Submarine cable positioning method and system

Abstract

The invention discloses a submarine cable positioning method and system, and the method comprises the following steps: carrying out the positioning solving step based on different starting points based on the number of pre-configured starting points, and obtaining a global optimal solution after all starting points are subjected to the positioning solving step, taking a position point corresponding to the globally optimal solution as a two-dimensional coordinate of the target cable; wherein each positioning solving step comprises the following steps of: initializing a wolf pack position by using a single-point crossover operation based on a corresponding starting point; calculating the fitness corresponding to each wolf based on the fitness function, and recording the three wolves with the optimal fitness as alpha wolf, beta wolf and delta wolf in sequence; and on the basis of the alpha wolf, the beta wolf and the delta wolf, performing iterative updating on the position of each wolf, performing fitness calculation on the basis of the updated position of each wolf, and updating the alpha wolf, the beta wolf and the delta wolf on the basis of the obtained fitness until a preset maximum number of iterations is reached. The method provided by the invention is high in submarine cable positioning speed and high in precision.

Description

Technical Field

[0001] The invention relates to the field of submarine cable positioning, and in particular to a submarine cable positioning technology based on an improved grey wolf algorithm. Background Art

[0002] Current methods for locating cables include acoustic positioning, optical positioning, and electromagnetic positioning.

[0003] The detection accuracy of acoustic positioning gradually decreases with the increase of water depth; when encountering an interface with unequal wave impedance of the media on both sides, reflection will occur, resulting in reduced positioning accuracy.

[0004] Optical positioning is easily affected by the seabed environment and water quality; in areas with turbid water and low visibility, the images obtained by the camera may become blurred due to factors such as attenuation, reflection and scattering of light waves, resulting in poor quality of the generated images, which in turn affects the accuracy.

[0005] The electromagnetic positioning method is less affected by the uneven impedance of the medium, has strong mud and sand penetration and is more mature. However, the existing electromagnetic positioning-based seabed positioning solutions still need to be improved in terms of speed and accuracy. Summary of the invention

[0006] Aiming at the disadvantages of poor positioning speed and accuracy of existing submarine positioning solutions based on electromagnetic positioning, the present invention provides a submarine cable positioning technology based on an improved grey wolf algorithm.

[0007] In order to solve the above technical problems, the present invention is solved by the following technical solutions:

[0008] A method for locating a submarine cable comprises the following steps:

[0009] Pre-configure a number of detection robots, wherein the detection robots measure the magnetic induction intensity in the detection plane where they are located;

[0010] Using the optimized grey wolf algorithm, based on the detection data acquired by each detection robot, the two-dimensional coordinates of the target cable are located in the detection plane;

[0011] The optimized gray wolf algorithm includes the following steps:

[0012] Construct the magnetic induction intensity expression corresponding to the target cable;

[0013] Constructing a fitness function, the fitness function is used to indicate the relationship between each detection value and each calculated value of the target wolf and its fitness; the target wolf here specifically refers to the wolf whose fitness is currently calculated based on the fitness function, calculating the magnetic induction intensity corresponding to the target wolf based on the magnetic induction intensity expression, and obtaining the calculated value corresponding to the detection robot one by one; using each detection robot to detect the magnetic induction intensity corresponding to the target wolf, and obtaining the detection value corresponding to the detection robot one by one;

[0014] Based on the number of pre-configured starting points, positioning and solving steps are performed based on different starting points. After all starting points have completed the positioning and solving steps, a global optimal solution is obtained, and the position point corresponding to the global optimal solution is used as the two-dimensional coordinate of the target cable;

[0015] Among them, each positioning solution step includes:

[0016] Initialize the wolf pack positions using single-point crossover operations based on the corresponding starting points;

[0017] The fitness of each wolf is calculated based on the fitness function. The three wolves with the best fitness are α wolf, β wolf and δ wolf.

[0018] Based on the α wolf, β wolf and δ wolf, the position of each wolf is iteratively updated, and the fitness is calculated based on the updated position of each wolf, and the α wolf, β wolf and δ wolf are updated based on the obtained fitness until a preset maximum number of iterations is reached.

[0019] The existing gray wolf algorithm process includes the following steps:

[0020] Step 1, Initialization: Randomly generate a group of gray wolves (i.e., solution candidates) in the search space and evaluate the fitness of each solution.

[0021] Step 2: Construct social hierarchy: Divide the gray wolves into four levels: Alpha, Beta, Delta, and Omega according to their fitness values.

[0022] Step 3, update position: Update the positions of other gray wolves according to the positions of Alpha, Beta and Delta and the coordination coefficient vectors A and C.

[0023] Step 4: Evaluate fitness: Calculate the fitness value of the updated gray wolf.

