A production line load balancing method, device, equipment and medium

Abstract

This application provides a method, apparatus, equipment, and medium for production line load balancing. The method includes the following steps: generating an initial allocation scheme; selecting an initial optimized allocation scheme; searching and updating to generate a search-optimized allocation scheme; comparing to obtain a search-determined scheme; performing advanced updates to generate an advanced optimized allocation scheme; comparing to obtain an advanced determined scheme; and iteratively executing until a target number of iterations is reached to generate a target determined scheme. This application generates initial allocation schemes for multiple production devices based on a task list; and performs multiple global, local, and advanced updates and optimizations on the initial allocation schemes to select the final target determined scheme. This method can achieve effective global and local balance; it can dynamically adjust task allocation according to the actual load of the production line, ensuring load balance among production devices, and has significant effects on improving production efficiency and balancing the load of various production devices, and is applicable to production lines of different sizes.

Description

Technical Field

[0001] This invention relates to the fields of optimization algorithms and intelligent manufacturing technology, and in particular to a method, apparatus, equipment and medium for production line load balancing. Background Technology

[0002] With the development of Industry 4.0 and smart manufacturing, the load balancing problem of PCB production lines, also known as surface mount technology (SMT) assembly lines, has received increasing attention. Modern SMT assembly lines typically consist of multiple machines working collaboratively to ensure efficient operation. However, due to differences in the processing capacity of each machine, the complexity of different tasks, and the diversity of production orders, load imbalances can easily occur during actual operation. This not only reduces production efficiency but may also lead to excessive wear or inefficient operation of some machines. Traditional load balancing methods struggle to cope with dynamic and complex production environments. Summary of the Invention

[0003] This invention provides a method, apparatus, equipment, and medium for production line load balancing, which solves the problem that existing load balancing methods have limitations when dealing with high-dimensional and multi-constraint load balancing problems and are difficult to cope with dynamic and complex production environments.

[0004] To solve the above-mentioned technical problems, the present invention provides a production line load balancing method, comprising the following steps: First, obtaining a task list, and according to the task list, performing task initialization allocation on multiple production devices on the production line to generate multiple initial allocation schemes; Second, evaluating the fitness of the multiple initial allocation schemes, and selecting the initial allocation scheme with the best fitness as the initial optimized allocation scheme; Third, according to the initial optimized allocation scheme, searching and updating the multiple initial allocation schemes to generate multiple corresponding search optimized allocation schemes; and selecting the search optimized allocation scheme with the best fitness among them, comparing its fitness with the initial optimized allocation scheme to obtain a search determined scheme; Fourth, according to the search determined scheme, performing advanced updates on the multiple search optimized allocation schemes to generate multiple corresponding advanced optimized allocation schemes; and selecting the advanced optimized allocation scheme with the best fitness among them, comparing its fitness with the search determined scheme to obtain an advanced determined scheme; Fifth, according to the advanced determined scheme, iteratively executing the third and fourth steps until the target number of iterations is reached to generate a target determined scheme.

[0005] In some embodiments, the step of initializing and allocating tasks to multiple production devices on the production line according to the task list specifically includes: randomly assigning first-type components to multiple first-type production devices; randomly assigning second-type components to multiple second-type production devices; and randomly assigning third-type components to multiple first-type or second-type production devices.

[0006] In some embodiments, the step of searching and updating multiple initial allocation schemes according to the initial optimized allocation scheme specifically includes: setting a search threshold and randomly generating a search algebra; if the search algebra is greater than the search threshold, then performing a global search update on multiple initial allocation schemes; if the search algebra is less than the search threshold, then performing a local search update on multiple initial allocation schemes.

[0007] In some embodiments, the global search update includes: performing a global search on a plurality of the initial allocation schemes; adjusting the position of the element in each of the initial allocation schemes according to the initial optimized allocation scheme and the global search parameters, and updating the plurality of the initial allocation schemes.

[0008] In some embodiments, the local search update includes: performing a local search on a plurality of the initial allocation schemes; adjusting the position of the element in each of the initial allocation schemes according to the initial optimized allocation scheme and the local search parameters, and updating the plurality of the initial allocation schemes.

[0009] In some embodiments, the step of performing an advanced update on multiple search optimization allocation schemes according to the search determination scheme specifically includes: adjusting the movement speed of the elements in each search optimization allocation scheme according to the initial allocation scheme, the search determination scheme, and the advanced parameters; adjusting the position of the elements in each search optimization allocation scheme according to the movement speed; and updating the multiple search optimization allocation schemes.

[0010] In some embodiments, the task list includes multiple different types of workpieces, the quantity of each type of workpiece, the processing time for each type of workpiece, and the constraints for each type of workpiece.

[0011] This invention also provides a production line load balancing device, comprising: an acquisition unit for acquiring a task list; an initialization unit for performing task initialization allocation on multiple production devices on the production line according to the task list, generating multiple initial allocation schemes; an initial evaluation unit for evaluating the fitness of the multiple initial allocation schemes and selecting the initial allocation scheme with the best fitness as the initial optimized allocation scheme; a search unit for searching and updating the multiple initial allocation schemes according to the initial optimized allocation scheme, generating multiple corresponding search optimized allocation schemes; a search evaluation unit for selecting the search optimized allocation scheme with the best fitness and comparing its fitness with the initial optimized allocation scheme to obtain a search determined scheme; an advancement unit for performing advanced updates on the multiple search optimized allocation schemes according to the search determined scheme, generating multiple corresponding advanced optimized allocation schemes; and an advancement evaluation unit for selecting the advanced optimized allocation scheme with the best fitness and comparing its fitness with the search determined scheme to obtain an advanced determined scheme.

