Transportation planning method, device and equipment for building components and medium

Abstract

The invention relates to the technical field of industrial network security, and discloses a transportation planning method, device and equipment for building components and a medium, and the method comprises the steps: S1, importing a three-dimensional model of a building into Grasshopper, and splitting all components of the building based on component identifiers; s2, creating a local coordinate system of each component for aligning the physical structure of each component, calculating the size of a bounding box of each component, and adjusting the stacking posture of the components based on the size of the bounding box of each component; s3, obtaining the size of a transportation space, and generating an optimal transportation sequence by using a genetic algorithm, and S4, outputting a transportation three-dimensional model, a component list and a three-dimensional model of each component according to the optimal transportation sequence to carry out transportation planning. Based on the combined application of the Grasshopper and the genetic algorithm, the three-dimensional model of each component related to the building can be quickly obtained, the transportation three-dimensional model of the building component can be automatically generated, the quality of transportation planning is effectively improved, and meanwhile, the manpower and time cost is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial network security, and in particular to a building component transportation planning method, device, equipment and medium. BACKGROUND

[0002] A factory will produce various forms of components such as ladders, composite beams, curved beams, beam columns with corbels based on a three-dimensional model of a building. Since the building involves a large number of components, it is usually necessary to reasonably plan the transportation of all components, i.e., to divide and stack all components so that all components can be transported by multiple vehicles in batches, thereby enabling the construction of the building at the destination. Therefore, obtaining the three-dimensional model of each component and the transportation planning of all components is a necessary work for transporting building components.

[0003] Currently, an engineer selects components one by one based on a three-dimensional model of a building in three-dimensional software to output the three-dimensional model of each component. Further, the engineer manually adjusts the stacking posture of each component, and then repeatedly attempts to divide and stack all components according to personal experience or by referring to a model comparison to obtain the required transportation planning and output the transportation three-dimensional model corresponding to each truck. The transportation three-dimensional model is a visual model of the components and the stacking form that the truck needs to load. The entire transportation planning process is not only time-consuming and labor-intensive, but also requires a certain level of experience in loading trucks for engineers. SUMMARY

[0004] The present application aims to: in view of the long time-consuming and low efficiency of the related art in the transportation planning of building components, provide a building component transportation planning method, device, equipment and medium, which can quickly obtain the three-dimensional model of each component involved in the building, and can also automatically generate the transportation three-dimensional model of the building component, thereby effectively improving the quality of the transportation planning and reducing the labor and time costs.

[0005] In order to achieve the above object, in a first aspect of the present application, a transportation planning method of a building component is provided, comprising: S1, importing a building three-dimensional model into Grasshopper, and splitting all components of the building based on component identification; S2, creating a local coordinate system of each component, aligning the physical structure of each component, calculating the bounding box size of each component, and adjusting the stacking pose of the component based on the bounding box size of the component; S3, obtaining the size of the transportation space, and generating an optimal transportation sequence using a genetic algorithm, the genetic algorithm comprising: S31, taking the loading sequence of all components as the coding of an individual, generating a plurality of heuristic individuals and random individuals to form an initial population; S32, decoding the individuals in the population by a decoder to obtain the transportation three-dimensional model corresponding to the individual, and calculating the fitness score based on the transportation three-dimensional model; S33, performing selection, crossover and mutation operations on the current population to generate a new generation of population; S34, repeating steps S32-S33 for a predetermined number of iterations, and outputting the individual with the highest fitness score as the optimal transportation sequence; and S4, outputting the transportation three-dimensional model, the component list and the three-dimensional model of each component according to the optimal transportation sequence for transportation planning.