[0024] Step 5, iterative position update: repeat steps 3 and 4 until the stop condition is met;

[0025] The existing Grey Wolf Algorithm has a slow convergence speed. It takes a lot of time to find the optimal solution or a solution close to the optimal solution in the submarine cable positioning problem in a complex environment. It may converge to the local optimal solution too early due to improper parameter settings or algorithm mechanism defects, thus missing the global optimal solution.

[0026] When the existing gray wolf algorithm handles submarine cable positioning tasks under different environments or conditions, it may be affected by different environments. For example, different submarine topography, water depth, cable type, etc. may affect positioning accuracy and efficiency. The existing gray wolf algorithm may not be able to effectively adjust its strategy to cope with these changes.

[0027] The lack of population diversity in the existing grey wolf algorithm may cause the algorithm to converge prematurely and lose the ability to explore new solutions.

[0028] In view of the above problems, the present invention optimizes the gray wolf algorithm as follows:

[0029] Multi-starting point strategy means that the algorithm starts iterative search from multiple different initial positions instead of just one starting point. Its advantages include:

[0030] Enhanced robustness: Starting the search from multiple starting points can enhance the robustness of the algorithm, because even if there are local optimal solutions near some starting points, other starting points may find better global solutions;

[0031] Improve diversity: The multi-starting point strategy can increase the diversity of the population, thereby improving the algorithm's search ability;

[0032] Adapt to different environments: In submarine cable positioning, different starting points may correspond to different cable distributions. The multi-starting point strategy helps the algorithm adapt to different search environments and improve positioning accuracy.

[0033] Single-point crossover operation: Single-point crossover operation randomly selects a crossover point in the gene sequence of the parent individual, and then exchanges the part after the crossover point with the corresponding part of another parent to generate a new offspring individual. In the gray wolf algorithm, this is equivalent to introducing new individuals into the wolf pack, increasing the diversity of the population; its advantages include:

[0034] Increase population diversity: Through the crossover operation, new individuals that are different from their parents can be generated, which helps the algorithm explore a wider search space and avoid falling into a local optimal solution;

[0035] Accelerate convergence: The introduction of new individuals can speed up the convergence of the algorithm because they may contain information about better solutions;

[0036] Improved positioning accuracy: In submarine cable positioning, diversity helps find a more precise cable location because the algorithm can explore multiple possible solutions.

[0037] Furthermore, in an iteration step, the step of updating the position of the target wolf includes:

[0038] Take the target wolf's position as the first position;

[0039] Processing the first position based on the MCMC random walk strategy to obtain a second position;

[0040] The second position is updated based on the positions of wolf α, wolf β and wolf δ to obtain a third position, and the third position is used as the position of the target wolf in the next iteration step.

[0041] The present invention further improves the gray wolf algorithm by adjusting the initial position of the wolf pack using the MCMC random walk strategy;

[0042] MCMC is a statistical simulation method that generates samples by random walks to estimate probability distributions. In the gray wolf algorithm, MCMC is used to introduce random changes in the wolf pack's position update process, allowing the wolves to perform small random explorations in the search space. Its advantages include:

[0043] Avoid local optimality: By introducing random changes, MCMC can help the algorithm escape from the local optimal solution and explore a better solution;

[0044] Balance exploration and exploitation: MCMC allows the algorithm to maintain a certain degree of randomness in the search process while taking advantage of information from the good solutions already found, thus achieving a balance between exploration and exploitation;

[0045] Improve positioning stability: In submarine cable positioning, this balance helps to find a more stable and reliable cable position.

[0046] As an implementable method, the first position is processed based on the MCMC random walk strategy to obtain the second position in the following specific steps:

[0047] generating a first random number;

[0048] When the first random number is less than the preset acceptance probability, the processing state is determined to be maintained; if it is greater than or equal to the preset acceptance probability, the processing state is determined to be updated;

[0049] When the processing state is maintained, taking the first position as the second position;

[0050] When the processing state is updating, a corresponding random walk step number is generated based on the convergence factor corresponding to the current iteration step and the first random number, and the first position is updated based on the random walk step number to obtain a second position, and the calculation formula is:

[0051]

[0052] in:

[0053] is the number of random walk steps in the MCMC random walk strategy;

[0054] a is the convergence factor corresponding to the current iteration step;

[0055] σ is the first random number;

[0056] The location of the target wolf;

[0057] is the second position.

[0058] As an implementable method, the calculation formula of the convergence factor a is:

[0059]

[0060] in:

[0061] t is the number of iterations;

[0062] a t is the convergence factor corresponding to the tth iteration step;

[0063] a t+1 is the convergence factor corresponding to the t+1th iteration step.