[0012] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the steps of the method described above.

[0013] The present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described above.

[0014] The beneficial effects of this invention are as follows: This invention discloses a method, apparatus, equipment, and medium for load balancing on a production line. The method includes the following steps: First, obtaining a task list, and according to the task list, performing task initialization allocation on multiple production devices on the production line to generate multiple initial allocation schemes; Second, evaluating the fitness of the multiple initial allocation schemes, and selecting the initial allocation scheme with the best fitness as the initial optimized allocation scheme; Third, according to the initial optimized allocation scheme, searching and updating the multiple initial allocation schemes to generate multiple corresponding search optimized allocation schemes; and selecting the search optimized allocation scheme with the best fitness, comparing its fitness with the initial optimized allocation scheme to obtain the search determined scheme; Fourth, according to the search determined scheme, performing advanced updates on the multiple search optimized allocation schemes to generate multiple corresponding advanced optimized allocation schemes; and selecting the advanced optimized allocation scheme with the best fitness, comparing its fitness with the search determined scheme to obtain the advanced determined scheme; Fifth, according to the advanced determined scheme, iteratively executing steps three and four until the target number of iterations is reached to generate the target determined scheme. This application initializes and allocates tasks to multiple production devices based on a task list, generating multiple initial allocation schemes. These initial allocation schemes are then updated multiple times globally, locally, and progressively to optimize them and ultimately select the final target-determined scheme. Through a two-way information exchange mechanism, this application avoids getting trapped in local optima while accelerating the optimization process and achieving an effective balance between global and local optimization. This method can dynamically adjust task allocation according to the actual load of the production line, ensuring balanced load on each production device. It demonstrates significant effects in improving production efficiency and balancing the workload of each production device, while also exhibiting good scalability and applicability to PCB production lines of different sizes. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating a production line load balancing method according to this application;

[0016] Figure 2 This is a schematic diagram of the load balancing efficiency of the first production line in a production line load balancing method of this application;

[0017] Figure 3 This is a schematic diagram of the load balancing efficiency of the second production line in a production line load balancing method of this application;

[0018] Figure 4 This is a schematic diagram of the load balancing efficiency of the third production line in a production line load balancing method of this application;

[0019] Figure 5 This is a schematic diagram of the cycle time corresponding to the first production line in a production line load balancing method of this application;

[0020] Figure 6 This is a schematic diagram of the cycle time corresponding to the second production line in a production line load balancing method of this application;

[0021] Figure 7 This is a schematic diagram of the cycle time corresponding to the third production line in a production line load balancing method of this application;

[0022] Figure 8 This is a schematic diagram of the order completion time corresponding to the first production line in a production line load balancing method of this application;

[0023] Figure 9 This is a schematic diagram of the order completion time corresponding to the second production line in a production line load balancing method of this application;

[0024] Figure 10 This is a schematic diagram of the order completion time corresponding to the third production line in a production line load balancing method of this application;

[0025] Figure 11 This is a schematic diagram of the convergence curve corresponding to the first production line in the production line load balancing method of this application;

[0026] Figure 12 This is a schematic diagram of the convergence curve corresponding to the second production line in the production line load balancing method of this application;

[0027] Figure 13 This is a schematic diagram of the convergence curve corresponding to the third production line in the production line load balancing method of this application;

[0028] Figure 14 This is a schematic diagram of the composition of a production line load balancing device according to this application;

[0029] Figure 15 This is a schematic diagram of the architecture of an embodiment of an electronic device according to this application;

[0030] Figure 16 This is a schematic block diagram of an embodiment of a computer-readable storage medium according to this application. Detailed Implementation

[0031] To facilitate understanding of the present invention, a more detailed description is provided below with reference to the accompanying drawings and specific embodiments. Preferred embodiments of the invention are shown in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a thorough and complete understanding of the disclosure of the invention.

[0032] It should be noted that, unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. The term "and / or" as used in this specification includes any and all combinations of one or more of the associated listed items.

[0033] It should be noted that there are two types of components in PCB (Printed Circuit Board) systems: pinhole components and SMT (Surface Mount Technology) components. This application primarily focuses on SMT components. SMT assembly lines involve various complex assembly processes, including solder paste printing, component placement, reflow soldering, manual quality inspection, and AOI (Automated Optical Inspection) quality inspection. SMT assembly line balancing is achieved by distributing components to each SMT assembly station, thereby maintaining a balanced workload among them. SMT assembly stations are typically equipped with automated production lines and intelligent equipment, such as high-speed pick-and-place machines, automated optical inspection systems, reflow ovens, and programming testers. Load balancing in the assembly line refers to load balancing among the pick-and-place machines, meaning that the component placement time for each pick-and-place machine should be as consistent as possible.

