Production line load balancing method, device, equipment and medium

Abstract

The invention provides a production line load balancing method and device, equipment and a medium. The method comprises the following steps: generating an initial allocation scheme; selecting an initial optimal distribution scheme; searching and updating, and generating a searching optimization distribution scheme; comparing to obtain a search determination scheme; advanced updating is carried out, and an advanced optimal distribution scheme is generated; comparing to obtain an advanced determination scheme; and iteratively executing until the target number of iterations is reached, and generating a target determination scheme. The method comprises the steps of generating an initial allocation scheme for multiple production devices according to a task list; and carrying out multiple times of global, local and advanced updating optimization on the initial allocation scheme, and screening out a final target determination scheme. According to the method, global and local effective balance can be realized; the task allocation can be dynamically adjusted according to the actual load condition of the production line, the load balance of each production device is ensured, the obvious effects of improving the production efficiency and balancing the load of each production device are achieved, and the method is suitable for production lines of different scales.

Description

Technical Field

[0001] The present invention relates to the field of optimization algorithms and intelligent manufacturing technology, and in particular to a production line load balancing method, device, equipment and medium. Background Art

[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 usually consist of multiple devices working together to ensure efficient operation of the production line. However, due to the differences in processing capabilities of each device, the complexity of different tasks, and the diversity of production orders, the production line is prone to load imbalance during actual operation, which not only reduces production efficiency, but may also cause excessive wear or inefficient operation of some equipment. Traditional load balancing methods are difficult to cope with dynamic and complex production environments. Summary of the invention

[0003] The present invention provides a production line load balancing method, device, equipment and medium to solve the problem that the existing load balancing method has limitations when dealing with high-dimensional and multi-constrained load balancing problems in processing production line load balancing problems, and is difficult to cope with dynamic and complex production environments.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is to provide a production line load balancing method, including the following steps: the first step is to obtain a task list, and according to the task list, respectively perform task initialization allocation for multiple production equipment on the production line to generate multiple initial allocation schemes; the second step is to perform fitness evaluation on multiple initial allocation schemes, and select the initial allocation scheme with the best fitness as the initial optimization allocation scheme; the third step is to search and update multiple initial allocation schemes according to the initial optimization allocation scheme, and generate multiple corresponding search optimization allocation schemes; and select the search optimization allocation scheme with the best fitness, compare the fitness with the initial optimization allocation scheme, and obtain a search determination scheme; the fourth step is to perform advanced update on multiple search optimization allocation schemes according to the search determination scheme, and generate multiple corresponding advanced optimization allocation schemes; and select the advanced optimization allocation scheme with the best fitness, compare the fitness with the search determination scheme, and obtain an advanced determination scheme; the fifth step is to iteratively execute the third and fourth steps according to the advanced determination scheme until the target number of iterations is reached, and generate a target determination scheme.

[0005] In some embodiments, according to the task list, task initialization allocation is performed on multiple production equipment on the production line, specifically including: randomly allocating first-category components to multiple first-category production equipment; randomly allocating second-category components to multiple second-category production equipment; randomly allocating third-category components to multiple first-category production equipment or second-category production equipment.

[0006] In some embodiments, based on the initial optimized allocation plan, multiple initial allocation plans are searched and updated, specifically including: setting a search threshold and randomly generating a search generation; if the search generation is greater than the search threshold, a global search update is performed on the multiple initial allocation plans; if the search generation is less than the search threshold, a local search update is performed on the multiple initial allocation plans.

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

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

[0009] In some embodiments, the multiple search optimization allocation schemes are advanced updated based on the search determination scheme, specifically including: adjusting the moving speed of the elements in each of the search optimization allocation schemes based on the initial allocation scheme, the search determination scheme and the advanced parameters; adjusting the position of the elements in each of the search optimization allocation schemes based on the moving speed, and updating the multiple search optimization allocation schemes.

