Spare part boxing method and system based on double-population parasitic genetic algorithm, electronic equipment and computer readable storage medium
By applying the spare parts packing method of dual population parasitic genetic algorithm in actual task scenarios, the problem that the existing technology cannot effectively ensure the task completion degree and the full load of spare parts is solved, and more efficient spare parts loading and task completion degree is achieved.
Patent Information
- Application Number
- CN202411966719.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-30
- Publication Date
- 2025-04-15
AI Technical Summary
The prior art cannot effectively ensure the completion of the task in actual task scenarios while ensuring all the spare parts to be carried.
The spare parts packing method based on a two-population parasitic genetic algorithm is adopted. By obtaining the information of the spare parts to be loaded and the loading container, the block generation is used to determine the loading threshold of the spare parts with the remaining space algorithm, and the spare parts quantity population and placement scheme population are constructed within the threshold range, and the genetic algorithm is optimized to determine the number and placement scheme of the spare parts that achieve the preset comprehensive satisfaction rate.
The number of task spare parts carrying is effectively increased, ensuring the satisfaction of task requirements, and ensuring the completion of tasks, and ensuring that all spare parts that need to be carried are loaded.
Smart Images
Figure CN119831498A_ABST
Abstract
Description
Background Art
[0002] In recent years, under the background of severe international situation, vehicles have played an extremely critical role in the execution of many tasks. The compactness of the vehicle structure is one of its important features, which to a certain extent limits the space available for loading spare parts. Spare parts are essential for mission execution. In the process of executing the mission, whether it is to deal with sudden mechanical failures or to meet special needs in different mission scenarios, it is inseparable from the support of various spare parts. If the spare parts are not carried enough or not loaded properly, it is very likely to cause the mission to be interrupted or fail to achieve the expected goals.
[0003] However, despite the large number of studies on spare parts carrying, most of them have not fully considered the spare parts loading problem in actual mission scenarios. In the relevant packing problem research, the number of items loaded is generally known, but due to the complexity and changeability of actual tasks, it usually involves the joint loading of multiple spare parts, in which the number of spare parts loaded and the spare parts loading scheme are unknown. Therefore, the existing technology is not very effective in solving actual tasks, and it is difficult to achieve the task completion requirements. How to ensure the task completion while ensuring the full loading of the spare parts to be carried has become an urgent problem to be solved. Summary of the invention
[0004] The present specification provides a spare parts packing method, system, electronic device and computer-readable storage medium based on a dual-population parasitic genetic algorithm to solve the problem that the existing technology cannot guarantee the completion of the task while ensuring the full loading of the spare parts required because it does not take into account the actual task scenario.
[0005] To achieve the above object, the present invention adopts the following technical solution:
[0006] In a first aspect of the present specification, a spare parts packing method based on a dual-population parasitic genetic algorithm is provided, comprising:
[0007] Acquire information of a plurality of spare parts to be loaded and spare parts loading containers as input information;
[0008] Based on the input information, a loading threshold of various spare parts to be loaded is determined by using a block generation combined with a remaining space algorithm, wherein the loading threshold includes an upper limit value of the number of spare parts that can be loaded;
[0009] Within the range of the loading threshold, construct a spare parts quantity population and a placement plan population, and use a dual-population parasitic genetic algorithm to optimize the spare parts quantity and the placement plan, so as to determine the spare parts quantity plan and the spare parts placement plan that achieve a preset comprehensive satisfaction rate, wherein the placement plan population is a parasitic population derived from the spare parts quantity population;
[0010] Output the spare parts packing plan based on the spare parts quantity plan and the spare parts placement plan.
[0011] In some preferred embodiments, the comprehensive satisfaction rate is:
[0012] P=0.1*P V +0.9*P T ;
[0013] In the formula, P is the comprehensive satisfaction rate, P V is the spare parts loading rate, P T For task completion.