[0064] As an implementable method, based on a position update formula, the second position is updated according to the positions of α wolf, β wolf and δ wolf to obtain the third position;

[0065] The position update formula is:

[0066]

[0067] in:

[0068] is the position of wolf α; is the position of β wolf; is the position of δ wolf; The second position for the target wolf; The third position for the target wolf;

[0069] represents the distance between wolf α and the target wolf;

[0070] represents the distance between β wolf and target wolf;

[0071] represents the distance between δ wolf and target wolf;

[0072] Indicates the distance the target wolf needs to move toward the α wolf;

[0073] Indicates the distance the target wolf needs to move toward the β wolf;

[0074] Indicates the distance the target wolf needs to move toward the δ wolf;

[0075] and Both are first control parameters, and are obtained by the convergence factor and random number calculation corresponding to the current iteration step;

[0076] and are both second control parameters, and are both generated based on random numbers.

[0077] As an implementable method:

[0078] When an α wolf, a β wolf or a δ wolf is updated, the updated wolf is recorded as the target leader wolf, and the first control parameter and the second control parameter corresponding to the target leader wolf are calculated for use in the next iteration step;

[0079] The specific steps of calculating the first control parameter and the second control parameter corresponding to the target wolf leader are:

[0080] Randomly generate a second random number and a third random number for the target wolf leader;

[0081] Calculating a first control parameter of the target wolf leader based on the convergence factor of the current iteration step and the second random number;

[0082] A second control parameter of the target wolf leader is calculated based on the third random number.

[0083] As an implementable method:

[0084] The magnetic induction intensity expression is:

[0085]

[0086] in:

[0087] B(r) is the magnetic induction intensity corresponding to the target wolf for the target detection robot;

[0088] r is the distance between the target wolf and the target detection robot;

[0089] k is the first environmental correction factor;

[0090] c is the second environmental correction factor;

[0091] I is the effective value of the rated current;

[0092] s is the phase spacing.

[0093] As an implementable method:

[0094] The formula of the fitness function is:

[0095]

[0096] in:

[0097] f(x c ,y c ) is the coordinate (x c ,y c )’s wolf fitness;

[0098] N is the number of detection robots;

[0099] B r(n) is the calculated value corresponding to the nth detection robot;

[0100] B s(n) is the detection value corresponding to the nth detection robot.

[0101] As an implementable method, the specific steps of initializing the wolf pack positions using a single-point crossover operation based on the corresponding starting points are:

[0102] A two-dimensional vector is used to represent the path of the submarine cable, and the starting points are two randomly selected vectors;

[0103] Determine a corresponding parent path based on the starting point, and randomly select a point from the parent path as an intersection point;

[0104] A crossover operation is performed based on the crossover points, and the resulting offspring position matrix is ​​used as the initial wolf population.

[0105] As an implementable method:

[0106] The method further includes executing a judgment step before determining the corresponding parent path based on the starting point and randomly selecting a point from the parent path as an intersection point, specifically:

[0107] generating a fourth random number;

[0108] If the random number is less than the preset execution probability, no crossover operation will be performed;

[0109] If it is greater than or equal to the preset execution probability, then crossover operation is performed.

[0110] As an implementable method:

[0111] When the α wolf is updated, the fitness of the updated α wolf is compared with the optimal fitness. When the fitness of the updated α wolf is better than the optimal fitness, the optimal fitness is updated.

[0112] The present invention also proposes a submarine cable positioning system, comprising a plurality of detection robots and a positioning system connected by signals:

[0113] The detection robot is used to measure the magnetic induction intensity in the corresponding detection plane;

[0114] The positioning system is used to locate the two-dimensional coordinates of the target cable in the detection plane based on the detection data acquired by each detection robot using the optimized grey wolf algorithm;

[0115] The positioning system comprises:

[0116] A simulation module is used to construct an expression of magnetic induction intensity corresponding to the target cable, and calculate the magnetic induction intensity corresponding to the target wolf based on the expression of magnetic induction intensity to obtain a detection value corresponding to the detection robot one by one;

[0117] A detection module is used to detect the magnetic induction intensity corresponding to the target quantity using each detection robot to obtain a detection value corresponding to the detection robot;

[0118] A configuration module, used to configure the number of starting points, the maximum number of iterations and a fitness function, wherein the fitness function is used to indicate the relationship between each detection value and each calculated value of the target wolf and its fitness;

[0119] A solution module, used for performing a positioning solution step based on different starting points according to the number of starting points, obtaining a global optimal solution after all starting points have completed the positioning solution step, and using the position point corresponding to the global optimal solution as the two-dimensional coordinate of the target cable;

[0120] Among them, the solution module is configured as:

[0121] Initialize the wolf pack positions using single-point crossover operations based on the corresponding starting points;

[0122] The fitness of each wolf is calculated based on the fitness function. The three wolves with the best fitness are α wolf, β wolf and δ wolf.

[0123] Based on the α wolf, β wolf and δ wolf, the position of each wolf is iteratively updated, and based on the updated position of each wolf, fitness calculation is performed through a fitness function, and the α wolf, β wolf and δ wolf are updated based on the obtained fitness until the maximum number of iterations is reached.

