Two-dimensional ship pipeline layout method based on artificial bee colony algorithm

Abstract

The invention relates to the technical field of ship pipeline planning, in particular to a two-dimensional ship pipeline layout method based on an artificial bee colony algorithm, and the method comprises the following steps: 1, carrying out the simplified expression of an equipment model and a layout space, and building a pipeline layout problem mathematical model; 2, improving an artificial bee colony algorithm through a chaotic elite inverse learning population to calculate an initial solution of a pipeline layout problem mathematical model; and step 3, continuously updating the initial solution through optimally guided employed bees and spirally searched following bees and scout bees until a convergence condition is met, so that the path planning efficiency and the layout design quality are improved, and the design cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of ship pipeline planning, and specifically relates to a two-dimensional ship pipeline layout method based on the artificial bee colony algorithm. Background Art

[0002] Pipeline design is crucial in the overall design of ships. A reasonable pipeline layout can reduce ship energy consumption, and a good pipeline design facilitates maintenance. Pipeline design plays a key role in the performance, safety, and economic operation of ships. With the continuous development of digitization and intelligence, in the field of pipeline layout, the trend of intelligence is irresistible. Currently, many scholars and designers have adopted intelligent algorithms to deal with pipeline layout problems. The automatic layout calculation method of ship pipeline lines disclosed in the publication number CN115587453A realizes the solution of the single-pipeline laying path based on the A* algorithm according to the cabin structure and pipeline laying rules, and realizes the solution of the multi-pipeline laying path by using the pipeline priority sorting and cost value correction methods; however, when deterministic algorithms such as A* are used to solve two-dimensional pipeline layout problems, as the layout space expands, the search performance decreases exponentially. Among them, the artificial bee colony algorithm (ABC), as a classic heuristic search algorithm, has attracted much attention due to its efficient search ability and has become one of the research hotspots. However, the traditional ABC algorithm has many limitations when applied to two-dimensional pipeline layout. Firstly, the traditional ABC algorithm is significantly affected by the initial solution; secondly, without modification, the traditional ABC algorithm cannot be directly used to solve pipeline layout problems. Summary of the Invention

[0003] The technical problem to be solved by the present invention is: to overcome the deficiencies of the prior art and provide a two-dimensional ship pipeline layout method based on the artificial bee colony algorithm.

[0004] The technical solution adopted by the present application to solve its technical problems is: the two-dimensional ship pipeline layout method based on the artificial bee colony algorithm includes the following steps:

[0005] Step 1: Simplify the expression of the equipment model and the layout space, and establish a mathematical model of the pipeline layout problem;

[0006] Step 2: Improve the initial solution of the artificial bee colony algorithm for calculating the mathematical model of the pipeline layout problem through the chaotic elite reverse learning population;

[0007] Step 3: Continuously update the initial solution through the employed bees guided by the optimal solution, the follower bees with spiral search, and the scout bees until the convergence condition is met;

[0008] Step 4: Calculate the coordinate solution of the pipeline, and convert the orthogonalized coordinate solution into a node solution as the final solution of the pipeline layout problem. The following sub-steps are included in the said Step 1:

[0009] 1-1: Simplify the expression of equipment in a ship using the axis-parallel bounding box method;

[0010] 1-2: Simplify the connection of pipelines into a point according to the centerline theory, and simplify the complete pipeline into a centerline;

[0011] 1-3: Determine the objective function of the mathematical model for the pipeline layout problem.

[0012] The objective function of the mathematical model for the pipeline layout problem is to minimize the weighted function min F(x), which is expressed as follows:

[0013]

[0014] In the formula, X i is the i-th optimization objective; w i is the weight factor of the i-th optimization objective; X ij is the pipeline storage information in each optimization objective, expressed as the j-th pipeline node in the i-th solution; X ij_no is the set of infeasible grids; lb is the lower limit of the layout space; ub is the upper limit of the layout space; i, j, k are natural numbers, and j and k are pipeline nodes in different dimensions.

[0015] The construction of the initial solution in step two is X i =(X i,1 , X i,2 ,...X i,j ...X i,D ), x i,j is the j-th node of the i-th pipeline solution, D is a natural number, and step two includes the following sub-steps:

[0016] 2-1: Generate a set of basic solutions, and select the most outstanding elite individuals from this set of basic solutions as the elite solutions.

[0017] 2-2: Perform chaotic inverse learning based on the elite solutions to generate another set of solutions.