[0014] In some preferred embodiments, the spare parts loading rate P V for:
[0015]
[0016] Where P V is the spare parts loading rate, V 放 is the total volume of the placed spare parts block, V 柜 is the volume of the spare parts cabinet;
[0017] The task completion degree is:
[0018]
[0019] Where n is the number of spare parts, Pi is the probability that at least Ni of the (qi+Ni) spare parts can work properly and qi cannot work properly, and λ i is the average failure-free probability of spare part Xi, N i is the number of single machine installations, qi is the number of spare parts carried, T represents the working time, and a is the number of available work pieces.
[0020] In some preferred implementations, the block generation combined with the remaining space algorithm is used to determine the loading thresholds of various spare parts to be loaded, including:
[0021] According to the target data, determine that the spare parts category set is {X1, X2, .... Xn}, and the spare parts initial quantity set is {min1, min2... minn};
[0022] Traverse the spare parts category set {X1, X2, .... Xn} to determine the target spare parts category Xi;
[0023] By utilizing block generation combined with the remaining space algorithm, the initial quantity mini corresponding to the target spare part type Xi is incremented until it exceeds the loading range of the spare parts loading container, and the upper limit of the portable quantity of spare parts of spare part type Xi is obtained. After traversing the spare parts type set, the loading thresholds of various spare parts to be loaded are obtained.
[0024] In some preferred embodiments, the method for obtaining the upper limit of the number of spare parts of spare part type Xi that can be carried is:
[0025] Initializing the space of the spare parts loading container, determining spare parts blocks corresponding to various spare parts to be loaded, sorting the spare parts blocks according to their volumes, and obtaining a spare parts block sorting result;
[0026] All remaining spaces are sorted according to the distance between the largest remaining space and the origin of the spare parts cabinet to obtain the space sorting result;
[0027] Loading each spare part block according to the spare part block sorting result and the space sorting result;
[0028] After loading is completed, the current remaining space is determined, and it is judged whether the current remaining space is sufficient to place the target spare part type Xi;
[0029] If so, the initial number mini is incremented, and the spare parts blocks are regenerated and loaded until the container loading range is exceeded, thereby obtaining the upper limit of the portable number of the Xi spare parts.
[0030] In some preferred embodiments, constructing a spare parts quantity population and a placement scheme population according to the loading threshold comprises:
[0031] Randomly generate the number of various types of spare parts to be loaded within the range of the loading threshold to construct the spare parts quantity population;
[0032] Generate homogeneous spare parts blocks by type and store them in the order of weight, length, width, height and volume;
[0033] Use random numbers to construct a population of spare parts placement solutions.
[0034] In some preferred embodiments, the method of using a dual-population parasitic genetic algorithm to optimize the number of spare parts and the placement plan to determine the number of spare parts and the placement plan that achieve a preset comprehensive satisfaction rate includes:
[0035] Based on the genetic algorithm of the priority retention strategy, the placement scheme population is solved with the loading rate as a constraint until a preset maximum number of iterations is reached to obtain the spare parts placement scheme;
[0036] Updating the genetic parameters of the quantity plan population, solving the quantity plan population with the task completion degree as a constraint, and obtaining the spare parts quantity plan;
[0037] Determine whether the spare parts placement plan and the spare parts quantity plan reach a preset comprehensive satisfaction rate;
[0038] If yes, the spare parts placement plan and spare parts quantity plan are output;
[0039] If not, the placement plan population and the quantity plan population are reconstructed, and the spare parts placement plan and the spare parts quantity plan are updated until the spare parts placement plan and the spare parts quantity plan reach the comprehensive satisfaction rate.