[0124] The present invention has significant technical effects due to the adoption of the above technical solution:

[0125] The present invention can effectively enhance the speed and accuracy of submarine cable positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0126] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0127] Figure 1 It is a schematic diagram of the solution process of submarine cable positioning based on the improved Grey Wolf algorithm of the present invention;

[0128] Figure 2 This is a schematic diagram of the process of updating the position of the target wolf;

[0129] Figure 3 It is a schematic diagram of the result of cable positioning based on the submarine cable positioning method of the present invention;

[0130] Figure 4 It is a schematic diagram of comparing the fitness curves of the improved Grey Wolf Algorithm of the present invention and the existing common Grey Wolf Algorithm for submarine cable positioning;

[0131] Figure 5 yes Figure 4 Schematic diagram of the comparison of fitness curves corresponding to the last five iterations. DETAILED DESCRIPTION

[0132] The present invention is further described in detail below in conjunction with embodiments. The following embodiments are for explanation of the present invention but the present invention is not limited to the following embodiments.

[0133] In the gray wolf algorithm, the gray wolf group is divided into four levels:

[0134] Alpha (α): The leader of the wolf pack, responsible for decision-making and leading the pack, with the highest status and power.

[0135] Beta (β): The deputy leader of the wolf pack, assisting Alpha in making decisions and managing other members of the wolf pack.

[0136] Delta (δ): The third level in the wolf pack, obeying the leadership of Alpha and Beta, but also participating in the decision-making process to a certain extent.

[0137] Omega (ω): The lowest level in the pack, responsible for executing the decisions of Alpha, Beta and Delta, and being the last to eat after hunting.

[0138] This social hierarchy is used in the Grey Wolf Algorithm to simulate the superiority of solutions during the search process, where the best solution is considered Alpha, the second best solution is Beta, the third best solution is Delta, and the remaining solutions are Omega.

[0139] The submarine cable positioning method proposed in the present invention is based on the improved gray wolf algorithm, and maps the submarine cable positioning process to the gray wolf foraging process, that is, mapping the updating of the submarine cable coordinates to the process of surrounding the prey, and mapping the process of obtaining the optimal submarine cable coordinates to attacking the prey, which specifically includes the following steps:

[0140] S100, data configuration;

[0141] S110, constructing an expression for magnetic induction intensity;

[0142] Based on the physical characteristics of the cable and the electromagnetic principles, the spatial characteristics of the submarine cable are accurately modeled, and the expression of the magnetic induction intensity around the cable is constructed, that is, the expression of the magnetic induction intensity corresponding to the target cable is constructed;

[0143] In this embodiment, the expression of magnetic induction intensity is:

[0144]

[0145] in:

[0146] B(r) is the magnetic induction intensity corresponding to the target wolf of the target detection robot. Here, the target wolf refers to the wolf whose calculation value is currently calculated based on the magnetic induction intensity expression;

[0147] r is the distance between the target wolf and the target detection robot;

[0148] k is the first environmental correction factor;

[0149] c is the second environmental correction factor;

[0150] I is the effective value of the rated current;

[0151] s is the phase spacing.

[0152] S120, construct fitness function:

[0153] The fitness function is constructed by combining the calculated value based on the expression of magnetic induction intensity with the detection value actually collected by the detection robot;

[0154] The formula of the fitness function in this embodiment is:

[0155]

[0156] in:

[0157] f(x c ,y c ) is the coordinate (x c ,y c )’s fitness, i.e., the target wolf;

[0158] N is the number of detection robots;

[0159] B r(n) is the calculated value corresponding to the nth detection robot;

[0160] B s(n) is the detection value corresponding to the nth detection robot.

[0161] S130, algorithm parameter configuration:

[0162] The algorithm parameters include the number of wolf packs, dimension, maximum number of iterations, first control parameter, second control parameter, convergence factor and number of starting points.

[0163] S131, Dimension:

[0164] In this embodiment, it is assumed that the cable path is in a two-dimensional space, so the dimension is set to 2.

[0165] S132, a first control parameter and a second control parameter;

[0166] In practical applications, when the α wolf, β wolf or δ wolf is updated, the corresponding wolf is recorded as the target leader wolf, and the first control parameter and the second control parameter corresponding to the target leader wolf are calculated for use in the next iteration step;

[0167] The specific steps of calculating the first control parameter and the second control parameter corresponding to the target wolf leader are:

[0168] Randomly generate a second random number and a third random number for the target wolf leader;

[0169] Calculating a first control parameter of the target wolf leader based on the convergence factor of the current iteration step and the second random number;

[0170] A second control parameter of the target wolf leader is calculated based on the third random number.

[0171] In this embodiment, it is assumed that:

[0172]

[0173] in:

[0174] is the first control parameter;

[0175] is the second control parameter;

[0176] is the second random number, is the third random number, which is a random number in the interval [0,1]. and Used to introduce randomness into the algorithm, simulating the randomness of a gray wolf moving around its prey.

