Workshop facility layout optimization method and equipment based on simulation and improved coral reef optimization algorithm

Abstract

The invention belongs to the related technical field of workshop facility layout optimization, and discloses a workshop facility layout optimization method and equipment based on a simulation and improved coral reef optimization algorithm, and the method comprises the steps: constructing a discrete event simulation model of an engine core part production and manufacturing workshop, and carrying out the accurate description of the discrete event simulation model; an improved coral reef optimization algorithm is adopted to carry out iterative optimization on the facility layout, so that the logistics transportation distance generated during order processing of a production and manufacturing workshop is reduced, and the logistics transportation cost of the workshop is further reduced; meanwhile, the logistics transportation condition obtained through simulation is real and reliable, and positive guidance can be provided for facility layout optimization of an engine core part production and manufacturing workshop.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field related to workshop facility layout optimization, and more particularly to a workshop facility layout optimization method and device based on simulation and improved coral reef optimization algorithm. BACKGROUND

[0002] The breakthrough and wide application of new generation intelligent manufacturing technology are leading and promoting the fourth wave of industrial revolution. With the rapid development of big data, artificial intelligence, and Internet of Things, manufacturing industry is facing unprecedented opportunities and challenges. The informatization, digitization, and intelligentization of enterprises are constantly advancing. In the face of today's complex and changing background and increasingly fierce competitive environment, enterprises often need to make continuous adjustments and changes to adapt to market demand. Among them, the facility layout of manufacturing site and the production cost, production efficiency, plant utilization rate, equipment life, and workshop safety of enterprise are closely related. Therefore, research on manufacturing system facility layout problem is of great significance to enhance the competitiveness of enterprises.

[0003] The facility layout of workshop is one of the key factors affecting the overall production efficiency and resource utilization. Traditional facility layout often relies on manual experience and lacks scientific and reasonable optimization methods, resulting in problems such as poor production flow, low equipment utilization, and long operation time. SUMMARY

[0004] In view of the above defects or improvement needs of the prior art, the present application provides a workshop facility layout optimization method and device based on simulation and improved coral reef optimization algorithm, which aims to solve the problem of high logistics cost of existing workshop facility layout.

[0005] To achieve the above-mentioned purpose, according to one aspect of the present application, a workshop facility layout optimization method based on simulation and improved coral reef optimization algorithm is provided, which comprises the following steps:

[0006] S1, obtaining the logistics transportation distance of completed orders based on the simulation model of engine core part processing and manufacturing workshop discrete events;

[0007] S2, generating an initial population based on the initial layout condition and SLP method random disturbance, randomly distributing the initial individuals in different spaces in the coral reef, and setting the iteration number t = 0;

[0008] S3, judging whether the iteration number t < T, if not, turning to step S4; otherwise, ending iteration and outputting the final workshop facility layout;

[0009] S4, decoding: inputting the layout code of the individual into the simulation model to generate the corresponding layout scheme of the individual;

[0010] S5: Repairing the layout scheme that does not meet the constraint condition by using a repair factor;

[0011] S6, fitness calculation: calculating the fitness of the individual based on the simulation model;

[0012] S7, external sexual reproduction: sorting the individual in the coral reef according to the logistics transportation distance from small to large, performing coding arithmetic crossover breeding on the first F b proportion of individuals in the sequence, releasing the generated offspring into the water, and calculating the fitness of the individual;

[0013] S8, internal sexual reproduction: breeding the remaining individuals in the coral reef, releasing the generated individuals into the water, and calculating the fitness of the individual;

[0014] S9, sexual reproduction offspring occupation: the offspring generated in the sexual reproduction stage occupy the coral reef and settle in the population, and the remaining individuals die;

[0015] S10, asexual reproduction: calculating the shared fitness of all individuals in the current population, and then selecting the first F a proportion of individuals to perform Gaussian-Cauchy mutation, releasing the generated new offspring into the water, and calculating the fitness of the individual;

[0016] S11, asexual reproduction occupation: the offspring generated in the asexual reproduction stage occupy the coral reef and settle in the population, and the remaining individuals die;

[0017] S12, polyp stage predation: selecting the first F d proportion of individuals in the offspring to be eliminated with a dynamic elimination probability with a radix of P d , completing a round of iteration of the population, setting t=t+1, and returning to step S3.