[0040] A second aspect of the specification provides a spare parts packing system based on a dual-population parasitic genetic algorithm, comprising:
[0041] A data acquisition module, used to acquire information of various spare parts to be loaded and spare parts loading containers as input information;
[0042] A data calculation module, for determining a loading threshold of various spare parts to be loaded based on the input information by using a block generation combined with a remaining space algorithm, wherein the loading threshold includes an upper limit value of the number of spare parts that can be loaded;
[0043] An optimization iteration module, used to construct a spare parts quantity population and a placement plan population within the range of the loading threshold, and use a dual-population parasitic genetic algorithm to optimize the spare parts quantity and the placement plan, so as to determine the spare parts quantity plan and the spare parts placement plan that achieve a preset comprehensive satisfaction rate, wherein the placement plan population is based on the spare parts quantity population;
[0044] The data output module is used to output the spare parts loading plan according to the spare parts quantity plan and the spare parts placement plan.
[0045] According to a third aspect of the present specification, an electronic device is provided, including:
[0046] at least one processor;
[0047] and a memory communicatively connected to at least one of the processors; wherein the memory stores instructions executable by the processor, the instructions being used to be executed by the processor to implement the spare parts packing method based on a dual-population parasitic genetic algorithm as described in the first aspect.
[0048] The third aspect of this specification provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores computer instructions, and the computer instructions are used to be executed by the computer to implement the spare parts packing method based on a dual-population parasitic genetic algorithm as described in the first aspect.
[0049] At least one of the above technical solutions adopted in the embodiments of this specification can achieve the following beneficial effects:
[0050] This application combines the block generation algorithm to set an upper threshold limit for the number of spare parts loaded, and performs optimization within the threshold based on task completion and loading rate, so as to obtain the optimal carrying quantity of each spare part under the maximum loading condition, which can effectively increase the number of spare parts carried for the task and better meet the task requirements, thereby ensuring the completion of the task while ensuring the full loading of the spare parts required. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0052] Figure 1 A schematic diagram of a flow chart of a spare parts packing method based on a dual-population parasitic genetic algorithm provided in an embodiment of this specification;
[0053] Figure 2 A schematic diagram of a spare parts packing solution provided in an embodiment of this specification. DETAILED DESCRIPTION
[0054] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.
[0055] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.
[0056] Please refer to Figure 1 ,like Figure 1 As shown, the first embodiment of the present application proposes a spare parts packing method based on a dual-population parasitic genetic algorithm, the method comprising:
[0057] Step S1, obtaining information of various spare parts to be loaded and spare parts loading containers as input information;
[0058] In this embodiment, the information of the spare parts to be loaded includes the type information and quantity information of all spare parts to be loaded. For the convenience of explanation, spare parts belonging to the same type will be referred to as homogeneous spare parts hereinafter. The quantity information of various homogeneous spare parts has been determined. The purpose of the subsequent steps of this embodiment is to determine the loading quantity and plan of each type of spare parts, as well as the loading plan between each homogeneous spare parts.
[0059] In this embodiment, the information of spare parts to be loaded can be obtained through the inventory management interface of the current system. In this system, each type of spare part has a corresponding entry, which records in detail key information such as its name (i.e., type), current inventory quantity, etc. For example, for spare parts to be loaded, corresponding screening conditions can be set, such as screening out spare parts to be used for a specific project, equipment maintenance, or a transportation task, so as to obtain the type information of spare parts to be loaded that meet the requirements and their corresponding quantity information.
[0060] Step S2, based on the input information, using block generation combined with a remaining space algorithm, determining a loading threshold of various spare parts to be loaded, wherein the loading threshold includes an upper limit value of the number of spare parts that can be loaded;
[0061] Among them, the block generation algorithm is a method that can divide the loading space (such as the cargo space of a transport vehicle, the storage area of a warehouse, etc.) into multiple logical blocks, each of which is in three-dimensional form (considering length, width, and height) to simulate the actual loading space. Specifically, first determine the geometric shape and size of the loading space (for example, for a truck, measure the length, width, and height of the compartment to obtain the overall space volume), and then divide the loading space into multiple smaller logical blocks according to preset rules. The preset rules can be based on past experience, can be evenly divided, or can be divided according to the common shapes and sizes of the spare parts to be loaded.