[0177] a is the convergence factor, and the value of a starts from 2 and gradually decreases to 0 during the iteration process.

[0178] S133, convergence factor;

[0179] In practical applications, the convergence factor a is updated based on the number of iterations, and its calculation formula is:

[0180]

[0181] in:

[0182] t is the number of iterations;

[0183] a t is the convergence factor corresponding to the tth iteration step;

[0184] a t+1 is the convergence factor corresponding to the t+1th iteration step.

[0185] S134, number of starting points;

[0186] This embodiment adopts a multi-starting point strategy. By searching or optimizing from multiple different starting points, the multi-starting point strategy can cover a wider solution space, reduce the risk of falling into a local optimal solution, and thus be more likely to find a global optimal solution; even if some starting points lead to unsatisfactory results, other starting points still have the opportunity to obtain better solutions, so that the algorithm can have relatively stable and reliable performance in different problem scenarios and initial conditions. In addition, searching or optimizing from multiple starting points at the same time may find a better solution faster, thereby accelerating the convergence speed of the entire algorithm.

[0187] In this embodiment, the number of wolf packs is set to 40, the number of iterations is set to 20, and the number of starting points is set to 5. Those skilled in the art can set the number of wolf packs, the maximum number of iterations, and the number of starting points according to actual needs.

[0188] S200, positioning solution;

[0189] Based on the number of configured starting points, positioning and solving steps are performed based on different starting points; after all starting points have completed the positioning and solving steps, a global optimal solution is obtained, and the position point corresponding to the global optimal solution is used as the two-dimensional coordinate of the target cable.

[0190] refer to Figure 1 , specifically including the following steps:

[0191] S210, initializing the wolf pack position;

[0192] Randomly generate the parent position of the wolf pack within the search range, that is, generate the starting point;

[0193] Use single-point crossover operation to initialize the wolf pack position to ensure that the initial position is within a reasonable search space range, specifically:

[0194] S211, using a two-dimensional vector to represent the path of the submarine cable, randomly selecting two vectors from historical data or the current search space as parents, and determining a starting point;

[0195] S212: Determine a corresponding parent path based on the starting point, and randomly select a point from the parent path as an intersection point; the intersection point is an index of the position vector.

[0196] S213, performing a crossover operation based on the intersection, that is, concatenating the first half of one parent generation (from index 0 to the intersection) with the second half of another parent generation (from the intersection to the end of the index) to form a new offspring position matrix, and using the formed offspring position matrix as the initial wolf pack population.

[0197] In another embodiment, before step S212, an additional determination step is performed, specifically:

[0198] generating a fourth random number;

[0199] If the random number is less than the preset execution probability, no crossover operation is performed, that is, an initial wolf population is generated based on an existing public wolf population generation method;

[0200] If it is greater than or equal to the preset execution probability, a crossover operation is performed, that is, step S212 and step S213 are executed.

[0201] S220, initializing α wolf, β wolf or δ wolf and optimal fitness;

[0202] In this embodiment, the fitness of each wolf in the initial wolf population is calculated based on the fitness function, and the three wolves with the best fitness are recorded as wolf α, wolf β and wolf δ, and the fitness of wolf α is updated to the optimal fitness.

[0203] S230, location update;

[0204] Based on the α wolf, β wolf and δ wolf, the position of each wolf is iteratively updated, and the fitness is calculated based on the updated position of each wolf, and the α wolf, β wolf and δ wolf are updated based on the obtained fitness until a preset maximum number of iterations is reached.

[0205] Reference Figure 2 , taking the gray wolf whose position is to be updated in the current iteration step as the target wolf, the steps of updating the position of a target wolf include:

[0206] S231, taking the position of the target wolf as the first position, and processing the first position based on the MCMC random walk strategy to obtain a second position;

[0207] This embodiment uses the standard deviation to construct a probability model, and the submarine cable position update process can be regarded as a Markov chain to determine whether to accept MCMC. In this embodiment, the probability of refusing to accept is 50%. If rejected, the position remains unchanged. If accepted, the corresponding random walk steps are generated, and the position is updated according to the random walk steps, specifically:

[0208] generating a first random number based on a probability model;

[0209] When the first random number is less than a preset acceptance probability (such as 0.5), the processing state is determined to be maintained; if it is greater than or equal to the preset acceptance probability, the processing state is determined to be updated;

[0210] When the processing state is maintained, taking the first position as the second position;

[0211] When the processing state is updating, a corresponding random walk step number is generated based on the convergence factor corresponding to the current iteration step and the first random number, and the first position is updated based on the random walk step number to obtain a second position, and the calculation formula is:

[0212]

[0213] in:

[0214] is the number of random walk steps in the MCMC random walk strategy;

[0215] a is the convergence factor corresponding to the current iteration step;

[0216] σ is the first random number;

[0217] The location of the target wolf;

[0218] is the second position.