[0018] Further, the calculation formula of the dynamic elimination probability is:

[0019]

[0020] In the formula, T is the total number of iterations.

[0021] Further, the remaining individuals in the coral reef are bred by using an improved internal sexual reproduction method based on the basic principle of grey wolf optimization algorithm. The individual is affected by the best individual in the population during the internal sexual reproduction process, and the three best individuals are denoted as α, β, and γ. The specific sub-steps are:

[0022] First, calculate the iteration factor of the current generation Where t and T represent the current iteration number and the total iteration number, respectively;

[0023] Then, the individual distance influence factor A and C are calculated, A = 2a r1-a, C = 2r2, wherein r1 and r2 are random numbers between 0 and 1;

[0024] Next, the distance between the individual p and the alpha, beta and gamma individuals is calculated, taking the alpha individual as an example: D α,p = |C α ·code α -code p |, wherein code α and code p are the encodings of the alpha and p individuals.

[0025] Finally, the final encoding of the offspring of the individual through sexual reproduction is calculated:

[0026] Further, the layout encoding of the individual is a three-segment encoding: a sequence of decimal integers containing 2n-3 elements, n being the number of devices to be arranged in the processing workshop; the first segment is a relative position encoding, with a length of 1, being a 01 encoding, indicating the relative position of the two large areas on the right side of the workshop; the second segment is a simulation order encoding, with a length of n-2, being a real number encoding between 0 and 1, and its size order indicates the arrangement order of the remaining n-2 devices, and if it exceeds the workshop boundary, it is adjusted from left to right and from top to bottom according to the automatic line change strategy; the third segment is a distance encoding, with a length of n-2, indicating the center point distance between the previous facility, and if it is the first device in a row, it indicates the distance from the left boundary of the workshop.

[0027] Further, the constraint conditions include: facility non-overlapping and distance greater than minimum safety distance constraint, not exceeding the workshop range constraint, facility in the layoutable area constraint.

[0028] Further, the repair factor repair process is: for the out-of-boundary problem, the longest distance d max in the third segment encoding is halved until the non-out-of-boundary condition is met; for the overlapping problem, the compensation Δd i is added to d i so that d i satisfies the minimum distance constraint of the facility.

[0029] Further, the sexual reproduction offspring occupies and the asexual reproduction offspring occupies, the offspring randomly selects a coral reef position, and if there is no coral in the current position, it directly colonizes; otherwise, based on the basic principle of simulated annealing, a poor-quality coral is accepted with a certain probability, and the probability of accepting the offspring to replace the parent in the current position is Wherein F(old) and F(new) are the fitness of the old and new corals respectively, T0 is the initial annealing temperature, rate is the annealing coefficient, if the occupation fails, a new position is re-occupied, and a maximum of k attempts is made.

[0030] Further, the fitness function of the individual is Wherein D is the total logistics transportation distance; the calculation steps of the shared fitness are:

[0031] S101, define the Euclidean distance of individual p relative to other individuals q in the population: And the fitness distance: Wherein L is the total length of the individual code;

[0032] S102, define the similarity of individual p and individual q: Wherein Is the distance threshold value in dimension i, also known as the niche radius, and alpha is the shape constant parameter of the niche;

[0033] S103, calculate the shared fitness of individual p to the population:

[0034] The application also provides a workshop facility layout optimization system based on simulation and improved coral reef optimization algorithm, the system comprises a memory and a processor, the memory stores a computer program, and the processor executes the computer program to execute the workshop facility layout optimization method based on simulation and improved coral reef optimization algorithm as described above.

