Plant layout method and device, computer equipment, storage medium and program product

Abstract

The invention relates to a factory layout method and device, computer equipment, a storage medium and a program product. The method comprises the following steps: acquiring initial iteration coordinates of a plurality of to-be-arranged monomers in a plant area; performing iterative optimization on the initial iteration coordinates of the to-be-arranged monomers by adopting a first cost function until a first iteration stop condition is met, and obtaining initial optimization coordinates of the to-be-arranged monomers; performing iterative optimization on the initial optimization coordinates of the to-be-arranged monomers by adopting a second cost function until a second iteration stop condition is met, and obtaining target optimization coordinates of the to-be-arranged monomers meeting a preset cost requirement; and generating a layout result of the plurality of to-be-arranged monomers in the factory according to the target optimization coordinates of the to-be-arranged monomers. By adopting the method, the layout efficiency of the plant layout can be improved.

Description

Technical Field

[0001] The present application relates to the field of new energy technology, and in particular to a plant layout method, device, computer equipment, storage medium and program product. Background Art

[0002] With the continuous expansion of production capacity, new factories are constantly being planned and constructed.

[0003] Taking the planning and construction of a battery production plant as an example, a battery production plant needs to plan and build multiple departments, such as logistics, plant department, production department, and logistics department. Each building or facility planned and constructed can be a unit to be laid out, so it is necessary to plan the units to be laid out within a limited battery production plant. However, in the planning process of the units to be laid out, there are many factors to consider. Therefore, it is necessary to complete the planning of the battery production plant in the drawing software based on experience and spend a lot of time to obtain the layout result of the plant.

[0004] However, in the related art, there is a problem of low efficiency in plant layout planning and layout. Summary of the invention

[0005] Based on this, the present application provides a plant layout method, apparatus, computer equipment, storage medium and program product, which can improve the layout efficiency of the plant layout.

[0006] In a first aspect, the present application provides a plant layout method, the method comprising: obtaining initial iterative coordinates of multiple units to be laid out in the plant; iteratively optimizing the initial iterative coordinates of each unit to be laid out using a first cost function until a first iterative stop condition is met, and obtaining the initial optimized coordinates of each unit to be laid out; the first cost function represents the relationship between the plant layout cost and the spatial distance between every two units to be laid out in the plant, and the spatial distance is a function of the coordinates of the units to be laid out; iteratively optimizing the initial optimized coordinates of each unit to be laid out using a second cost function until a second iterative stop condition is met, and obtaining target optimized coordinates of each unit to be laid out that meet preset cost requirements; the second cost function represents the relationship between the plant layout cost and the path distance between every two units to be laid out in the plant, and the path distance is a function of the coordinates of the units to be laid out, and the path distance between every two units to be laid out represents the shortest travel distance between every two units to be laid out bypassing other units to be laid out; and generating layout results of multiple units to be laid out in the plant according to the target optimized coordinates of each unit to be laid out.

[0007] In the technical solution of the embodiment of the present application, the coordinates of the monomers to be laid out are iteratively optimized through the cost function, so as to generate layout results of multiple monomers to be laid out in the plant area according to the target optimization coordinates of each monomer to be laid out. There is no need to complete the planning of the plant area in the drawing software based on experience and spend a lot of time. Instead, the planning of the plant area is completed by iterating the coordinates of each monomer to be laid out through the cost function, thereby improving the layout efficiency of the plant layout; in addition, when determining the target optimization coordinates of each monomer to be laid out, it is not planned according to the experience of the planners, but it is iteratively optimized according to the pre-established cost function, thereby providing a calculation basis for determining the target optimization coordinates of each monomer to be laid out, thereby improving the layout accuracy of the plant layout; and in the first optimization stage, every two The first cost function associated with the spatial distance between the monomers to be laid out is iterated. In the second optimization stage, the second cost function associated with the path distance between every two monomers to be laid out is used for iteration. The path distance is obtained through a search algorithm. Compared with the spatial distance, it is closer to the travel distance in the real scene. The calculation method of the path distance is more complicated than the calculation method of the spatial distance. Therefore, the initial optimization coordinates of the monomer to be laid out can be iterated by calculating the simple first cost function associated with the spatial distance, which can improve the iteration speed and thus improve the layout efficiency of the plant layout. Then, the target optimization coordinates of the monomer to be laid out can be iterated by calculating the complex second cost function associated with the path distance, which can improve the accuracy of the iteration, thereby further improving the layout accuracy and layout efficiency of the plant layout.

[0008] In some embodiments, the first cost function is used to iteratively optimize the initial iterative coordinates of each monomer to be arranged, and the second cost function is used to iteratively optimize the initial optimized coordinates of each monomer to be arranged, including: obtaining the setback distance between every two monomers to be arranged in the plant, the size of the plant, and the size of each monomer to be arranged; determining the target constraint conditions according to the setback distance between every two monomers to be arranged in the plant, the size of the plant, and the size of each monomer to be arranged; using the first cost function and the target constraint conditions to iteratively optimize the initial iterative coordinates of each monomer to be arranged, and using the second cost function and the target constraint conditions to iteratively optimize the initial optimized coordinates of each monomer to be arranged. In the technical solution of the embodiment of the present application, the coordinates of each monomer to be arranged are iteratively optimized by the target constraint conditions determined by the size of each monomer to be arranged, the size of the plant, and the setback distance between every two monomers to be arranged in the plant, so that the iteratively optimized coordinates meet the set target constraint conditions, thereby improving the layout effectiveness of the plant layout.

[0009] In some embodiments, target constraints are determined based on the setback between every two cells to be arranged in the plant, the size of the plant, and the size of each cell to be arranged, including: determining setback constraints based on the setback between every two cells to be arranged in the plant and the size of each cell to be arranged; determining plant constraints based on the size of the plant and the size of each cell to be arranged; combining the setback constraints and the plant constraints to obtain target constraints. In the technical solution of the embodiment of the present application, the target constraints include setback constraints and plant constraints, so that the plant layout can be performed according to the specified setback requirements and the specified plant size, avoiding the situation where the iterated target optimized coordinates of each cell to be arranged do not meet the specified setback requirements and the specified plant size, and further improving the effectiveness of the plant layout.

[0010] In some embodiments, the setback constraint is determined according to the setback distance between every two cells to be arranged in the factory and the size of each cell to be arranged, including: determining the first shortest distance in the horizontal direction and the second shortest distance in the vertical direction between every two cells to be arranged according to the coordinates of every two cells to be arranged and the size of every two cells to be arranged; determining the setback constraint according to the relationship between the first shortest distance, the second shortest distance and the setback distance. In the technical solution of the embodiment of the present application, the setback constraint is determined according to the first shortest distance in the horizontal direction and the second shortest distance in the vertical direction between every two cells to be arranged, and the relationship between the setback distances between every two cells to be arranged, so that cells to be arranged of different sizes can have corresponding setback requirements, and then the setback distance between the cells to be arranged can be accurately constrained, thereby improving the accuracy of the determined setback constraint.

[0011] In some embodiments, the plant constraints are determined according to the size of the plant and the size of each unit to be arranged, including: determining the horizontal range and vertical range of the plant according to the size of the plant; determining the horizontal position and vertical position of each unit to be arranged according to the coordinates of each unit to be arranged and the size of each unit to be arranged; determining the horizontal position of each unit to be arranged within the horizontal range, and the vertical position of each unit to be arranged within the vertical range as the plant constraints. In the technical solution of the embodiment of the present application, the horizontal position of each unit to be arranged within the horizontal range of the plant, and the vertical position of each unit to be arranged within the vertical range of the plant, are determined as plant constraints, so that units to be arranged of different sizes can have corresponding range requirements, and then the position of the unit to be arranged can be accurately constrained within the horizontal range and vertical range of the plant, thereby improving the accuracy of the determined plant constraints.

[0012] In some embodiments, obtaining the setback distance between every two units to be arranged in the factory includes: obtaining the building category of each unit to be arranged and the setback requirements under each building category; determining the setback distance between every two units to be arranged in the factory according to the building category of each unit to be arranged and the setback requirements under each building category. In the technical solution of the embodiment of the present application, since the setback distance between every two units to be arranged in the factory is determined according to the building category of each unit to be arranged and the setback requirements under each building category, the layout of the units to be arranged in the factory can strictly follow the setback requirements under each building category, thereby improving the accuracy of the determined setback distance between every two units to be arranged in the factory.

[0013] In some embodiments, the coordinates of each monomer to be laid out are iteratively optimized, including: obtaining the i-th round parent population; the parent population includes M individuals, each individual includes N coordinates, i is an integer greater than or equal to 1, M is an integer greater than or equal to 2, and N is the number of monomers to be laid out in the plant area; selecting at least some individuals from the i-th round parent population, and performing crossover and mutation on at least some individuals to obtain the i-th round offspring population; merging the i-th round parent population and the i-th round offspring population to obtain the i-th round merged population; selecting the i+1-th round parent population from the i-th round merged population according to the target constraint and the first cost function or the second cost function. In the technical solution of the embodiment of the present application, by selecting at least some individuals in each round, performing crossover and mutation on at least some of the selected individuals, merging the parent population and the offspring population, and selecting the next generation parent population, the iterative next generation parent population increasingly minimizes the cost function, making the iterative next generation parent population increasingly accurate, thereby improving the layout accuracy of the plant area layout.

[0014] In some embodiments, according to the target constraint and the first cost function or the second cost function, the i+1th round parent population is selected from the i-th round merged population, including: substituting the N coordinates of the m-th individual in the i-th round merged population into the first cost function or the second cost function to obtain the function value of the m-th individual; m is an integer greater than or equal to 1 and less than or equal to M; when the N coordinates of the m-th individual meet the target constraint, determine the fitness value of the m-th individual according to the function value of the m-th individual; m is an integer greater than or equal to 1 and less than or equal to M; when the N coordinates of the m-th individual do not meet the target constraint, obtain the penalty coefficient of the i-th round, and determine the fitness value of the m-th individual according to the penalty coefficient and the function value of the m-th individual; select the i+1th round parent population from the i-th round merged population according to the ranking of the fitness values ​​of each individual in the i-th round merged population. In the technical solution of the embodiment of the present application, the i+1th round parent population is selected from the i-th round merged population according to the ranking of the fitness value of each individual in the i-th round merged population, so that the individuals in the i+1th round parent population selected each time are individuals with higher fitness to the cost function and the target constraint conditions. As the iteration continues, the fitness of the parent population to the cost function and the target constraint conditions becomes higher and higher, and the iterative next-generation parent population increasingly minimizes the cost function, thereby making the iterative next-generation parent population more and more accurate, thereby improving the layout accuracy of the plant layout.

[0015] In some embodiments, the fitness value of the mth individual is determined according to the penalty coefficient and the function value of the mth individual, including: determining the overlapping area of ​​the N monomers to be arranged corresponding to the mth individual according to the N coordinates in the mth individual and the size of each monomer to be arranged; determining the fitness value of the mth individual according to the overlapping area, the penalty coefficient and the function value of the mth individual. In the technical solution of the embodiment of the present application, the larger the overlapping area between the N monomers to be arranged corresponding to the mth individual, the worse the compliance with the target constraint condition. Therefore, through the overlapping area, the fitness value of the determined mth individual is made lower, thereby avoiding the mth individual from being selected as the next generation parent population, so that as the iteration continues, the parent population becomes more and more adaptable to the cost function and the target constraint condition, thereby improving the layout accuracy of the plant layout.

[0016] In some embodiments, obtaining the penalty coefficient of the i-th round includes: determining the number of individuals that meet the target constraint conditions in the i-th round merged population; determining the i-th round compliance ratio by the ratio of the number of individuals in the i-th round to the number of individuals included in the i-th round merged population; and determining the penalty coefficient of the i-th round according to the i-th round compliance ratio. In the technical solution of the embodiment of the present application, the penalty coefficient of each round will be determined according to the number of individuals that meet the target constraint conditions in each round, so that the size of the penalty coefficient is adapted to the number of individuals that meet the target constraint conditions in the current population, avoiding the situation where the penalty coefficient is too large or too small, resulting in search deviation, and thus falling into the local optimal solution, thereby improving the accuracy of the target optimization coordinates of each monomer to be laid out.