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

[0011] The present invention also provides a production line load balancing device, including: an acquisition unit, used to acquire a task list; an initialization unit, used to perform task initialization allocation for multiple production equipment on the production line according to the task list, and generate multiple initial allocation schemes; an initial evaluation unit, 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; a search unit, used to search and update multiple initial allocation schemes according to the initial optimized allocation scheme, and generate multiple corresponding search optimized allocation schemes; a search evaluation unit, used to select the search optimized allocation scheme with the best fitness, compare the fitness with the initial optimized allocation scheme, and obtain a search determined scheme; an advanced unit, used to perform advanced update on multiple search optimized allocation schemes according to the search determined scheme, and generate multiple corresponding advanced optimized allocation schemes; an advanced evaluation unit, used to select the advanced optimized allocation scheme with the best fitness, compare the fitness with the search determined scheme, and obtain an advanced determined scheme.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned method when executing the computer program.

[0013] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described above are implemented.

[0014] The beneficial effects of the present invention are as follows: the present invention discloses a method, device, equipment and medium for load balancing of a production line. The method comprises the following steps: the first step is to obtain a task list, and according to the task list, respectively perform task initialization allocation for multiple production equipment on the production line to generate multiple initial allocation schemes; the second step is to perform fitness evaluation on multiple initial allocation schemes, and select an initial allocation scheme with the best fitness as the initial optimization allocation scheme; the third step is to search and update multiple initial allocation schemes according to the initial optimization allocation scheme, and generate multiple corresponding search optimization allocation schemes; and select a search optimization allocation scheme with the best fitness, and compare the fitness with the initial optimization allocation scheme to obtain a search determination scheme; the fourth step is to perform advanced updates on multiple search optimization allocation schemes according to the search determination scheme, and generate multiple corresponding advanced optimization allocation schemes; and select an advanced optimization allocation scheme with the best fitness, and compare the fitness with the search determination scheme to obtain an advanced determination scheme; the fifth step is to iteratively execute the third step and the fourth step according to the advanced determination scheme until the target number of iterations is reached, and generate a target determination scheme. This application performs task initialization allocation for multiple production equipment according to the task list, generates multiple initial allocation plans; and performs multiple global, local and advanced updates on the initial allocation plan, optimizes the initial allocation plan, and screens out the final target determination plan. Through the two-way information exchange mechanism, this application can avoid falling into the local optimum, while accelerating the optimization process and achieving an effective balance between the global and local. This method can dynamically adjust the task allocation according to the actual load of the production line to ensure the load balance of each production equipment. It shows significant results in improving production efficiency and balancing the workload of each production equipment. At the same time, it has good scalability and is suitable for PCB production lines of different sizes. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of a production line load balancing method of the present application;

[0016] Figure 2 It is a load balancing efficiency diagram corresponding to the first production line in a production line load balancing method of the present application;

[0017] Figure 3 It is a load balancing efficiency diagram corresponding to the second production line in a production line load balancing method of the present application;

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

[0023] Fig. 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 the present application;

[0024] Fig.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 the present application;

[0025] Fig.11 It is a schematic diagram of a convergence curve corresponding to the first production line in a production line load balancing method of the present application;

[0026] Fig.12 It is a schematic diagram of a convergence curve corresponding to the second production line in a production line load balancing method of the present application;

[0027] Fig.13 It is a schematic diagram of a convergence curve corresponding to the third production line in a production line load balancing method of the present application;

[0028] Fig.14 This is a schematic diagram of the composition of a production line load balancing device of the present application;

[0029] Fig.15 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present application;

[0030] Fig.16 It is a schematic block diagram of an embodiment of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0031] In order to facilitate the understanding of the present invention, the present invention is described in more detail below in conjunction with the accompanying drawings and specific embodiments. Preferred embodiments of the present invention are provided in the accompanying drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described in this specification. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present invention more thorough and comprehensive.