[0035] The application also provides a computer readable storage medium, the computer readable storage medium stores machine executable instructions, when the machine executable instructions are called and executed by a processor, the machine executable instructions cause the processor to implement the workshop facility layout optimization method based on simulation and improved coral reef optimization algorithm as described above.

[0036] Overall, compared with the prior art, the workshop facility layout optimization method and device based on simulation and improved coral reef optimization algorithm provided by the application mainly have the following beneficial effects:

[0037] 1. The application accurately describes the engine core component production and manufacturing workshop by constructing a simulation model of the engine core component production and manufacturing workshop, and improves and optimizes the facility layout of the engine core component production and manufacturing workshop by using the improved coral reef optimization algorithm, thereby reducing the logistics transportation distance generated by the production and manufacturing workshop when processing orders, and further reducing the logistics transportation cost of the workshop; at the same time, the logistics transportation situation obtained by simulation is real and reliable, and can provide positive guidance for the facility layout optimization of the engine core component production and manufacturing workshop.

[0038] 2. The improved coral reef optimization algorithm provided by the present application greatly improves the solution efficiency and accuracy of the original algorithm by improving and optimizing the reproduction, occupation, predation and polyp stage of the traditional coral reef algorithm, thereby ensuring the effectiveness of the algorithm in solving multi-row facility layout problems.

[0039] 3. The workshop facility layout optimization method based on simulation and improved coral reef optimization algorithm provided by the present application is simple and easy to implement, has fast solution speed and strong flexibility, and can flexibly adjust the facility layout according to new production order conditions. BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 is a flowchart of a workshop facility layout optimization method based on simulation and improved coral reef optimization algorithm provided by the present application;

[0041] Figure 2 is a modeling and simulation model icon diagram of the initial layout of a workshop provided by an embodiment of the present application;

[0042] Figure 3 is a device comprehensive relationship diagram provided by an embodiment of the present application;

[0043] Figure 4 is a decoding layout diagram provided by an embodiment of the present application;

[0044] Figure 5 is an optimal layout diagram after optimization of the algorithm provided by an embodiment of the present application;

[0045] Figure 6 is an algorithm iteration history diagram provided by an embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of the present application clearer and more apparent, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application. In addition, the technical features involved in each embodiment of the present application described below can be combined with each other as long as they do not conflict with each other.

[0047] Please refer to Figure 1 The present application provides a workshop facility layout optimization method based on simulation and improved coral reef optimization algorithm, which mainly includes the following steps:

[0048] S1, a discrete event simulation model of an engine core component manufacturing workshop is established, and the initial position of the equipment, the logistics transportation equipment, the product process route, and the production order are input into the simulation model to obtain the logistics transportation distance of the completed order.

[0049] The simulation model can be modeled using the simulation software Factory Simulation developed by Huazhong University of Science and Technology, and the specific steps are as follows:

[0050] First, data modeling: the initial layout CAD model of the engine core component manufacturing workshop, process data, production order, workshop equipment processing parameters, and other workshop information description key data are imported into the simulation software.

[0051] Then, physical modeling: create processing stations, buffer zones, AGV logistics transportation trolleys, data tables, script methods, and other model objects in the simulation software.

[0052] Next, logical modeling, define scripts, triggers, and other objects to ensure that the simulation model can run according to the established logic.

[0053] Specifically, the engine core component manufacturing workshop is 290m x 90m in size and contains 11 processing areas, one of which is a fixed area, and the information of related facilities is shown in Table 1. According to the initial layout scheme, the simulation model diagram and the meaning of each icon in the diagram are shown in Figure 2

[0054] S2, generate an initial population based on the initial layout and SLP method random disturbance, randomly distribute the initial individuals in different spaces in the coral reef, and let the iteration number t = 0.

[0055] Where the total number of initial individuals generated is M x p, where M is the total space size of the coral reef, and p is the initial individual proportion.