[0017] In some embodiments, satisfying the first iteration stop condition includes one of the following: the same optimal solution appears for a first preset number of consecutive times; the running time of the iterative optimization exceeds the preset first running time; the number of iterations of the iterative optimization reaches the preset first number of iterations; the optimal solution iterated meets the first business requirement; satisfying the second iteration stop condition includes one of the following: the same optimal solution appears for a second preset number of consecutive times; the running time of the iterative optimization exceeds the preset second running time; the number of iterations of the iterative optimization reaches the preset second number of iterations; the optimal solution iterated meets the second business requirement. In the technical solution of the embodiment of the present application, by setting the first iteration stop condition of the first stage using the spatial distance and the second iteration stop condition of the second stage using the path distance, the iteration can be stopped according to the set iteration stop condition, avoiding the situation where the iterations of the first stage and the second stage do not meet the requirements, resulting in inaccurate target optimization coordinates of each to-be-layout monomer finally iterated. Therefore, the embodiment of the present application can improve the accuracy of the determined target optimization coordinates of each to-be-layout monomer.

[0018] In some embodiments, according to the target optimization coordinates of each to-be-arranged monomer, a layout result of multiple to-be-arranged monomers in the plant is generated, including: according to the target optimization coordinates of each to-be-arranged monomer and the size of each to-be-arranged monomer obtained, a layout diagram of multiple to-be-arranged monomers in the plant is drawn, and the optimized path distance between every two to-be-arranged monomers in the plant in the layout diagram is determined; the layout diagram of multiple to-be-arranged monomers in the plant and the union of the optimized path distance between every two to-be-arranged monomers in the plant are determined as the layout result of multiple to-be-arranged monomers in the plant. In the technical solution of the embodiment of the present application, when the target optimization coordinates of each to-be-arranged monomer are iterated for the last time, the computer device can automatically draw the layout diagram in the plant, and can also determine the optimized path distance between every two to-be-arranged monomers in the plant in the layout diagram in the plant, without the need for planners to draw the layout diagrams of each to-be-arranged monomer in the plant one by one in the drawing software, and without the need for planners to obtain the path distance between every two to-be-arranged monomers in the plant by measuring the layout diagram. Therefore, the embodiment of the present application can improve the efficiency of obtaining the plant layout result.

[0019] In some embodiments, the method further includes: determining the passable area between each two cells to be arranged according to the coordinates of each two cells to be arranged in the plant area and the size of each two cells to be arranged; performing a path search in the passable area according to the obtained entrance and exit coordinates of each two cells to be arranged to obtain the path distance between the two cells to be arranged. In the technical solution of the embodiment of the present application, the path distance between the two cells to be arranged is obtained by performing a path search between the passable areas between each two cells to be arranged, thereby avoiding the problem of low efficiency of path search caused by performing a path search outside the passable area, thereby improving the search efficiency of the path search.

[0020] In some embodiments, the passable area between every two cells to be arranged is determined according to the coordinates of every two cells to be arranged and the size of every two cells to be arranged in the plant area, including: determining the passable area of ​​each of the two cells to be arranged according to the coordinates of each of the two cells to be arranged and the size of each of the two cells to be arranged; determining the minimum rectangular area used to cover the passable area of ​​each of the two cells to be arranged; removing the area of ​​the cells to be arranged outside the two cells to be arranged from the minimum rectangular area to obtain the passable area between every two cells to be arranged. In the technical solution of the embodiment of the present application, by limiting the minimum rectangular area used to cover the passable area of ​​each of the two cells to be arranged, and removing the area of ​​the cells to be arranged outside the two cells to be arranged from the minimum rectangular area, the passable area obtained conforms to the actual passable area between every two cells to be arranged, thereby improving the accuracy of the determined passable area between every two cells to be arranged.

[0021] In some embodiments, the method further includes: determining multiple combinations of monomers to be arranged according to multiple monomers to be arranged in the plant; each combination of monomers to be arranged includes two monomers to be arranged, and different combinations of monomers to be arranged include different monomers to be arranged; and calculating the path distances corresponding to the multiple combinations of monomers to be arranged in parallel to obtain the path distance between every two monomers to be arranged in the plant. In the technical solution of the embodiment of the present application, by calculating the path distances corresponding to the multiple combinations of monomers to be arranged in parallel, the calculation process of the path distance between every two monomers to be arranged in the multiple combinations of monomers to be arranged is accelerated, thereby reducing the calculation time of the path distance between every two monomers to be arranged, and thus the optimization efficiency of iterative optimization using the second cost function can be improved.

[0022] In some embodiments, the method further includes: determining the first personnel flow cost, the first facility flow cost, and the first logistics cost between each two units to be arranged according to the spatial distance between each two units to be arranged; determining the sum of the first personnel flow cost, the first facility flow cost, and the first logistics cost as the first cost function; determining the second personnel flow cost, the second facility flow cost, and the second logistics cost between each two units to be arranged according to the path distance between each two units to be arranged; determining the sum of the second personnel flow cost, the second facility flow cost, and the second logistics cost as the second cost function. In the technical solution of the embodiment of the present application, the cost function is the sum of the personnel flow cost, the facility flow cost, and the logistics cost, and the method of determining the cost function is more in line with the actual situation of the plant, thereby improving the accuracy of the plant layout.

[0023] In a second aspect, the present application provides a plant layout device, which includes: an optimization module, which is used to obtain the initial iteration coordinates of multiple monomers to be laid out in the plant, and iteratively optimize the initial iteration coordinates of each monomer to be laid out using a first cost function until the first iteration stop condition is met, and obtain the initial optimized coordinates of each monomer to be laid out; the first cost function represents the relationship between the plant layout cost and the spatial distance between every two monomers to be laid out in the plant, and the spatial distance is a function of the coordinates of the monomers to be laid out; the optimization module is also used to iteratively optimize the initial optimized coordinates of each monomer to be laid out using a second cost function until the second iteration stop condition is met, and obtain the target optimized coordinates of each monomer to be laid out that meets the preset cost requirements; the second cost function represents the relationship between the plant layout cost and the path distance between every two monomers to be laid out in the plant, and the path distance is a function of the coordinates of the monomers to be laid out, and the path distance between every two monomers to be laid out represents the shortest travel distance between every two monomers to be laid out bypassing other monomers to be laid out; a layout generation module is used to generate layout results of multiple monomers to be laid out in the plant according to the target optimization coordinates of each monomer to be laid out.

[0024] In a third aspect, the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above methods when executing the computer program.

[0025] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any of the above methods when the computer program is executed by a processor.

[0026] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the steps of any of the above methods when the computer program is executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 A schematic flow chart of a plant layout method provided for the first embodiment;

[0029] Figure 2 A schematic flow chart of a plant layout method provided for the second embodiment;

[0030] Figure 3 A schematic flow chart of an iterative optimization method provided for the first embodiment;

[0031] Figure 4 A schematic flow chart of an iterative optimization method provided for the second embodiment;

[0032] Figure 5 A schematic flow chart of a plant layout method provided for the third embodiment;

[0033] Figure 6 A schematic flow chart of a factory layout method provided for a fourth embodiment;

[0034] Figure 7 A schematic flow chart of a factory layout method provided for the fifth embodiment;

[0035] Figure 8 A schematic diagram of a process for iterating target optimization coordinates of each to-be-layouted monomer through a genetic algorithm provided in some embodiments;

[0036] Fig. 9 A schematic diagram of the structure of a plant layout device provided in some embodiments;

[0037] Fig.10 A schematic diagram of the structure of a computer device is provided for some embodiments. DETAILED DESCRIPTION

[0038] The following embodiments of the technical solution of the present application are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0040] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined. In the description of the embodiments of the present application, "each" means each or each of the multiple, unless otherwise clearly and specifically defined.

[0041] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0042] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0043] At present, in the layout of the plant, it is very complicated to balance the needs of various departments and achieve the optimal plane layout. The current plan for plant layout is mainly completed by planners in drawing software based on the needs of various departments and their own experience. In the planning, it is necessary to consider the strength of the logistics relationship between different units to be laid out, the distance of facility flow (such as lines and / or pipelines, etc.), and whether the flow of people is convenient. Factors such as the convenience of the flow channel are considered to complete the general plan layout of the plant. However, this process generally consumes a lot of time for planners. After completing the layout, it is necessary to manually measure the distance between the two units to be laid out in the drawing software. Therefore, the plant layout is time-consuming and labor-intensive. Therefore, the plant layout has the problem of low layout efficiency. In addition, due to differences among planners, different planners draw different general layouts for the same needs, and the layout may not be the optimal solution. Therefore, there is also a problem of low layout accuracy of the plant layout.

[0044] To alleviate the above problems, research has found that if an optimization algorithm (such as a genetic algorithm) is used for layout optimization, the global optimal solution can be obtained within an acceptable time, thereby improving the efficiency of layout planning.

[0045] Based on the above considerations, the present application provides a plant layout method, which obtains the initial iterative coordinates of multiple monomers to be laid out in the plant; uses a first cost function to iteratively optimize the initial iterative coordinates of each monomer to be laid out until the first iterative stop condition is met, and the initial optimized coordinates of each monomer to be laid out are obtained; the first cost function represents the relationship between the plant layout cost and the spatial distance between every two monomers to be laid out in the plant, and the spatial distance is a function of the coordinates of the monomers to be laid out; uses a second cost function to iteratively optimize the initial optimized coordinates of each monomer to be laid out until the second iterative stop condition is met, and obtains the target optimized coordinates of each monomer to be laid out that meets the preset cost requirements; the second cost function represents the relationship between the plant layout cost and the path distance between every two monomers to be laid out in the plant, and the path distance is a function of the coordinates of the monomers to be laid out, and the path distance between every two monomers to be laid out represents the shortest travel distance between every two monomers to be laid out to bypass other monomers to be laid out; according to the target optimized coordinates of each monomer to be laid out, the layout results of multiple monomers to be laid out in the plant are generated. In this way, the coordinates of the monomers to be laid out are iteratively optimized through the cost function, so that the layout results of multiple monomers to be laid out in the factory are generated according to the target optimization coordinates of each monomer to be laid out. There is no need to complete the planning of the factory in the drawing software based on experience and spend a lot of time. Instead, the planning of the factory is completed by iterating the coordinates of each monomer to be laid out through the cost function, thereby improving the layout efficiency of the factory layout; in addition, when determining the target optimization coordinates of each monomer to be laid out, it is not planned according to the experience of the planners, but it is iteratively optimized according to the pre-established cost function, thereby providing a calculation basis for determining the target optimization coordinates of each monomer to be laid out, and improving the layout accuracy of the factory layout; and in the first optimization stage, every two monomers to be laid out are used. The first cost function associated with the spatial distance between local monomers is iterated, and in the second optimization stage, the second cost function associated with the path distance between every two monomers to be laid out is used for iteration. The path distance is obtained through a search algorithm, which is closer to the travel distance in the real scene than the spatial distance. The calculation method of the path distance is more complicated than the calculation method of the spatial distance. Therefore, the initial optimization coordinates of the monomer to be laid out can be iterated by calculating the simple first cost function associated with the spatial distance, which can improve the iteration speed and thus improve the layout efficiency of the plant layout. Then, the target optimization coordinates of the monomer to be laid out can be iterated by calculating the complex second cost function associated with the path distance, which can improve the accuracy of the iteration, thereby further improving the layout accuracy and layout efficiency of the plant layout.

[0046] The computer device in the embodiments of the present application may include one or a combination of at least two of the following: a server, a mobile phone, a computer, a tablet computer, a computer with a transceiver function, a PDA, a desktop computer, a personal digital assistant, a portable media player, a smart speaker, a smart watch, a smart glasses, a smart necklace and other wearable devices, a pedometer, a digital TV, a virtual reality (VR) device, an augmented reality (AR) device, an industrial control (Industrial Control) device, a self-driving (Self Driving) device, a remote medical surgery (Remote Medical Surgery) device, a smart grid (Smart Grid) device, a transportation safety (Transportation Safety) device, a smart city (Smart City) device, a smart home (SmartHome) device, a vehicle, a vehicle-mounted device, a vehicle-mounted module, and the like.

