A submarine pipe cable routing optimization method, system and readable medium based on a fusion agent model and an intelligent optimization algorithm

Abstract

This invention belongs to the field of submarine cable routing technology, and relates to a method, system, and readable medium for submarine cable routing optimization based on a fusion surrogate model and intelligent optimization algorithm. The method includes the following steps: randomly and uniformly sampling several candidate submarine cable routes; constructing a cable routing optimization objective; constructing a Kriging model or a PC-Kriging model based on the sampling results; inputting the sampling results into a genetic algorithm, a particle swarm optimization algorithm, and a simulated annealing algorithm; and optimizing the submarine cable routing based on the optimization objective. This invention replaces high-cost evaluation with a surrogate model, and integrates the complementary advantages of the genetic algorithm (GA), particle swarm optimization algorithm (PSO), and simulated annealing algorithm (SA) in parallel. It achieves rapid and robust optimization under small sample conditions, thereby improving design efficiency and reducing engineering costs.

Description

Technical Field

[0001] This invention relates to a method, system, and readable medium for optimizing submarine cable routing based on a fusion agent model and intelligent optimization algorithm, belonging to the field of submarine cable routing technology. Background Technology

[0002] Deepwater subsea pipeline laying technology is one of the key technologies for deepwater oil and gas development. The development of marine oil and gas resources, especially in deepwater areas, is a vital source of global energy supply. Subsea pipelines, as indispensable transportation channels in deepwater oil and gas development, are responsible for the efficient and safe transport of offshore oil and gas resources to onshore processing and consumption markets. With the acceleration of deepwater oil and gas development, the efficient and reliable laying of subsea pipelines to ensure stable oil and gas transportation has become extremely crucial.

[0003] Submarine cables are often subjected to combined loads from the random marine environment, floating body motion, and their own mass during service. Simultaneously, multiple nonlinear factors exist between components, including contact, friction, large displacement, and large deformation. These coupling effects significantly weaken the overall stability of the cable and exacerbate fatigue damage, thus shortening its service life. However, traditional submarine cable route design methods rely heavily on the knowledge and experience of professionals, manually selecting routes based on seabed topography and obstacles. The design process primarily focuses on the cable's geometry, failing to adequately consider the impact of stability and fatigue on cable selection. This results in complex design iterations, long design cycles, high costs, and poor performance. Summary of the Invention

[0004] To address the aforementioned problems, the present invention aims to provide a method, system, and readable medium for optimizing submarine cable routes based on a fusion agent model and intelligent optimization algorithm, thereby solving the problems of low efficiency and high computational load in cable route design.

[0005] To achieve the above objectives, the present invention proposes the following technical solution: a submarine cable routing optimization method based on a fusion proxy model and an intelligent optimization algorithm, comprising the following steps: randomly and uniformly sampling several candidate submarine cable routes; constructing a cable routing optimization objective; constructing a Kriging model or a PC-Kriging model based on the sampling results; inputting the sampling results into a genetic algorithm, a particle swarm optimization algorithm, and a simulated annealing algorithm; and optimizing the submarine cable routing based on the optimization objective.

[0006] Furthermore, the random uniform sampling adopts hypercubic sampling, which divides a certain variable in several candidate submarine cable routes into N small intervals, randomly selects a value from each of the small intervals, obtains N values ​​for each variable, and randomly combines the N values ​​of a certain variable with the values ​​of other variables to obtain the random uniform sampling result.

[0007] Furthermore, the cable route optimization objectives are established using three indicators: the physical length of the cable, the ballast weight of the cable, and the fatigue life of the cable. The physical length of the cable is calculated by integrating the geometric discreteness of the candidate submarine cable routes. The ballast weight of the cable is determined based on in-situ stability.

[0008] Furthermore, the costs of the physical length, ballast weight, and fatigue life of the cable are dimensionless, and the dimensionless costs are added together to obtain the total cost.

[0009] Furthermore, the formula for the total cost is:

[0010]

[0011] in, It is the total cost. Cost of the physical length of the cable; The cost required for ballast weight; The cost corresponding to fatigue life.

[0012] Furthermore, a Kriging model or a PC-Kriging model is constructed based on the sample points and response values ​​selected in the sampling results. The Kriging model is used for small samples, and the PC-Kriging model is used for medium to large samples.