[0034] like Figure 1 As shown, the present invention provides a production line load balancing method, including the following steps:

[0035] S1: Obtain the task list, and based on the task list, initialize and allocate tasks to multiple production equipment on the production line to generate multiple initial allocation schemes.

[0036] S2: Evaluate the fitness of multiple initial allocation schemes and select the initial allocation scheme with the best fitness as the initial optimal allocation scheme.

[0037] S3: Based on the initial optimized allocation scheme, search and update multiple initial allocation schemes to generate multiple corresponding search optimized allocation schemes; select the search optimized allocation scheme with the best fitness and compare its fitness with the initial optimized allocation scheme to obtain the search determined scheme.

[0038] S4: Based on the search-determined scheme, perform advanced updates on multiple search optimization allocation schemes to generate multiple corresponding advanced optimization allocation schemes; and select the advanced optimization allocation scheme with the best fitness among them, compare its fitness with the search-determined scheme, and obtain the advanced determined scheme.

[0039] S5: Based on the advanced solution, iteratively execute S3 and S4 until the target number of iterations is reached, and generate the target solution.

[0040] This application initializes and allocates tasks to multiple production devices based on a task list, generating multiple initial allocation schemes. These initial allocation schemes are then updated multiple times globally, locally, and progressively to optimize them and ultimately select the final target-determined scheme. Through a two-way information exchange mechanism, this application avoids getting trapped in local optima while accelerating the optimization process and achieving an effective balance between global and local optimization. This method can dynamically adjust task allocation according to the actual load of the production line, ensuring balanced load on each production device. It demonstrates significant effects in improving production efficiency and balancing the workload of each production device, while also exhibiting good scalability and applicability to PCB production lines of different sizes.

[0041] The following is combined with Figures 1 to 16 The present application will be further described in detail with reference to specific embodiments.

[0042] Figure 1 A flowchart illustrating the production line load balancing method provided in an embodiment of this application is shown below, and is described in detail below:

[0043] S1: Obtain the task list, and based on the task list, initialize and allocate tasks to multiple production equipment on the production line to generate multiple initial allocation schemes.

[0044] The task list includes multiple different types of processed parts, the quantity of each type of processed part, the processing time for each type of processed part, and the constraints for each type of processed part. Processed parts include Category I, Category II, and Category III components. Each of these categories includes various types of components. The production equipment on a production line includes Category I and Category II production equipment. The constraints state that Category I components can only be processed using Category I production equipment; Category II components can only be processed using Category II production equipment; and Category III components are unrestricted and can be processed using either Category I or Category II production equipment.

[0045] Therefore, to keep the production line load balanced, the first and second types of components need to be allocated to the corresponding production equipment according to the constraints, and the position of the third type of components in the production line can be further adjusted.

[0046] Therefore, this application constructs a load balancing (MILP, Mixed-integer linear programming) model based on the production equipment and the obtained task list, and performs task initialization allocation on multiple production equipment on the production line based on the load balancing model.

[0047] In this embodiment, the first type of production equipment refers to a high-speed pick-and-place machine, and the second type of production equipment refers to a multi-functional pick-and-place machine. Assuming there are a total of n types of components in this application, the first k types are all first-type components, and the th type... Planted to the first The first type is the second type of element, the second type is the third type of element. The nth type is the third type of element.

[0048] Specifically, the first type of components are randomly assigned to multiple first type of production equipment, as expressed by the following formula:

[0049]

[0050] in, Represents the first type of production equipment. Represents the number of Class I production equipment. Represents a random function. k This represents one of the initial allocation schemes. i Represents one type of component. Represents a matrix. Representative matrix The Middle k Line 1 i The element of the column, i.e., the first k In the initial allocation scheme, the first... i The position of the component.

[0051] Furthermore, the second type of components are randomly assigned to multiple second type of production equipment, as expressed by the following formula:

[0052]

[0053] in, Represents the first type of production equipment. Represents the number of Class I production equipment. Represents a random function. Represents the second type of production equipment. This represents the number of second-class production equipment. k This represents one of the initial allocation schemes. i Represents one type of component. Represents a matrix. Representative matrix The Middle k Line 1 i The element of the column, i.e., the first k In the initial allocation scheme, the first... i The position of the component.

[0054] Furthermore, the third type of components are randomly assigned to multiple first type or second type production equipment, as expressed by the following formula:

[0055]

[0056] in, Representing the Type III components (i.e., third-class components). The number of types of processed parts. Represents a random function. k This represents one of the initial allocation schemes. i Represents one type of component. Represents a matrix. Representative matrix The Middle k Line 1 i The element of the column, i.e., the first k In the initial allocation scheme, the first... i The position of the component.

[0057] After allocation is completed, multiple initial allocation schemes are generated, i.e., matrices. ( ).in, Represents the number of initial allocation schemes. This represents the number of types of processed parts.

[0058] By applying constraints to different types of workpieces, specific production equipment is allocated to the workpieces, and multiple corresponding initial allocation schemes are generated, making the load on the production equipment more balanced and effectively improving production efficiency.

[0059] S2: Evaluate the fitness of multiple initial allocation schemes and select the initial allocation scheme with the best fitness as the initial optimal allocation scheme.