[0047] Figure 1 A schematic diagram of a process flow of a plant layout method provided in the first embodiment, such as Figure 1 As shown, the method is applied to a computer device, and the method includes:

[0048] S101, obtaining initial iteration coordinates of multiple units to be arranged in the factory area, and iteratively optimizing the initial iteration coordinates of each unit to be arranged using a first cost function until a first iteration stop condition is met, thereby obtaining initial optimized coordinates of each unit to be arranged.

[0049] The first cost function represents the relationship between the factory layout cost and the spatial distance between every two units to be laid out in the factory, and the spatial distance is a function of the coordinates of the units to be laid out.

[0050] Exemplarily, the coordinates of the to-be-placed cell are the coordinates of the center point of the to-be-placed cell.

[0051] The embodiments of the present application do not limit the scenario of the plant layout. For example, the plant may be a plant in the new energy industry. For example, the plant may be a battery production plant. For example, the plant may be a plant in other fields. The plant may be replaced by a park or a base.

[0052] The unit to be laid out in the factory area may be any unit to be constructed in the factory area. Exemplarily, the unit to be laid out may include at least one of the following: a factory building, a warehouse, a logistics building, an entertainment area, a fitness area, a parking lot, etc.

[0053] Exemplarily, the spatial distance may include Manhattan distance. Also exemplary, the spatial distance may include Euclidean distance.

[0054] The cost function may include a loss function, and the cost function represents a function that can be iteratively optimized. In an embodiment of the present application, the decision variable corresponding to the cost function may be the coordinates of each unit to be laid out. In some embodiments, before S101, the steps of establishing a first cost function and a second cost function may also be included. Exemplarily, a first cost function may be established based on the spatial distance between every two units to be laid out in the plant. Exemplarily, a second cost function may be established based on the path distance between every two units to be laid out in the plant.

[0055] Among them, as the coordinates of every two monomers to be arranged change, the spatial distance and path distance between every two monomers to be arranged also change accordingly. Exemplarily, the spatial distance between every two monomers to be arranged and the path distance between every two monomers to be arranged in the factory area can be determined according to the coordinates of each monomer to be arranged in the factory area obtained by each iteration, so that as the coordinates of each monomer to be arranged are continuously updated, the corresponding spatial distance between every two monomers to be arranged and the path distance between every two monomers to be arranged will also change accordingly.

[0056] Exemplarily, the initial iteration coordinates of the plurality of cells to be arranged may be randomly generated. Also exemplarily, the initial iteration coordinates of the plurality of cells to be arranged may be coordinates input by a user into a computer.

[0057] In some embodiments, the initial iteration coordinates of the plurality of cells to be laid out are Q groups of coordinates, the initial optimization coordinates of the plurality of cells to be laid out are Q groups of coordinates, and Q is an integer greater than or equal to 1.

[0058] The initial optimized coordinates of each to-be-placed monomer may be the coordinates of each to-be-placed monomer obtained in the last round of iteration when it is determined that the first iteration stop condition is met.

[0059] S102 , iteratively optimizing the initial optimized coordinates of each to-be-placed monomer using a second cost function until a second iteration stop condition is met, thereby obtaining target optimized coordinates of each to-be-placed monomer that meets a preset cost requirement.

[0060] Among them, the second cost function represents the relationship between the factory layout cost and the path distance between every two units to be laid out in the factory. The path distance is a function of the coordinates of the units to be laid out. The path distance between every two units to be laid out represents the shortest travel distance between every two units to be laid out bypassing other units to be laid out.

[0061] In some embodiments, in the process of iteratively optimizing the initial optimized coordinates of each unit to be arranged using the second cost function, the optimal solution of each unit to be arranged includes N coordinates in each round, and the N coordinates are the coordinates of multiple units to be arranged in the factory area. The N coordinates included in the optimal solution obtained in each round are substituted into the second cost function to obtain the function value (i.e., the cost value). When it is found that the function value corresponding to the N coordinates included in the optimal solution of a certain round meets the preset cost requirements, the N coordinates included in the optimal solution of this round are determined as the target optimization coordinates of each unit to be arranged that meet the preset cost requirements, and the iteration ends.

[0062] Exemplarily, the function value meeting the preset cost requirement may include: the function value is less than or equal to the preset cost value, or the function value is within a preset cost range.

[0063] The path distance is determined by path search. Exemplarily, the path search can be performed by the A-star algorithm or other path search algorithms to obtain the path distance between every two cells to be arranged in the plant. In some embodiments, the path distance between every two cells to be arranged in the plant is determined according to the coordinates of each cell to be arranged in the plant, and according to the size of each cell to be arranged in the plant. Exemplarily, the size of the cell to be arranged may include the length and width of the cell to be arranged.

[0064] The target optimized coordinates of each to-be-placed monomer may be the coordinates of each to-be-placed monomer obtained in the last round of iteration when it is determined that the second iteration stop condition is met.

[0065] S103 , generating layout results of multiple units to be arranged in the factory area according to the target optimization coordinates of each unit to be arranged.

[0066] Exemplarily, the layout results of the multiple units to be laid out in the factory area may include a layout diagram of the multiple units to be laid out in the factory area and / or an optimized path distance between every two units to be laid out in the factory area. The optimized path distance between every two units to be laid out in the factory area may be determined based on the coordinates of each unit to be laid out obtained in the last round of iteration when it is determined that the second iteration stop condition is met.

[0067] Exemplarily, the layout results of multiple cells to be arranged in the factory area may be generated according to the target optimization coordinates of each cell to be arranged and the size of each cell to be arranged.

[0068] In the technical solution of the embodiment of the present application, the coordinates of the monomers to be laid out are iteratively optimized through the cost function, so as to generate layout results of multiple monomers to be laid out in the plant area according to the target optimization coordinates of each monomer to be laid out. There is no need to complete the planning of the plant area in the drawing software based on experience and spend a lot of time. Instead, the planning of the plant area is completed by iterating the coordinates of each monomer to be laid out through the cost function, thereby improving the layout efficiency of the plant layout; in addition, when determining the target optimization coordinates of each monomer to be laid out, it is not planned according to the experience of the planners, but it is iteratively optimized according to the pre-established cost function, thereby providing a calculation basis for determining the target optimization coordinates of each monomer to be laid out, thereby improving the layout accuracy of the plant layout; and in the first optimization stage, every two The first cost function associated with the spatial distance between the monomers to be laid out is iterated. In the second optimization stage, the second cost function associated with the path distance between every two monomers to be laid out is used for iteration. The path distance is obtained through a search algorithm. Compared with the spatial distance, it is closer to the travel distance in the real scene. The calculation method of the path distance is more complicated than the calculation method of the spatial distance. Therefore, the initial optimization coordinates of the monomer to be laid out can be iterated by calculating the simple first cost function associated with the spatial distance, which can improve the iteration speed and thus improve the layout efficiency of the plant layout. Then, the target optimization coordinates of the monomer to be laid out can be iterated by calculating the complex second cost function associated with the path distance, which can improve the accuracy of the iteration, thereby further improving the layout accuracy and layout efficiency of the plant layout.

[0069] Figure 2 A schematic flow chart of a plant layout method provided for a second embodiment, the method being applied to computer equipment, Figure 2 Example compared to Figure 1 The difference between the embodiments is that S104 and S105 are included before S101, S101 includes S1011, and S102 includes S1021.

[0070] S104: Obtain the setback distance between every two cells to be arranged in the factory, the size of the factory, and the size of each cell to be arranged.

[0071] Among them, the setback distance between every two units to be arranged is the minimum distance between every two units to be arranged. By setting the setback distance between every two units to be arranged, the closest distance between every two units to be arranged in the target optimization coordinates can be greater than or equal to the required setback distance, and then the target optimization coordinates meet the setback requirements. Exemplarily, the setback distance between every two units to be arranged in the factory area can be pre-planned, or can be obtained from a database, or can be determined according to the setback requirements of the specified buildings.

[0072] Exemplarily, the size of each unit to be arranged and / or the size of the plant area may be obtained from a database, or may be pre-planned. For example, the size of each unit to be arranged and / or the size of the plant area may be determined according to requirements.

[0073] S105 , determining target constraint conditions according to the setback distance between every two units to be arranged in the factory area, the size of the factory area, and the size of each unit to be arranged.

[0074] Objective constraints are used to restrict decision variables.

[0075] S1011 , using a first cost function and a target constraint condition, iteratively optimize the obtained initial iteration coordinates of each to-be-placed monomer until a first iteration stop condition is met, thereby obtaining the initial optimized coordinates of each to-be-placed monomer.

[0076] S1021 , using the second cost function and the target constraint condition, iteratively optimize the initial optimization coordinates of each to-be-placed monomer until the second iteration stop condition is met, thereby obtaining the target optimization coordinates of each to-be-placed monomer.

[0077] In the technical solution of the embodiment of the present application, the coordinates of each unit to be arranged are iteratively optimized based on the target constraints determined by the size of each unit to be arranged, the size of the plant area, and the retreat distance between every two units to be arranged in the plant area, so that the iteratively optimized coordinates meet the set target constraints, thereby improving the layout effectiveness of the plant layout.

[0078] In some embodiments, the target constraint condition is determined according to the setback distance between every two cells to be arranged in the plant, the size of the plant, and the size of each cell to be arranged. This can be achieved in the following ways: the setback constraint condition is determined according to the setback distance between every two cells to be arranged in the plant and the size of each cell to be arranged; the plant constraint condition is determined according to the size of the plant and the size of each cell to be arranged; the setback constraint condition and the plant constraint condition are combined to obtain the target constraint condition.

[0079] For example, if the required setback distance of the cell A to be arranged is the first distance and the required setback distance of the cell B to be arranged is the second distance, the setback distance between the cell A to be arranged and the cell B to be arranged is the larger one of the first distance and the second distance.

[0080] Among them, the setback constraint condition requires that the setback distance between every two units to be arranged in the factory area meets the setback requirement. Among them, the factory area constraint condition requires that each unit to be arranged in the factory area must be within the factory area.

[0081] In the technical solution of the embodiment of the present application, the target constraints include setback constraints and plant area constraints, so that the plant layout can be carried out according to the specified setback requirements and the specified plant area size, avoiding the situation where the iterated target optimization coordinates of each unit to be laid out do not meet the specified setback requirements and the specified plant area size, and further improving the effectiveness of the plant layout.

[0082] In some embodiments, the setback constraint condition is determined according to the setback distance between every two cells to be arranged in the factory and the size of each cell to be arranged, which can be achieved in the following way: according to the coordinates of every two cells to be arranged and the size of every two cells to be arranged, the first shortest distance in the horizontal direction (exemplarily, the horizontal direction may also include the horizontal coordinate direction) and the second shortest distance in the vertical direction (exemplarily, the vertical direction may also include the vertical coordinate direction) between every two cells to be arranged are determined; according to the relationship between the first shortest distance, the second shortest distance and the setback distance, the setback constraint condition is determined.

[0083] In some embodiments, the overlapping result of each two monomers to be arranged can be determined according to the coordinates of each two monomers to be arranged and the size of each two monomers to be arranged; when the overlapping result indicates that each two monomers to be arranged overlap in the horizontal direction but do not overlap in the vertical direction, the first shortest distance in the vertical direction between each two monomers to be arranged is greater than or equal to the setback distance of each two monomers to be arranged in the factory area, which is determined as the first constraint condition; when the overlapping result indicates that each two monomers to be arranged do not overlap in the horizontal direction but overlap in the vertical direction, the second shortest distance in the horizontal direction between each two monomers to be arranged is greater than or equal to the setback distance of each two monomers to be arranged in the factory area, which is determined as the second constraint condition; when the overlapping result indicates that each two monomers to be arranged do not overlap in the horizontal direction and do not overlap in the vertical direction, the first shortest distance in the vertical direction and the second shortest distance in the horizontal direction between each two monomers to be arranged are both greater than or equal to the setback distance of each two monomers to be arranged in the factory area, which is determined as the third constraint condition; the union of the first constraint condition, the second constraint condition and the third constraint condition is determined as the setback constraint condition.