[0013] This invention discloses a submarine cable routing optimization system based on a fusion surrogate model and an intelligent optimization algorithm, comprising: a sampling module for randomly and uniformly sampling several candidate submarine cable routes; a target construction module for constructing a cable routing optimization target; a surrogate model module for constructing a Kriging model or a PC-Kriging model based on the sampling results; and an intelligent optimization algorithm module for inputting the sampling results into a genetic algorithm, a particle swarm optimization algorithm, and a simulated annealing algorithm, and obtaining the submarine cable routing optimization result based on the optimization target.

[0014] Furthermore, the cable route optimization objectives are established using three indicators: the physical length of the cable, the ballast weight of the cable, and the fatigue life of the cable. The physical length of the cable is calculated by integrating the geometric discreteness of the candidate submarine cable routes. The ballast weight of the cable is determined based on in-situ stability.

[0015] Furthermore, the costs of the physical length, ballast weight, and fatigue life of the cable are dimensionless, and the dimensionless costs are added together to obtain the total cost.

[0016] The present invention also discloses a computer-readable storage medium storing a computer program that is executed by a processor to implement submarine cable routing optimization based on a fusion agent model and intelligent optimization algorithm as described in any of the preceding claims.

[0017] The technical solution of this invention has at least the following technical effects or advantages: This invention develops a submarine cable routing optimization method that replaces high-cost evaluation with a surrogate model, and integrates the complementary advantages of Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Simulated Annealing (SA) in parallel. It achieves rapid and robust optimization under small sample conditions, thereby improving design efficiency and reducing engineering costs. This invention also constructs Kriging and PC-Kriging models simultaneously, overcoming the instability of a single surrogate model under different sample sizes or qualities. This invention integrates the complementary advantages of GA, PSO, and SA in parallel, forming a collaborative global search mechanism, significantly reducing the risk of a single algorithm getting trapped in local optima. Attached Figure Description

[0018] Figure 1 This is a flowchart of a submarine cable routing optimization method according to an embodiment of the present invention. Detailed Implementation

[0019] To enable those skilled in the art to better understand the technical solutions of the present invention, the present invention is described in detail through specific embodiments. However, it should be understood that the specific embodiments are provided only for a better understanding of the present invention and should not be construed as limiting the present invention. In the description of the present invention, it should be understood that the terminology used is for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0020] To address the problems of numerous optimization parameters, low efficiency in cable route design, high computational load, complex design iteration processes, long design cycles, high costs, and poor results in existing technologies for submarine cables, this invention proposes a submarine cable route optimization method, system, and readable medium based on a fusion surrogate model and intelligent optimization algorithms. The method includes the following steps: random and uniform sampling of several candidate submarine cable routes; construction of a cable route optimization objective; construction of a Kriging model or PC-Kriging model based on the sampling results; inputting the sampling results into a genetic algorithm, particle swarm optimization algorithm, and simulated annealing algorithm; and obtaining the optimized submarine cable route based on the optimization objective. This invention replaces high-cost evaluation with a surrogate model and integrates the complementary advantages of the genetic algorithm (GA), particle swarm optimization algorithm (PSO), and simulated annealing algorithm (SA) in parallel. It achieves rapid and robust optimization under small sample conditions, thereby improving design efficiency and reducing engineering costs. The invention is described in detail below with reference to the accompanying drawings.

[0021] Example 1 This embodiment discloses a submarine cable routing optimization method based on a fusion agent model and intelligent optimization algorithm, such as... Figure 1 As shown, it includes the following steps: S1 performs random and uniform sampling on several candidate submarine cable routes.

[0022] To ensure more uniform sample collection, hypercubic sampling (LHS) is used for random uniform sampling. LHS is a stratified random sampling method that can efficiently sample from the distribution range of variables. Assuming there are k variables for the candidate submarine cable route, let's denote the k variables as: , N samples are taken from a specified interval. Each variable in several candidate submarine cable routes is divided into N smaller intervals. A value is randomly selected from each smaller interval to obtain N values ​​for each variable. The N values ​​of a certain variable are then randomly combined with the values ​​of other variables to obtain a random uniform sampling result. Hypercubic sampling (LHS) maximizes the stratification of each edge distribution, ensuring full coverage of the range of each variable.

[0023] S2 establishes the goal of optimizing cable routing.