[0006] In a second aspect of the present application, a transportation planning device of a building component is provided, comprising: a splitting module for importing a building three-dimensional model into Grasshopper, and splitting all components of the building based on component identification; an adjusting module for creating a local coordinate system of each component, aligning the physical structure of each component, calculating the bounding box size of each component, and adjusting the stacking pose of the component based on the bounding box size of the component; a calculation module for obtaining the size of the transportation space, and generating an optimal transportation sequence using a genetic algorithm, the genetic algorithm comprising: an encoding module for taking the loading sequence of all components as the coding of an individual, generating a plurality of heuristic individuals and random individuals to form an initial population; a decoding module for decoding the individuals in the population by a decoder to obtain the transportation three-dimensional model corresponding to the individual, and calculating the fitness score based on the transportation three-dimensional model; a derivation module for performing selection, crossover and mutation operations on the current population to generate a new generation of population; an iteration module for repeating the decoding module and the derivation module for a predetermined number of iterations, and outputting the individual with the highest fitness score as the optimal transportation sequence; and an output module for outputting the transportation three-dimensional model, the component list and the three-dimensional model of each component according to the optimal transportation sequence for transportation planning.

[0007] In a third aspect of the present application, an electronic device is provided, comprising a memory and a processor coupled to the memory, the processor being configured to execute the method of the first aspect based on instructions stored in the memory.

[0008] In a fourth aspect of the present application, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the method of the first aspect.

[0009] The technical scheme of the present application can batch split and output the three-dimensional model of each component based on the component splitting processing of the Grasshopper on the architectural three-dimensional model, effectively improve the processing speed of the architectural component, meet the loading demand of the workshop, and automatically generate the transportation three-dimensional model of the architectural component in the Rhino by combining the design application of the genetic algorithm, which not only can obtain a high-quality transportation scheme, but also can effectively reduce the labor and time cost. BRIEF DESCRIPTION OF DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0011] Figure 1 is a flow chart of the transportation planning method of the architectural component described in the embodiment.

[0012] Figure 2 is a partial schematic view of the architectural three-dimensional model described in the embodiment.

[0013] Figure 3 is a partial schematic view of the batch adjustment of the posture of the architectural component described in the embodiment.

[0014] Figure 4 is a schematic view of the transportation three-dimensional model described in the embodiment.

[0015] Figure 5 is a stacking schematic of the L-shaped steel described in the embodiment Figure 1 .

[0016] Figure 6 is a stacking schematic of the L-shaped steel described in the embodiment Figure 2 .

[0017] Figure 7 is a structural schematic view of the transportation planning device of the architectural component described in the embodiment.

[0018] Figure 8 is a structural schematic view of the electronic device described in the embodiment. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0020] Rhino (3D modeling software) is widely used in fields such as architecture, industrial design, and mechanical design, while Grasshopper is a visual programming language that runs on the Rhino platform. It connects different types of components (batteries) to form a visual model. Components, also known as elements, components or operators, are editable and reusable computing units in algorithm programs. Parameters can be quickly adjusted through Rhino, and the required visual models can be efficiently established in Grasshopper.

[0021] The present application is described below with reference to specific embodiments in conjunction with the accompanying drawings.

[0022] like Figure 1 As shown, a transportation planning method for building components of this embodiment includes: S1, importing a building three-dimensional model into Grasshopper, and splitting all components of the building based on component identification; S2, creating a local coordinate system for each component to align the physical structure of each component, calculating the bounding box size of each component, and adjusting the stacking posture of the components based on the bounding box size of the component; S3, obtaining the size of the transportation space, and using a genetic algorithm to generate an optimal transportation sequence, the genetic algorithm includes: S31, using the loading order of all components as the encoding of individuals, generating multiple heuristic individuals and random individuals to form an initial population; S32, decoding the individuals in the population through a decoder to obtain the corresponding three-dimensional transportation model of the individual, and calculating the fitness score based on the three-dimensional transportation model; S33, performing selection, crossover and mutation operations on the current population to generate a new generation of population; S34, repeating steps S32-S33 to a preset number of iterations, and outputting the individual with the highest fitness score as the optimal transportation sequence; S4, according to the optimal transportation sequence, outputting the three-dimensional transportation model, the component list and the three-dimensional model of each component for transportation planning.