[0060] Specifically, in this embodiment, the fitness evaluation is performed using the following function:

[0061]

[0062] in, Represents the final objective function. represent The balance parameters, represent The balance parameters, The objective function representing the order completion time. Represents constraint terms. Represents the number of production equipment. Represents one of the production equipment m The completion time, , Represents the number of PCB boards. Represents the periodic time. , Represents the next production equipment m+1 The completion time, This represents the upper limit of the balance constraint. This represents the average completion time of all production equipment. , This represents the time required for the production equipment with the shortest completion time. , , j Representing the j Such components, This represents a collection of various components allocated to one of the production equipment. represent Scale.

[0063] The best fitness represents the final objective function. The initial allocation scheme that minimizes the value of the final objective function is taken as the initial optimized allocation scheme.

[0064] S3: Based on the initial optimized allocation scheme, search and update multiple initial allocation schemes to generate multiple corresponding search optimized allocation schemes; select the search optimized allocation scheme with the best fitness and compare its fitness with the initial optimized allocation scheme to obtain the search determined scheme.

[0065] Specifically, first, set the search threshold. The search threshold is then randomly generated. Specifically, the search threshold ranges from (0, 1), and this application sets the search threshold to 0.5.

[0066] Furthermore, if the search generation is greater than the search threshold, such as randomly generating a search generation of 0.7, then a global search update is performed on multiple initial allocation schemes. If the search generation is less than the search threshold, such as randomly generating a search generation of 0.3, then a local search update is performed on multiple initial allocation schemes.

[0067] Specifically, the global search update includes: performing a global search on multiple initial allocation schemes; adjusting the positions of components in each initial allocation scheme based on the initial optimized allocation scheme and global search parameters, and updating multiple initial allocation schemes. Here, global search refers to a large-scale search for the positions of components across multiple initial allocation schemes. The above process can be represented by the following formula:

[0068]

[0069] in, Representing the In the initial allocation scheme during the iteration, the first... The position of the component Represents global search parameters. Represents the initial optimized allocation scheme. The position of the component Represents the global scaling factor. Representing the t+1 In the nth iteration, the search optimization allocation scheme is in the th... The position of the component This represents the current iteration number.

[0070] Furthermore, the local search update includes: performing a local search on multiple initial allocation schemes; adjusting the positions of components in each initial allocation scheme based on the initial optimized allocation scheme and local search parameters, and updating multiple initial allocation schemes. Here, local search refers to searching a small range of component positions within multiple initial allocation schemes. The above process can be represented by the following formula:

[0071]

[0072] in, Representing the In the initial allocation scheme during the iteration, the first... The position of the component Represents local search parameters. Represents the initial optimized allocation scheme. The position of the component Represents the local scaling factor. Representing the In the nth iteration, the search optimization allocation scheme is in the th... The position of the component Represents the current iteration number. Representing the In the nth randomly selected initial allocation scheme, the nth The position of the component.

[0073] It should be noted that in this embodiment, only the position of the third type of element is adjusted, while the positions of the first type of element and the second type of element remain unchanged.

[0074] Furthermore, after performing global or local search updates on multiple initial allocation schemes, several corresponding optimized allocation schemes are generated. For each optimized allocation scheme, the final objective function in S2 is used for fitness evaluation, and the optimized allocation scheme with the best fitness is selected and compared with the initial optimized allocation scheme. If the selected optimized allocation scheme has a lower fitness value, it is adopted as the final search scheme; if the initial optimized allocation scheme has a lower fitness value, it is adopted as the final search scheme.

[0075] S4: Based on the search-determined scheme, perform advanced updates on multiple search optimization allocation schemes to generate multiple corresponding advanced optimization allocation schemes; and select the advanced optimization allocation scheme with the best fitness among them, compare its fitness with the search-determined scheme, and obtain the advanced determined scheme.

[0076] Specifically, the information on the positions of components in multiple initial allocation schemes and search-determined schemes is first initialized.

[0077] Furthermore, based on the initial allocation scheme, the search-determined scheme, and the advanced parameters, the movement speed of the components in each search-optimized allocation scheme is adjusted. The advanced parameters include inertia weights, individual learning factors, and social learning factors. The above process can be expressed by the following formula:

[0078]

[0079] in, Representing the During the nth iteration i In the first advanced optimization allocation scheme, the first... The moving speed of the component Representing the During the nth iteration i In the first search optimization allocation scheme, the first The moving speed of the component Represents inertia weight. Represents individual learning factors. Represents social learning factors. and Represents a random number between [0, 1] Representing the The best historical position of this component Representing the During the nth iteration i In the first search optimization allocation scheme, the first The position of the component The representative search determines the first scheme. The position of the component This represents the current iteration number.