[0024] The optimization objectives for cable routing are established using three indicators: physical length, ballast weight, and fatigue life. The physical length is calculated by integrating the geometric discreteness of candidate submarine cable routes. The ballast weight is determined based on in-situ stability, i.e., by verifying in-situ stability according to relevant standards and determining the required ballast weight accordingly. For example, DNV-RP-F109 is used to verify in-situ stability and determine the required ballast weight. The fatigue life of the cable is assessed according to relevant standards, such as DNV-RP-F105. These three results serve as sample response values ​​for subsequent proxy modeling and optimization. The costs of the physical length, ballast weight, and fatigue life of the cable are dimensionless. The dimensionless costs are summed to obtain the total cost, and minimizing the total cost is used as the optimization objective to facilitate subsequent optimization.

[0025] The formula for total cost is: .

[0026] in, It is the total cost. Cost of the physical length of the cable; The cost required for ballast weight; The cost corresponding to fatigue life.

[0027] S3 constructs a Kriging model or a PC-Kriging (Polynomial-Chaos-based Kriging) model based on the sampling results.

[0028] Based on the sample points and response values ​​selected from the sampling results, a Kriging model or a PC-Kriging model is constructed. The Kriging model is used for small samples, while the PC-Kriging model is used for medium to large samples. By comparing the accuracy performance of the two types of models, the optimal model is selected to obtain more robust performance, replacing the cable analysis program for subsequent intelligent route optimization design and improving computational efficiency. An optimal proxy is available from both scarce and abundant sample sizes, avoiding the performance instability of a single model under different sample scales.

[0029] The expression for the Kriging model is:

[0030]

[0031]

[0032] in, x These are the collected sample data. yes x and Functional relationship, It is the correlation vector composed of sample points and prediction points. , It is a predicted value. It is the optimal weight vector. It is the optimal Lagrange multiplier. F It is the trend basis function matrix. , R It is a spatial correlation matrix. It is a column vector of observed response values ​​for all sampling points.

[0033] The expression for the PC-Kriging model is:

[0034]

[0035]

[0036] in, x These are the collected sample data. It is the PCE basis function vector of the prediction point. It is the optimal PCE coefficient vector. B It is the PCE basis function matrix (design matrix) of the sampling points. .

[0037] It should be noted that the input parameters for the constructed Kriging model and PCK-Kriging model include the cost of the physical length of the cable, the cost required for the ballast weight of the cable, and the cost corresponding to the fatigue life of the cable. The sum of these three costs is the construction cost, as shown in Table 1. The specific formula is: .

[0038] in, It is the total cost. Cost of the physical length of the cable; The cost required for ballast weight; The cost corresponding to fatigue life.

[0039] Specifically, the physical length of the pipeline directly affects the cost during the optimization process; longer pipelines cost more, for example, submarine pipelines cost 10,000 yuan per meter. Submarine pipelines also encounter stability and fatigue life issues. To improve stability, ballast treatment is generally required, costing 800 yuan per meter. Pipeline segments that do not meet fatigue life requirements require further treatment, costing 2,000 yuan per segment. The total cost of each pipeline varies with these three variables. Finally, a surrogate model is constructed based on an initial sample of the total input and output costs. Then, based on the surrogate model and intelligent optimization algorithms, the path with the lowest total cost is found.

[0040] Table 1 Input and output parameters of the Kriging model and the PCK-Kriging model

[0041] S4 inputs the sampling results into the genetic algorithm, particle swarm algorithm, and simulated annealing algorithm, and optimizes the submarine cable route according to the optimization objective.

[0042] Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Simulated Annealing (SA) are employed in parallel to conduct global path search and evaluation on the optimal surrogate model. With cable length, ballast weight, and fatigue life as objectives, each objective is normalized according to its respective benchmark, and a weighted composite objective is constructed to reflect the project cost. The minimum value of each algorithm is calculated, and the path corresponding to the minimum value is selected as the optimal path.

[0043] Example 2 Based on the same inventive concept, this embodiment discloses a submarine cable routing optimization system based on a fusion agent model and intelligent optimization algorithm, including: The sampling module is used to randomly and uniformly sample several candidate submarine cable routes.

[0044] The target construction module is used to construct the pipeline route optimization target. The pipeline route optimization target is established by three indicators: physical length of pipeline, ballast weight of pipeline, and fatigue life of pipeline. The physical length of pipeline is calculated by integrating the geometric discreteness of candidate submarine pipeline routes. The ballast weight of pipeline is determined based on in-situ stability.