[0023] The local coordinate system of each component is created in Grasshopper for aligning the physical structure of each component, that is, by analyzing the geometric characteristics of the component through an algorithm, extracting the structure data to generate an independent coordinate system aligned with the physical structure thereof, for example, the vertex, edge or face data of the component can be extracted by using the geometric analysis tool of Grasshopper (such as Deconstruct Brep) first, then the main axis direction of the component (such as the longest side, the symmetry axis or the maximum extension direction from the center of gravity to the surface) is calculated to determine the X axis of the local coordinate system, and then the Y axis and the Z axis are generated with the end point or the center of gravity of the component as the origin, for example, the Y axis is perpendicular to the main axis and points to the width direction of the component, and the Z axis points to the height direction of the component, finally the component can be transformed to the local coordinate system through the Transform component to complete the creation of the local coordinate system. By creating the local coordinate system of each component, the direction of the component is standardized, which eliminates the problem of chaotic direction of each component in the same building coordinate system in the building three-dimensional model, simplifies the calculation of the bounding box size, and facilitates the subsequent batch adjustment of the stacking posture of the component through the components of Grasshopper, effectively reducing the calculation complexity of the subsequent constraint check.

[0024] The bounding box is a virtual frame for simplifying the calculation of three-dimensional geometry, which is a cuboid structure capable of completely containing the corresponding component. By abstracting the geometric characteristics of the complex component into a simple regular shape through the bounding box, the complexity of the subsequent transportation planning calculation is reduced, and the processing efficiency is improved. In Grasshopper, for example, the Bounding Box component can be used in combination with the XYZ axes of the local coordinate system of the component to calculate the bounding box.

[0025] As shown in Figure 2 , it is a partial schematic view of the building three-dimensional model. Since in the building three-dimensional model, each component is in a predetermined connection position, for example, the ladder component is usually placed vertically or inclined at various angles, so the original posture of many components is not conducive to stacking and transportation. Adjusting the stacking posture of the component means re-rotating and placing the components of the building to facilitate subsequent stacking planning and transportation. The specific adjustment of the stacking posture can be determined according to the structure and shape of the component or the site conditions of the transportation space, for example, the ladder component is usually adjusted to a horizontal state as the stacking posture under the condition that the transportation space is sufficient, so as to facilitate smooth transportation.

[0026] According to the actual working conditions, the adjustment of the stacking posture can be manually adjusted one by one in the software interface, or it can be adjusted in batches by using an algorithm, or both can be combined to complete the adjustment of the stacking posture of all components, as shown in Figure 3As shown, the schematic diagram shows that part of the components are adjusted in batch by algorithm, and the posture of the components is adjusted based on the size of the bounding box, which not only facilitates the rapid rotation adjustment of the components by artificial, avoids the visual confusion caused by the complex shape of the components, but also simplifies the shape parameters, facilitates the batch posture adjustment by algorithm and subsequent transportation planning.

[0027] The transportation space can be provided by various transportation tools. For example, the transportation space is the corresponding truck compartment size, and the loading sequence of the components is the corresponding loading sequence when the truck transports the components. The loading of all components may require multiple transportation spaces, i.e. multiple trucks to complete the transportation.

[0028] In the design of genetic algorithm, each individual corresponds to a loading mode of all components. For example, a building has three components C1, C2 and C3, and a certain individual can be a sequence code (C3, C1, C2), which represents the loading sequence of the components as C3, C1 and C2.

[0029] The current population is selected, crossed and mutated, which is the prior art for the operation of individuals in the initial population in genetic algorithm. In this application, the loading sequence of the components is adjusted by various means to generate multiple individuals with different codes (i.e. the loading sequence of all components), so as to optimize and expand the population sample for iteration. Specifically, the algorithm can be run in a loop by Grasshopper Goat or HoopSnake components, or the functions of the algorithm can be encapsulated as a Grasshopper battery component by using C# or Python language, and the different battery components are coupled to realize the full function of the algorithm. The preset iteration number is determined based on the actual working condition, the computing power and the operation time limit. Of course, the iteration can also be stopped gradually based on the convergence of the preset target.

