] The pipeline node layout feasibility constraint is:

[0087] ;

[0088] wherein, is a modulo operation; is the distance between the pipeline node The number of intersections of the rays drawn from the pipeline node to the obstacle is determined, the rays being rays drawn from the pipeline node to the obstacle, if the number of intersections is odd, it is proved that the pipeline node and the pipe section have an overlapping area at the obstacle, and if the number of intersections is even, they do not overlap.

[0089] After the rerouting optimization model is established, the embodiment applies a hybrid grey wolf-goat algorithm to solve the rerouting optimization model to obtain an optimal suitable-laying rerouting optimization scheme.

[0090] In the embodiment, the rerouting optimization model is solved, specifically including: solving the rerouting optimization model by using an improved grey wolf algorithm, wherein the improved grey wolf algorithm is a grey wolf algorithm obtained by improving a grey wolf position updating formula of the grey wolf algorithm.

[0091] The embodiment adopts a new type of swarm intelligence optimization algorithm: a hybrid grey wolf-goat algorithm, which combines the advantages of the grey wolf algorithm and the goat algorithm, and effectively improves the global search ability and local mining ability of the algorithm.

[0092] The grey wolf algorithm is widely used in path planning, feature selection and parameter optimization and other fields due to its good self-adaptive adjustment mode, group cooperation mechanism and fast convergence. However, due to its specific mechanism, the grey wolf algorithm has some limitations in practical application: the algorithm is prone to fall into a local optimal solution in the solving process, and it is difficult to break through the current local optimal constraint and explore the global optimal solution; the algorithm relies on the guidance of the leader wolf for search and development, which makes the algorithm limited in search range when facing complex problems due to the limitations of the leader wolf; the generation of core parameters of the algorithm highly depends on the randomness of random numbers, and this uncertainty brings potential optimization efficiency problems. In order to solve these limitations, an innovative hybrid grey wolf-goat algorithm is proposed, which takes the grey wolf algorithm as the main framework, skillfully integrates the jumping strategy and avoidance of parasitic ideas of the goat algorithm, and adds a jumping and avoidance vector to the position updating formula of the grey wolf, thereby effectively solving the problem that the grey wolf algorithm is difficult to jump out of the local optimal solution; the goat group orientation operator is introduced to adjust the weight of the leader wolf in the grey wolf algorithm, so that the algorithm pays more attention to the exploration ability of the wolf in the early stage of iteration, and focuses on the improvement of the development ability of the wolf in the later stage; the goat social cooperation operator is introduced to effectively improve the uncertainty problem of the grey wolf algorithm in the core parameter generation process which depends on random numbers. Through these optimization mechanisms, the robustness of the hybrid grey wolf-goat algorithm is significantly enhanced, which can better adapt to complex environments and improve its stability, thereby showing stronger solving ability in variable optimization problems.

[0093] ​​After incorporating the ideas of the goat algorithm, the improved gray wolf algorithm's gray wolf position update formula is as follows:

[0094] ;

[0095] in, For the first During the nth iteration The position vectors of individual gray wolves; for The weight of wolves; for The target position vector guided by the wolf; for The weight of wolves; for The target position vector guided by the wolf; for The weight of wolves; for The target position vector guided by the wolf; For the part where the goat jumps, take values. As the trigger condition, if the first random number Less than the jump probability This will trigger a jump. equal to jump vector ,otherwise, Equal to 0, ,Right now To obey Uniformly distributed random numbers, , This represents the current iteration number. This represents the maximum number of iterations. The values ​​for the parasite avoidance portion of goats are taken. As a trigger condition, if the second random number Less than the probability of infection This will trigger an avoidance mechanism. Equal to avoidance vector ,otherwise, Equal to 0, ,Right now To obey Uniformly distributed random numbers, .

[0096] Drawing inspiration from the leadership mechanisms of goat groups, a goat group orientation operator is introduced to simulate changes in goat leadership and dynamically adjust [the strategy / method]. The weight of the wolf is adjusted adaptively with iteration, while emphasizing its importance in the early stages of iteration. Wolves enhance their exploration capabilities and focus on later stages. If the wolf enhances its development capabilities, the formula for calculating its weight is:

[0097] ;

[0098] in, For the first The first-stage dependency parameters in the next iteration are based on the current iteration number. The maximum number of iterations is determined; To obey Uniformly distributed random numbers; For the first The second-stage dependency parameter in the next iteration is based on the current iteration number. The maximum number of iterations is determined; For the first The third-stage dependency parameter in the next iteration is based on the current iteration number. The maximum number of iterations is determined.