[0219] S232. Update the second position based on the positions of wolf α, wolf β and wolf δ to obtain a third position, and use the third position as the position of the target wolf in the next iteration step.

[0220] The position update formula is:

[0221]

[0222] in:

[0223] is the position of wolf α; is the position of β wolf; is the position of δ wolf; The second position for the target wolf; The third position for the target wolf;

[0224] represents the distance between wolf α and the target wolf;

[0225] represents the distance between β wolf and target wolf;

[0226] represents the distance between δ wolf and target wolf;

[0227] Indicates the distance the target wolf needs to move toward the α wolf;

[0228] Indicates the distance the target wolf needs to move toward the β wolf;

[0229] Indicates the distance the target wolf needs to move toward the δ wolf;

[0230] and are all first control parameters, which are calculated from the convergence factor corresponding to the current iteration step and the second random number corresponding to the corresponding leader;

[0231] and are all second control parameters, which are generated based on the third random number corresponding to the corresponding wolf leader.

[0232] S240: Parameter update.

[0233] Update of α wolf, β wolf and δ wolf: After updating the positions of all wolves, the fitness of each updated position is calculated and sorted based on the fitness function, and the α wolf, β wolf and δ wolf are updated based on the sorting results;

[0234] Update of optimal fitness: When an update occurs to the α wolf, the fitness of the updated α wolf is compared with the optimal fitness. When the fitness of the updated α wolf is better than the optimal fitness, the optimal fitness is updated.

[0235] Convergence factor update: Based on the current number of iterations, the convergence factor a is updated for use in the next iteration step to adjust the position update amplitude of the submarine cable.

[0236] Update of the first state parameters and the second state parameters: based on the update status and iteration number of α wolf, β wolf and δ wolf, the first state parameters and the second state parameters of each wolf are updated.

[0237] S250, iterative completion judgment, judging whether the maximum number of iterations has been reached, if so, the iteration is judged to be completed and the current positioning solution step is completed, otherwise, it is judged that the iteration is not completed and steps S231 to S234 are repeated.

[0238] S260, determining whether the solution is completed;

[0239] Determine whether the number of positioning solutions reaches the number of starting points;

[0240] If it is achieved, it is determined that the positioning solution is completed, and the optimal fitness obtained by each positioning solution step is compared to obtain the corresponding global optimal solution, and the cable coordinates are located based on the global optimal solution, that is, the position corresponding to the global optimal solution is used as the two-dimensional coordinate of the target cable;

[0241] If not reached, repeat step S200.

[0242] Reference Figure 3 In this embodiment, two detection robots are used, whose coordinates are (0, 0) and (0, 2) respectively. The actual coordinate of the cable is (3, -3). Figure 3 The green circle in the middle represents the position of the detection robot, the red circle represents the final position of the Grey Wolf (coordinates of the submarine cable), and the five-pointed star represents the cable coordinates corresponding to the global optimal solution, that is, the cable coordinates calculated by the improved Grey Wolf algorithm.

[0243] The cable coordinates calculated based on the method disclosed in this embodiment are (3.00321528, -2.9992662).

[0244] Based on the error calculation formula, the error between the obtained cable coordinates (3.00321528, -2.9992662) and the actual cable coordinates (3, -3) was calculated, and the error was 0.0033, indicating that the algorithm has strong ability in submarine cable positioning tasks under specific conditions.

[0245] The error calculation formula used in this embodiment is:

[0246]

[0247] Among them, e rr represents the error, (x s ,y s ) represents the calculated value of the cable coordinate; (x r ,y r ) represents the actual value of the cable coordinates.

[0248] After obtaining the global optimal solution based on the comparison of the optimal fitness obtained in each positioning solution step, the iterative data corresponding to the positioning solution step corresponding to the global optimal solution is extracted, and the corresponding fitness curve is drawn according to the update of the optimal fitness in each iteration step, where the horizontal axis corresponds to the number of iterations and the vertical axis corresponds to the optimal fitness. The obtained fitness curve is as follows: Figure 4 As shown by the yellow curve;

[0249] The improved grey wolf algorithm used is replaced by the existing public common grey wolf algorithm, and the rest remains unchanged to locate the submarine cable. The corresponding fitness curve is as follows: Figure 4 The blue curve in the middle shows;

[0250] By comparison, the improved grey wolf algorithm has stronger convergence ability.

[0251] Figure 5 for Figure 4 The corresponding improved grey wolf algorithm ( Figure 5 The yellow curve in the middle) is compared with the existing public common grey wolf algorithm ( Figure 5 The fitness curve comparison chart corresponding to the last five iterations (blue curve in the middle) is based on Figure 5 It can be seen that the improved grey wolf algorithm has better accuracy.