[0062] In this embodiment, on the basis of the block generation algorithm, the remaining space algorithm is further used to calculate the remaining space after the spare parts are loaded at each stage. It is easy to understand that before starting to load the spare parts, the remaining space is the entire loading space, that is, all the logical blocks divided as mentioned above, and when starting to load a spare part, the shape and size of the spare part need to be considered. For example, a spare part is a rectangular parallelepiped with a length of, a width of, and a height of, and the number of blocks occupied by each such spare part (the calculation here is also based on the unit of the previously divided blocks), and the number of blocks of the remaining space is continuously updated as each spare part is loaded.
[0063] Step S3, within the range of the loading threshold, constructing a spare parts quantity population and a placement plan population, and using a dual-population parasitic genetic algorithm to optimize the spare parts quantity and the placement plan, so as to determine a spare parts quantity plan and a spare parts placement plan that achieve a preset comprehensive satisfaction rate, wherein the placement plan population is a parasitic population derived from the spare parts quantity population;
[0064] It is understandable that in a dual-population parasitic genetic algorithm, the survival and evolution of one population (called the parasitic population) depends on another population (called the host population). In this embodiment, the placement scheme population is the parasitic population, and the spare parts quantity population is the host population, wherein the individuals of the parasitic population are generated based on the individuals of the host population, and for each individual in the host population (such as a combination of spare parts quantity), multiple corresponding individuals will be generated in the parasitic population (such as multiple placement schemes based on the combination of spare parts quantity). Based on this parasitic relationship, the parasitic population is closely connected with the host population, and since the optimization of the placement scheme population is performed on the basis of the spare parts quantity population, it is possible to more effectively explore the joint optimization space and find the optimal solution that satisfies both the reasonable number of spare parts and the efficient placement scheme.
[0065] Specifically, when an individual in the spare parts quantity population (representing a spare parts quantity plan) changes after operations such as selection, crossover and mutation, the corresponding placement plan individuals in the parasitic population will be regenerated to adapt to the new spare parts quantity, and then these placement plan individuals will be selected, optimized and other operations will be performed to achieve the co-evolution of the two populations.
[0066] Step S4: outputting a spare parts packing plan according to the spare parts quantity plan and the spare parts placement plan.
[0067] In this embodiment, after determining the spare parts quantity plan and the spare parts placement plan, the loading order of various spare parts can be determined in order, thereby outputting the spare parts packing plan. According to the determined spare parts quantity plan, the specific quantity of each spare part is listed in detail.
[0068] Specifically, there are 10 spare parts A to be loaded, 15 spare parts B, and 8 spare parts C. At the same time, according to the spare parts placement plan, the specific placement information of each spare part in the loading space (such as a box) is clarified, such as the coordinate position of each spare part, the placement angle, and the layout relationship relative to other spare parts. For example, 5 spare parts A are placed in the upper left corner of the bottom of the box, arranged in 2 rows and 3 columns, with an angle of 0 degrees; the other 5 pieces are arranged in 1 row and 5 columns on the right side, with an angle of 90 degrees, etc., and in this way, all the spare parts to be loaded are packed.
[0069] Furthermore, in this embodiment, the comprehensive satisfaction rate is:
[0070] P=0.1*P V +0.9*P T ;
[0071] In the formula, P is the comprehensive satisfaction rate, P V is the spare parts loading rate, P T For task completion.
[0072] It should be noted that, according to actual research in this field, the task completion rate or spare parts satisfaction rate is generally required to be above 90%. Therefore, the weight distribution of loading rate and task completion rate is 1:9, and the comprehensive satisfaction rate is determined based on the allocated weights.