[0080] It should be noted that inertia weight Individual learning factors Social learning factors The inertia weight changes continuously with the number of iterations. It decreases linearly with increasing iterations to provide a larger search space initially. Later, the inertia weight gradually decreases, facilitating finer adjustments to the solution and accelerating convergence to a better solution. In the early stages, a larger individual learning factor encourages the solution to move towards its past best allocations, fully utilizing its experience and enhancing its local search capability. As the number of iterations increases, increasing the individual learning factor makes the solution more inclined to explore already discovered better solutions, thus improving the solution's quality. In the early stages, a larger social learning factor prompts the solution to focus more on the global optimum, guiding it closer to the global optimum and improving global search capability, avoiding getting trapped in local optima. As the number of iterations increases, appropriately decreasing the social learning factor reduces dependence on the global optimum, allowing the solution to explore deeper into local regions and improving the utilization efficiency of current better solutions. The inertia weight, individual learning factor, and social learning factor can be represented by the following formula:

[0081]

[0082] in, Represents inertia weight. Represents individual learning factors. Represents social learning factors. The maximum value representing the inertia weight. This represents the minimum value of the inertia weight. The maximum value of the individual's learning factor. The minimum value representing the individual's learning factor. Represents the maximum value of the social learning factor. This represents the minimum value of the social learning factor. Represents the maximum number of iterations. This represents the current iteration number.

[0083] Furthermore, based on the movement speed, the positions of the elements in each search optimization allocation scheme are adjusted, and multiple search optimization allocation schemes are updated. The above process can be represented by the following formula:

[0084] ,

[0085] in, Representing the During the nth iteration iIn the first advanced optimization allocation scheme, the first... The moving speed of the component Representing the During the nth iteration i In the first advanced optimization allocation scheme, the first... The position of the component Representing the During the nth iteration i In the first search optimization allocation scheme, the first The position of the component This represents the current iteration number.

[0086] It should be noted that in this embodiment, only the position and moving speed of the third type of element are adjusted, while the position and moving speed of the first type of element and the second type of element remain unchanged.

[0087] Furthermore, after performing advanced updates on multiple search optimization allocation schemes, multiple corresponding advanced optimization allocation schemes are generated. For multiple advanced optimization allocation schemes, the final objective function in S2 is used for fitness evaluation, and the advanced optimization allocation scheme with the best fitness is selected and compared with the search-determined scheme. If the selected advanced optimization allocation scheme has a smaller fitness value, it is adopted as the advanced determined scheme; if the search-determined scheme has a smaller fitness value, it is adopted as the advanced determined scheme.

[0088] S5: Based on the advanced solution, iteratively execute S3 and S4 until the target number of iterations is reached, and generate the target solution.

[0089] Based on the obtained advanced determination scheme, further execute S3 and S4 to search and update multiple advanced optimization allocation schemes, compare the fitness of the results, iterate multiple times until the target number of iterations is reached, and generate a final target determination scheme.

[0090] In this embodiment, the target iteration count is set to 100 times. Therefore, after iterating through steps S3 and S4 100 times in sequence, the target determination scheme can be obtained.

[0091] In summary, for reference Figures 2 to 13 As shown, to verify the efficiency and performance of the production line load balancing method (i.e., iGCRA algorithm) of this application, it was further compared with existing load balancing optimization methods (ABC algorithm, PSO algorithm, GABC algorithm and GCRA algorithm) through experiments. The comparison results are detailed below.

[0092] Specifically, three different production lines are first set up, each with a different number of production equipment (i.e., pick-and-place machines), as shown in Table 1 below:

[0093] Table 1

[0094]

[0095] For each production line, five task lists (i.e. BOMs) are randomly selected for testing. Each task list is tested 20 times to ensure the accuracy of the results, and the average value of the results is calculated.

[0096] To accurately assess the differences among these five methods, four metrics were used for evaluation: load balancing efficiency (… ), cycle time (T), order completion time ( ) and the convergence curve.

[0097] For details, please refer to Figures 2 to 4 As shown, the load balancing efficiencies of the five methods are displayed on three different production lines. A schematic diagram of the load balancing efficiency ( ). In this embodiment, the load balancing efficiency ( ) The formula for ) is expressed as:

[0098]

[0099] in, It represents the total processing time of all production equipment on a production line. Represents the periodic time. This represents the number of production equipment on a production line.

[0100] from Figures 2 to 4 As can be seen from this, the load balancing efficiency of the production line load balancing method in this application ( ,Too Figures 2 to 4 The method described in the blue section achieved superior performance in almost all production line experiments, with load balancing efficiency values ​​approaching 1 and surpassing other comparative methods (ABC, PSO, GABC, and GCRA). This not only demonstrates the adaptability and stability of the proposed method under different production line and task list configurations but also further proves its superior optimization capabilities in complex production environments. In contrast, other methods failed to achieve the same optimization results in multiple production line experiments, revealing their limitations in handling such problems.

[0101] Further reference Figures 5 to 7 The diagram shows the cycle time (T) for the five methods on three different production lines. Cycle time (T) is the processing time required by the longest-running production equipment on a production line. In this embodiment, the formula for cycle time (T) is:

[0102]

[0103] in, This represents the processing time required for production equipment m, which has the longest processing time in a production line.

[0104] from Figures 5 to 7 As can be seen from the data, the production line load balancing method of this application achieved the lowest cycle time in all production line experiments. Figures 5 to 7 (The blue section in the middle) demonstrates superior performance compared to other comparative methods. Through effective optimization strategies, the method in this application significantly reduces the cycle time required for production, thereby lowering order completion time and highlighting its high efficiency in handling complex production tasks. In contrast, other methods have failed to achieve the same level of optimization in most cases, clearly demonstrating the advantage of the method in optimizing load balancing.