[0252] The present invention also provides a submarine cable positioning system for executing the above-mentioned submarine cable positioning method, comprising a plurality of detection robots and a positioning system connected by signals:

[0253] The detection robot is used to measure the magnetic induction intensity in the corresponding detection plane;

[0254] The positioning system is used to locate the two-dimensional coordinates of the target cable in the detection plane based on the detection data acquired by each detection robot using the optimized grey wolf algorithm;

[0255] The positioning system comprises:

[0256] A simulation module is used to construct an expression of magnetic induction intensity corresponding to the target cable, and calculate the magnetic induction intensity corresponding to the target wolf based on the expression of magnetic induction intensity to obtain a detection value corresponding to the detection robot one by one;

[0257] A detection module is used to detect the magnetic induction intensity corresponding to the target quantity using each detection robot to obtain a detection value corresponding to the detection robot;

[0258] A configuration module, used to configure the number of starting points, the maximum number of iterations and a fitness function, wherein the fitness function is used to indicate the relationship between each detection value and each calculated value of the target wolf and its fitness;

[0259] A solution module, used for performing a positioning solution step based on different starting points according to the number of starting points, obtaining a global optimal solution after all starting points have completed the positioning solution step, and using the position point corresponding to the global optimal solution as the two-dimensional coordinate of the target cable;

[0260] Among them, the solution module is configured as:

[0261] Initialize the wolf pack positions using single-point crossover operations based on the corresponding starting points;

[0262] The fitness of each wolf is calculated based on the fitness function. The three wolves with the best fitness are α wolf, β wolf and δ wolf.

[0263] Based on the α wolf, β wolf and δ wolf, the position of each wolf is iteratively updated, and based on the updated position of each wolf, fitness calculation is performed through a fitness function, and the α wolf, β wolf and δ wolf are updated based on the obtained fitness until the maximum number of iterations is reached.

[0264] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0265] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0266] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented 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.

[0267] The present invention is described with reference to the flowcharts and / or block diagrams of the method, terminal device (system), and computer program product according to the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0268] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0269] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0270] It should be noted that:

[0271] The "one embodiment" or "embodiment" mentioned in the specification means that the specific features, structures or characteristics described in conjunction with the embodiment are included in at least one embodiment of the present invention. Therefore, the phrases "one embodiment" or "embodiment" appearing in various places throughout the specification do not necessarily refer to the same embodiment.

[0272] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0273] In addition, it should be noted that the shapes and names of the parts and components of the specific embodiments described in this specification may be different. Any equivalent or simple changes made based on the structure, features and principles described in the patent concept of the present invention are included in the protection scope of the patent of the present invention. The technicians in the technical field of the present invention can make various modifications or supplements to the specific embodiments described or replace them in a similar manner, as long as they do not deviate from the structure of the present invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. A method for locating a submarine cable, characterized in that: The following steps are involved: Pre-configure a number of detection robots, wherein the detection robots measure the magnetic induction intensity in the detection plane where they are located; Using the optimized grey wolf algorithm, based on the detection data acquired by each detection robot, the two-dimensional coordinates of the target cable are located in the detection plane; The optimized gray wolf algorithm includes the following steps: Construct the magnetic induction intensity expression corresponding to the target cable; Constructing a fitness function, the fitness function is used to indicate the relationship between each detection value and each calculated value of the target wolf and its fitness; calculating the magnetic induction intensity corresponding to the target wolf based on the magnetic induction intensity expression to obtain the calculated value corresponding to the detection robot one by one; using each detection robot to detect the magnetic induction intensity corresponding to the target wolf to obtain the detection value corresponding to the detection robot one by one; Based on the number of pre-configured starting points, positioning and solving steps are performed based on different starting points. After all starting points have completed the positioning and solving steps, a global optimal solution is obtained, and the position point corresponding to the global optimal solution is used as the two-dimensional coordinate of the target cable; Among them, each positioning solution step includes: Initialize the wolf pack positions using single-point crossover operations based on the corresponding starting points; The fitness of each wolf is calculated based on the fitness function. The three wolves with the best fitness are α wolf, β wolf and δ wolf. Based on the α wolf, β wolf and δ wolf, the position of each wolf is iteratively updated, and the fitness is calculated based on the updated position of each wolf, and the α wolf, β wolf and δ wolf are updated based on the obtained fitness until a preset maximum number of iterations is reached.

2. The method for locating a submarine cable according to claim 1, characterized in that: In one iteration, the steps of updating the position of the target wolf include: Take the target wolf's position as the first position; Processing the first position based on the MCMC random walk strategy to obtain a second position; The second position is updated based on the positions of wolf α, wolf β and wolf δ to obtain a third position, and the third position is used as the position of the target wolf in the next iteration step.