[0056] Where, the systematic layout planning (SLP) mainly obtains the relationship between devices according to the logistics intensity between devices and the production required, and the relationship between different devices can be divided into five levels from high to low: A, E, I, O, U, and X. Based on the comprehensive relationship of device logistics intensity, the placement of devices is considered from high to low.

[0057] Table 1 Information of related facilities

[0058]

[0059] ​In one embodiment, the total number of iterations T of the algorithm is set to 200, the number of coral reefs M is 50, the initial population occupies the proportion of coral reefs ρ is 0.8, and the number of initial population individuals generated is 40. According to the analysis and calculation of the product process data, the logistics of each device is shown in Table 2, and the corresponding device comprehensive relationship diagram is shown in Figure 3 .

[0060] S3, judge the number of iterations t < T, if not, go to step S4; otherwise, end the iteration and output the final workshop facility layout.

[0061] S4, decoding: input the layout encoding of the individual into the simulation model to generate the corresponding layout scheme of the individual.

[0062] The layout encoding of the individual is a three-segment encoding: a sequence of decimal integers containing 2n-3 elements, n is the number of devices in the processing workshop to be planned. The first segment of the code is the relative position code, which is 01 code with a length of 1, indicating the relative position of the two large areas on the right side of the workshop; the second segment of the code is the simulation order code, which is a real number code between [0, 1] with a length of n-2, and its size order represents the placement order of the remaining n-2 devices, if it exceeds the workshop boundary, it will be adjusted from left to right and from top to bottom according to the automatic line change strategy; the third segment of the code is the distance code, which is n-2 in length, indicating the center point distance between the previous facility, if it is the first device in a row, it indicates the distance from the left boundary of the workshop.

[0063] Table 2 Logistics of each device

[0064]

[0065] Specifically, taking the code [1, 0.1, 0.2, 0.6, 0.7, 0.5, 0.8, 0.3, 0.4, 54, 55, 45, 30, 30, 145, 40, 30] as an example, the decoding process is: first, according to the first part, get the relative position of M9 and M10 (M9 is above), then sort the 8 codes of the second part to get the placement order of M1, M2, M6, M7, M5, M8, M3, M4, and place them from top to bottom and from left to right, where the distance between the ith device and the i-1th device is the distance code corresponding to the third part. The code corresponds to the layout as shown in Figure 4 .

[0066] S5: repair the layout scheme that does not meet the constraint condition by using a repair factor.

[0067] The constraint conditions include: facility non-overlapping and distance greater than minimum safety distance constraint, not exceeding the workshop range constraint, facility in the layout area constraint. The minimum safety distance between devices is set to 10m.

[0068] The repair factor repair process is: for the out-of-bound problem, by halving the longest distance d in the third segment code max Until the non-out-of-bound condition is met; for the overlap problem, by compensating Δd i To d i So that d i Satisfy the minimum distance constraint of the facility.

[0069] Specifically, taking the code [1, 0.1, 0.2, 0.6, 0.7, 0.5, 0.8, 0.3, 0.4, 54, 55, 45, 30, 30, 290, 40, 30] as an example, the device M8 in the layout scheme represented by the code exceeds the workshop boundary, and needs to be repaired by the repair factor, at this time the longest distance in the code is 290, the halved distance is 145, and the code becomes [1, 0.1, 0.2, 0.6, 0.7, 0.5, 0.8, 0.3, 0.4, 54, 55, 45, 30, 30, 145, 40, 30], satisfying the constraint.

[0070] Taking the code [1, 0.1, 0.2, 0.6, 0.7, 0.5, 0.8, 0.3, 0.4, 54, 25, 45, 30, 30, 145, 40, 30] as an example, M1 and M2 in the layout scheme represented by the code overlap, and the distance compensation factor Δd i Is set to 1m, at this time the distance factor 25 in M2 represented in the code is compensated by loop until 49, and the code becomes [1, 0.1, 0.2, 0.6, 0.7, 0.5, 0.8, 0.3, 0.4, 54, 49, 45, 30, 30, 145, 40, 30], satisfying the constraint.