[0105] Further reference Figures 8 to 10 As shown, the order completion times for the five methods are displayed on three different production lines. A schematic diagram of the order completion time. In this embodiment, the order completion time ( The formula for ) is expressed as:

[0106]

[0107] in, This represents the number of PCBs required in the task list. Represents the periodic time. This represents the number of production equipment on a production line. This represents the processing time required for production equipment m, which has the longest processing time in a production line.

[0108] from Figures 8 to 10 As can be seen from the data, the production line load balancing method proposed in this application achieved the shortest order completion time in all production line experiments. Figures 8 to 10 (The blue section in the middle) In contrast, other methods showed relatively unstable performance, with significantly longer order completion times in some production line experiments. This indicates that the method proposed in this application has strong stability in optimizing order completion time, effectively improving production line operating efficiency and reducing the total order processing time. Regardless of the different production lines or the complexity of different task lists, the method proposed in this application significantly outperforms other comparative methods in shortening order completion time.

[0109] Further reference Figures 11 to 13The diagram shows the convergence curves of the five methods on three different production lines. The convergence curves are plotted based on the values ​​of the fitness function; in this embodiment, the plotting parameters for the convergence curves are shown in Table 2 below:

[0110] Table 2

[0111]

[0112] in, and Representing two balance parameters, This represents the upper limit of the balance constraint. The maximum value representing the inertia weight. This represents the minimum value of the inertia weight. The maximum value of the individual's learning factor. The minimum value representing the individual's learning factor. Represents the maximum value of the social learning factor. This represents the minimum value of the social learning factor.

[0113] from Figures 11 to 13 As can be seen, the production line load balancing method of this application demonstrates significant advantages in the optimization process. Specifically, in the first 20 iterations, the fitness value of the method in this application ( Figures 11 to 13 The dark blue curve (symbolizing convergence) drops rapidly, demonstrating an extremely fast convergence speed; within 50 iterations, the proposed method approaches the optimal solution. In contrast, other methods converge more slowly within the same number of iterations and achieve higher final fitness values. The proposed method not only converges rapidly in the initial iteration phase but also demonstrates continuous optimization capabilities in later iterations, further fine-tuning the accuracy of the fitness value. This contrasts sharply with other methods, which, after reaching a high fitness value early on, experience a significant slowdown in convergence speed, or even stagnate. This indicates that the proposed method possesses stronger global search and local exploitation capabilities throughout the optimization process, enabling it to find superior solutions more effectively and maintain high optimization efficiency.

[0114] Corresponding to the production line load balancing method in the above embodiment, Figure 14 A schematic diagram of the composition of the production line load balancing device provided in the embodiments of this application is shown. For ease of explanation, only the parts related to the embodiments of this application are shown.

[0115] refer to Figure 14 The load balancing device for this production line includes:

[0116] Acquisition unit 101 is used to acquire the task list.

[0117] The initialization unit 102 is used to perform task initialization and allocation on multiple production equipment on the production line according to the task list, and generate multiple initial allocation schemes.

[0118] The initial evaluation unit 103 is used to evaluate the fitness of multiple initial allocation schemes and select the initial allocation scheme with the best fitness as the initial optimized allocation scheme.

[0119] Search unit 104 is used to search and update multiple initial allocation schemes based on the initial optimized allocation scheme, and generate multiple corresponding search optimized allocation schemes.

[0120] The search evaluation unit 105 is used to select the search optimization allocation scheme with the best fitness and compare its fitness with the initial optimization allocation scheme to obtain the search determination scheme.

[0121] The advanced unit 106 is used to perform advanced updates on multiple search optimization allocation schemes based on the search-determined scheme, and generate multiple corresponding advanced optimization allocation schemes.

[0122] The advanced evaluation unit 107 is used to select the advanced optimization allocation scheme with the best fitness and compare its fitness with the search-determined scheme to obtain the advanced determined scheme.

[0123] It should be noted that the above-mentioned production line load balancing device is based on the same concept as the method embodiment of this application. Its specific functions, the process by which each module performs its respective function, and the resulting technical effects can be specifically referred to the description of the embodiment of the aforementioned production line load balancing method, and will not be repeated here.

[0124] Based on the same inventive concept, this application also provides an electronic device, which includes a processor, a memory, and a communication circuit, wherein the processor is connected to the memory and the communication circuit respectively; wherein the communication circuit is used for communication connection, the memory is used to store a computer program, and the processor is used to execute the computer program to implement the above-mentioned production line load balancing method.

[0125] See Figure 15 The electronic device described in this application embodiment may specifically include a processor 210 and a memory 220. The memory 220 is coupled to the processor 210.

[0126] Processor 210 is used to control the operation of electronic devices. Processor 210 can also be referred to as a CPU (Central Processing Unit). Processor 210 may be an integrated circuit chip with signal processing capabilities. Processor 210 can also be a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor, or processor 210 can be any conventional processor.