[0032] It should be noted that, unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used in this specification includes any and all combinations of one or more related listed items.

[0033] It should be noted that there are two types of components in PCB (Printed Circuit Board), namely pinhole components and SMT (Surface Mount Technology) components. This application mainly studies SMT components. The SMT assembly line involves a variety of complex assembly processes, including solder paste printing, component mounting, reflow soldering, manual quality inspection and AOI (Automated Optical Inspection) quality inspection. The balance of the SMT assembly line is achieved by allocating components to each SMT assembly station so that the workload between them is balanced. Among them, the SMT assembly station is usually equipped with automated production lines and intelligent equipment, such as high-speed placement machines, automatic optical detectors, reflow ovens, and programming testers and other key equipment. The load balancing of the assembly line is the load balancing between placement machines, that is, the time for placing components on each placement machine is as consistent as possible.

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

[0035] S1: Obtain a task list, and according to the task list, perform initial task allocation for multiple production equipment on the production line to generate multiple initial allocation plans.

[0036] S2: Evaluate the fitness of multiple initial allocation plans and select the initial allocation plan with the best fitness as the initial optimized allocation plan.

[0037] S3: According to the initial optimization allocation plan, multiple initial allocation plans are searched and updated to generate multiple corresponding search optimization allocation plans; and a search optimization allocation plan with the best fitness is selected from them, and the fitness is compared with the initial optimization allocation plan to obtain a search determination plan.

[0038] S4: According to the search determination plan, multiple search optimization allocation plans are advanced updated to generate multiple corresponding advanced optimization allocation plans; and an advanced optimization allocation plan with the best fitness is selected from them, and the fitness is compared with the search determination plan to obtain the advanced determination plan.

[0039] S5: According to the advanced determination plan, iteratively execute S3 and S4 until the target number of iterations is reached, and a target determination plan is generated.

[0040] This application performs task initialization allocation for multiple production equipment according to the task list, generates multiple initial allocation plans; and performs multiple global, local and advanced updates on the initial allocation plan, optimizes the initial allocation plan, and screens out the final target determination plan. Through the two-way information exchange mechanism, this application can avoid falling into the local optimum, while accelerating the optimization process and achieving an effective balance between the global and local. This method can dynamically adjust the task allocation according to the actual load of the production line to ensure the load balance of each production equipment. It shows significant results in improving production efficiency and balancing the workload of each production equipment. At the same time, it has good scalability and is suitable for PCB production lines of different sizes.

[0041] Combine the following Figures 1 to 16 , the present application is further described in detail with specific embodiments.

[0042] Figure 1 The following is a flow chart of a production line load balancing method provided by an embodiment of the present application, which is described in detail as follows:

[0043] S1: Obtain a task list, and according to the task list, perform initial task allocation for multiple production equipment on the production line to generate multiple initial allocation plans.

[0044] The task list includes multiple different types of workpieces, the number of each type of workpiece, the processing time of each type of workpiece, and the constraints of each type of workpiece. Workpieces include first-class components, second-class components, and third-class components. First-class components, second-class components, and third-class components all include multiple different components. The production equipment on a production line includes first-class production equipment and second-class production equipment. The constraints mean that first-class components can only be processed by first-class production equipment; second-class components can only be processed by second-class production equipment; and third-class components are unrestricted and can be processed by either first-class production equipment or second-class production equipment.

[0045] Therefore, in order to keep the load of the production line balanced, it is necessary to allocate the first and second type components to the corresponding production equipment according to the constraints, and further adjust the position of the third type components in the production line.

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

[0047] In this embodiment, the first type of production equipment refers to a high-speed placement machine, and the second type of production equipment refers to a multifunctional placement machine. Assuming that there are a total of n types of components in this application, the first k types are all first-type components, the k+1th to k+pth types are second-type components, and the k+p+1th to nth types are third-type components.