[0071] S6, fitness calculation: calculate the fitness of the individual based on the simulation model.

[0072] Wherein, the simulation model is run, the total logistics transportation distance of completing the production order under the layout scheme is calculated according to the simulation running instance result, and the fitness function of the individual is defined as Where D is the total logistics transportation distance.

[0073] Specifically, the initial layout scheme is run, the simulation time is set to 30 days, the AGV system objects in the simulation instance are counted, and the total transportation distance of the AGV under the initial condition is 177167m, and the corresponding individual fitness is

[0074] S7, external sexual reproduction: sort the logistics transportation distances of the individuals in the coral reef from small to large, and perform coding arithmetic crossover breeding on the individuals in the middle F b Proportion of the sequence, and release the offspring generated to the water area, and calculate the fitness of the individual.

[0075] Specifically, set F b = 0.6.

[0076] S8, internal sexual reproduction: the improved internal sexual reproduction method is used to reproduce the remaining individuals in the coral reef, and the generated individuals are released into the water area, and the fitness of the individuals is calculated.

[0077] The improved internal sexual reproduction method is based on the basic principle of grey wolf optimization algorithm. The individual is affected by the optimal individual in the population during internal sexual reproduction. The three optimal individuals are denoted as a, β, and γ. The specific sub-steps are:

[0078] First, calculate the iteration factor of the current generation number Where t and T represent the current iteration number and the total iteration number, respectively.

[0079] Then, calculate the individual distance influence factor A and C, A = 2a·r1-a, C = 2r2, where r1 and r2 are random numbers between 0 and 1.

[0080] Next, calculate the distance between individual p and a, β, and γ. Take a as an example: D α,p = |C α ·code α -code p |, where code α and code p are the encodings of a and p.

[0081] Finally, calculate the final encoding of the offspring of the individual after internal sexual reproduction:

[0082] S9, sexual reproduction offspring occupation: the offspring produced in the sexual reproduction stage occupy the coral reef in the water area and settle in the population, and the remaining individuals die.

[0083] Sexual reproduction offspring occupation and asexual reproduction offspring occupation, offspring randomly select a coral reef location, if the current location does not exist coral, then directly settle; otherwise, based on the basic principle of simulated annealing, accept the inferior coral with a certain probability, the probability of accepting offspring to replace the parent in the current location Where F(old) and F(new) are the fitness of the old coral and the new coral, respectively, T0 is the initial annealing temperature, rate is the annealing coefficient, if the occupation fails, then re-occupy a new location, and try at most k times.

[0084] In one embodiment, the offspring can try to occupy at most k = 3 times in offspring occupation, the initial annealing temperature T0 = 10000, and the annealing coefficient rate = 0.95.

[0085] S10, asexual reproduction: calculate the shared fitness of all individuals in the current population, then select the top F a Some individuals are subjected to Gaussian-Cauchy mutation, and the new offspring generated are released into the water area, and the fitness of the individuals is calculated.

[0086] The calculation steps of shared fitness are as follows:

[0087] S101, define the Euclidean distance of individual p relative to other individuals q in the population: And the fitness distance is: Where L is the total length of the individual code.

[0088] S102, define the similarity of individual p and individual q: Where is the distance threshold in dimension i, also known as the niche radius, and a is the shape constant parameter of the niche.

[0089] S103, calculate the shared fitness of individual p to the population:

[0090] Gaussian-Cauchy mutation is: code child,i = code p,i ·[1+λ1Cauchy(σ1)+λ2Gauss(σ2)], where λ1 and λ2 represent the disturbance proportion coefficients respectively. In this embodiment, λ1=0.5, λ2=0.5.

[0091] S11, asexual reproduction occupies: the offspring generated in the asexual reproduction stage occupy the coral reef in the water area, and settle in the population, and the rest of the individuals die.

[0092] S12, hydrozoan stage predation: select the top F d Some individuals are subjected to Gaussian-Cauchy mutation, and the new offspring generated are released into the water area, and the fitness of the individuals is calculated. d Complete a round of iteration of the population, let t=t+1, and return to step S3.