[0018] 2-3: Select elite individuals from the two sets of solutions again to generate the elite initial solution.

[0019] Step three includes the following sub-steps:

[0020] 3-1: Employed bee stage, guide the search direction based on the current optimal solution and the global optimal solution, control the search direction by adjusting the influence degree of the current optimal solution and the global optimal solution based on the weight, and update the solution;

[0021] 3-2: The follower bees perform spiral development around the global optimal solution. Meanwhile, the follower bees exchange information with other solutions, search from different angles and directions, increase the possibility of jumping out of the local optimal solution, and update the solution.

[0022] The 3-1 includes the following sub-steps:

[0023] 3-1-1: Calculate the current optimal solution;

[0024] 3-1-2: Calculate the global optimal solution;

[0025] 3-1-3: Based on the weights, update the expression of the solution by adjusting the influence degrees of the current optimal solution and the global optimal solution on the search direction as follows:

[0026] X i,j = X i,j + φ(X i,j - X k,j ) + λ 1 (X pbest,j - X i,j ) + λ 2 (X gbest,j - X i,j );

[0027] Where φ is a random number with a value in the interval [-1, 1]; λ 1 and λ 2 are the influence factors of the current optimal and global optimal individuals respectively, which are 1.5 and 1 in the first 1 / 2 iterations and 1 and 1.5 in the last 1 / 2 iterations; X pbest and X gbest are the current optimal and global optimal individuals respectively.

[0028] In the 3-1-1, the one with the optimal fitness value among the employed bees in the current iteration is the current optimal solution.

[0029] In the 3-1-2, the optimal solution in the completed iteration process is the global optimal solution.

[0030] In the 3-2, the expression of the updated solution is as follows:

[0031]

[0032] In the formula, a 1 and a 2 are the weight coefficients that control the tendency of the follower bees to move towards other bees and the global optimal solution, and i and k are the numbers of the current follower bees.

[0033] In the fourth step, the orthonormalized coordinate solution is converted into the node solution through the conversion formula as the final solution of the pipeline layout problem. The conversion formula is as follows:

[0034]

[0035] Among them, P x and P y are the solutions obtained by the artificial bee colony algorithm, corresponding to the coordinate information of the pipeline nodes mapped on the grid map. P is the pipeline node information, mod is the modulo operation, ceil is the ceiling operation, d is the grid size, R x and R y are the number of rows and columns of the grid map respectively.

[0036] Compared with the prior art, the present application has the following beneficial effects:

[0037] The present invention proposes an improved artificial bee colony algorithm for ship pipeline layout design, which improves the path planning efficiency and the quality of layout design, reduces the design cost, provides an effective reference for designers, enables the pipeline layout to better meet the complex multi-objective and multi-constraint requirements of ship pipeline design, and has important engineering significance for the intellectualization and automation of pipeline design.

[0038] The present invention uses an improved artificial bee colony algorithm for two-dimensional ship pipeline design, making the layout efficiency less affected by the layout space size. Compared with deterministic algorithms, it is not easy to fall into local optima, and the layout efficiency and quality are significantly improved;

[0039] The present invention proposes a chaotic elite inverse learning strategy to improve the quality of the initial solution and accelerate the convergence speed;

[0040] The present invention proposes an employed bee search formula guided by the cross of the current optimal solution and the global optimal solution, making the search more directional;

[0041] The present invention proposes a follower bee search formula that refers to random solutions and develops spirally around the global optimal solution, improving the development efficiency and avoiding falling into local optimal solutions to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is the flow chart of the artificial bee colony algorithm of the present invention;

[0043] Figure 2 is the schematic diagram of the layout simulation result of the original artificial bee colony algorithm;

[0044] Figure 3 is the schematic diagram of the layout simulation result of the present application. DETAILED DESCRIPTION OF THE INVENTION

[0045] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0046] It should be noted that all directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative positional relationship and movement conditions between components in a specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly.

[0047] In the present invention, unless otherwise clearly defined and limited, terms such as "connection" and "fixation" should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or integrated; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and can be the communication inside two components or the interaction relationship between two components, unless otherwise clearly limited. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0048] The artificial bee colony algorithm is inspired by the foraging behavior of bees in nature and divides the population into employed bees and follower bees. The traditional artificial bee colony algorithm first initializes the population through the following formula to obtain the initial solution, and the number of initial solution updates is set to zero. The specific formula is:

[0049] X j =lb j +rand·(ub j -lb j );

[0050] Among them, lb is the lower limit of the layout space; ub is the upper limit of the layout space; rand is a random number between 0 and 1; X j is the solution of the jth dimension.