[0084] In this way, the back-off constraint condition includes a first constraint condition only when every two monomers to be arranged overlap in the horizontal direction, a second constraint condition only when every two monomers to be arranged overlap in the vertical direction, and a third constraint condition when every two monomers to be arranged do not overlap in the horizontal and vertical directions. When every two monomers to be arranged meet any one of the first constraint condition, the second constraint condition, and the third constraint condition, it indicates that the back-off between every two monomers to be arranged meets the requirement, and then every two monomers to be arranged meet the back-off constraint condition.

[0085] In the technical solution of the embodiment of the present application, the back-off constraint condition is determined based on the first shortest distance in the horizontal direction and the second shortest distance in the vertical direction between every two monomers to be arranged, as well as the relationship between the back-off distances of every two monomers to be arranged, so that monomers to be arranged of different sizes can have corresponding back-off requirements, and the back-off distance between the monomers to be arranged can be accurately constrained, thereby improving the accuracy of the determined back-off constraint condition.

[0086] In some embodiments, the factory constraints are determined based on the factory size and the size of each unit to be arranged, which can be achieved in the following ways: determine the horizontal and vertical ranges of the factory based on the factory size; determine the horizontal and vertical positions of each unit to be arranged based on the coordinates of each unit to be arranged and the size of each unit to be arranged; and determine that the horizontal position of each unit to be arranged is within the horizontal range, and the vertical position of each unit to be arranged is within the vertical range, as factory constraints.

[0087] In some embodiments, the first maximum point and the first minimum point of each to-be-arranged monomer in the horizontal direction, as well as the second maximum point and the second minimum point of each to-be-arranged monomer in the vertical direction can be determined according to the coordinates of each to-be-arranged monomer and the size of each to-be-arranged monomer; the first maximum point is less than or equal to the length in the plant size, and the first minimum point is greater than or equal to 0, which are determined as the fourth constraint condition; the second maximum point is less than or equal to the width in the plant size, and the second minimum point is greater than or equal to 0, which are determined as the fifth constraint condition; the union of the fourth constraint condition and the fifth constraint condition is determined as the plant constraint condition.

[0088] For example, if the coordinates of the center point of a cell to be laid out are ( , ), the size of the unit to be laid out includes length and width, the length is , the width is , then the first maximum point and the first minimum point of the unit to be laid out in the horizontal direction are and The second maximum point and the second minimum point of the to-be-layouted monomer in the vertical direction are and .

[0089] In the technical solution of the embodiment of the present application, the horizontal position of each unit to be arranged is within the horizontal range of the factory area, and the vertical position of each unit to be arranged is within the vertical range of the factory area, which are determined as factory area constraints. Therefore, units to be arranged of different sizes can have corresponding range requirements, and the position of the unit to be arranged can be accurately constrained within the horizontal and vertical ranges of the factory area, thereby improving the accuracy of the determined factory area constraints.

[0090] In some embodiments, obtaining the setback distance between every two units to be arranged in the factory includes: obtaining the building category of each unit to be arranged and the setback requirements under each building category; determining the setback distance between every two units to be arranged in the factory according to the building category of each unit to be arranged and the setback requirements under each building category.

[0091] In some embodiments, the building category of each unit to be arranged is pre-set. For example, before the embodiment of the present application, the number of units to be arranged in the factory area and the building category of each unit to be arranged can be determined, and then the setback requirements under the building category of each unit to be arranged can be determined according to the building category of each unit to be arranged. Exemplarily, the building category of the unit to be arranged may include at least one of the following: production plant category, warehouse category, logistics building category, road category, entertainment area category, fitness area category, parking lot category, etc. Exemplarily, different building categories may have different setback requirements, or there may be at least partially different building categories that have the same setback requirements.

[0092] In this way, by obtaining the building category of each unit to be arranged and the setback requirement under each building category, the building category of each unit to be arranged and the setback requirement of each unit to be arranged can be determined, and the setback between each two units to be arranged can be determined according to the building category of each unit to be arranged and the setback requirement of each unit to be arranged, according to the larger setback requirement of each two units to be arranged in the factory area. For example, if the setback requirement of unit A to be arranged is greater than or equal to the first distance, and if the setback requirement of unit B to be arranged is greater than or equal to the second distance, then the setback between unit A to be arranged and unit B to be arranged is the larger distance between the first distance and the second distance.

[0093] In the technical solution of the embodiment of the present application, since the setback distance between every two units to be arranged in the factory is determined according to the building category of each unit to be arranged and the setback requirements under each building category, the layout of the units to be arranged in the factory can strictly follow the setback requirements under each building category, thereby improving the accuracy of the determined setback distance between every two units to be arranged in the factory.

[0094] Figure 3 A flowchart of an iterative optimization method provided in the first embodiment is shown in FIG. Figure 3 As shown, the method is applied to computer equipment. The iterative optimization method provided in the embodiment of the present application is not only applicable to the scheme of iteratively optimizing the initial iterative coordinates of each to-be-arranged monomer in the factory area by using the first cost function, but also applicable to the scheme of iteratively optimizing the initial optimized coordinates of each to-be-arranged monomer by using the second cost function. In the embodiment of the present application, the method of iteratively optimizing the coordinates of each to-be-arranged monomer may include the following steps:

[0095] S301, obtaining the parent population of the i-th round; the parent population includes M individuals, each individual includes N coordinates, i is an integer greater than or equal to 1, M is an integer greater than or equal to 2, and N is the number of units to be laid out in the plant area.

[0096] In the scheme of iteratively optimizing the initial iteration coordinates of each to-be-placed monomer using the first cost function, when i is equal to 1, the M individuals included in the first round of the parent population are randomly generated. For example, when N is 20 and M is equal to 100, 100 individuals are randomly generated, each of which includes 20 coordinates (i.e., the coordinates of 20 to-be-placed monomers), and the 20 coordinates included in each individual are randomly generated. Exemplarily, the initial iteration coordinates of each to-be-placed monomer include the coordinates in each of the M individuals.

[0097] In the scheme of iteratively optimizing the initial optimized coordinates of each to-be-layouted monomer using the second cost function, when i is equal to 1, the M individuals included in the first round of the parent population are the M individuals obtained when the first cost function is iterated.

[0098] S302, selecting at least some individuals from the i-th round parent population, and performing crossover and mutation on at least some of the individuals to obtain the i-th round offspring population.

[0099] Among them, the individuals in the offspring population are those after crossover and mutation.

[0100] Exemplarily, at least some of the individuals may be randomly selected from the parent population of the i-th round. Also exemplarily, the first preset number of individuals in the parent population of the i-th round may be determined as at least some of the individuals.

[0101] Exemplarily, at least part of the individuals may include a first part of the individuals and a second part of the individuals, and the first part of the individuals may be cross-crossed, and the second part of the individuals may be mutated to obtain the i-th round of offspring population. For example, the first part of the individuals are divided into groups of two, and at least one coordinate in each group is exchanged to obtain two new individuals after cross-crossing, and some coordinate values ​​(including horizontal coordinate values ​​and vertical coordinate values) are selected from each individual in the second part of the individuals, and a value is added or subtracted from the selected coordinate values, and the added or subtracted value may be a fixed value or a random value, to obtain each mutated individual.

[0102] For example, the first individual includes the following coordinates (x1, y1), (x2, y2), (x3, y3), (x4, y4) and (x5, y5), and the second individual includes the following coordinates (x6, y6), (x7, y7), (x8, y8), (x9, y9) and (x10, y10). Crossing the two individuals can obtain the third and fourth individuals. The third individual includes the following coordinates (x1, y1), (x2, y2), (x3, y3), (x9, y9) and (x10, y10), and the fourth individual includes the following coordinates (x6, y6), (x7, y7), (x8, y8), (x4, y4) and (x5, y5).

[0103] For example, the fifth individual includes the following coordinates (x11, y11), (x12, y12), (x13, y13), (x14, y14) and (x15, y15). By mutating the fifth individual, a sixth individual can be obtained. The sixth individual includes the following coordinates (x11, y11+A), (x12+B, y12), (x13, y13), (x14+C, y14+C) and (x15, y15). A, B and C are all real numbers that are not 0.

[0104] S303, merging the i-th round parent population and the i-th round child population to obtain the i-th round merged population.

[0105] Among them, the merged population in the i-th round is the union of the parent population in the i-th round and the child population in the i-th round.

[0106] S304. According to the target constraint and the first cost function or the second cost function, select the i+1th round parent population from the i-th round merged population, and select the i+1th round parent population from the i-th round merged population.

[0107] Among them, when the first cost function is used to iteratively optimize the initial iterative coordinates of each monomer to be laid out, the i+1th round parent population is selected according to the target constraint condition and the first cost function; when the second cost function is used to iteratively optimize the initial optimized coordinates of each monomer to be laid out, the i+1th round parent population is selected according to the target constraint condition and the second cost function.

[0108] In some embodiments, when the parent population of the i+1th round is obtained, it can be determined whether the first iteration stop condition is met. If the first iteration stop condition is met, the iteration is stopped, and the coordinates of the M individuals included in the parent population obtained for the last time are determined as the initial optimized coordinates of each monomer to be laid out; if the first iteration stop condition is not met, i=i+1, and then steps S301 to S304 are executed to continue the next round of iteration until the first iteration stop condition is met.

[0109] In some embodiments, when the parent population of the i+1th round is obtained, it can be determined whether the second iteration stop condition is met. If the second iteration stop condition is met, the iteration is stopped, and the coordinates of the M individuals included in the parent population obtained for the last time are substituted into the second cost function respectively to obtain M second function values, and the coordinates of the individual corresponding to the maximum value of the M second function values ​​are determined as the target optimization coordinates of each monomer to be laid out; if the second iteration stop condition is not met, i=i+1 again, and then steps S301 to S304 are executed to continue the next round of iteration until the second iteration stop condition is met.

[0110] In the technical solution of the embodiment of the present application, by selecting at least part of the individuals in each round, performing crossover and mutation on at least part of the selected individuals, merging the parent population and the child population, and selecting the next generation parent population, the iterative next generation parent population increasingly minimizes the cost function, making the iterative next generation parent population increasingly accurate, thereby improving the layout accuracy of the factory layout.

[0111] Figure 4 A flowchart of an iterative optimization method provided for the second embodiment is shown in FIG. Figure 4 As shown, the method is applied to a computer device, Figure 4 Example compared to Figure 3 The difference between the embodiments is that S304 includes S3041 to S3044.

[0112] S3041. Substitute the N coordinates of the mth individual in the i-th round merged population into the first cost function or the second cost function to obtain the function value of the mth individual.

[0113] Here, m is an integer greater than or equal to 1 and less than or equal to M.

[0114] When the first cost function is used to iteratively optimize the initial iterative coordinates of each to-be-placed unit, the first cost function is substituted; when the second cost function is used to iteratively optimize the initial optimized coordinates of each to-be-placed unit, the second cost function is substituted.

[0115] S3042. When the N coordinates of the mth individual satisfy the target constraint condition, determine the fitness value of the mth individual according to the function value of the mth individual.

[0116] In some implementations, the function value of the mth individual may be multiplied by -1 to obtain the fitness value of the mth individual. In other implementations, the reciprocal of the function value of the mth individual may be determined as the fitness value of the mth individual.

[0117] S3043. When the N coordinates in the mth individual do not satisfy the target constraint condition, obtain the penalty coefficient of the i-th round, and determine the fitness value of the mth individual based on the penalty coefficient and the function value of the mth individual.

[0118] In some embodiments, the fitness value of the mth individual can be determined based on the product of the penalty coefficient and the function value of the mth individual. Exemplarily, the product can be multiplied by -1 to obtain the fitness value of the mth individual. Exemplarily, the reciprocal of the product can be determined as the fitness value of the mth individual.

[0119] In some embodiments, the penalty coefficient of the i-th round may be a fixed value, and the penalty coefficients of different rounds are the same. In other embodiments, the penalty coefficients of different rounds are different.