[0030] Since the decoder decodes all individuals in multiple populations and obtains one or more transportation three-dimensional models corresponding to each individual, the optimal transportation sequence is selected by fitness score. The fitness score is the optimization target of genetic algorithm, and the specific calculation method can be determined according to the actual working condition. One transportation three-dimensional model corresponds to one transportation space and the components loaded therein, such as Figure 4As shown, it is a schematic diagram of a transport three-dimensional model, after determining the optimal transport sequence, the number of corresponding transport spaces and the corresponding loaded components in each transport space can be obtained based on the decoding result, and finally a visual transport three-dimensional model is formed in the Rhino view, after outputting the transport three-dimensional model and the component list, workers can divide the actual production components according to the component list, and can plan the specific loading according to the transport three-dimensional model, and output the three-dimensional model of each component, which is to facilitate workers to find the corresponding components by combining the component list and the three-dimensional model of the components, so as to successfully complete the subsequent transport planning.

[0031] The application can batch split and output the three-dimensional model of each component based on the Grasshopper component splitting processing of the building three-dimensional model, effectively improve the processing speed of the building component, meet the loading demand of the workshop, and automatically generate the transport three-dimensional model of the building component in Rhino by combining the design application of the genetic algorithm, not only can obtain a high-quality transport scheme, but also can effectively reduce the labor and time cost.

[0032] In some optional embodiments, in step S32, the decoder is configured to: based on the encoding of the individual and the preset loading rule, load each component in the transport space in turn, and simultaneously perform collision and boundary constraint checking, if the current component violates the constraint checking, add a new transport space to load the current component, and until all components are loaded, obtain the number of transport spaces and the utilization rate to calculate the fitness score.

[0033] The preset loading rule is usually determined based on the actual working condition, for example, the transport space is the truck compartment, which can be set as: the components are preferentially loaded from the position as low as possible, as left as possible and as close to the head as possible in the compartment, thereby conforming to the regular sequence of loading the truck, if the transport space is a trailer platform, appropriate loading rules can be formulated based on the crane position and other factors.

[0034] The collision and boundary constraint checking refers to finding the candidate position of the current component in the transport space, and performing collision detection between the current component and the components already placed in the transport space, and checking whether the current component exceeds the size of the transport space when in the candidate position, the collision detection can be calculated by the Bounding Box component whether there is an intersection of the bounding box, and the boundary checking can be judged by whether each corner coordinate of the bounding box is in the coordinate space of the transport space.

[0035] If the current component violates the constraint check, i.e. if the current component collides with other components or exceeds the transportation space when loaded in the candidate position of the transportation space, it indicates that the current transportation space is not suitable for placing the current component, so a new transportation space is developed to load the current component, and after the loading of all components is completed according to the coding order of individuals, the number of transportation spaces required by the individual and the corresponding components loaded in each transportation space can be determined, and the space utilization rate of each transportation space after loading the corresponding components can also be calculated. The decoder can be implemented and run in Grasshopper through C# or Python components.

[0036] In some optional embodiments, in step S32, the fitness score G = a * (1 / Q) + b * K, wherein a and b are weight coefficients, Q is the number of transportation spaces, and K is the utilization rate of the transportation spaces.

[0037] The utilization rate K of the transportation spaces is the average value of the volume utilization rates of all transportation spaces, and the volume utilization rate of each transportation space = the sum of the volumes of all the bounding boxes of the components in the transportation space / the volume of the transportation space. a and b are used to balance the importance of the number of transportation spaces and the utilization rate. The number of transportation spaces is the most important optimization target of transportation planning, and the weight coefficient of a can be larger, for example, a = 0.7 and b = 0.3. Because the cost saving brought by reducing one transportation space is much higher than the improvement of the space utilization rate by a little, therefore, the higher the fitness score is, the better the component loading sequence represented by the corresponding individual is.

[0038] In some optional embodiments, in step S31, the heuristic rules of the heuristic individual generation include one or more of descending order of volume, descending order of base area, and descending order of volume-base area ratio, and a plurality of heuristic individuals are generated based on any heuristic rule combined with random disturbance.