[0051] Next, enter the employed bee stage. The employed bees update the solution according to the information of the primary solution through the following formula. If the new solution is better than the old solution, it is replaced, and the number of solution updates is reset to zero; if not replaced, the number of solution updates is incremented by one.

[0052] X i,j =X i,j +φ(X i,j -X k,j );

[0053] Among them, φ is a random number with a value in the interval [-1, 1]. X i,j 、Xk,j are the j-th dimension in the i-th solution and the j-th solution respectively.

[0054] Follower bees select the solution with the richest information for development according to the greedy criterion. The richness of information is determined by the proportion of its fitness value in the sum of all solution fitness values. The information calculation and development formula are as follows:

[0055]

[0056] X i,j =X i,j +φ(X i,j -X k,j );

[0057] Among them, p i is the information richness of the i-th solution, fit i is the fitness value of the i-th solution, and SN is the number of solutions.

[0058] The solution updated by the follower bee is also replaced and the number of updates is calculated according to the greedy criterion. When a solution has not been updated for a long time, the bee corresponding to the solution is converted into a scout bee and a new solution is generated by referring to the initialization formula.

[0059] The present invention improves the search mechanism and coding rules of the traditional artificial bee colony algorithm, making the algorithm more suitable for solving the two-dimensional ship pipeline layout problem. Figures 1 - 3 ,The 2D ship pipeline layout method based on artificial bee colony algorithm includes the following steps:

[0060] Step 1: Use the grid method to simplify the equipment model and layout space, and build a mathematical model for the pipeline layout problem with the laying length, number of elbows, and the convenience of arranging brackets as the goal;

[0061] The layout environment of the ship only includes the maximum geometric information of the equipment, which can not only meet the requirements but also improve the search speed of the algorithm. Therefore, the step 1 includes the following sub-steps:

[0062] 1-1: Use the axis-parallel containment box method to simplify the equipment in the ship;

[0063] 1-2: The simplified pipeline model will not affect the expression of the pipeline direction, so according to the centerline theory, the connection of the pipeline is simplified to a point, and the complete pipeline is simplified to a centerline;

[0064] 1-3: The objective function of the mathematical model of the pipeline layout problem mainly considers the influence of pipe length and elbows. In addition, the energy value is used to express the goal of facilitating the arrangement of brackets by being as close as possible to the position where brackets can be arranged. Determine the objective function of the mathematical model of the pipeline layout problem.

[0065] The objective function for determining the mathematical model of the pipeline layout problem is to minimize the weighted function minF(x). It simplifies the multi-objective problem into a single-objective problem using the linear weighting method, and is specifically expressed as follows:

[0066]

[0067]

[0068] In the formula, X i is the i-th optimization objective; w i is the weight factor of the i-th optimization objective; X i,j is the pipeline storage information in each optimization objective, expressed as the j-th pipeline node in the i-th solution; X i,j_no is the set of infeasible grids; lb is the lower limit of the layout space; ub is the upper limit of the layout space; i, j, k are natural numbers, and j and k are pipeline nodes in different dimensions.

[0069] Step 2: Improve the initial solution of the artificial bee colony algorithm for calculating the mathematical model of the pipeline layout problem through the chaotic elite reverse learning population. To be applicable to solving the ship pipeline layout problem, the construction of all solutions is as shown in X i =(X i,1 , X i,2 ,... X i, j ... X i,D ), where x i,j is the j-th node of the i-th pipeline solution, and D is a natural number;

[0070] The initial solution of this application is generated using the chaotic elite reverse learning strategy, and this strategy has significant advantages. The second step includes the following sub-steps:

[0071] 2-1: Generate a set of basic solutions according to the initial solution generation formula of the traditional artificial bee colony algorithm, laying the foundation for the subsequent optimization process. Among this set of basic solutions, sort them by calculating the fitness values of each basic solution, and select the solution with the best fitness value as the elite solution. These elite individuals have high quality and potential and are the key to further optimization. The fitness value of each basic solution is the sum of the length and the number of elbows of the pipeline.

[0072] 2-2: Perform chaotic reverse learning based on the elite solution to generate another set of solutions, as shown in the following formula. The process of reverse learning can fully explore the potential information of the elite solution, expand the solution space, and provide more possibilities for finding a better solution. In this way, both sets of solutions obtained have certain value.