[0120] S3044. Select the (i+1) round parent population from the i-round merged population according to the ranking of the fitness value of each individual in the i-round merged population.

[0121] Exemplarily, the N coordinates included in the individual with the highest fitness value may be determined as the N coordinates included in the optimal solution.

[0122] Exemplarily, the fitness value of each individual in the i-th round merged population can be sorted from large to small or from small to large. Exemplarily, the M individuals with the largest fitness value in the i-th round merged population can be determined as the i+1-th round parent population.

[0123] In the technical solution of the embodiment of the present application, the i+1th round parent population is selected from the i-th round merged population according to the ranking of the fitness value of each individual in the i-th round merged population, so that the individuals in the i+1th round parent population selected each time are individuals with higher fitness to the cost function and the target constraint conditions. As the iteration continues, the fitness of the parent population to the cost function and the target constraint conditions becomes higher and higher, and the iterative next-generation parent population increasingly minimizes the cost function, thereby making the iterative next-generation parent population more and more accurate, thereby improving the layout accuracy of the plant layout.

[0124] In some embodiments, the fitness value of the mth individual is determined based on the penalty coefficient and the function value of the mth individual, including: determining the overlapping area of ​​N monomers to be laid out corresponding to the mth individual based on the N coordinates in the mth individual and the size of each monomer to be laid out; determining the fitness value of the mth individual based on the overlapping area, the penalty coefficient and the function value of the mth individual.

[0125] Among them, there is at least one overlapping area of ​​the N units to be laid out corresponding to the mth individual. When there is one overlapping area, the area of ​​the area is determined as the overlapping area. When there are at least two overlapping areas, the sum of the areas of at least two overlapping areas is determined as the overlapping area.

[0126] In some embodiments, the fitness value of the mth individual can be determined based on the product of the overlapping area, the penalty coefficient, and the function value of the mth individual. Exemplarily, the product can be multiplied by -1 to obtain the fitness value of the mth individual. Exemplarily again, the reciprocal of the product can be determined as the fitness value of the mth individual.

[0127] In some embodiments, when the overlapping area is greater than or equal to 1, the fitness value of the mth individual is determined based on the product of the overlapping area, the penalty coefficient, and the function value of the mth individual. In other embodiments, when the overlapping area is less than 1, the overlapping area is added by 1 to obtain a new overlapping area or the overlapping area is determined to be 1, and then the fitness value of the mth individual is determined based on the product of the new overlapping area, the penalty coefficient, and the function value of the mth individual.

[0128] In the technical solution of the embodiment of the present application, the larger the overlapping area between the N to-be-layout units corresponding to the m-th individual, the worse the compliance with the target constraint conditions. Therefore, the fitness value of the determined m-th individual is made lower through the overlapping area, thereby avoiding the m-th individual from being selected as the parent population of the next generation. As a result, as the iteration continues, the parent population becomes more and more adaptable to the cost function and the target constraint conditions, thereby improving the layout accuracy of the plant layout.

[0129] In some embodiments, obtaining the penalty coefficient of the i-th round includes: determining the number of individuals in the i-th round merged population that meet the target constraint conditions; determining the i-th round compliance ratio by the ratio of the number of individuals in the i-th round to the number of individuals included in the i-th round merged population; and determining the penalty coefficient of the i-th round based on the i-th round compliance ratio.

[0130] For example, if an individual satisfies the target constraint, it is required that all N coordinates included in the individual must satisfy the target constraint. For example, the i-th round merged population includes 180 individuals, and 120 individuals satisfy the target constraint. Then the number of individuals satisfying the target constraint is 120, and the corresponding compliance ratio is 2 / 3.

[0131] In some embodiments, the reciprocal of the compliant solution ratio of the i-th round can be determined as the penalty coefficient of the i-th round. In this way, due to the limitation of the target constraint, as the iterative optimization continues, the number of individuals that meet the target constraint will increase, and the obtained compliance ratio will be closer and closer to 1. By determining the reciprocal of the compliant solution ratio of the i-th round as the penalty coefficient of the i-th round, a smaller penalty coefficient is used when the compliance ratio is high, and a larger penalty coefficient is used when the compliance ratio is high.

[0132] In the technical solution of the embodiment of the present application, the penalty coefficient of each round will be determined according to the number of individuals that meet the target constraints in each round, so that the size of the penalty coefficient is adapted to the number of individuals that meet the target constraints in the current population, avoiding the situation where the search deviation is caused by the penalty coefficient being too large or too small, thereby falling into the local optimal solution. Therefore, the accuracy of the target optimization coordinates of each unit to be laid out can be improved.

[0133] In some embodiments, satisfying the first iteration stop condition includes one of the following: the same optimal solution appears for a first preset number of consecutive times; the running time of the iterative optimization exceeds the preset first running time; the number of iterations of the iterative optimization reaches the preset first number of iterations; the optimal solution iterated satisfies the first business requirement.

[0134] Exemplarily, in an embodiment of the present application, satisfying the first iteration stop condition includes the number of iterations of the iterative optimization reaching a preset first number of iterations.

[0135] The optimal solution is the N coordinates of the individuals with the lowest fitness value in the merged population; N is the number of units to be laid out in the plant. Exemplarily, the first preset number of times is 10 times. If the individuals with the lowest fitness value in the j-th round of merged populations to the j+9-th round of merged populations are all the N coordinates of the target individuals, the first iteration stop condition is met, and j is an integer greater than or equal to 1.

[0136] Exemplarily, the start time of the iterative optimization is the time when the first round of parent population is obtained, and the difference between the current time and the start time of the iterative optimization is determined as the running time of the iterative optimization.

[0137] For example, the number of iterations of iterative optimization is increasing, and the process of each round of iterative optimization is as follows: Figure 3For example, taking the first iteration number of 5000 as an example, when the iteration number is 1, the first round of iteration process is performed. Since the iteration number is 1 and does not reach 5000, the iteration number is 2, and the second round of iteration process is performed. Since the iteration number is 2 and does not reach 5000, the iteration number is 3, and so on, until the iteration number is 5000, the 5000th round of iteration process is performed. Since 5000 is reached, the iteration ends. After the 5000th round of iteration process, the individual with the lowest fitness value in the 5000th round of merged population is determined as the optimal solution.

[0138] Exemplarily, the iterative optimal solution that meets the first business requirement may include at least one of the following: the discreteness of the N coordinates included in the iterative optimal solution meets the discreteness requirement, the function value of the first cost function corresponding to the N coordinates included in the iterative optimal solution meets the specific cost requirement, and the uniformity of the N coordinates included in the iterative optimal solution meets the requirement.

[0139] Exemplarily, the discreteness of the N coordinates meeting the discreteness requirement may include: the discreteness of the N coordinates is greater than or equal to a preset discreteness, or the discreteness of the N coordinates is within a preset discreteness range.

[0140] The function value of the first cost function corresponding to the N coordinates is calculated in the following manner: the N coordinates are substituted into the first cost function to obtain the function value of the first cost function.

[0141] Exemplarily, the function value meeting a specific cost requirement includes: the function value is less than or equal to a specific cost value, or the function value is within a specific cost range.

[0142] Exemplarily, the uniformity of the N coordinates meets the requirement, which may include: for each coordinate, obtaining another coordinate with the closest Euclidean distance to the coordinate, obtaining a line connecting each coordinate with another coordinate, and if the angle between the line and the horizontal axis is less than or equal to a preset angle, or the angle between the line and the vertical axis is less than or equal to a preset angle, then determining that the uniformity of the N coordinates meets the requirement. For example, the preset angle may be less than or equal to 30 degrees, for example, the preset angle may be 30 degrees, 15 degrees, or 5 degrees.

[0143] In some embodiments, the second iteration stop condition is met, including one of the following: the same optimal solution appears for a second preset number of times in a row; the running time of the iterative optimization exceeds the preset second running time; the number of iterations of the iterative optimization reaches a preset second number of iterations; the optimal solution iterated meets the second business requirement.

[0144] The explanation of the contents included in satisfying the second iteration stop condition may be similar to the explanation of the contents included in satisfying the first iteration stop condition, and will not be repeated here.

[0145] In some embodiments, the first preset number and the second preset number may both be integers greater than or equal to 2. In some embodiments, the second preset number may be greater than or equal to the first preset number. In some embodiments, the second running time may be greater than or equal to the first running time. In some embodiments, the second number of iterations may be greater than or equal to the first number of iterations.

[0146] Exemplarily, the iterative optimal solution that meets the second business requirement may include at least one of the following: the discreteness of the N coordinates included in the iterative optimal solution meets the discreteness requirement, the function value of the second cost function corresponding to the N coordinates included in the iterative optimal solution meets the preset cost requirement, and / or the uniformity of the N coordinates included in the iterative optimal solution meets the requirement.

[0147] In the technical solution of the embodiment of the present application, by setting the first iteration stop condition of the first stage using the spatial distance and the second iteration stop condition of the second stage using the path distance, the iteration can be stopped according to the set iteration stop condition, thereby avoiding the situation where the iterations of the first stage and the second stage do not meet the requirements, resulting in inaccurate target optimization coordinates of each unit to be laid out in the final iteration. Therefore, the embodiment of the present application can improve the accuracy of the determined target optimization coordinates of each unit to be laid out.

[0148] Figure 5 A schematic flow chart of a factory layout method provided in the third embodiment, the method is applied to computer equipment, Figure 5 Example compared to Figure 1 The difference between the embodiments is that S103 includes S1031 and S1032.

[0149] S1031. Draw a layout diagram of multiple units to be arranged in the factory area according to the target optimization coordinates of each unit to be arranged and the acquired size of each unit to be arranged, and determine the optimized path distance between every two units to be arranged in the factory area in the layout diagram.

[0150] Exemplarily, the computer equipment automatically draws a layout diagram of multiple units to be arranged in the factory area according to the target optimization coordinates of each unit to be arranged and the acquired size of each unit to be arranged, without the need for planners to draw on drawing software.

[0151] Among them, the optimized path distance between every two units to be arranged in the factory area in the layout diagram can be achieved in the following way: according to the target optimization coordinates of each unit to be arranged, the optimized path distance between every two units to be arranged in the factory area in the layout diagram is determined.

[0152] S1032: Determine the union of the layout diagram of the plurality of units to be arranged in the factory and the optimized path distance between every two units to be arranged in the factory as the layout result of the plurality of units to be arranged in the factory.

[0153] In some embodiments, the optimized path distance between every two units to be arranged in the factory area can be marked in the layout diagram in the factory area to obtain the layout results of multiple units to be arranged in the factory area. In other embodiments, the file corresponding to the layout diagram of multiple units to be arranged in the factory area and the file corresponding to the optimized path distance between every two units to be arranged in the factory area can be determined as the layout results of multiple units to be arranged in the factory area. Exemplarily, the layout diagram in the factory area can be converted into a file in a preset format for output, and the optimized path distance between every two units to be arranged in the factory area can be converted into a file in a predetermined format for output.

[0154] In the technical solution of the embodiment of the present application, when the target optimized coordinates of each unit to be laid out are reached in the last iteration, the computer equipment can automatically draw a layout diagram within the factory area, and can also determine the optimized path distance between every two units to be laid out in the factory area in the layout diagram within the factory area. There is no need for planners to draw the layout diagram of each unit to be laid out in the factory area one by one in the drawing software, and there is no need for planners to obtain the path distance between every two units to be laid out in the factory area by measuring the layout diagram. Therefore, the embodiment of the present application can improve the efficiency of obtaining the factory layout results.

[0155] In some embodiments, the method further includes: determining a passable area between every two units to be arranged according to the coordinates of every two units to be arranged in the factory and the size of every two units to be arranged; performing a path search within the passable area according to the obtained entrance and exit coordinates of every two units to be arranged to obtain the path distance between the two units to be arranged.

[0156] In this way, when the coordinates of each to-be-placed cell are iterated each time, the passable area between every two to-be-placed cells can be determined according to the coordinates of each to-be-placed cell and the size of every two to-be-placed cells.