[0127] Memory 220 is used to store computer programs and may be RAM, ROM, or other types of storage terminals. Specifically, memory 220 may include one or more computer-readable storage media, which may be non-transitory or transient. Memory 220 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage terminals or flash memory terminals. In some embodiments, the non-transitory computer-readable storage media in memory 220 is used to store at least one line of program code.

[0128] The processor 210 is used to execute computer programs stored in the memory 220 to implement the methods described in the various method embodiments of this application.

[0129] In some embodiments, the electronic device may further include: a peripheral terminal interface 230 and at least one peripheral terminal. The processor 210, memory 220, and peripheral terminal interface 230 can be connected via a bus or signal line. Each peripheral terminal can be connected to the peripheral terminal interface 230 via a bus, signal line, or circuit board. Specifically, the peripheral terminal includes at least one of: a radio frequency circuit 240, a display screen 250, an audio circuit 260, and a power supply 270.

[0130] The peripheral terminal interface 230 can be used to connect at least one I / O (Input / output) related peripheral terminal to the processor 210 and the memory 220. In some embodiments, the processor 210, memory 220 and peripheral terminal interface 230 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 210, memory 220 and peripheral terminal interface 230 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0131] The radio frequency (RF) circuit 240 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 240 communicates with communication networks and other IoT devices via electromagnetic signals; it is the communication circuit of the electronic device. The RF circuit 240 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. Optionally, the RF circuit 240 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, an operator identification module card, etc. The RF circuit 240 can communicate with other terminals through at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 240 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0132] Display screen 250 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 250 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 210 for processing. In this case, display screen 250 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 250, located on the front panel of the electronic device; in other embodiments, there may be at least two display screens, located on different surfaces of the electronic device or in a folded design; in still other embodiments, display screen 250 may be a flexible display screen, located on a curved or folded surface of the electronic device. Furthermore, display screen 250 may be configured as a non-rectangular, irregular shape, i.e., a non-rectangular screen. Display screen 250 may be made of materials such as LCD (Liquid Crystal Display) or OLED (Organic Light-Emitting Diode).

[0133] The audio circuit 260 may include a microphone and a speaker. The microphone is used to collect sound waves from the operator and the environment, converting the sound waves into electrical signals that are input to the processor 210 for processing, or input to the radio frequency circuit 240 for voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each positioned in a different part of the electronic device. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor 210 or the radio frequency circuit 240 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 260 may also include a headphone jack.

[0134] Power supply 270 is used to supply power to various components in an electronic device. Power supply 270 can be alternating current, direct current, a disposable battery, or a rechargeable battery. When power supply 270 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged via a wired line, while a wireless rechargeable battery is a battery that is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0135] For a detailed description of the functions and execution processes of each functional module or component in the electronic device embodiments of this application, please refer to the descriptions in the above-described method embodiments of this application, which will not be repeated here.

[0136] In the embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the embodiments of the electronic devices described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0137] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0138] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0139] Based on the same inventive concept, this application also provides a computer-readable storage medium storing a computer program that can be executed by a processor to implement the above-described production line load balancing method.

[0140] See Figure 16 If the integrated units described above are implemented as software functional units and sold or used as independent products, they can be stored in computer-readable storage medium 300. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions / computer programs to cause an Internet of Things device (which may be a personal computer, server, or network terminal, etc.) or processor to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned storage medium includes various media such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, as well as electronic terminals such as computers, mobile phones, laptops, tablets, and cameras that have the aforementioned storage media.

[0141] The description of the execution process of program data in a computer-readable storage medium can be found in the descriptions in the various method embodiments of this application above, and will not be repeated here.

[0142] Therefore, this invention discloses a production line load balancing method, apparatus, equipment, and medium. The method includes the following steps: First, obtaining a task list, and based on the task list, performing initial task allocation on multiple production devices on the production line to generate multiple initial allocation schemes; Second, evaluating the fitness of the multiple initial allocation schemes, and selecting the initial allocation scheme with the best fitness as the initial optimized allocation scheme; Third, based on the initial optimized allocation scheme, searching and updating the multiple initial allocation schemes to generate multiple corresponding search optimized allocation schemes; and selecting the search optimized allocation scheme with the best fitness, comparing its fitness with the initial optimized allocation scheme to obtain the search determined scheme; Fourth, based on the search determined scheme, performing advanced updates on the multiple search optimized allocation schemes to generate multiple corresponding advanced optimized allocation schemes; and selecting the advanced optimized allocation scheme with the best fitness, comparing its fitness with the search determined scheme to obtain the advanced determined scheme; Fifth, based on the advanced determined scheme, iteratively executing steps three and four until the target number of iterations is reached to generate the target determined scheme. This application initializes and allocates tasks to multiple production devices based on a task list, generating multiple initial allocation schemes. These initial allocation schemes are then updated multiple times globally, locally, and progressively to optimize them and ultimately select the final target-determined scheme. Through a two-way information exchange mechanism, this application avoids getting trapped in local optima while accelerating the optimization process and achieving an effective balance between global and local optimization. This method can dynamically adjust task allocation according to the actual load of the production line, ensuring balanced load on each production device. It demonstrates significant effects in improving production efficiency and balancing the workload of each production device, while also exhibiting good scalability and applicability to PCB production lines of different sizes.