[0073] Furthermore, in this embodiment, the spare parts loading rate P V for:
[0074]
[0075] Where V 放 The total volume of the placed spare parts block, V 柜 is the volume of the spare parts cabinet;
[0076] It is known that there are n types of spare parts, among which the average failure-free probability of spare part Xi is λ i , the number of single machine installations is Ni, the number of spare parts carried is qi, within the working time T, at least Ni of the (qi+Ni) spare parts can work normally, and the probability that qi cannot work normally is Pi, a is the number of workable parts, then the intact rate of spare part Xi is P i for:
[0077]
[0078] The task completion degree P T for:
[0079]
[0080] Furthermore, in this embodiment, the block generation is combined with the remaining space algorithm to determine the loading thresholds of various spare parts to be loaded, including:
[0081] According to the target data, determine that the spare parts category set is {X1, X2, .... Xn}, and the spare parts initial quantity set is {min1, min2... minn};
[0082] Traverse the spare parts category set {X1, X2, .... Xn} to determine the target spare parts category Xi;
[0083] By utilizing block generation combined with the remaining space algorithm, the initial quantity mini corresponding to the target spare part type Xi is incremented until it exceeds the loading range of the spare parts loading container, and the upper limit of the portable quantity of spare parts of spare part type Xi is obtained. After traversing the spare parts type set, the loading thresholds of various spare parts to be loaded are obtained.
[0084] Furthermore, the block generation is combined with the remaining space algorithm to increase the initial quantity mini corresponding to the target spare parts type Xi, including: initializing the spare parts cabinet space, determining the spare parts blocks corresponding to various spare parts to be loaded, sorting each spare parts block according to the volume size, and obtaining the spare parts block sorting result; sorting all the remaining space according to the distance between the maximum remaining space and the origin of the spare parts cabinet, and obtaining the space sorting result; loading each spare parts block according to the spare parts block sorting result and the space sorting result; after loading is completed, determining the current remaining space, and judging whether the current remaining space meets the requirements for placing the target spare parts type Xi; if so, increasing the initial quantity mini, regenerating spare parts blocks and loading them until the container loading range is exceeded, and obtaining the upper limit of the portable quantity of the Xi spare parts.
[0085] Specifically, the loading process includes: initializing the spare parts cabinet space, generating a neat spare parts block for the same type of spare parts, that is, homogeneous spare parts, sorting the spare parts blocks according to the size of the spare parts blocks, and sorting all the remaining spaces according to the distance between the maximum remaining space and the origin of the spare parts cabinet, that is, considering placing the spare parts block at the bottom of the box close to the origin first, so as to achieve the purpose of compact loading; if any condition of the length, width and height of the spare parts block does not meet the maximum remaining space requirement of the spare parts cabinet, then consider trying to load the spare parts block into the next maximum remaining space; adjust the loading direction of the spare parts block so that the maximum remaining space after loading is kept minimum in one direction, that is, keep the minimum loading gap; determine whether the newly added maximum remaining space has an inclusion relationship with the original maximum remaining space set, add, delete and update the elements of the maximum remaining space set after loading, until all spare parts blocks are placed, determine whether the remaining space can continue to place Xi spare parts, if so, increase the number of Xi spare parts, regenerate spare parts blocks, and load until the container loading range is exceeded, so as to obtain the upper limit hi of the number of Xi spare parts that can be carried. Repeat the above operation to traverse the set of spare parts types {X1, X2, .... Xn}, and obtain the upper limit set of the number of each spare part that can be carried {max1, max2, .... maxn}.
[0086] Furthermore, in the present embodiment, constructing a spare parts quantity population and a placement plan population according to the loading threshold includes: randomly generating the quantity of each type of spare parts to be loaded within the range of the loading threshold to construct the spare parts quantity population; generating homogeneous spare parts blocks according to the type, and storing the spare parts blocks in the order of weight, length, width, height, and volume; and using random numbers to construct a spare parts placement plan population.