[0073] Furthermore, define a point X e in the D-dimensional space as the elite individual of the initial solution set (corresponding to sub-step 2-1), where Xe It is expressed as follows:

[0074]

[0075] Wherein, is the j-th dimension of the elite solution; D is the upper limit of the dimension.

[0076] Reverse solution is expressed as and its definition is as follows:

[0077]

[0078] Wherein, is a random number generated by using the Tent chaotic map and taking values in the interval [0, 1].

[0079] α j , β j are dynamic boundary conditions. Compared with the fixed boundary conditions, they can make the construction of the elite reverse solution in a more accurate search space. Among them, α j = min(X i,j ), β j = max(X i,j ).

[0080] To avoid the elite reverse point crossing the boundary and becoming an infeasible solution, a randomization method is adopted for resetting, and the expression is as follows:

[0081]

[0082] 2 - 3: Re-screen the elite individuals from the two groups of solutions, and these elite individuals jointly form the elite initial solution.

[0083] The chaotic elite inverse learning strategy greatly improves the quality and diversity of the initial solution. The improvement in quality makes the initial solution more likely to guide the optimization process towards a better direction, reducing ineffective searches and iterations. The increase in diversity provides a broader search space for the optimization process, avoiding falling into local optimal solutions. This strategy can effectively improve the search efficiency and solution accuracy of the algorithm, providing strong support for solving complex pipeline layout optimization problems.

[0084] Step 3: Continuously update the initial solution through the optimal-guided employed bees, spiral-searching follower bees, and scout bees until the convergence condition is met. The following sub-steps are included in Step 3:

[0085] 3 - 1: In the employed bee stage, based on the current optimal solution and the global optimal solution, clearly guide the search direction, control the influence degree of the current optimal solution and the global optimal solution based on the weight to adjust the search direction, and update the solution;

[0086] In the employed bee stage, in-depth exploration and development are mainly carried out around the optimal solution. The importance of this stage lies in that it can greatly affect the convergence speed and solution quality of the entire algorithm. Different from the traditional artificial bee colony algorithm, the traditional algorithm often relies on the information of two random solutions for development, which has certain uncertainty and blindness. In the improved algorithm, the current optimal solution and the global optimal solution are introduced to clearly guide the search direction. The current optimal solution represents the solution that performs the best in the current iteration process, which can provide a strong direction for local search. The global optimal solution, from the perspective of the entire search process, represents the optimal solution found so far, which provides the algorithm with a global vision and goal. Specifically, 3-1 includes the following sub-steps:

[0087] 3-1-1: Calculate the current optimal solution. The one with the best fitness value among the employed bees in the current iteration is the current optimal solution;

[0088] 3-1-2: Calculate the global optimal solution. The optimal solution in the completed iteration process is the global optimal solution;

[0089] 3-1-3: Update the solution based on the weights to adjust the influence degree of the current optimal solution and the global optimal solution on the search direction. The expression for updating the solution is as follows:

[0090] X i,j =X i,j +φ(X i,j -X k,j )+λ 1 (X pbest,j -X i,j )+λ 2 (X gbest,j -X i,j );

[0091] where φ is a random number with a value in the interval [-1, 1]; λ 1 and λ 2 are the influence factors of the current optimal and global optimal individuals respectively, which are 1.5 and 1 in the first 1 / 2 iteration, and 1 and 1.5 in the last 1 / 2 iteration; X pbest and X gbes are the current optimal and global optimal individuals respectively.

[0092] By adjusting the influence degree between the two through weights, the search direction can be controlled more flexibly. When the weight biases towards the current optimal solution, the algorithm pays more attention to the local fine search, and can conduct a more in-depth exploration near the current optimal solution in the hope of finding a better solution. When the weight biases towards the global optimal solution, the algorithm tends to conduct a global exploration to avoid falling into the local optimal solution. This way of weight adjustment enables the algorithm to adjust the search strategy according to different problems and search stages, thereby improving the adaptability and solving ability of the algorithm.

[0093] 3-2: The onlooker bees conduct spiral development around the global optimal solution. At the same time, the onlooker bees exchange information with other solutions, search from different angles and directions, increase the possibility of jumping out of the local optimal solution, and update the solution.

[0094] After the employed bees complete the update, the onlooker bees exhibit characteristics quite different from those of the traditional ABC algorithm. In the traditional ABC algorithm, the onlooker bees and the employed bees use the same update formula around two random solutions. This method has certain limitations because the uncertainty of the random solutions may lead to blindness and inefficiency in the search process.