[0157] In some embodiments, the entrance and exit coordinates of every two cells to be laid out may be preset.

[0158] In some embodiments, performing a path search in the traversable area may include performing a path search in the traversable area using an A-star algorithm.

[0159] In the technical solution of the embodiment of the present application, by performing a path search between the passable areas between each two units to be laid out, the path distance between the two units to be laid out is obtained, thereby avoiding the problem of low efficiency of the path search caused by performing a path search outside the passable area, thereby improving the search efficiency of the path search.

[0160] In some embodiments, the passable area between every two cells to be arranged is determined according to the coordinates of every two cells to be arranged and the sizes of every two cells to be arranged in the factory, including: determining the passable area of ​​each two cells to be arranged according to the coordinates of each two cells to be arranged and the sizes of each two cells to be arranged; determining the minimum rectangular area for covering the passable area of ​​each two cells to be arranged; removing the area of ​​the cells to be arranged outside every two cells to be arranged from the minimum rectangular area to obtain the passable area between every two cells to be arranged.

[0161] Among them, the passable area of ​​each two monomers to be laid out can be an area outside the area of ​​each two monomers to be laid out. For example, the area of ​​each monomer to be laid out is extended by an area of ​​a first length in the length direction and an area of ​​a second length in the width direction, and the extended area is determined as the passable area of ​​each monomer to be laid out. For example, when the monomer to be laid out is a rectangle, and the coordinates of the four vertices of the rectangle are (a1, b1), (a2, b1), (a1, b2) and (a2, b2), the coordinates of the four vertices of the passable area of ​​the monomer to be laid out are (a1-c, b1+d), (a2+c, b1+d), (a1-c, b2-d) and (a2+c, b2-d).

[0162] In some embodiments, when there are cell regions outside every two cells to be laid out in the minimum rectangular area, the cell regions outside every two cells to be laid out are removed from the minimum rectangular area to obtain a passable area between every two cells to be laid out.

[0163] In some embodiments, when there is no cell area to be laid out other than every two cells to be laid out in the minimum rectangular area, the minimum rectangular area is determined as a passable area between every two cells to be laid out.

[0164] In the technical solution of the embodiment of the present application, by limiting the minimum rectangular area used to cover the passable area of ​​each two monomers to be laid out, and removing the area of ​​the monomers to be laid out outside each two monomers to be laid out from the minimum rectangular area, the passable area obtained is consistent with the actual passable area between each two monomers to be laid out, thereby improving the accuracy of the determined passable area between each two monomers to be laid out.

[0165] In some embodiments, the method further includes: determining multiple combinations of monomers to be arranged based on multiple monomers to be arranged in the factory; each combination of monomers to be arranged includes two monomers to be arranged, and different combinations of monomers to be arranged include different monomers to be arranged; and calculating the path distances corresponding to the multiple combinations of monomers to be arranged in parallel to obtain the path distance between every two monomers to be arranged in the factory.

[0166] Exemplarily, when the number of cells to be arranged in the factory is N, the number of combinations of cells to be arranged is C(2,N).

[0167] In the embodiment of the present application, since the path search process is long, and in each iteration process, the path between each two units to be laid out needs to be searched, in order to avoid the problem of long time occupied by the path search, the path distances corresponding to multiple combinations of units to be laid out are calculated in parallel, and the path distances between each two units to be laid out in the factory are obtained, so that the calculation of the path distances can be carried out in parallel, reducing the long time occupied by the path search.

[0168] In the technical solution of the embodiment of the present application, by calculating the path distances corresponding to multiple combinations of monomers to be laid out in parallel, the calculation process of the path distance between each two monomers to be laid out in the multiple combinations of monomers to be laid out is accelerated, thereby reducing the calculation time of the path distance between each two monomers to be laid out, and thus being able to improve the optimization efficiency of iterative optimization using the second cost function.

[0169] Figure 6 A schematic flow chart of a plant layout method provided in a fourth embodiment, the method is applied to computer equipment, Figure 6 Example compared to Figure 1 The difference between the embodiments is that before S101, S601 to S604 are also included.

[0170] S601. Determine a first people flow cost, a first facility flow cost, and a first logistics cost between each two units to be arranged according to the spatial distance between each two units to be arranged.

[0171] For example, the personnel flow cost, facility flow cost, and logistics cost between each two units to be arranged can be determined according to the building category of each two units to be arranged. For example, when the two units to be arranged are a battery production plant and a warehouse, respectively, there is only logistics transportation between the two units to be arranged, and the total personnel flow cost and facility flow cost are both 0. For another example, when the two units to be arranged are both battery production plants, there are only logistics and facility flows between the two units to be arranged, and the personnel flow cost is 0. For another example, when the two units to be arranged are a battery production plant and a dormitory, respectively, there is only personnel flow between the two units to be arranged, and the facility flow cost and logistics cost are both 0.

[0172] Among them, the first personnel flow cost represents the total personnel flow cost determined by the spatial distance between every two units to be arranged in the factory. For example, the total personnel flow distance in the factory is determined by the spatial distance between every two units to be arranged in the factory, and the total personnel flow cost is determined according to the total personnel flow distance. The first facility flow cost represents the total facility flow cost determined by the spatial distance between every two units to be arranged in the factory. The first logistics cost represents the total logistics cost determined by the spatial distance between every two units to be arranged in the factory.

[0173] Taking the first personnel flow cost as an example, the personnel flow distance between each two units to be arranged in the factory is determined according to the spatial distance between each two units to be arranged and the building type of each unit to be arranged, and the first personnel flow cost is determined based on the personnel flow distance.

[0174] S602: Determine the sum of the first personnel flow cost, the first facility flow cost, and the first logistics cost as a first cost function.

[0175] S603: Determine a second people flow cost, a second facility flow cost, and a second logistics cost between each two units to be arranged according to the path distance between each two units to be arranged.

[0176] Among them, the second personnel flow cost represents the total personnel flow cost determined by the path distance between each two units to be arranged in the factory. The second facility flow cost represents the total facility flow cost determined by the path distance between each two units to be arranged in the factory. The second logistics cost represents the total logistics cost determined by the path distance between each two units to be arranged in the factory.

[0177] S604: Determine the sum of the second personnel flow cost, the second facility flow cost, and the second logistics cost as the second cost function.

[0178] In the technical solution of the embodiment of the present application, the cost function is the sum of the personnel flow cost, the facility flow cost and the logistics cost. The method of determining the cost function is more in line with the actual situation of the factory and improves the accuracy of the factory layout.

[0179] In some embodiments, a genetic algorithm is used for layout planning, and the A-star algorithm is used when calculating the objective function. At the same time, an adaptive penalty function and an elite retention strategy are used during genetic iteration. Within an acceptable time range, the optimal overall layout plan can be obtained, which reduces the requirements for layout personnel, improves layout efficiency, and accelerates layout freezing. In this way, a genetic algorithm is used to model and optimize the overall layout with the total cost of three flows (logistics handling cost, facility flow cost, and personnel flow cost) as the target, and the A-star algorithm is used to calculate the distance between two monomers to be laid out, while parallel computing is used to accelerate the calculation efficiency. At the same time, an adaptive penalty function method is used to jump out of the local optimal solution, and the elite retention strategy is used to accelerate the convergence of the algorithm, and finally the global optimal solution is obtained for reference by business personnel, thereby improving the planning efficiency of business personnel.

[0180] In some embodiments, the initial population is generated using Manhattan distance evaluation, so that a high-quality initial solution can be obtained and the algorithm convergence can be accelerated.

[0181] In some embodiments, when the A-star algorithm calculates the shortest path, only the area around the unit to be laid out is set as passable, and the rest of the factory area is an obstacle. In this way, the efficiency of the A-star algorithm can be increased and the algorithm calculation can be accelerated.

[0182] Figure 7 A schematic flow chart of a plant layout method provided for the fifth embodiment, such as Figure 7 As shown, the method comprises the following steps:

[0183] S701. Obtain input data.

[0184] In some embodiments, the input sources required by the algorithm are diverse. To ensure that the algorithm obtains correct input, the validity of the data needs to be checked after the data is input. The main data processing item is to organize the data fields such as structured tables and database records with appropriate data structures to make them the standard input of the program.

[0185] S702: Check whether the input data is abnormal.

[0186] For example, if the input data does not conform to the preset format, it is determined that the input data is abnormal. For another example, if there is conflicting data in the input data, it is determined that the conflicting data is abnormal. Exemplarily, a matching check is performed on multiple table fields with related relationships. If the check fails, an error message is prompted and the data is returned for modification. For another example, if the input data does not conform to the preset requirements, it is determined that the input data is abnormal.

[0187] If the input data is abnormal, execute S703; if the input data is normal, execute S704.

[0188] S703: Instruct to modify data.

[0189] After the data modification is completed, go to execution S701.

[0190] S704, iterating through a genetic algorithm to obtain target optimized coordinates of each unit to be laid out.

[0191] This step includes three processes: problem encoding and modeling, algorithm iteration, and stop condition judgment and output.

[0192] In the coding and modeling of the problem, the key to the genetic algorithm is to use a reasonable coding method to determine the decision variables. The decision variables in the present invention are mainly the placement positions of the rectangular monomers to be laid out, that is, to determine the coordinates of their center points. Therefore, the X-axis coordinates and Y-axis coordinates of the center points of each monomer to be laid out are used as decision variables ( ) and use it for chromosome encoding.

[0193] The cost function value is determined based on the distance and the corresponding cost. There are two ways to calculate the distance. One is to use the Manhattan distance calculation method to determine the distance between two units to be laid out ( and ) The corresponding spatial distance between the corresponding entrances and exits , the other is to use the A-star algorithm to determine the two monomers to be laid out ( and ) The corresponding path distance between the corresponding entrances and exits . For two units to be laid out ( and ) is the sum of the three flow costs (logistics flow, facility flow, and personnel flow).

[0194] The cost function is expressed as .in, It is the number of units to be laid out in the factory.

[0195] The constraint processing is completed by the penalty function method. Because there are safe fire setbacks between different types of buildings, and some special units to be laid out have special setback specifications. This constraint mainly includes the setback relationship between various types of factories and units to be laid out.

[0196] The target constraint condition includes that each unit to be laid out does not exceed the given factory area. For example, the target constraint condition includes ; ; ; .in, For the monomer to be laid out The length and width of are the length and width of the factory area respectively. , They are the monomers to be laid out The horizontal and vertical coordinates of .

[0197] The target constraint conditions include the back-off constraints between the cells to be laid out. Exemplarily, the target constraint conditions include:

[0198] ;

[0199] in, Indicates two monomers to be laid out ( and ) at different positions, is the minimum value of the constraint backoff distance. For the monomer to be laid out The length and width of For the monomer to be laid out The length and width of ; ; ; .in,( ), ) are , The center point coordinates of the two cells to be laid out, , They are the monomers to be laid out The horizontal and vertical coordinates of , They are the monomers to be laid out The horizontal and vertical coordinates of .

[0200] The algorithm iteration process is divided into two stages.

[0201] In the first stage, after the algorithm completes the encoding, it will randomly initialize the initial population (the individuals in the population are the coordinates of each unit to be laid out), and use the Manhattan distance to calculate the distance between the entrances and exits of each unit to be laid out. Calculations are performed to find the objective function value and fitness value of each individual in the initial population. Then, the population is judged to stop evolving based on the set number of iterations (experience value).

[0202] If the stopping generation number is not reached, individuals are selected from the parent population for crossover and mutation to obtain the child population, the parent and child populations are merged and the objective function value is calculated. The selection algorithm selects a new generation population from the merged population to continue the above operation.

[0203] After reaching the first iteration number in the first stage, the last generation of population is used as the prophet population in the second stage to continue the above operation, but at this time the objective function The calculation is completed by the independent A-star algorithm. In order to speed up the calculation efficiency, this part uses the multi-core performance of the computer for parallel calculation. When setting the map, the A-star algorithm only sets the area around the monomer to be laid out as passable, which can also greatly improve the performance. After each iteration, the algorithm stops judging. If the stop condition is met, the optimal solution is output, otherwise the iteration continues.