[0048] Specifically, the first-category components are randomly assigned to a plurality of first-category production devices, which can be expressed by the following formula:

[0049] Pos k,i =randint(1,num_MSH)

[0050] Among them, MSH represents the first type of production equipment, num_MSH represents the number of the first type of production equipment, randint represents the random function, k represents one of the initial allocation schemes, i represents one of the components, Pos represents the matrix, Pos k,i Represents the element in the k-th row and i-th column of the matrix Pos, that is, the position of the i-th element in the k-th initial allocation scheme.

[0051] Furthermore, the second-type components are randomly distributed to multiple second-type production devices, which can be expressed by the following formula:

[0052] Pos k,i =randint(num_MSH,num_MSH+num_MPA)

[0053] Among them, MSH represents the first type of production equipment, num_MSH represents the number of the first type of production equipment, randint represents the random function, MPA represents the second type of production equipment, num_MPA represents the number of the second type of production equipment, k represents one of the initial allocation schemes, i represents one of the components, Pos represents the matrix, Pos k,i Represents the element in the k-th row and i-th column of the matrix Pos, that is, the position of the i-th element in the k-th initial allocation scheme.

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

[0055] Pos k,i =randint(lb i ,ub i )

[0056] Among them, lb i represents the k+p+1th type of component (i.e., the third type of component), ub irepresents the number of types of workpieces, randint represents a random function, k represents one of the initial allocation schemes, i represents one of the components, Pos represents a matrix, Pos k,i Represents the element in the k-th row and i-th column of the matrix Pos, that is, the position of the i-th element in the k-th initial allocation scheme.

[0057] After the allocation is completed, multiple initial allocation schemes are generated, namely, the matrix Pos(Search_Agents×dimension), where Search_Agents represents the number of initial allocation schemes and dimension represents the number of types of workpieces.

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

[0059] S2: Evaluate the fitness of multiple initial allocation plans and select the initial allocation plan with the best fitness as the initial optimized allocation plan.

[0060] Specifically, in this embodiment, the following function is used to evaluate the fitness:

[0061] f=min(α·f1+β·f2);

[0062]

[0063] Among them, f represents the final objective function, α represents the balance parameter of f1, β represents the balance parameter of f2, f1 represents the order completion time objective function, f2 represents the constraint term, N m Represents the number of production equipment, represents the completion time of one of the production equipment m, N represents the number of PCB boards, T represents the cycle time, represents the completion time of the next production equipment m+1, ξ represents the upper limit of the balance constraint, avg_T represents the average completion time of all production equipment, T min Represents the time required for the production equipment with the shortest completion time, j represents the jth component, G i Represents a collection of various components allocated to a production facility, G i .s stands for G i scale.

[0064] The best fitness means that the value of the final objective function f is the smallest. The initial allocation plan with the smallest value of the final objective function is used as the initial optimization allocation plan.

[0065] S3: According to the initial optimization allocation plan, multiple initial allocation plans are searched and updated to generate multiple corresponding search optimization allocation plans; and a search optimization allocation plan with the best fitness is selected from them, and the fitness is compared with the initial optimization allocation plan to obtain a search determination plan.

[0066] Specifically, firstly, a search threshold GR_rho is set, and a search algebra is randomly generated. Specifically, the value range of the search threshold is (0, 1), and the present application sets the search threshold to 0.5.

[0067] Furthermore, if the search number is greater than the search threshold, such as a randomly generated search number of 0.7, then a global search update is performed on multiple initial allocation schemes. If the search number is less than the search threshold, such as a randomly generated search number of 0.3, then multiple initial allocation schemes are globally searched and updated.

[0068]

[0069] Perform a local search update.