[0039] The heuristic individual is an individual generated based on a heuristic rule. The descending order of volume means that the components are sorted according to the volume of the corresponding bounding box from large to small to generate a sequence coded individual, so that the decoder can preferentially process large components that are difficult to place, and it is easy to produce a high-quality transportation sequence. The descending order of base area means that the components with the largest base area (length x width of the bounding box) are preferentially loaded, which can effectively utilize the space. The descending order of volume-base area ratio means that the ratio of the volume to the base area of each component is calculated and sorted in descending order. Since the components with a high ratio are usually unstable components with high and thin shapes, and are prone to waste the gap space around them, they can be preferentially processed to avoid high and thin components from being difficult to insert into the gap in the later loading stage.

[0040] Random disturbance refers to randomly exchanging the positions of a small part (such as 5%) of components in an individual generated according to a certain heuristic rule, thereby generating multiple similar sequence coded individuals, so as to improve the diversity of high-quality individuals.

[0041] In addition, the random individual is an individual generated by completely randomly arranging all components, which is helpful to explore the optimization space and avoid falling into local optimum too early. Therefore, the method of combining the heuristic and randomness to generate the initial population can effectively ensure that the initial population has both high-quality individuals and diverse individuals.

[0042] In some optional embodiments, in step S33, the current population is subjected to tournament selection, sequential crossover and exchange mutation operations to generate a new generation population.

[0043] Further refining the genetic operation method, when selecting individuals for crossover and mutation operations, the top 10%-20% of individuals can be selected according to the ranking of the fitness score for crossover, mutation to form new individuals and constitute a new generation population. Alternatively, the tournament selection method can be used, that is, a plurality of individuals are randomly selected from the current population as a competition group, and the individual with the highest fitness score is selected as the winner. In the formed multiple competition groups, all winners are combined to form the parent generation, and the new generation population is formed by crossover and mutation. Compared with roulette selection, tournament selection can better maintain population diversity and is easier to select in the component loading scenario. Compared with partial match crossover, sequential crossover can maximize the preservation of the relative order of components in the parent individual, which is more suitable for finding the optimal solution in the component loading problem. Compared with inversion mutation, exchange mutation can avoid destructive random operations that are too large, and the loading order of the components can be fine-tuned to more easily explore a better loading order.

[0044] In some optional embodiments, step S2 further includes: stacking multiple components with the same or related structure to form a package component, calculating the bounding box size of the package component, and regarding the package component as a single component to participate in the genetic algorithm.

[0045] Components with related structures refer to components that have complementary structures or are easily assembled and transported due to connection relationships, such as mortise and tenon structure components, arc structure components, etc. After adjusting the poses of all components, the genetic algorithm in step S3 is based on the bounding box size to plan the stacking, which has certain limitations. For some components, the optimal stacking mode may be missed, for example, when the component is a conventional L-shaped steel, if the stacking is based on the bounding box size, it will produce a stacking mode as shown in the following figure. Figure 5The stacking result is shown, so before the stacking planning is performed by the genetic algorithm, multiple L-shaped steels with the same shape can be stacked and packaged in advance by manual adjustment or preset operation to form a package component as shown in Figure 6 The package three-dimensional model is shown, and further, the package component stacked by multiple L-shaped steels is regarded as one component, and the subsequent step is continued, that is, the package component is stacked with other components in the genetic algorithm, so that the quality of the final transportation planning can be effectively improved, a better stacking scheme is obtained, and meanwhile, in actual production, multiple same components can be directly batch-stacked and packaged on the same production line, and then a subsequent assembly process is performed.

[0046] In some optional embodiments, step S2 further includes: establishing a posture library based on historical stacking postures and historical stacking forms of the conventional component, and calling the posture library to adjust the posture of the component or form the package component.

[0047] The conventional component refers to a component commonly used in buildings, such as a ladder, an L-shaped steel, etc. Based on historical stacking experience of the conventional component, an optimal stacking posture and stacking form of the conventional component during transportation are stored in the posture library, and then the components of the existing building three-dimensional model can be matched with the components of the posture library in Grasshopper. Specifically, the efficient mapping and quick query of the component features and the posture library data can be realized through a hash table, and then the matched components can be automatically adjusted in the stacking posture, or multiple matched components can be formed into a package component according to a preset stacking form, so as to effectively reduce the amount of manual operation and improve the efficiency of transportation planning.