[0087] Based on this, the dual-population parasitic genetic algorithm is used to optimize the spare parts quantity and placement plan to determine the spare parts quantity plan and spare parts placement plan that achieve a preset comprehensive satisfaction rate, including: based on a genetic algorithm with a priority retention strategy, solving the placement plan population with a loading rate as a constraint until a preset maximum number of iterations is reached to obtain the spare parts placement plan; updating the genetic parameters of the quantity plan population, solving the quantity plan population with a task completion degree as a constraint to obtain the spare parts quantity plan; determining whether the spare parts placement plan and the spare parts quantity plan achieve a preset comprehensive satisfaction rate; if so, outputting the spare parts placement plan and the spare parts quantity plan; if not, reconstructing the placement plan population and the quantity plan population, and updating the spare parts placement plan and the spare parts quantity plan until the spare parts placement plan and the spare parts quantity plan achieve the comprehensive satisfaction rate.
[0088] The number of each spare part to be carried is randomly generated within the spare parts threshold range to construct a spare parts quantity population; homogeneous spare parts blocks are generated according to the type, and the spare parts blocks are placed in the order of weight, length, width, height, and volume, where length>width>height; random numbers are used to construct a spare parts placement plan population.
[0089] Since the parasitic population is derived from the host population, the reproduction of the parasitic population will also affect the host population, so the two populations use different crossover mutation factors.
[0090] First, encode the parasitic population and construct the parasitic population chromosome. The natural number sequence encoding with a length equal to Nb+Nc (the sum of the number of spare parts blocks to be loaded and the number of spare parts cabinets) is used. The encoding is divided into two sections, front and back, which are composed of sequence strings representing the sequence of spare parts blocks and spare parts cabinets respectively. For example, in a loading process, assuming that there are 7 spare parts blocks to be loaded and 3 available spare parts cabinets, the encoding is a 10-digit code composed of natural numbers 1-7 and 1-3 randomly sorted respectively. For example, the code (6142573231) means that the order of spare parts block 6 is the highest priority, spare parts block 1 is the second priority... spare parts block 3 is the last priority. The sequence is combined with the remaining space algorithm to load into spare parts cabinet 2. After reaching the volume, load capacity or length, width and height limit, the remaining spare parts blocks are loaded into spare parts cabinet 3, and so on. Assuming that the placement plan population consists of p individuals, the population initialization result should be a two-dimensional array composed of p*(Nb+Nc) natural numbers;
[0091] Set the parasitic population crossover operator. When performing crossover, the chromosome spare block segment and the chromosome spare cabinet segment are crossovered at a single point respectively. Then, the illegal genes in the chromosome substrings obtained by the crossover are determined by repeatability test. These illegal genes are marked by their positions. For example, repeated genes represent that the spare block is loaded twice, which is an illegal gene. Then, they are stored in the gene set to be repaired in order. The genes in the gene set to be repaired are used to replace the genes in the other illegal gene position in order respectively, so as to complete the repair and legalization of the chromosome segment. Finally, the crossover is completed and the new offspring is returned.
[0092] Set the parasitic population mutation operator, use the random exchange of gene positions to perform mutation operations, and complete the mutation by randomly exchanging the positions of spare parts blocks;
[0093] Set the parasitic population selection operator. In the selection process, in order to keep the excellent individuals in the population well, first select a few individuals with the highest fitness value (i.e. the above-mentioned loading rate) to enter the offspring population, and then use the conventional tournament selection method to operate;
[0094] Set the host population crossover to single-point crossover and the mutation probability to 0.9. Calculate the fitness in the host population according to the comprehensive satisfaction rate in step S2, and select the operator with the highest fitness for replication.