[0204] The constraints of both stages of the algorithm are completed by the penalty function method. That is, a constraint check is performed on each generation of individuals. If the constraint conditions are not met, a penalty function determined by the penalty coefficient (the product of the cost function and the penalty coefficient) is applied to the individual. In order to enable the algorithm to find the global optimal solution, the embodiment of the present application adopts an adaptive penalty coefficient setting method. The determining factor that determines the penalty coefficient is determined by the ratio of compliant solutions in the population. The higher the ratio, the smaller the penalty coefficient. This is conducive to the algorithm jumping out of the local optimal solution. Among them, the penalty coefficient is inversely proportional to the ratio of compliant solutions.

[0205] In the stopping condition judgment and output, in order to ensure that the algorithm can find the global optimal solution within a limited time, the stopping condition of the algorithm is set to meet at least one of the following: the same optimal solution appears multiple times in a row; the algorithm exceeds the maximum running time; the algorithm reaches the specified number of iterations; the algorithm result meets the business requirements.

[0206] Exemplarily, if one of the above conditions is met, the algorithm stops, and then the algorithm uses the drawing module to output the layout diagram and a structured table with detailed distances (including Manhattan distance and A-star distance) for reference by business personnel.

[0207] S705: Whether it is necessary to re-run.

[0208] If the target optimization coordinates of each unit to be arranged do not meet the preset requirements, it is determined that the input data is incorrect and needs to be re-run. If the target optimization coordinates of each unit to be arranged meet the preset requirements, it is determined that it does not need to be re-run.

[0209] If it is determined that re-running is required, the process goes to S703. If it is determined that re-running is not required, the process goes to S706.

[0210] S706: Output the target optimization coordinates of each unit to be laid out.

[0211] In some embodiments, the result output module is mainly composed of a drawing part and a table generation part. The drawing part mainly decodes the received algorithm results (obtains the target optimization coordinates of each unit to be laid out through decoding), and uses the drawing function to draw the overall plan layout diagram. The algorithm results received by the table generation part are post-processed to obtain detailed three-flow routes (path distances) and data, which is convenient for business personnel to use the results. In some embodiments, the first stage of the genetic algorithm can also be replaced by a mathematical programming model. After the initial solution is obtained by the solver, it is used as the initial population input to directly start the iteration of the second stage genetic algorithm.

[0212] Figure 8 A schematic diagram of a process for iterating target optimization coordinates of each to-be-layouted monomer through a genetic algorithm is provided in some embodiments, such as Figure 8 As shown, the method is applied to a computer device, and the method includes:

[0213] S801. Randomly initialize the population.

[0214] S802: Whether the number of iterations reaches the set number of population iterations (ie, the first number of iterations mentioned above).

[0215] When the number of iterations reaches the set number of population iterations, it is determined that the first phase iterations are completed, and S803 is executed; when the number of iterations does not reach the set number of population iterations, S804 is executed.

[0216] S803: Output the last generation of population (ie, the initial optimized coordinates of each to-be-layouted monomer).

[0217] After S803, the second phase of iteration is performed, that is, the step S808 is continued to be executed.

[0218] S804, crossover mutation to generate offspring population.

[0219] S805. Merge the father and son populations.

[0220] S806, Manhattan distance evaluation population.

[0221] S807. Screening the new generation population.

[0222] After S807, go to step S802.

[0223] S808: Whether the convergence condition (ie, the second iteration stop condition mentioned above) is satisfied.

[0224] If the convergence condition is met, it is determined that the second stage iteration is completed, and S813 is executed; if the convergence condition is not met, S809 is executed.

[0225] S809, crossover mutation to generate offspring population.

[0226] S810, merge the parent and child populations.

[0227] S811 and A star parallel evaluation population.

[0228] S812. Screening the new generation population.

[0229] After S812, go to step S808.

[0230] S813. Output the optimization result (ie, the target optimization coordinates of each unit to be laid out).

[0231] Based on the same inventive concept, the embodiment of the present application also provides a plant layout device for implementing the plant layout method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more plant layout device embodiments provided below can refer to the limitations of the plant layout method above, and will not be repeated here.

[0232] In an exemplary embodiment, Fig. 9 A schematic diagram of a plant layout device provided in some embodiments, such as Fig. 9 As shown, the plant layout device 900 includes:

[0233] The optimization module 901 is used to obtain the initial iteration coordinates of multiple units to be arranged in the factory area, and iteratively optimize the initial iteration coordinates of each unit to be arranged by using the first cost function until the first iteration stop condition is met, and the initial optimization coordinates of each unit to be arranged are obtained; the first cost function represents the relationship between the factory area layout cost and the spatial distance between every two units to be arranged in the factory area, and the spatial distance is a function of the coordinates of the units to be arranged; the optimization module is also used to iteratively optimize the initial optimization coordinates of each unit to be arranged by using the second cost function until the second iteration stop condition is met, and obtain the target optimization coordinates of each unit to be arranged that meets the preset cost requirements; the second cost function represents the relationship between the factory area layout cost and the path distance between every two units to be arranged in the factory area, and the path distance is a function of the coordinates of the units to be arranged, and the path distance between every two units to be arranged represents the shortest travel distance between every two units to be arranged to bypass other units to be arranged; the layout generation module 902 is used to generate the layout results of multiple units to be arranged in the factory area according to the target optimization coordinates of each unit to be arranged.

[0234] In some embodiments, the optimization module 901 includes a constraint determination unit and an optimization unit. The constraint determination unit is used to obtain the setback distance between every two cells to be arranged in the factory, the size of the factory, and the size of each cell to be arranged; determine the target constraint condition according to the setback distance between every two cells to be arranged in the factory, the size of the factory, and the size of each cell to be arranged; the optimization unit is used to iteratively optimize the initial iterative coordinates of each cell to be arranged using a first cost function and a target constraint condition, and iteratively optimize the initial optimized coordinates of each cell to be arranged using a second cost function and a target constraint condition.

[0235] In some embodiments, the constraint determination unit is also used to determine the setback constraint based on the setback between every two cells to be arranged in the plant and the size of each cell to be arranged; determine the plant constraint based on the size of the plant and the size of each cell to be arranged; and combine the setback constraint and the plant constraint to obtain the target constraint.

[0236] In some embodiments, the constraint determination unit is further used to determine the first shortest distance in the horizontal direction and the second shortest distance in the vertical direction between each two monomers to be laid out according to the coordinates of each two monomers to be laid out and the sizes of each two monomers to be laid out; and determine the retreat constraint according to the relationship between the first shortest distance, the second shortest distance and the retreat.

[0237] In some embodiments, the constraint determination unit is also used to determine the horizontal and vertical ranges of the factory area according to the size of the factory area; determine the horizontal and vertical positions of each monomer to be arranged according to the coordinates of each monomer to be arranged and the size of each monomer to be arranged; and determine that the horizontal position of each monomer to be arranged is within the horizontal range, and the vertical position of each monomer to be arranged is within the vertical range, as factory constraints.

[0238] In some embodiments, the constraint determination unit is also used to obtain the building category of each unit to be arranged and the setback requirements under each building category; based on the building category of each unit to be arranged and the setback requirements under each building category, determine the setback between every two units to be arranged in the factory.

[0239] In some embodiments, the optimization module 901 is also used to obtain the i-th round parent population; the parent population includes M individuals, each individual includes N coordinates, i is an integer greater than or equal to 1, M is an integer greater than or equal to 1, and N is the number of units to be laid out in the plant; at least some individuals are selected from the i-th round parent population, and at least some individuals are crossovered and mutated to obtain the i-th round offspring population; the i-th round parent population and the i-th round offspring population are merged to obtain the i-th round merged population; according to the target constraint conditions and according to the first cost function or the second cost function, the i+1-th round parent population is selected from the i-th round merged population.

[0240] In some embodiments, the optimization module 901 is also used to substitute the N coordinates of the mth individual in the i-th round merged population into the first cost function or the second cost function to obtain the function value of the m-th individual; m is an integer greater than or equal to 1 and less than or equal to M; when the N coordinates of the m-th individual meet the target constraint condition, determine the fitness value of the m-th individual according to the function value of the m-th individual; when the N coordinates of the m-th individual do not meet the target constraint condition, obtain the penalty coefficient of the i-th round, and determine the fitness value of the m-th individual according to the penalty coefficient and the function value of the m-th individual; select the i+1-th round parent population from the i-th round merged population according to the ranking of the fitness values ​​of each individual in the i-th round merged population.

[0241] In some embodiments, the optimization module 901 is further used to determine the overlapping area of ​​N monomers to be laid out corresponding to the mth individual according to the N coordinates in the mth individual and the size of each monomer to be laid out; and determine the fitness value of the mth individual according to the overlapping area, the penalty coefficient and the function value of the mth individual.

[0242] In some embodiments, the optimization module 901 is also used to determine the number of individuals in the i-th round merged population that meet the target constraint conditions; determine the i-th round compliance ratio by the ratio of the number of individuals in the i-th round to the number of individuals included in the i-th round merged population; and determine the penalty coefficient of the i-th round based on the i-th round compliance ratio.

[0243] In some embodiments, satisfying the first iteration stop condition includes one of the following: the same optimal solution appears for a first preset number of consecutive times; the running time of the iterative optimization exceeds the preset first running time; the number of iterations of the iterative optimization reaches the preset first number of iterations; the optimal solution iterated satisfies the first business requirement.

[0244] In some embodiments, the second iteration stop condition is met, including one of the following: the same optimal solution appears for a second preset number of times in a row; the running time of the iterative optimization exceeds the preset second running time; the number of iterations of the iterative optimization reaches a preset second number of iterations; the optimal solution iterated meets the second business requirement.

[0245] Among them, the optimal solution is the N coordinates of the individuals with the lowest fitness value in the merged population; N is the number of units to be laid out in the plant area.

[0246] In some embodiments, the layout generation module 902 is also used to draw a layout diagram of multiple units to be laid out within the factory area according to the target optimization coordinates of each unit to be laid out and the acquired size of each unit to be laid out, and determine the optimized path distance between every two units to be laid out in the factory area in the layout diagram; the union of the layout diagram of the multiple units to be laid out in the factory area and the optimized path distance between every two units to be laid out in the factory area is determined as the layout result of the multiple units to be laid out in the factory area.

[0247] In some embodiments, the optimization module 901 is also used to determine the passable area between every two units to be arranged according to the coordinates of every two units to be arranged in the factory and the sizes of every two units to be arranged; and perform a path search in the passable area according to the obtained entrance and exit coordinates of every two units to be arranged to obtain the path distance between the two units to be arranged.

[0248] In some embodiments, the optimization module 901 is further used to determine the passable area of ​​each two monomers to be laid out according to the coordinates of each two monomers to be laid out and the size of each two monomers to be laid out; determine the minimum rectangular area used to cover the passable area of ​​each two monomers to be laid out; remove the area of ​​the monomers to be laid out outside each two monomers to be laid out from the minimum rectangular area to obtain the passable area between each two monomers to be laid out.

[0249] In some embodiments, the optimization module 901 is also used to determine multiple combinations of monomers to be laid out based on multiple monomers to be laid out in the factory; each combination of monomers to be laid out includes two monomers to be laid out, and different combinations of monomers to be laid out include different monomers to be laid out; and the path distances corresponding to the multiple combinations of monomers to be laid out are calculated in parallel to obtain the path distance between every two monomers to be laid out in the factory.

[0250] In some embodiments, the plant layout device 900 also includes a cost function establishment module, which is used to determine the first personnel flow cost, the first facility flow cost and the first logistics cost between each two units to be laid out according to the spatial distance between each two units to be laid out; the sum of the first personnel flow cost, the first facility flow cost and the first logistics cost is determined as the first cost function; the second personnel flow cost, the second facility flow cost and the second logistics cost between each two units to be laid out according to the path distance between each two units to be laid out; the sum of the second personnel flow cost, the second facility flow cost and the second logistics cost is determined as the second cost function.

[0251] The description of the above device embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the device embodiment of the present application, please refer to the description of the method embodiment of the present application for understanding.