[0099] ;

[0100] ;

[0101] ;

[0102] in, This represents the maximum number of iterations.

[0103] The formula for calculating the target position vector is:

[0104] ;

[0105] in, for The position vector of the wolf (the optimal solution, i.e., the gray wolf with the smallest fitness value) guides the group to move towards the global optimum. This is the encirclement step size coefficient; For the first Random search parameters during the next iteration; For the first The position vectors of individual gray wolves; for The position vector of the wolf (the suboptimal solution, i.e., the gray wolf with the second smallest fitness value) is used to help explore potential optimal areas; for The position vector of the wolf (the third best solution, i.e., the gray wolf individual with the third smallest fitness value) is used to maintain the diversity of the population.

[0106] The formula for calculating the encirclement step size coefficient is:

[0107] ;

[0108] in, The convergence factor decreases linearly from 2 to 0; It is the third random number.

[0109] Referring to the social behavior of goat groups, a goat social collaboration operator is introduced. This operator automatically adjusts the random search parameters based on the group dispersion and goat social behavior. When the group dispersion is high, the random search parameters increase; when the group is clustered (i.e., the group dispersion is low), the random search parameters decrease. The random search parameters are dynamically adjusted random exploration weights that control the random perturbation component in the gray wolf algorithm. The formula for calculating the random search parameters is:

[0110] ;

[0111] in, The base value is set to a fixed value of 2 to provide a benchmark adjustment scale for the exploration weights of the Grey Wolf algorithm. As the first dispersion state adjustment factor, based on the first Group dispersion at the next iteration Determine the appropriate magnification / reduction factor based on the degree of dispersion; As the second dispersion state adjustment factor, based on the first Group dispersion at the next iteration Determine the appropriate magnification / reduction factor based on the degree of dispersion; It is the hyperbolic tangent function, and its range is... To avoid parameter mutations; Historical dependency length is used to improve the performance of goat social behavior. Essentially, it introduces the "experience-based learning" mechanism from swarm intelligence into algorithm design, by adjusting... The sensitivity of the algorithm to historical information can be controlled, and the value is generally set to 3-5. For the first Group dispersion at the next iteration; For the first Population dispersion at the next iteration.

[0112] The range of values ​​for population dispersion is: Quantify the distribution of the group. Indicates a fully aggregated state. The formula for calculating the population dispersion, which represents a completely dispersed state and quantifies the spatial distribution of a population, is:

[0113] ;

[0114] in, To normalize the dispersion, The number of individual gray wolves in the pack. For the first The position vectors of individual gray wolves. Let be the position vector of the group's centroid, which is equal to the average position vector of each individual gray wolf. For the first The position vectors of individual gray wolves. To find the minimum value, prevent the denominator from being 0; As a dimensional adjustment factor, The dimensions of the problem.

[0115] ;

[0116] ;

[0117] in, For the first Population dispersion at the next iteration.

[0118] Referring to the goat jumping and parasite avoidance strategy of the goat algorithm, the goat jumping and parasite avoidance strategy of the goat algorithm is embedded into the gray wolf algorithm. The jumping and avoidance mechanisms can be triggered simultaneously, and the two mechanisms are executed in parallel to form a composite search strategy of "approaching the high-quality area + moving away from the low-quality area". The specific operation is as follows.

[0119] Update the goat memory matrix using an elite retention strategy:

[0120] ;

[0121] in, For goat memory matrix; for The wolf's position vector is the globally optimal solution that is directly preserved; The average of the position vectors of the top ten gray wolf individuals (sorted in ascending order of fitness value); In order to be in Add a randomly perturbed position vector to the wolf's position vector. It is a random number, and its value range is (0,1). This is the upper bound of the algorithm's search space. This is the lower bound of the algorithm's search space.

[0122] Design a directional random jump operator based on the goat jump strategy: unlike random walks which randomly select a direction, the jump direction is determined by the goat's memory matrix. The guide, with its memory-oriented nature, can effectively improve global search capabilities. After updating the basic location of the Grey Wolf, a jump option can be added to prioritize guiding users to historically high-quality areas.