[0095] To better explain the effect of this embodiment, please refer to Tables 1 to 3 and Figure 2 , given the types of spare parts and the minimum carrying quantity required for a certain task, the working time T is 1000 hours, the spare parts parameters are shown in Table 1, and the spare parts cabinet size is shown in Table 2. The final carrying quantity of spare parts is determined according to the above method proposed in this embodiment as shown in Table 3, and the final spare parts packing plan is as shown in Figure 2 As shown:
[0096] Table 1, spare parts index data:
[0097] Table 2, spare parts cabinet parameters:
[0098]
[0099] Table 3, Final quantity of spare parts to be carried:
[0100] Spare part name Final amount of spare parts Spare Part 1 14 Spare Part 2 10 Spare Part 3 7 Spare Parts 4 20 Spare Parts 5 21 Spare Parts 6 16 Spare Parts 7 12 Spare Parts 8 2 Spare Parts 9 1 Spare Parts 10 1
[0101] The second embodiment of the present application proposes a spare parts packing system based on a dual-population parasitic genetic algorithm, including:
[0102] A data acquisition module, used to acquire target data of spare parts to be loaded, wherein the target data includes type and quantity information of spare parts to be loaded;
[0103] A data calculation module, used to determine the loading threshold of various spare parts to be loaded by using block generation combined with a remaining space algorithm, wherein the loading threshold includes an upper limit value of the number of spare parts that can be loaded;
[0104] An optimization iteration module, used to construct a spare parts quantity population and a placement plan population within the range of the loading threshold, and use a dual-population parasitic genetic algorithm to optimize the spare parts quantity and the placement plan, so as to determine the spare parts quantity plan and the spare parts placement plan that achieve a preset comprehensive satisfaction rate, wherein the placement plan population is based on the spare parts quantity population;
[0105] The data output module is used to output the spare parts loading plan according to the spare parts quantity plan and the spare parts placement plan.
[0106] The third embodiment of the present application proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to at least one of the processors; wherein the memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to implement the spare parts packing method based on a dual-population parasitic genetic algorithm as described in the first embodiment of the present application.
[0107] The fourth embodiment of the present application proposes a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to be executed by the computer to implement the spare parts packing method based on the dual-population parasitic genetic algorithm as described in the first embodiment of the present application.
[0108] Technical personnel in the relevant technical field can clearly understand that, for the convenience and conciseness of description, the specific working process of each module in the system described above and the relevant description of the electronic device or computer-readable storage medium can refer to the corresponding process in the aforementioned method example and will not be repeated here.
[0109] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A spare parts packing method based on a dual-population parasitic genetic algorithm, characterized in that: include: Acquire information of a plurality of spare parts to be loaded and spare parts loading containers as input information; Based on the input information, a loading threshold of various spare parts to be loaded is determined by using a block generation combined with a remaining space algorithm, wherein the loading threshold includes an upper limit value of the number of spare parts that can be loaded; Within the range of the loading threshold, construct a spare parts quantity population and a placement plan population, and use a dual-population parasitic genetic algorithm to optimize the spare parts quantity and the placement plan, so as to determine the spare parts quantity plan and the spare parts placement plan that achieve a preset comprehensive satisfaction rate, wherein the placement plan population is a parasitic population derived from the spare parts quantity population; Output the spare parts packing plan based on the spare parts quantity plan and the spare parts placement plan.
2. The spare parts packing method based on dual-population parasitic genetic algorithm according to claim 1 is characterized in that: The comprehensive satisfaction rate is: P=0.1*P V +0.9*P T ; In the formula, P is the comprehensive satisfaction rate, P V is the spare parts loading rate, P T For task completion.
3. The spare parts packing method based on dual-population parasitic genetic algorithm according to claim 2 is characterized in that: The spare parts loading rate is: Where P V is the spare parts loading rate, V 放 is the total volume of the placed spare parts block, V 柜 is the volume of the spare parts cabinet; The task completion degree P T for: Where n is the number of spare parts, Pi is the probability that at least Ni of the (qi+Ni) spare parts can work properly and qi cannot work properly, and λ i is the average failure-free probability of spare part Xi, N i is the number of single machine installations, qi is the number of spare parts carried, T represents the working time, and a is the number of available work pieces.
4. The spare parts packing method based on dual-population parasitic genetic algorithm according to claim 1 is characterized in that: The block generation is combined with the remaining space algorithm to determine the loading thresholds of various spare parts to be loaded, including: Determine the spare parts type set as {X1,X2,....Xn} and the spare parts initial quantity set as {min1,min2...minn}; By utilizing block generation combined with the remaining space algorithm, the initial quantity mini corresponding to the target spare part type Xi is incremented until it exceeds the loading range of the spare parts loading container, and the upper limit of the portable quantity of spare parts of spare part type Xi is obtained. After traversing the spare parts type set, the loading thresholds of various spare parts to be loaded are obtained.