[0143] The above are merely embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structural transformations made based on the content of the present invention specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A production line load balancing method, characterized in that, Including the following steps: The first step is to obtain a task list, and based on the task list, perform task initialization and allocation for multiple production devices on the production line to generate multiple initial allocation schemes. The second step is to evaluate the fitness of the multiple initial allocation schemes and select the initial allocation scheme with the best fitness as the initial optimized allocation scheme. Use the following function to evaluate fitness: in, Represents the final objective function. represent The balance parameters, represent The balance parameters, The objective function representing the order completion time. Represents constraint terms. Represents the number of production equipment. Represents one of the production equipment m The completion time, Represents the number of PCB boards. Represents the periodic time. Represents the next production equipment m+1 The completion time, This represents the upper limit of the balance constraint. This represents the average completion time of all production equipment. The time required for the production equipment with the shortest completion time; The third step involves searching and updating multiple initial allocation schemes based on the initial optimized allocation scheme to generate multiple corresponding search optimized allocation schemes; and selecting the search optimized allocation scheme with the best fitness among them, comparing its fitness with the initial optimized allocation scheme to obtain the search determined scheme. Specifically, according to the initial optimized allocation scheme, searching and updating multiple initial allocation schemes includes: Based on the initial allocation scheme, the search determination scheme, and the advanced parameters, adjust the movement speed of the elements in each of the search optimization allocation schemes; Based on the moving speed, the position of the element in each of the search optimization allocation schemes is adjusted, and the multiple search optimization allocation schemes are updated; Fourth step: Based on the search determination scheme, perform advanced updates on multiple search optimization allocation schemes to generate multiple corresponding advanced optimization allocation schemes; and select the advanced optimization allocation scheme with the best fitness among them, compare its fitness with the search determination scheme, and obtain the advanced determination scheme. Fifth, based on the advanced determination scheme, iteratively execute the third and fourth steps until the target number of iterations is reached, and generate the target determination scheme.

2. The production line load balancing method according to claim 1, characterized in that, The step of initializing and allocating tasks to multiple production devices on the production line according to the task list specifically includes: The first type of components are randomly assigned to multiple first type of production equipment; The second type of components are randomly assigned to multiple second type of production equipment; The third type of components are randomly assigned to multiple first type of production equipment or second type of production equipment.

3. The production line load balancing method according to claim 1, characterized in that, The step of searching and updating multiple initial allocation schemes based on the initial optimized allocation scheme specifically includes: Set a search threshold and randomly generate a search algebra; If the search algebra is greater than the search threshold, then a global search update is performed on the multiple initial allocation schemes; If the search algebra is less than the search threshold, then a local search update is performed on the multiple initial allocation schemes.

4. The production line load balancing method according to claim 3, characterized in that, The global search update includes: Perform a global search on multiple initial allocation schemes; Based on the initial optimized allocation scheme and global search parameters, the positions of the components in each initial allocation scheme are adjusted, and multiple initial allocation schemes are updated.

5. The production line load balancing method according to claim 3, characterized in that, The local search update includes: Perform a local search on multiple of the initial allocation schemes; Based on the initial optimized allocation scheme and local search parameters, the positions of the elements in each of the initial allocation schemes are adjusted, and multiple initial allocation schemes are updated.

6. The production line load balancing method according to claim 1, characterized in that, The task list includes multiple different types of workpieces, the quantity of each type of workpiece, the processing time for each type of workpiece, and the constraints for each type of workpiece.

7. A production line load balancing device, characterized in that, include: The acquisition unit is used to retrieve the task list; An initialization unit is used to perform task initialization allocation on multiple production equipment on the production line according to the task list, and generate multiple initial allocation schemes. An initial evaluation unit is used to evaluate the fitness of multiple initial allocation schemes and select the initial allocation scheme with the best fitness as the initial optimized allocation scheme. Use the following function to evaluate fitness: in, Represents the final objective function. represent The balance parameters, represent The balance parameters, The objective function representing the order completion time. Represents constraint terms. Represents the number of production equipment. Represents one of the production equipment m The completion time, Represents the number of PCB boards. Represents the periodic time. Represents the next production equipment m+1 The completion time, This represents the upper limit of the balance constraint. This represents the average completion time of all production equipment. The time required for the production equipment with the shortest completion time; A search unit is configured to perform search updates on multiple initial allocation schemes based on the initial optimized allocation scheme, generating multiple corresponding search optimized allocation schemes; specifically including: Based on the initial allocation scheme, the search determination scheme, and the advanced parameters, adjust the movement speed of the elements in each of the search optimization allocation schemes; Based on the moving speed, the position of the element in each of the search optimization allocation schemes is adjusted, and the multiple search optimization allocation schemes are updated; The search evaluation unit is used to select the search optimization allocation scheme with the best fitness and compare it with the initial optimization allocation scheme to obtain the search determination scheme; The advanced unit is used to perform advanced updates on multiple search optimization allocation schemes based on the search determination scheme, and generate multiple corresponding advanced optimization allocation schemes. The advanced evaluation unit is used to select the advanced optimization allocation scheme with the best fitness and compare its fitness with the search-determined scheme to obtain the advanced determination scheme.

8. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the method as claimed in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 6.

Images