[0093] The elimination proportion base F d =0.4.

[0094] After the iteration is completed, the optimal solution is:

[0095] [0,0,0,0.00203,0.07942,0.02766,0.70043,0,0.01479,54.000,53.86,33.97,27.43,33.25,132.86,44.99,31.53], and the corresponding layout scheme is as shown in Figure 5 ​As shown, the algorithm iteration history is as follows Figure 6 As shown, compared with the layout scheme before and after optimization, the total travel distance of AGV is reduced from 177167m to 110580m, and the total logistics transportation distance is reduced by about 37.58%, and the optimization effect is remarkable.

[0096] The application further provides a workshop facility layout optimization system based on simulation and improved coral reef optimization algorithm, the system comprises a memory and a processor, the memory stores a computer program, and the processor executes the computer program to execute the workshop facility layout optimization method based on simulation and improved coral reef optimization algorithm as described above.

[0097] The application further provides a computer readable storage medium, the computer readable storage medium stores machine executable instructions, and the machine executable instructions make the processor realize the workshop facility layout optimization method based on simulation and improved coral reef optimization algorithm when the machine executable instructions are called and executed by the processor.

[0098] Those skilled in the art can easily understand that the above description is only a preferred embodiment of the present application, and is not used to limit the present application, and any modification, equivalent replacement and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for optimizing workshop facility layout based on simulation and an improved coral reef optimization algorithm, characterized in that, The method includes the following steps: S1. Obtain the logistics transportation distance of the completed order based on the simulation model of the discrete events in the engine core component processing and manufacturing workshop; S2. Generate an initial population based on the initial layout situation and the SLP method with random perturbation. The initial individuals are randomly distributed in different spaces in the coral reef, and let the iteration number t = 0; S3. Judge whether the iteration number t < T. If not, go to step S4; otherwise, end the iteration and output the final layout of the workshop facilities; S4. Decoding: Input the layout encoding of the individual into the simulation model to generate the corresponding layout plan of the individual; S5: Use a repair factor to repair the layout plan that does not meet the constraint conditions; S6. Fitness calculation: Calculate the fitness of the individual based on the simulation model; S7, Exogenous Reproduction: Sort individuals in the coral reef according to their logistical transport distance from smallest to largest, and select the top F in the resulting sequence. b Individuals are crossbred using coded arithmetic and the resulting offspring are released into the water, and the fitness of the individuals is calculated. S8. Intra-coral reef reproduction: Reproduce the remaining individuals in the coral reef, release the generated individuals into the water area, and calculate the fitness of the individuals at the same time; S9. Occupation of the offspring of sexual reproduction: The offspring generated in the water area during the sexual reproduction stage occupy the coral reef and settle in the population, and the remaining individuals die; S10, Asexual Reproduction: Calculate the shared fitness of all individuals in the current population, and then select the top F individuals. a Some individuals undergo Gaussian-Cauchy mutation, and the resulting offspring are released into the water, and the fitness of the individuals is calculated. S11. Occupation of the offspring of asexual reproduction: The offspring generated in the water area during the asexual reproduction stage occupy the coral reef and settle in the population, and the remaining individuals die; S12, predation during the hydroid stage: F is selected after considering the total logistics transport distance of the offspring. d Some individuals are represented by a base number of P. d The dynamic elimination probability is used to eliminate populations, completing one round of population iteration. Let t = t + 1, and return to step S3.

2. The workshop facility layout optimization method based on simulation and improved coral reef optimization algorithm as described in claim 1, characterized in that: Wherein, The calculation formula of the dynamic elimination probability is: In the formula, T is the total number of iterations.