[0095] In the improved algorithm, the onlooker bees will conduct spiral development around the global optimal solution. As the global optimal solution is the currently known best solution in the entire search space, it provides a clear goal and direction for the onlooker bees. By conducting spiral development around the global optimal solution, the onlooker bees can search more targeted near it, thereby improving the efficiency and accuracy of the search.

[0096] The onlooker bees also exchange information with other solutions. This information exchange mechanism enables the onlooker bees to obtain the characteristics and advantages of different solutions, thereby enriching their own search strategies. Through interaction with other solutions, the onlooker bees can avoid falling into the local optimal solution. The local optimal solution is a common problem in optimization algorithms. When the algorithm falls into the local optimal solution, it is very difficult to further find a better solution. Through information exchange with other solutions, the onlooker bees can search from different angles and directions, increasing the possibility of jumping out of the local optimal solution. At this time, the expression for updating the solution is as follows:

[0097]

[0098] β = e bl ·cos(2πl);

[0099] In the formula, a 1 and a 2is the weight coefficient that controls the tendency of follower bees to move towards other bees and the global optimal solution. a is a constant used to determine the degree of the movement tendency. i and k are the numbers of the current follower bees. rand is a function that generates random numbers between 0 and 1. β is the spiral control parameter. T is the total number of iterations. t is the current iteration number. b is a constant that defines the spiral shape. l is a random number with a value between [-1, 1].

[0100] Step 4: Calculate the coordinate solution of the pipeline through the improved artificial bee colony algorithm. The orthogonally transformed coordinate solution is converted into a node solution through a conversion formula as the final solution to the pipeline layout problem. When used in the actual environment, the node solution can be converted back to the coordinate solution. Referring to the traditional artificial bee colony algorithm, if the solutions corresponding to either the employed bees or the follower bees reach the set upper limit of the update times without being updated, they will be transformed into scout bees and updated according to the generation formula of the initial solution of the traditional artificial bee colony algorithm, and the update times will be reset to zero.

[0101] Meanwhile, considering the requirements of the grid method for environment description and pipeline orthogonality, it is necessary to convert the solutions calculated by the iterative calculation of the artificial bee colony algorithm into node solutions that store pipeline information. The conversion formula is as follows:

[0102]

[0103] Among them, P x and P y are the solutions obtained by the artificial bee colony algorithm, corresponding to the coordinate information of the pipeline nodes mapped on the grid map. P is the pipeline node information, which is the x i,j above, mod is the remainder calculation, ceil is the ceiling calculation, d is the grid size, R x and R y are the number of rows and columns of the grid map respectively.

[0104] For the pipeline node solutions obtained by the improved artificial bee colony algorithm, path orthogonality can be achieved by introducing an orthogonality operation. That is: for the coordinate information (x1, y1) and (x2, y2) corresponding to two pipeline nodes, one can choose to add the point (x1, y2), or add the point (x2, y1). Such an operation can make the path formed by the original two points present an orthogonal state and meet the design requirements of the pipeline.

[0105] The chaotic numbers of the present invention are used for the generation of reverse solutions and have a boundary control strategy. The present invention improves the exploration and exploitation capabilities of the artificial bee colony algorithm respectively based on the improvement of the search equations of the employed bees and the follower bees, the influence of other solutions, the current optimal solution and the global optimal solution in the employed bee equation, and the use of the spiral development formula in the follower bee equation.

[0106] The above are only alternative embodiments of the present invention, and thus do not limit the patent scope of the present invention. Any equivalent structural transformation made using the content of the specification of the present invention under the concept of the present invention, or direct / indirect application in other related technical fields, is included in the patent protection scope of the present invention.

Claims

1. A two-dimensional ship pipeline layout method based on artificial bee colony algorithm, characterized in that: The steps include: Step 1: Simplify the equipment model and layout space, and build a mathematical model for the pipeline layout problem; Step 2: Improve the initial solution of the mathematical model of pipeline layout problem by using the chaotic elite inverse learning population to calculate the artificial bee colony algorithm; Step 3: The initial solution is continuously updated by the optimally guided employed bees, spiral search follower bees and scout bees until the convergence condition is met; Step 4: Obtain the coordinate solution of the pipeline, and convert the orthogonalized coordinate solution into a node solution as the final solution to the pipeline layout problem.