[0070] Specifically, the global search update includes: performing a global search on multiple initial allocation schemes; adjusting the position of the components in each initial allocation scheme according to the initial optimized allocation scheme and the global search parameters, and updating the multiple initial allocation schemes. The global search refers to a large-scale search for the positions of the components in multiple initial allocation schemes. The above process can be expressed by the following formula:

[0071]

[0072] in, represents the position of the jth component in the initial allocation scheme at the tth iteration, GR_alpha represents the global search parameter, and Alpha_pos j represents the position of the jth component in the initial optimal allocation scheme, GR_r represents the global scaling factor, Represents the position of the jth element in the search optimization allocation scheme at the t+1th iteration, and t represents the current iteration number.

[0073] Furthermore, the local search update includes: performing local search on multiple initial allocation schemes; adjusting the position of the components in each initial allocation scheme according to the initial optimized allocation scheme and the local search parameters, and updating the multiple initial allocation schemes. The local search refers to searching the positions of the components in multiple initial allocation schemes in a small range. The above process can be expressed by the following formula:

[0074]

[0075] in, represents the position of the jth component in the initial allocation scheme at the tth iteration, GR_beta represents the local search parameter, and Alpha_pos j represents the position of the jth component in the initial optimal allocation scheme, GR_mu represents the local scaling factor, represents the position of the jth component in the search optimization allocation scheme at the t+1th iteration, t represents the current iteration number, Represents the position of the jth element in the pth randomly selected initial allocation.

[0076] It should be noted that, in this embodiment, only the position of the third type of components is adjusted, and the positions of the first type of components and the second type of components remain unchanged.

[0077] Furthermore, after performing global search updates or local search updates on multiple initial allocation plans, multiple corresponding search optimization allocation plans are generated. For multiple search optimization allocation plans, the final objective function in S2 is used to evaluate the fitness, and a search optimization allocation plan with the best fitness is selected from them and compared with the initial optimization allocation plan for fitness. If the fitness value of the selected search optimization allocation plan is small, the selected search optimization allocation plan is used as the search determination plan; if the fitness value of the initial optimization allocation plan is small, the initial optimization allocation plan is used as the search determination plan.

[0078] S4: According to the search determination plan, multiple search optimization allocation plans are advanced updated to generate multiple corresponding advanced optimization allocation plans; and an advanced optimization allocation plan with the best fitness is selected from them, and the fitness is compared with the search determination plan to obtain the advanced determination plan.

[0079] Specifically, firstly, information on the positions of components in a plurality of initial allocation schemes and search determination schemes is initialized.

[0080] Furthermore, according to the initial allocation scheme, the search determination scheme and the advanced parameters, the moving speed of the components in each search optimization allocation scheme is adjusted. Among them, the advanced parameters include inertia weight, individual learning factor and social learning factor. The above process can be expressed by the following formula:

[0081] v i,j (t+1)=w(t)·v i,j (t)+c1(t)·r 1,j ·(p i,j -x i,j (t))+c2(t)·r 2,j ·(gj -x i,j (t))

[0082] Among them, v i,j (t+1) represents the moving speed of the jth component in the i-th advanced optimization allocation scheme at the t+1th iteration, v i,j (t) represents the moving speed of the jth element in the i-th search optimization allocation scheme at the t-th iteration, w(t) represents the inertia weight, c1(t) represents the individual learning factor, c2(t) represents the social learning factor, r 1,j and r 2,j represents a random number between [0, 1], p i,j represents the historical best position of the jth component, x i,j (t) represents the position of the jth component in the i-th search optimization allocation scheme at the t-th iteration, g j Represents the position of the jth component in the search and determination solution, and t represents the current iteration number.