[0045] The costs of the physical length, ballast weight, and fatigue life of the cable are dimensionless, and the dimensionless costs are added together to obtain the total cost.

[0046] The surrogate model module is used to construct a Kriging model or a PC-Kriging model based on the sampling results.

[0047] The intelligent optimization algorithm module is used to input the sampling results into the genetic algorithm, particle swarm optimization algorithm, and simulated annealing algorithm, and obtain the optimized results of submarine cable routing according to the optimization objective.

[0048] Example 3 Based on the same inventive concept, this embodiment discloses a computer-readable storage medium storing a computer program, which is executed by a processor to implement submarine cable routing optimization based on a fusion agent model and intelligent optimization algorithm as described above.

[0049] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0050] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0051] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0052] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0053] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific embodiments of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention. The above content is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be determined by the protection scope of the claims.

Claims

1. A method for optimizing submarine cable routing based on a fusion agent model and intelligent optimization algorithm, characterized in that, Includes the following steps: Random and uniform sampling was performed on several candidate submarine cable routes. Establish cable routing optimization objectives; Based on the sampling results, construct a Kriging model or a PC-Kriging model; The sampling results are input into the genetic algorithm, particle swarm optimization algorithm, and simulated annealing algorithm. Based on the optimization objective, the submarine cable route optimization results are obtained.

2. The submarine cable routing optimization method based on a fusion agent model and intelligent optimization algorithm as described in claim 1, characterized in that, The random uniform sampling adopts hypercubic sampling, which divides a certain variable in several candidate submarine cable routes into N small intervals, randomly selects a value from each of the small intervals, obtains N values ​​for each variable, and randomly combines the N values ​​of a certain variable with the values ​​of other variables to obtain the random uniform sampling result.

3. The submarine cable routing optimization method based on a fusion agent model and intelligent optimization algorithm as described in claim 1, characterized in that, The cable route optimization objective is established based on three indicators: the physical length of the cable, the ballast weight of the cable, and the fatigue life of the cable. The physical length of the cable is calculated by integrating the geometric discreteness of the candidate submarine cable routes. The ballast weight of the cable is determined based on in-situ stability.

4. The submarine cable routing optimization method based on a fusion agent model and intelligent optimization algorithm as described in claim 3, characterized in that, The costs of the physical length, ballast weight, and fatigue life of the cable are dimensionless, and the dimensionless costs are added together to obtain the total cost.

5. The submarine cable routing optimization method based on a fusion agent model and intelligent optimization algorithm as described in claim 4, characterized in that, The formula for the total cost is: in, It is the total cost. Cost of the physical length of the cable; The cost required for ballast weight; The cost corresponding to fatigue life.

6. The submarine cable routing optimization method based on a fusion agent model and intelligent optimization algorithm as described in claim 1, characterized in that, A Kriging model or a PC-Kriging model is constructed based on the sample points and response values ​​selected in the sampling results. The Kriging model is used for small samples, and the PC-Kriging model is used for medium to large samples.

7. A submarine cable routing optimization system based on a fusion agent model and intelligent optimization algorithm, characterized in that, include: The sampling module is used to randomly and uniformly sample several candidate submarine cable routes. The target building module is used to build cable routing optimization targets; The proxy model module is used to construct a Kriging model or a PC-Kriging model based on the sampling results. The intelligent optimization algorithm module is used to input the sampling results into the genetic algorithm, particle swarm optimization algorithm and simulated annealing algorithm, and obtain the submarine cable route optimization results according to the optimization objective.

8. The submarine cable routing optimization system based on a fusion agent model and intelligent optimization algorithm as described in claim 7, characterized in that, The cable route optimization objective is established based on three indicators: the physical length of the cable, the ballast weight of the cable, and the fatigue life of the cable. The physical length of the cable is calculated by integrating the geometric discreteness of the candidate submarine cable routes. The ballast weight of the cable is determined based on in-situ stability.

9. The submarine cable routing optimization system based on a fusion agent model and intelligent optimization algorithm as described in claim 8, characterized in that, The costs of the physical length, ballast weight, and fatigue life of the cable are dimensionless, and the dimensionless costs are added together to obtain the total cost.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is executed by a processor to implement the submarine cable routing optimization based on the fusion agent model and intelligent optimization algorithm as described in any one of claims 1-6.

Images