[0123] ;

[0124] wherein, is a jump vector; is a jump step, subject to a Gaussian distribution, the jump step is designed as , standard deviation ; is a position vector of any one wolf individual in the goat memory matrix.

[0125] A repulsive field driving operator based on the goat's parasite avoidance strategy is designed: gradually attenuated according to an exponential law, focusing on local development.

[0126] ;

[0127] wherein, is an avoidance vector; is an avoidance strength, the basic avoidance strength is set to 0.5, the overall avoidance strength ranges from 0.5 to 0 exponentially attenuated, is a maximum iteration number; is a randomly selected repulsion target, the repulsion target is a non-goat memory matrix individual, i.e., a position vector of any one wolf individual in the goat memory matrix.

[0128] This embodiment further utilizes boundary to limit the position vector of the wolf individual:

[0129] ;

[0130] wherein, is the final position vector of the wolf individual.

[0131] The objective of the hybrid grey wolf-goat algorithm is to combine the advantages of the two algorithms, and the two algorithms work together, the global search ability and the local development ability are greatly enhanced, the grey wolf algorithm is responsible for rough global search, and the goat algorithm performs fine local development, and the robustness of the algorithm is better under the double strategy.

[0132] As shown in Figure 7 , the process of the hybrid grey wolf-goat algorithm is as follows.

[0133] (1) initialization to generate an initial grey wolf population and parameters of the hybrid grey wolf-goat algorithm.

[0134] The initial grey wolf population of the grey wolf algorithm is initialized, and the initial grey wolf population includes multiple wolf individuals, each wolf individual represents a layout scheme (i.e., a line routing optimization scheme), and in this embodiment, the grey wolf individual is initialized by random assignment, and the initial grey wolf population is obtained.

[0135] The parameters for initializing the two algorithms mainly include the number of individual gray wolves and the maximum number of iterations for the gray wolf algorithm, and the jump probability, infection probability, and avoidance strength for the goat algorithm.

[0136] Each gray wolf individual in this embodiment carries a layout scheme including the position of the pipe nodes, the connection relationship of the pipe nodes, and the pipe specifications of the pipe between two connected pipe nodes. In practical applications, the position of the pipe nodes can be encoded using real numbers, and the connection relationship of the pipe nodes and the pipe specifications of the pipe between two connected pipe nodes can be encoded using integers to obtain the gray wolf individual.

[0137] (2) For the randomly generated initial gray wolf population, calculate the fitness value for each gray wolf individual, and select the three gray wolf individuals with the best (i.e., the smallest) fitness values ​​as the first three individuals. Wolves, while simultaneously constructing a goat memory matrix.

[0138] (3) Calculate the population dispersion, and then dynamically adjust the random search parameters. The values ​​of the random search parameters are used to calculate... The weight of wolves.

[0139] (4) Update the position vector of individual gray wolves according to the gray wolf position update formula. During the position update process, there is a probability of triggering the goat jump mechanism and the parasite avoidance mechanism. After the position is updated, perform boundary processing on the position vector of gray wolf individuals that exceed the boundary position.

[0140] (5) Based on the new position vectors obtained in steps (2) to (4), obtain the updated gray wolf population, calculate its fitness value, and continue updating. The wolf's position vector is updated, and the goat's memory matrix is ​​updated simultaneously. The iteration termination condition is checked; if satisfied, the optimal solution is output, including... The algorithm returns the wolf's fitness value and position vector; if not, it re-enters the loop until the iteration termination condition is met, and then outputs the optimal solution.

[0141] The iteration termination condition can be: reaching the maximum number of iterations or during two iterations. The rate of change of the wolf's fitness value (i.e., in two iterations) The absolute value of the difference in fitness values ​​between wolves and the previous iteration The ratio of the wolf's fitness value to its fitness value is less than a threshold, which is typically set to 10. -8 .

[0142] In this embodiment, the improved Grey Wolf algorithm is used to solve the route optimization model, specifically including the following steps.

[0143] (1) randomly generate an initial grey wolf population, the initial grey wolf population comprising a plurality of grey wolf individuals, a position vector of the grey wolf individual being an improved route optimization scheme satisfying a constraint condition.

[0144] (2) calculate an adaptability value of each grey wolf individual in the initial grey wolf population, determine wolves, wolves and wolves based on the adaptability value of each grey wolf individual in the initial grey wolf population, the adaptability value being a value of a target function.