[0252] Each module in the above-mentioned plant layout device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0253] In an exemplary embodiment, Fig.10 A schematic diagram of the structure of a computer device provided for some embodiments, the computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through wireless fidelity (Wireless Fidelity, WIFI), a mobile cellular network, near field communication (Near Field Communication, NFC) or other technologies. When the computer program is executed by the processor, a method for plant layout is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0254] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0255] For example, a computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method of any of the above embodiments when executing the computer program.

[0256] In one embodiment, a computer-readable storage medium is provided, and when a computer program is executed by a processor, the steps of the method provided in any of the above embodiments are implemented.

[0257] In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps of the method provided in any of the above embodiments are implemented.

[0258] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0259] The processor, each functional module or each functional unit in any embodiment of the present application may include any one or more of the following integrations: general-purpose processor, application-specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), central processing unit (CPU), graphics processing unit (GPU), embedded neural network processor (neural-network processing units, NPU), controller, microcontroller, microprocessor, programmable logic device, discrete gate or transistor logic device, discrete hardware component, data processing logic based on quantum computing, artificial intelligence (AI) processor, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0260] The memory or computer-readable storage medium in any embodiment of the present application may include at least one of a non-volatile memory and a volatile memory. Non-volatile memory includes the integration of one or more of the following: Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Ferromagnetic Random Access Memory (FRAM), Flash Memory, Magnetic Surface Storage, Optical Disc, Compact Disc Read-Only Memory (CD-ROM), Tape, Floppy Disk, Flash Memory, Optical Storage, High-density Embedded Non-volatile Memory, Resistive Random Access Memory (ReRAM), Magnetoresistive Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), Graphene Memory, Volatile Memory, etc. Volatile memory includes an integration of one or more of the following: Random Access Memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0261] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0262] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A factory layout method, characterized in that: The method comprises: Obtaining initial iteration coordinates of multiple units to be laid out within the plant area; Iteratively optimize the initial iteration coordinates of each of the to-be-arranged monomers using a first cost function until a first iteration stop condition is met, and obtain the initial optimized coordinates of each of the to-be-arranged monomers; the first cost function represents the relationship between the plant layout cost and the spatial distance between every two to-be-arranged monomers in the plant, and the spatial distance is a function of the coordinates of the to-be-arranged monomers; The second cost function is used to iteratively optimize the initial optimized coordinates of each of the to-be-arranged monomers until the second iteration stop condition is met, so as to obtain the target optimized coordinates of each of the to-be-arranged monomers that meet the preset cost requirements; the second cost function represents the relationship between the plant layout cost and the path distance between every two to-be-arranged monomers in the plant, the path distance being a function of the coordinates of the to-be-arranged monomers, and the path distance between every two to-be-arranged monomers represents the shortest travel distance between every two to-be-arranged monomers bypassing other to-be-arranged monomers; According to the target optimization coordinates of each of the to-be-arranged monomers, a layout result of the plurality of to-be-arranged monomers in the factory area is generated.

2. The method according to claim 1, characterized in that The iterative optimization of the initial iterative coordinates of each to-be-arranged monomer by using the first cost function, and the iterative optimization of the initial optimized coordinates of each to-be-arranged monomer by using the second cost function, include: Obtaining the setback distance between every two cells to be arranged in the plant area, the size of the plant area, and the size of each cell to be arranged; Determining target constraint conditions according to the setback distance between every two units to be arranged in the plant area, the size of the plant area, and the size of each unit to be arranged; The first cost function and the target constraint condition are used to iteratively optimize the initial iterative coordinates of each of the cells to be arranged, and the second cost function and the target constraint condition are used to iteratively optimize the initial optimized coordinates of each of the cells to be arranged.

3. The method according to claim 2, characterized in that Determining the target constraint condition according to the setback distance between every two cells to be arranged in the plant area, the size of the plant area and the size of each cell to be arranged includes: Determining a setback constraint condition according to the setback distance between every two cells to be arranged in the plant area and the size of each cell to be arranged; Determining plant area constraints according to the plant area size and the size of each of the units to be laid out; The setback constraint condition and the plant area constraint condition are combined to obtain the target constraint condition.

4. The method according to claim 3, characterized in that The step of determining the setback constraint condition according to the setback distance between every two cells to be arranged in the plant area and the size of each cell to be arranged includes: Determine a first shortest distance in the horizontal direction and a second shortest distance in the vertical direction between each two cells to be arranged according to the coordinates of each two cells to be arranged and the size of each two cells to be arranged; The back-off distance constraint condition is determined according to a relationship among the first shortest distance, the second shortest distance, and the back-off distance.

5. The method according to claim 3, characterized in that: The step of determining the plant area constraint conditions according to the plant area size and the size of each of the units to be laid out includes: Determine the horizontal and vertical extents of the plant area according to the size of the plant area; Determine the horizontal position and the vertical position of each of the to-be-arranged cells according to the coordinates of each of the to-be-arranged cells and the size of each of the to-be-arranged cells; The horizontal position of each of the to-be-arranged cells is within the horizontal range, and the vertical position of each of the to-be-arranged cells is within the vertical range, which are determined as the plant area constraint conditions.

6. The method according to claim 2, characterized in that The obtaining of the setback distance between every two cells to be arranged in the plant area includes: Obtaining the building category of each unit to be laid out and the setback requirements under each building category; The setback distance between every two units to be arranged in the factory area is determined according to the building category of each unit to be arranged and the setback requirements under each building category.

7. The method according to claim 2, characterized in that The iterative optimization of the coordinates of each of the cells to be laid out includes: Obtain the parent population of the i-th round; the parent population includes M individuals, each of the individuals includes N coordinates, i is an integer greater than or equal to 1, M is an integer greater than or equal to 1, and N is the number of units to be laid out in the plant area; Selecting at least some individuals from the i-th round parent population, and performing crossover and mutation on the at least some individuals to obtain the i-th round offspring population; Merging the parent population of the i-th round and the offspring population of the i-th round to obtain a merged population of the i-th round; According to the target constraint and according to the first cost function or the second cost function, the i+1th round parent population is selected from the i-th round merged population.

8. The method according to claim 7, characterized in that The selecting the i+1th round parent population from the i-th round merged population according to the target constraint condition and the first cost function or the second cost function comprises: Substituting the N coordinates of the mth individual in the i-th round merged population into the first cost function or the second cost function to obtain the function value of the mth individual; m is an integer greater than or equal to 1 and less than or equal to M; When the N coordinates of the m-th individual satisfy the target constraint condition, determining the fitness value of the m-th individual according to the function value of the m-th individual; When the N coordinates of the m-th individual do not satisfy the target constraint condition, obtain the penalty coefficient of the i-th round, and determine the fitness value of the m-th individual according to the penalty coefficient and the function value of the m-th individual; According to the ranking of the fitness value of each individual in the i-th round merged population, the (i+1)-th round parent population is selected from the i-th round merged population.

9. The method according to claim 8, characterized in that Determining the fitness value of the m-th individual according to the penalty coefficient and the function value of the m-th individual includes: Determine the overlapping area of ​​the N to-be-arranged monomers corresponding to the m-th individual according to the N coordinates of the m-th individual and the size of each to-be-arranged monomer; The fitness value of the m-th individual is determined according to the overlapping area, the penalty coefficient and the function value of the m-th individual.

10. The method according to claim 8, characterized in that The step of obtaining the penalty coefficient of the i-th round includes: Determine the number of individuals in the i-th round merged population that meet the target constraint condition; Determine the compliance ratio for round i by taking the ratio of the number of individuals in round i to the number of individuals included in the combined population for round i; A penalty coefficient for the i-th round is determined according to the i-th round compliance ratio.

11. The method according to any one of claims 1 to 10, characterized in that: The first iteration stop condition is satisfied, including one of the following: the same optimal solution appears for a first preset number of times in a row; the running time of the iterative optimization exceeds a preset first running time; The number of iterations of iterative optimization reaches a preset first number of iterations; The iterative optimal solution meets the first business requirement; The second iteration stopping condition is satisfied, including one of the following: the same optimal solution appears for a second preset number of times in a row; The running time of the iterative optimization exceeds the preset second running time; The number of iterations of the iterative optimization reaches a preset second number of iterations; the optimal solution obtained by iteration meets the second business requirement; The optimal solution is the N coordinates of the individuals with the lowest fitness value in the merged population; N is the number of units to be laid out in the plant area.

12. The method according to any one of claims 1 to 10, characterized in that: Generating layout results of the plurality of units to be arranged in the plant area according to the target optimization coordinates of each unit to be arranged includes: Draw a layout diagram of the plurality of cells to be arranged in the plant area according to the target optimization coordinates of each cell to be arranged and the acquired size of each cell to be arranged, and determine the optimized path distance between every two cells to be arranged in the plant area in the layout diagram; The union of the layout diagram of the plurality of units to be arranged in the factory and the optimized path distance between every two units to be arranged in the factory is determined as the layout result of the plurality of units to be arranged in the factory.

13. The method according to any one of claims 1 to 10, characterized in that: The method further comprises: Determine a passable area between each two units to be arranged according to the coordinates of each two units to be arranged in the plant area and the sizes of each two units to be arranged; According to the acquired entrance and exit coordinates of each two cells to be arranged, a path search is performed in the passable area to obtain the path distance between the two cells to be arranged.

14. The method according to claim 13, characterized in that The determining the passable area between each two units to be arranged according to the coordinates of each two units to be arranged in the plant area and the sizes of each two units to be arranged includes: Determining the passable areas of each of the two cells to be arranged according to the coordinates of each of the two cells to be arranged and the sizes of each of the two cells to be arranged; Determine a minimum rectangular area for covering the passable areas of each of the two cells to be laid out; The cell area to be arranged outside every two cells to be arranged is removed from the minimum rectangular area to obtain a passable area between every two cells to be arranged.

15. The method according to any one of claims 1 to 10, characterized in that The method further comprises: Determine a plurality of combinations of monomers to be arranged according to the plurality of monomers to be arranged in the plant area; each combination of monomers to be arranged includes two monomers to be arranged, and different combinations of monomers to be arranged include different monomers to be arranged; The path distances corresponding to the plurality of combinations of cells to be arranged are calculated in parallel to obtain the path distance between every two cells to be arranged in the plant area.

16. The method according to any one of claims 1 to 10, characterized in that The method further comprises: Determine, according to the spatial distance between each two units to be arranged, a first personnel flow cost, a first facility flow cost, and a first logistics cost between each two units to be arranged; determining the sum of the first personnel flow cost, the first facility flow cost, and the first logistics cost as the first cost function; Determine, according to the path distance between each two units to be arranged, a second personnel flow cost, a second facility flow cost, and a second logistics cost between each two units to be arranged; The sum of the second personnel flow cost, the second facility flow cost and the second logistics cost is determined as the second cost function.

17. A plant layout device, characterized in that: The plant layout device comprises: An optimization module, used to obtain initial iteration coordinates of multiple units to be arranged in the plant area, iteratively optimize the initial iteration coordinates of each unit to be arranged using a first cost function until a first iteration stop condition is met, and obtain the initial optimized coordinates of each unit to be arranged; the first cost function represents the relationship between the plant area layout cost and the spatial distance between every two units to be arranged in the plant area, and the spatial distance is a function of the coordinates of the units to be arranged; The optimization module is further used to iteratively optimize the initial optimized coordinates of each of the to-be-arranged monomers using a second cost function until a second iteration stop condition is met, thereby obtaining target optimized coordinates of each of the to-be-arranged monomers that meet preset cost requirements; the second cost function represents the relationship between the plant layout cost and the path distance between every two to-be-arranged monomers in the plant, the path distance being a function of the coordinates of the to-be-arranged monomers, and the path distance between every two to-be-arranged monomers represents the shortest travel distance between every two to-be-arranged monomers that bypasses other to-be-arranged monomers; The layout generation module is used to generate layout results of the plurality of units to be arranged in the factory area according to the target optimization coordinates of each unit to be arranged.

18. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 16 are implemented.

19. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 16 are implemented.

20. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 16 are implemented.

Images