[0048] In some optional embodiments, the component identifier includes one or more of a layer, a component number, and a geometric feature.

[0049] The component identifier serves as the basis for splitting the components, and Grasshopper can identify and separate the components based on the component identifier. Specifically, the component identifier can be selected from a single dimension or multiple dimensions according to the working condition to ensure the efficiency of splitting the components. For example, if the building three-dimensional model has a layer structure that distinguishes or preliminarily distinguishes the components in detail, the layer information can be directly used to split or preliminarily split the components. When splitting, the related components of Grasshopper can be selected according to the working condition to realize the use of the component identifier. For example, the Dispatch and Split List components can be combined to perform conditional screening and division, realize the automatic classification of multiple components, and quickly complete the splitting work of the components.

[0050] Next, an apparatus for transportation planning of a building component provided by an embodiment of the present application is described. The apparatus described below can be correspondingly referred to the method described above. Based on the above embodiments, Figure 7Fig. 1 is a structural schematic diagram of a building component transportation planning device provided by the embodiment.

[0051] As shown in Figure 7 Fig. 1, the building component transportation planning device comprises a splitting module 10, which is used for importing a building three-dimensional model into Grasshopper, and splitting all components of the building based on component identification; an adjustment module 20, which is used for creating a local coordinate system of each component, aligning the physical structure of each component, calculating the bounding box size of each component, and adjusting the stacking pose of the component based on the bounding box size of the component; a calculation module 30, which is used for obtaining the size of a transportation space, and generating an optimal transportation sequence using a genetic algorithm, the genetic algorithm comprising: an encoding module, which is used for taking the loading sequence of all components as the encoding of an individual, and generating an initial population composed of multiple heuristic individuals and random individuals; a decoding module, which is used for decoding the individual in the population through a decoder to obtain a transportation three-dimensional model corresponding to the individual, and calculating a fitness score based on the transportation three-dimensional model; a derivation module, which is used for performing selection, crossover and mutation operations on the current population to generate a new generation population; an iteration module, which is used for repeatedly executing the decoding module and the derivation module to a preset iteration number, and outputting the individual with the highest fitness score as the optimal transportation sequence; and an output module 40, which is used for outputting a transportation three-dimensional model, a component list and a three-dimensional model of each component according to the optimal transportation sequence to perform transportation planning.

[0052] Based on the above method embodiment, please refer to Figure 8 , Figure 8 Fig. 1 is a structural schematic diagram of an electronic device provided by the embodiment, and the electronic device 300 provided by the embodiment comprises a processor 301 and a memory 302, the memory 302 stores machine readable instructions executable by the processor 301, the machine readable instructions are executed by the processor 301 to execute the method as above; the electronic device can be a physical device.

[0053] Based on the above method embodiment, a computer readable storage medium is further provided, and the computer readable storage medium stores a computer program, the computer program is executed by the processor to implement the steps of the method in any one of the above embodiments.

[0054] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can adopt a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can adopt a computer program product implemented on one or more computer readable storage media containing computer usable program code (including but not limited to disk storage, CD-ROM, optical storage, etc.).

[0055] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0056] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0057] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 Figure 1 one or more flow or blocks

[0058] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0059] The memory can include non-persistent memory and / or persistent memory, such as flash memory, read-only memory (ROM), and / or volatile or non-volatile random access memory (RAM), among others. The memory is an example of computer readable media.

[0060] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can be implemented by any method or technology for storing information, which can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0061] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusions, such that a process, method, article or apparatus that comprises a list of elements does not only include those elements, but can also include other elements not expressly listed or inherent to such process, method, article or apparatus. Without more limitations, the element defined by the phrase "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0062] Those skilled in the art will appreciate that embodiments of the present application can be provided as a method, system or computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) containing computer usable program code.