[0145] (3) based on the wolves, wolves and wolves in the initial grey wolf population, update the position vector of each grey wolf individual in the initial grey wolf population by using a grey wolf position updating formula, obtain an updated grey wolf population, calculate an adaptability value of each grey wolf individual in the updated grey wolf population, determine wolves, wolves and wolves based on the adaptability value of each grey wolf individual in the updated grey wolf population.

[0146] (4) determine whether an iteration termination condition is reached.

[0147] (5) if yes, select the position vector of the wolf in the updated grey wolf population as the improved route optimization scheme.

[0148] (6) if no, take the updated grey wolf population as an initial grey wolf population of the next iteration, and return to the step of calculating the adaptability value of each grey wolf individual in the initial grey wolf population.

[0149] The embodiment relates to an oil and gas pipeline improved route optimization method, which comprises the following steps: evaluating an active oil and gas pipeline according to an active pipeline improved line evaluation method, improving and newly building a pipeline section with an evaluation result of "suggested improved line", evaluating a pipeline laying area by using a pipeline suitable laying comprehensive evaluation method, taking a grid with a comprehensive evaluation value less than a suitable laying comprehensive evaluation permission value as an available grid, allowing a pipeline node to be arranged, finally establishing an improved route optimization model, solving the improved route optimization model by using a hybrid grey wolf-goat algorithm, and obtaining an optimal suitable laying improved route optimization scheme. The method can effectively avoid problems such as a large pipeline route layout engineering quantity, high construction cost and no laying area risk avoidance caused by artificial decision uncertainty, is suitable for route planning and design of an active oil and gas pipeline, can optimize and design a pipeline improved route, makes the pipeline be laid in a relatively reliable area, avoids pipeline failure accidents, and realizes cost reduction and efficiency improvement.

[0150] The performance of the oil and gas pipeline rerouting optimization method of the embodiment is verified in combination with specific examples below.

[0151] (1) Description of the planning problem.

[0152] A certain submarine oil and gas pipeline was put into use in 1996, and less consideration was given to geological disasters, soil corrosion and elevation problems at the beginning of the design, resulting in multiple leakage accidents of the submarine oil and gas pipeline in recent years. Therefore, the submarine oil and gas pipeline needs to be rerouted and newly built. First, the submarine oil and gas pipeline is divided into five pipe sections, and the active pipeline rerouting evaluation method is applied to each pipe section for analysis one by one. The pipe sections with an evaluation result of "recommended rerouting" are rerouted and newly built. For the pipe sections that are rerouted and newly built, a rerouting route optimization model is established, and a hybrid grey wolf-goat algorithm is used for solving to obtain the optimal rerouting route optimization scheme.

[0153] (2) Solution of the planning problem.

[0154] According to the operation data of each pipe section, two groups of pipeline data are obtained by using the decision tree method, as shown in the following table.

[0155] Table 1 First pipeline data

[0156]

[0157] Table 2 Second pipeline data

[0158]

[0159] The average value of the ranking of each pipe section in the above two groups of pipeline data is used as the input, and the Friedman test method is used for testing to obtain the chi-square value, value and the rank average value of each pipe section, which can be completed through the SPSS software, as shown in the following table.

[0160] Table 3 Chi-square value and value

[0161]

[0162] Table 4 Rank average value of each pipe section

[0163]

[0164] According to the Friedman test result in Table 3, the value is lower than the significance level α=0.05, indicating that there is a significant difference between the five pipe sections.

[0165] In order to more intuitively display the Friedman test result obtained by the Friedman test method, a rank average column chart is drawn by using the Bonferroni-Dunn test method, as shown in Figure 8 . Figure 8 In the figure, the optimal rank average is the minimum value of the rank average of the five pipe sections, the 90% threshold is the threshold when the significance level is 10%, and the 95% threshold is the threshold when the significance level is 5%. The pink horizontal line is drawn according to the minimum value of the rank average of the five pipe sections, and the red and black horizontal lines correspond to the thresholds when the significance levels are 5% and 10%, respectively. In this example, the decision tree method is applied to integrate the operation data from two dimensions, the number of pipe sections is 5, and according to , in combination with the minimum value of the rank average being 1.50, the thresholds when the significance levels are 5% and 10% can be obtained. According to the rank average column chart, the pipe sections with column heights below the red horizontal line perform well and do not recommend reline, and the pipe sections with column heights higher than the red horizontal line perform poorly and recommend reline. Finally, it is determined that pipe section 3 and pipe section 4 recommend reline.