3. The method for locating a submarine cable according to claim 2, characterized in that: The specific steps of processing the first position based on the MCMC random walk strategy to obtain the second position are: generating a first random number; When the first random number is less than the preset acceptance probability, the processing state is determined to be maintained; if it is greater than or equal to the preset acceptance probability, the processing state is determined to be updated; When the processing state is maintained, taking the first position as the second position; When the processing state is updating, a corresponding random walk step number is generated based on the convergence factor corresponding to the current iteration step and the first random number, and the first position is updated based on the random walk step number to obtain a second position, and the calculation formula is: in: is the number of random walk steps in the MCMC random walk strategy; a is the convergence factor corresponding to the current iteration step; σ is the first random number; The location of the target wolf; is the second position.

4. The method for locating a submarine cable according to claim 3, characterized in that: The calculation formula of the convergence factor a is: in: t is the number of iterations; a t is the convergence factor corresponding to the tth iteration step; a t+1 is the convergence factor corresponding to the t+1th iteration step.

5. The method for locating a submarine cable according to claim 4, characterized in that: Based on the position update formula, the second position is updated according to the positions of wolf α, wolf β and wolf δ to obtain the third position; The position update formula is: in: is the position of wolf α; is the position of β wolf; is the position of δ wolf; The second position for the target wolf; The third position for the target wolf; represents the distance between wolf α and the target wolf; represents the distance between β wolf and target wolf; represents the distance between δ wolf and target wolf; Indicates the distance the target wolf needs to move toward the α wolf; Indicates the distance the target wolf needs to move toward the β wolf; Indicates the distance the target wolf needs to move toward the δ wolf; and Both are first control parameters, and are obtained by the convergence factor and random number calculation corresponding to the current iteration step; and are both second control parameters, and are both generated based on random numbers.

6. The method for locating a submarine cable according to claim 5, characterized in that: When the α wolf, β wolf or δ wolf is updated, the corresponding wolf is recorded as the target leader wolf, and the first control parameter and the second control parameter corresponding to the target leader wolf are calculated for use in the next iteration step; The specific steps of calculating the first control parameter and the second control parameter corresponding to the target wolf leader are: Randomly generate a second random number and a third random number for the target wolf leader; Calculating a first control parameter of the target wolf leader based on the convergence factor of the current iteration step and the second random number; A second control parameter of the target wolf leader is calculated based on the third random number.

7. The method for locating a submarine cable according to any one of claims 1 to 6, characterized in that: The magnetic induction intensity expression is: in: B(r) is the magnetic induction intensity corresponding to the target wolf for the target detection robot; r is the distance between the target wolf and the target detection robot; k is the first environmental correction factor; c is the second environmental correction factor; I is the effective value of the rated current; s is the phase spacing.

8. The method for locating a submarine cable according to any one of claims 1 to 6, characterized in that: The formula of the fitness function is: in: f(x c ,y c ) is the coordinate (x c ,y c )’s wolf fitness; N is the number of detection robots; B r(n) is the calculated value corresponding to the nth detection robot; B s(n) is the detection value corresponding to the nth detection robot.

9. The method for locating a submarine cable according to any one of claims 1 to 6, characterized in that: The specific steps of initializing the wolf pack positions using single-point crossover operations based on the corresponding starting points are: A two-dimensional vector is used to represent the path of the submarine cable, and the starting points are two randomly selected vectors; Determine a corresponding parent path based on the starting point, and randomly select a point from the parent path as an intersection point; A crossover operation is performed based on the crossover points, and the resulting offspring position matrix is ​​used as the initial wolf population.

10. A submarine cable positioning system, characterized in that: Including several detection robots and positioning systems connected by signals: The detection robot is used to measure the magnetic induction intensity in the corresponding detection plane; The positioning system is used to locate the two-dimensional coordinates of the target cable in the detection plane based on the detection data acquired by each detection robot using the optimized grey wolf algorithm; The positioning system comprises: A simulation module is used to construct an expression of magnetic induction intensity corresponding to the target cable, and calculate the magnetic induction intensity corresponding to the target wolf based on the expression of magnetic induction intensity to obtain a detection value corresponding to the detection robot one by one; A detection module is used to detect the magnetic induction intensity corresponding to the target quantity using each detection robot to obtain a detection value corresponding to the detection robot; A configuration module, used to configure the number of starting points, the maximum number of iterations and a fitness function, wherein the fitness function is used to indicate the relationship between each detection value and each calculated value of the target wolf and its fitness; A solution module, used for performing a positioning solution step based on different starting points according to the number of starting points, obtaining a global optimal solution after all starting points have completed the positioning solution step, and using the position point corresponding to the global optimal solution as the two-dimensional coordinate of the target cable; Among them, the solution module is configured as: Initialize the wolf pack positions using single-point crossover operations based on the corresponding starting points; The fitness of each wolf is calculated based on the fitness function. The three wolves with the best fitness are α wolf, β wolf and δ wolf. Based on the α wolf, β wolf and δ wolf, the position of each wolf is iteratively updated, and based on the updated position of each wolf, fitness calculation is performed through a fitness function, and the α wolf, β wolf and δ wolf are updated based on the obtained fitness until the maximum number of iterations is reached.

Images