[0063] The above merely provides embodiments of the present application and is not intended to limit the present application. Various modifications and changes can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the scope of the claims of the present application.

Claims

1. A method for transport planning of building components, characterized in that: include: S1, import the building 3D model into Grasshopper and split all the building components based on component identification; S2, creating a local coordinate system for each component, used to align the physical structure of each component, calculate the bounding box size of each component, and adjust the stacking posture of the components based on the bounding box size of the components; S3, obtains the size of the transportation space and uses a genetic algorithm to generate the optimal transportation sequence. The genetic algorithm includes: S31, taking the loading order of all components as the encoding of individuals, generates multiple heuristic individuals and random individuals to form the initial population; S32, decoding the individuals in the population through a decoder to obtain a three-dimensional transport model corresponding to the individual, and calculating a fitness score based on the three-dimensional transport model; S33, performing selection, crossover and mutation operations on the current population to generate a new generation of population; S34, repeating steps S32-S33 until a preset number of iterations is reached, and outputting the individual with the highest fitness score as the optimal transport sequence; S4, according to the optimal transportation sequence, output the transportation 3D model, component list and the 3D model of each component for transportation planning.

2. The method for transport planning of building components according to claim 1, characterized in that: In step S32, the decoder is configured to load each component into the transport space in turn based on the individual encoding and preset loading rules, and simultaneously perform collision and boundary constraint checks. If the current component violates the constraint check, a new transport space is added to load the current component. After all components are loaded, the number and utilization of the transport space are obtained to calculate the fitness score.

3. The method for transport planning of building components according to claim 2, characterized in that: In step S32 , the fitness score G=a*(1 / Q)+b*K, where a and b are weight coefficients, Q is the amount of transportation space, and K is the utilization rate of the transportation space.

4. The method for transport planning of building components according to claim 1, characterized in that: In step S31, the heuristic rules for generating heuristic individuals include one or more of arranging in descending order of volume, arranging in descending order of base area, and arranging in descending order of volume-base area ratio, and multiple heuristic individuals are generated based on any heuristic rule combined with random perturbation.

5. The method for transport planning of building components according to claim 1, characterized in that: In step S33, the current population is subjected to tournament selection, sequential crossover and exchange mutation operations to generate a new generation of population.

6. The method for transport planning of building components according to any one of claims 1 to 5, characterized in that: Step S2 also includes: stacking multiple components with the same or related structural shapes to form a packaging component, calculating the bounding box size of the packaging component, and treating the packaging component as a single component to participate in the genetic algorithm.

7. The method for transport planning of building components according to claim 6, characterized in that: Step S2 also includes: establishing a posture library based on historical stacking postures and historical stacking forms of conventional components, and calling the posture library to adjust the posture of the component or form a packaged component.

8. A transportation planning device for building components, characterized in that: include: The splitting module is used to import the building 3D model into Grasshopper and split all the building components based on component identification; An adjustment module, which is used to create a local coordinate system for each component, align the physical structure of each component, calculate the bounding box size of each component, and adjust the stacking posture of the components based on the bounding box size of the components; The calculation module is used to obtain the size of the transportation space and generate the optimal transportation sequence using a genetic algorithm. The genetic algorithm includes: The encoding module is used to take the loading order of all components as the encoding of individuals and generate multiple heuristic individuals and random individuals to form the initial population; The decoding module decodes the individuals in the population through a decoder to obtain the corresponding three-dimensional transport model of the individuals and calculates the fitness score based on the three-dimensional transport model; The derivative module is used to perform selection, crossover and mutation operations on the current population to generate a new generation of population; The iteration module is used to repeatedly execute the decoding module and the derivation module to a preset number of iterations, and output the individual with the highest fitness score as the optimal transportation sequence; The output module is used to output the transportation three-dimensional model, the component list and the three-dimensional model of each component according to the optimal transportation sequence for transportation planning.

9. An electronic device, characterized in that: The method comprises a memory and a processor coupled to the memory, wherein the processor is configured to execute the method according to any one of claims 1 to 7 based on instructions stored in the memory.

10. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images