[0166] According to the pipeline suitable laying comprehensive evaluation method, the pipeline laying area is evaluated, and the grid with a comprehensive evaluation value less than the allowable value of the suitable laying comprehensive evaluation is regarded as an available grid. First, the pipeline laying area of the oilfield gathering and transportation pipeline network to be laid is divided into 30 30 grids, and each grid is divided into three levels from three influencing factors of geological disasters, soil corrosion and elevation, to obtain the comprehensive evaluation value and the comprehensive evaluation result of each grid.

[0167] (3) Parameter setting of planning method application.

[0168] This example is realized by using the Matlab r2020b platform program, and the population size is set to 100, the maximum number of iterations , the automatic adjustment of the random search parameter is 2, the basic avoidance intensity is 0.5, and the fixed infection probability is 0.07.

[0169] (4) Comparison and analysis of planning schemes.

[0170] As shown in Figure 9 , the oil and gas pipeline reline route optimization design in this example is obtained by using the oil and gas pipeline reline route optimization method of the embodiment to solve the automatic design scheme (i.e., the reline route optimization scheme). Compared with the manual design schemes H1-H4, the total investment construction cost of the automatic design schemes G1-G4 is saved by 7.32%, realizing cost reduction and efficiency improvement.

[0171] The application further provides an application scenario of the oil and gas pipeline rerouting optimization method. Specifically, the oil and gas pipeline rerouting optimization method provided by the embodiment can be applied in a rerouting scenario. The rerouting scenario includes a design link and a display link. The design link is used to design a rerouting optimization scheme, and the display link is used to display the rerouting optimization scheme. The oil and gas pipeline rerouting optimization method provided by the embodiment belongs to the design link.

[0172] Embodiment 2.

[0173] In an exemplary embodiment, a computer device is provided, which can be a server or a terminal. An internal structure diagram of the computer device can be as shown in Figure 10 The computer device includes a processor, a memory, an input / output interface (I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is used to store data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement an oil and gas pipeline rerouting optimization method.

[0174] Those skilled in the art can understand that Figure 10 the structure shown in the figure is only a block diagram of part of the structure related to the scheme of the application, and does not constitute a limitation on the computer device to which the scheme of the application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0175] In an exemplary embodiment, a computer device is provided, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the oil and gas pipeline rerouting optimization method in embodiment 1.

[0176] Embodiment 3.

[0177] In an exemplary embodiment, a computer readable storage medium is provided, which stores a computer program. The computer program is executed by a processor to implement the oil and gas pipeline rerouting optimization method in embodiment 1.

[0178] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0179] The technical features of the above embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present disclosure.

[0180] The principles and implementation modes of the present application are described by applying specific examples herein, and the above embodiment descriptions are only used to help understand the method and its core idea of the present application; meanwhile, for those skilled in the art, the specific implementation modes and application ranges will be changed according to the idea of the present application. In conclusion, the content of the present description should not be understood as a limitation of the present application.