2. The two-dimensional ship pipeline layout method based on artificial bee colony algorithm according to claim 1 is characterized in that: The step 1 includes the following sub-steps: 1-1: Use the axis-parallel containment box method to simplify the equipment in the ship; 1-2: According to the centerline theory, the connection of the pipeline is simplified to a point, and the complete pipeline is simplified to a centerline; 1-3: Determine the objective function of the mathematical model of the pipeline layout problem.

3. The two-dimensional ship pipeline layout method based on artificial bee colony algorithm according to claim 2 is characterized in that: The objective function of the mathematical model for determining the pipeline layout problem is to minimize the weighted function min F(x), which is expressed as follows: Where, X i is the i-th optimization objective; w i is the weight factor of the i-th optimization objective; X ij Store information for the pipelines in each optimization target, represented as the jth pipeline node in the i-th solution; X ij_no is the set of infeasible grids; lb is the lower limit of the layout space; ub is the upper limit of the layout space; i, j, k are natural numbers, and j and k are pipeline nodes of different dimensions.

4. The two-dimensional ship pipeline layout method based on artificial bee colony algorithm according to claim 2 is characterized in that: The initial solution in step 2 is constructed as X i =(X i,1 ,X i,2 ,...X i,j ...X i,D ), x i,j is the jth node of the i-th pipeline solution, D is a natural number, and the step 2 includes the following sub-steps: 2-1: Generate a set of basic solutions, and select the elite individuals with the most outstanding performance from this set of basic solutions as the elite solutions. 2-2: Perform chaotic inverse learning based on the elite solution to generate another set of solutions; 2-3: Select elite individuals from the two sets of solutions again to generate elite initial solutions.

5. The two-dimensional ship pipeline layout method based on artificial bee colony algorithm according to claim 4 is characterized in that: The step three includes the following sub-steps: 3-1: Hired bee stage, guiding the search direction based on the current optimal solution and the global optimal solution, adjusting the influence of the current optimal solution and the global optimal solution based on the weight to control the search direction and update the solution; 3-2: Follower bees perform spiral development around the global optimal solution. At the same time, follower bees exchange information with other solutions, search from different angles and directions, increase the possibility of jumping out of the local optimal solution, and update the solution.

6. The two-dimensional ship pipeline layout method based on artificial bee colony algorithm according to claim 5 is characterized in that: The 3-1 step includes the following sub-steps: 3-1-1: Calculate the current optimal solution; 3-1-2: Calculate the global optimal solution; 3-1-3: The expression after updating the solution based on the weight adjustment of the influence of the current optimal solution and the global optimal solution on the search direction is as follows: X i,j =X i,j +φ(X i,j -X k,j )+λ1(X pbest,j -X i,j )+λ2(X gbest,j -X i,j ); Where φ is a random number in the interval [-1, 1]; λ1 and λ2 are the influence factors of the current optimal and global optimal individuals, which are 1.5 and 1 in the first 1 / 2 iterations and 1 and 1.5 in the second 1 / 2 iterations; X pbest and X gbest are the current optimal and global optimal individuals respectively.

7. The two-dimensional ship pipeline layout method based on artificial bee colony algorithm according to claim 6 is characterized in that: The employed bee with the best fitness value in the current iteration number in 3-1-1 is the current optimal solution.

8. The two-dimensional ship pipeline layout method based on artificial bee colony algorithm according to claim 6 is characterized in that: The optimal solution in the iterative process completed in 3-1-2 is the global optimal solution.

9. The two-dimensional ship pipeline layout method based on artificial bee colony algorithm according to claim 6 is characterized in that: The updated solution in 3-2 The following expression is: Where a1 and a2 are weight coefficients that control the tendency of the follower bee to move toward other bees and the global optimal solution, i and k are the numbers of the current follower bee, rand is a function that generates random numbers between 0 and 1, and β is the spiral control parameter.

10. The two-dimensional ship pipeline layout method based on artificial bee colony algorithm according to claim 9 is characterized in that: The orthogonalized coordinate solution in step 4 is converted into a node solution as the final solution of the pipeline layout problem through a conversion formula. The conversion formula is as follows: Among them, P x and P y is the solution calculated by the artificial bee colony algorithm, corresponding to the coordinate information of the pipeline node mapped on the grid map, P is the pipeline node information, mod is the remainder calculation, ceil is the rounding up calculation, d is the grid size, R x and R y are the number of rows and columns of the raster map, respectively.

Images