3. The workshop facility layout optimization method based on simulation and improved coral reef optimization algorithm as described in claim 1, characterized in that: Use the improved intra-coral reef reproduction method to reproduce the remaining individuals in the coral reef. The improved intra-coral reef reproduction method is based on the basic principle of the grey wolf optimization algorithm. During the intra-coral reef reproduction process, an individual will be affected by the three optimal individuals in the population. The three optimal individuals are respectively denoted as α, β, and γ. The specific sub-steps are as follows: First, calculate the iteration factor of the current algebra. Where t and T represent the current iteration number and the total number of iterations, respectively; After that, calculate the individual distance influence factors A and C. A = 2a·r1 - a, C = 2r2, where r1 and r2 are both random numbers between 0 and 1; Next, calculate the distances D between individual p and individuals α, β, and γ. α,p =|C α ·code α -code p |, where code α and code p Encoding for α and p; Finally, calculate the final code of the offspring of this individual after endogenous reproduction:

4. The workshop facility layout optimization method based on simulation and improved coral reef optimization algorithm as described in claim 1, characterized in that: The layout encoding of the individual is a three-segment encoding: a decimal integer sequence containing 2n - 3 elements, where n is the number of devices at the positions to be planned in the processing workshop; the first segment encoding is the relative position encoding, with a length of 1, which is a 01 encoding, indicating the relative positions of the two types of large areas on the right side of the workshop; the second segment encoding is the simulation sequence encoding, with a length of n - 2, which is a real number encoding between [0, 1]. The size order thereof represents the placement order of the remaining n - 2 devices. If it exceeds the workshop boundary, it will be adjusted from left to right and from top to bottom according to the automatic line wrapping strategy; the third segment encoding is the distance encoding, with a length of n - 2, representing the center point distance from the previous facility. If it is the first device in a certain row, it represents the distance from the left boundary of the workshop.

5. The workshop facility layout optimization method based on simulation and improved coral reef optimization algorithm as described in claim 1, characterized in that: The constraint conditions include: the facilities do not overlap and the distance is greater than the minimum safety distance constraint, the constraint of not exceeding the workshop range, and the constraint that the facilities are in the layoutable area.

6. The workshop facility layout optimization method based on simulation and improved coral reef optimization algorithm as described in claim 1, characterized in that: The repair factor repair process is as follows: For the boundary violation problem, the longest spacing d in the third segment of the encoding is halved. max Until the non-boundary condition is met; for the overlap problem, compensation Δd is used. i Give d i Make d i Meet the minimum spacing constraints for facilities.

7. The workshop facility layout optimization method based on simulation and improved coral reef optimization algorithm as described in claim 1, characterized in that: Both sexually reproduced and asexually reproduced offspring occupy a reef location. Offspring randomly choose a reef location; if no coral exists at the current location, they settle there directly. Otherwise, based on the principle of simulated annealing, they accept inferior corals with a certain probability, and there is a probability that their offspring will replace the parent at the current location. Where F(old) and F(new) are the fitness of old and new corals respectively, T0 is the initial annealing temperature, and rate is the annealing coefficient. If the attempt fails, the coral will try to occupy a new position, with a maximum of k attempts.

8. The workshop facility layout optimization method based on simulation and improved coral reef optimization algorithm as described in claim 1, characterized in that: The fitness function of an individual is Where D is the total logistics transportation distance; the calculation steps for shared fitness are as follows: S101, Define the Euclidean distance of individual p relative to other individuals q in the population: And fitness distance: Where L is the total length of the individual code; S102, Define the similarity between individual p and individual q: in The distance threshold in dimension i is also known as the niche radius, and α is the shape constant parameter of the niche. S103, Calculate the shared fitness of individual p in relation to the population:

9. A workshop facility layout optimization system based on simulation and an improved coral reef optimization algorithm, characterized in that: The system includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, it executes the workshop facility layout optimization method based on simulation and improved coral reef optimization algorithm according to any one of claims 1 - 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores machine-executable instructions, which, when invoked and executed by a processor, cause the processor to implement the workshop facility layout optimization method based on simulation and improved coral reef optimization algorithm as described in any one of claims 1-8.

Images