Claims

1. A method for optimizing the routing of oil and gas pipelines, characterized in that, The oil and gas pipeline rerouting optimization method comprises the following steps: segmenting an active oil and gas pipeline to obtain a plurality of pipe segments, for each pipe segment, determining whether the pipe segment needs to be rerouted based on operation data of the pipe segment, and recording the pipe segments that need to be rerouted as to-be-rerouted pipe segments; for each to-be-rerouted pipe segment, taking the starting point and the ending point of the to-be-rerouted pipe segment as inputs, solving a rerouting optimization model to obtain a rerouting optimization scheme; the objective function of the rerouting optimization model is to minimize the sum of the comprehensive evaluation value of the suitability of laying and the converted value of the construction cost of pipeline rerouting; the constraint conditions include pipeline node position constraint, pipeline node quantity constraint, pipeline turning angle constraint and pipeline node layout feasibility constraint; the rerouting optimization scheme includes the position of each pipeline node, the connection relationship between pipeline nodes and the pipe specification of the pipeline connecting two pipeline nodes; the pipeline nodes include the starting point, the routing nodes between the starting point and the ending point and the ending point; the operation data of the pipe segment includes the actual corrosion point number, the actual historical leakage times and the actual third-party damage repair times of the pipe segment; for each pipe segment, based on the operation data of the pipe segment, determining whether the pipe segment needs to be rerouted, specifically comprising: for each pipe segment, if the actual corrosion point number is greater than a preset corrosion point number, setting the corrosion point number equal to the actual corrosion point number, otherwise, setting the corrosion point number equal to 0; if the actual historical leakage times is greater than a preset historical leakage times, setting the historical leakage times equal to the actual historical leakage times, otherwise, setting the historical leakage times equal to 0; if the actual third-party damage repair times is greater than a preset third-party damage repair times, setting the third-party damage repair times equal to the actual third-party damage repair times, otherwise, setting the third-party damage repair times equal to 0; the corrosion point number, the historical leakage times and the third-party damage repair times of all the pipe segments form the first pipeline data; for each pipe segment, if the corrosion point number is greater than 0, setting the corrosion judgment result as yes, otherwise, setting the corrosion judgment result as no; if the historical leakage times is greater than 0, setting the leakage judgment result as yes, otherwise, setting the leakage judgment result as no; if the third-party damage repair times is greater than 0, setting the third-party damage judgment result as yes, otherwise, setting the third-party damage judgment result as no; the corrosion judgment result, the leakage judgment result and the third-party damage judgment result of all the pipe segments form the second pipeline data; using Friedman test method to test the first pipeline data and the second pipeline data to obtain the rank average value of each pipe segment; using Bonferroni-Dunn test method to draw a rank average value bar chart by taking the rank average value of each pipe segment as input; determining whether each pipe segment needs to be rerouted based on the rank average value bar chart.

2. The oil and gas pipeline re-route optimization method of claim 1, wherein, the objective function is: ； wherein, is a sum of a proper laying comprehensive evaluation value and a pipeline reline construction cost conversion value; is a pipeline node set; is a pipeline specification set; is a pipeline node and a pipeline node between which a pipeline is laid; is a pipeline node and a pipeline node between which a pipeline is laid; is a pipeline reline construction cost conversion value when a pipeline specification ； wherein is a binary variable representing whether pipe node is connected to pipe node is a binary variable representing whether pipe node and pipe node are connected, then is 1; is a binary variable representing whether the pipe between pipe node and pipe node is of pipe specification is a binary variable representing whether the pipe between pipe node and pipe node is of pipe specification , then is 1; is the length of the pipe between pipe node and pipe node ; is the material procurement cost of the pipe between pipe node and pipe node if the pipe is of pipe specification ; is the labor cost of the pipe between pipe node and pipe node if the pipe is of pipe specification ; is the cost conversion factor; ； wherein, is the ratio of the circumference of a circle to its diameter; is the pipe node and the pipe node selects a pipe specification when the pipe cost fit coefficient is is the pipe node and the pipe node selects a pipe specification when the pipe wall thickness is is the pipe node and the pipe node selects a pipe specification when the pipe diameter is 3. The oil and gas pipeline re-route optimization method of claim 1, wherein, the pipeline node position constraint is: ； ； wherein, is a suitable laying integrated evaluation value of a pipeline between the pipeline node and the pipeline node ; is a suitable laying integrated evaluation permission value; is a set of pipeline nodes; is a set of routing nodes in the pipe section to be re-routed; is an empty set; the pipeline node quantity constraint is: ； wherein, is a minimum value for the number of pipeline nodes; is a set of pipeline nodes the number of pipeline nodes in is a maximum value for the number of pipeline nodes; the pipeline turning angle constraint is: ； wherein is a binary variable representing whether pipe node is connected to pipe node is a binary variable representing whether pipe node is connected to pipe node is 1 if pipe node and pipe node are connected; is a binary variable representing whether pipe node is connected to pipe node is a binary variable representing whether pipe node is connected to pipe node is 1 if pipe node and pipe node are connected; is the turning angle of the pipe between pipe node and pipe node ; is the maximum value of the turning angle; The pipeline node layout feasibility constraint is: ； wherein, is a modulo operation; is the number of intersections of the ray emanating from the pipe node with the obstacle.