5. The spare parts packing method based on dual-population parasitic genetic algorithm according to claim 4 is characterized in that: The method for obtaining the upper limit of the number of spare parts of spare part type Xi that can be carried is: Initializing the space of the spare parts loading container, determining spare parts blocks corresponding to various spare parts to be loaded, sorting the spare parts blocks according to their volumes, and obtaining a spare parts block sorting result; All remaining spaces are sorted according to the distance between the largest remaining space and the origin of the spare parts cabinet to obtain the space sorting result; Loading each spare part block according to the spare part block sorting result and the space sorting result; After loading is completed, the current remaining space is determined, and it is judged whether the current remaining space is sufficient to place the target spare part type Xi; If so, the initial quantity mini is incremented, and spare parts blocks are regenerated and loaded until the loading range of the spare parts loading container is exceeded, thereby obtaining the upper limit of the portable quantity of spare parts of the spare parts type Xi.
6. The spare parts packing method based on dual-population parasitic genetic algorithm according to claim 1 is characterized in that: The step of constructing a spare parts quantity population and a placement scheme population within the range of the loading threshold comprises: Randomly generate the number of various types of spare parts to be loaded within the range of the loading threshold, and construct the spare parts quantity population; Generate homogeneous spare parts blocks according to spare parts types, sort the homogeneous spare parts blocks according to a set order, and use random numbers to construct the spare parts placement plan population; the set order includes the order of sorting according to weight, length, width, height, and volume.
7. The spare parts packing method based on dual-population parasitic genetic algorithm according to claim 1 is characterized in that: The method of using a dual-population parasitic genetic algorithm to optimize the number of spare parts and the placement plan to determine the number of spare parts and the placement plan that achieve a preset comprehensive satisfaction rate includes: Based on the genetic algorithm of the priority retention strategy, the placement scheme population is solved with the loading rate as a constraint until a preset maximum number of iterations is reached to obtain the spare parts placement scheme; Updating the genetic parameters of the quantity plan population, solving the quantity plan population with the task completion degree as a constraint, and obtaining the spare parts quantity plan; Determine whether the spare parts placement plan and the spare parts quantity plan reach a preset comprehensive satisfaction rate; If yes, the spare parts placement plan and spare parts quantity plan are output; If not, the placement plan population and the quantity plan population are reconstructed, and the spare parts placement plan and the spare parts quantity plan are updated until the spare parts placement plan and the spare parts quantity plan reach the comprehensive satisfaction rate.
8. A spare parts packing system based on a dual-population parasitic genetic algorithm, characterized in that: include: A data acquisition module, used to acquire information of various spare parts to be loaded and spare parts loading containers as input information; A data calculation module, for determining a loading threshold of various spare parts to be loaded based on the input information by using a block generation combined with a remaining space algorithm, wherein the loading threshold includes an upper limit value of the number of spare parts that can be loaded; An optimization iteration module, used to construct a spare parts quantity population and a placement plan population within the range of the loading threshold, and use a dual-population parasitic genetic algorithm to optimize the spare parts quantity and the placement plan, so as to determine the spare parts quantity plan and the spare parts placement plan that achieve a preset comprehensive satisfaction rate, wherein the placement plan population is based on the spare parts quantity population; The data output module is used to output the spare parts loading plan according to the spare parts quantity plan and the spare parts placement plan.
9. An electronic device, characterized in that: include: at least one processor; And a memory communicatively connected to at least one of the processors; wherein the memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to implement the spare parts packing method based on a dual-population parasitic genetic algorithm as described in any one of claims 1-7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to be executed by the computer to implement the spare parts packing method based on a dual-population parasitic genetic algorithm as described in any one of claims 1 to 7.