4. The oil and gas pipeline re-route optimization method of claim 2, wherein, Pipe node And pipe node The comprehensive evaluation value of the suitable laying of the pipe between the pipe node and the pipe node is determined based on a comprehensive evaluation value set of a pipe laying area corresponding to the pipe segment to be re-routed, the comprehensive evaluation value set being obtained by comprehensively evaluating the pipe laying area by using a pipe suitable laying comprehensive evaluation method based on soil corrosion conditions, geological disaster conditions and elevation of each grid in the pipe laying area, and the comprehensive evaluation value set including a comprehensive evaluation value of each grid in the pipe laying area. At this time, the comprehensive evaluation value of the pipeline between the pipeline node and the pipeline node is the maximum value of the comprehensive evaluation values of all the meshes of the pipeline path between the pipeline node and the pipeline node .

5. The oil and gas pipeline re-route optimization method of claim 1, wherein, The improved grey wolf algorithm is used to solve the rerouting optimization model, and specifically includes: The improved grey wolf algorithm is used to solve the rerouting optimization model, and specifically includes: ； in, For the first During the nth iteration The position vectors of individual gray wolves; for The weight of wolves; for The target position vector guided by the wolf; for The weight of wolves; for The target position vector guided by the wolf; for The weight of wolves; for The target position vector guided by the wolf; For the goat jumping part, take the value, if the first random number Less than the jump probability ,but equal to jump vector ,otherwise, Equals 0; For the part of the goat parasite avoidance, if the second random number is... Less than the probability of infection ,but Equal to avoidance vector ,otherwise, It equals 0. The improved grey wolf algorithm is used to solve the rerouting optimization model, and specifically includes: ； in, For the first The first-stage dependency parameters in the next iteration are based on the current iteration number. The maximum number of iterations is determined; To obey Uniformly distributed random numbers; For the first The second-stage dependency parameter in the next iteration is based on the current iteration number. The maximum number of iterations is determined; For the first The third-stage dependency parameter in the next iteration is based on the current iteration number. The maximum number of iterations is determined; ； wherein is a position vector of the wolf; is a step size coefficient; is a random search parameter at the th iteration; is a position vector of the th grey wolf individual; is a position vector of the wolf; is a position vector of the wolf; ； wherein, is a base value; is a first dispersion state adjustment factor based on a population dispersion at the iteration; is determined; is a second dispersion state adjustment factor based on a population dispersion at the iteration; is determined; is a hyperbolic tangent function; is a history dependency length; is a population dispersion at the iteration; is a population dispersion at the iteration; ； wherein, is a hop size; is a position vector of any one wolf individual in the goat memory matrix; ； wherein, to avoid strength; is the maximum number of iterations; is the position vector of any one wolf individual in the non-goat memory matrix.

7. The method of claim 5, wherein, 6. The oil and gas pipeline rerouting optimization method according to claim 5, characterized in that, The improved grey wolf algorithm is used to solve the rerouting optimization model, and specifically includes: computing a fitness value for each gray wolf individual in the initial gray wolf population, determining a fitness value for each gray wolf individual in the initial gray wolf population based on wolves, wolves and wolves; the fitness value is a value of an objective function; Based on the initial gray wolf population Wolf, wolves and The position vector of each individual gray wolf in the initial gray wolf population is updated using the gray wolf position update formula to obtain the updated gray wolf population. The fitness value of each individual gray wolf in the updated gray wolf population is calculated, and a determination is made based on the fitness value of each individual gray wolf in the updated gray wolf population. Wolf, wolves and Wolf; An initial grey wolf population is randomly generated, the initial grey wolf population includes a plurality of grey wolf individuals, and a position vector of the grey wolf individual is a rerouting optimization scheme satisfying a constraint condition; If so, then selecting a position vector from the updated wolf population the position vector of the wolf as a rerouting optimization scheme; It is determined whether an iteration termination condition is reached.

8. A computer device comprising: If not, the updated grey wolf population is taken as an initial grey wolf population of the next iteration, and the step of calculating the fitness value of each grey wolf individual in the initial grey wolf population is returned.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, A memory, a processor, and a computer program stored on the memory and capable of running on the processor, characterized in that the processor executes the computer program to implement the oil and gas pipeline rerouting optimization method of any one of claims 1-7. The computer program is executed by the processor to implement the oil and gas pipeline rerouting optimization method of any one of claims 1-7.

Images