[0083] It should be noted that the inertia weight w(t), individual learning factor c1(t) and social learning factor c2(t) will change continuously according to the number of iterations. The inertia weight will decrease linearly with the increase of the number of iterations, so that there is a larger search space in the early stage. The inertia weight will gradually decrease in the later stage, which will help to make more detailed adjustments to the scheme, thereby accelerating the convergence to the better scheme. In the early stage, the larger individual learning factor makes the scheme more inclined to move towards the best allocation scheme found in the past, so as to make full use of its own experience and enhance the local search ability of the scheme. As the number of iterations increases, the increase of the individual learning factor makes the scheme more inclined to explore the better scheme that has been found, thereby improving the quality of the scheme. In the early stage, the larger social learning factor value prompts the scheme to pay more attention to the global best position and guide the scheme to approach the global best scheme, which can improve the global search ability and avoid falling into the local optimum. As the number of iterations increases, appropriately reducing the social learning factor can reduce the dependence on the global best scheme, enable the scheme to conduct a deeper exploration in the local area, and improve the utilization efficiency of the current better scheme. Among them, the inertia weight, individual learning factor and social learning factor can be expressed by the following formula:

[0084]

[0085] Among them, w(t) represents the inertia weight, c1(t) represents the individual learning factor, c2(t) represents the social learning factor, and w max Represents the maximum value of the inertia weight, w min represents the minimum value of inertia weight, c 1,max represents the maximum value of the individual learning factor, c 1,min represents the minimum value of the individual learning factor, c2,max represents the maximum value of the social learning factor, c 2,min Represents the minimum value of the social learning factor, Max_iterations represents the maximum number of iterations, and t represents the current number of iterations.

[0086] Furthermore, according to the moving speed, the position of the components in each search optimization allocation scheme is adjusted, and multiple search optimization allocation schemes are updated. The above process can be expressed by the following formula:

[0087] x i,j (t+1)=x i,j (t)+v i,j (t+1)

[0088] Among them, v i,j (t+1) represents the moving speed of the jth component in the i-th advanced optimization allocation scheme at the t+1th iteration, x i,j (t+1) represents the position of the jth component in the ith advanced optimization allocation scheme at the t+1th iteration, x i,j (t) represents the position of the jth component in the i-th search optimization allocation scheme at the t-th iteration, and t represents the current iteration number.

[0089] It should be noted that, in this embodiment, only the position and moving speed of the third type of components are adjusted, and the position and moving speed of the first type of components and the second type of components remain unchanged.

[0090] 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 to evaluate fitness, and an advanced optimization allocation scheme with the best fitness is selected to compare fitness with the search determination scheme. If the fitness value of the selected advanced optimization allocation scheme is small, the selected advanced optimization allocation scheme is used as the advanced determination scheme; if the fitness value of the search determination scheme is small, the search determination scheme is used as the advanced determination scheme.

[0091] S5: According to the advanced determination plan, iteratively execute S3 and S4 until the target number of iterations is reached, and a target determination plan is generated.

[0092] According to the obtained advanced determination plan, S3 and S4 are further executed to search and update multiple advanced optimization allocation plans and perform advanced updates, and compare the results for fitness, iterate multiple times until the target number of iterations is reached, and generate a final target determination plan.

[0093] In this embodiment, the target iteration number is set to 100 times. Therefore, after iterating and executing steps S3 and S4 100 times in sequence, a target determination solution can be obtained.

[0094] In summary, reference Figures 2 to 13 As shown, in order to verify the efficiency and performance of the production line load balancing method (i.e., the iGCRA algorithm) of the present application, it was further compared with the existing load balancing optimization methods (ABC algorithm, PSO algorithm, GABC algorithm, and GCRA algorithm) through experiments, and the comparison results are detailed as follows.

[0095] Specifically, three different production lines are first set up, and the number of production equipment (i.e., placement machines) in each production line is different, as shown in Table 1 below:

[0096] Table 1

[0097]

[0098] For each production line, five task lists (i.e. BOM lists) were randomly selected for testing. Each task list was tested 20 times to ensure the accuracy of the results, and the average value of the results was calculated.

[0099] In order to accurately evaluate the differences between the five methods, four indicators are used for judgment. These four indicators are load balancing efficiency (E b ), cycle time (T), order completion time (O_Total) and convergence curve.

[0100] Specifically, refer to Figures 2 to 4 As shown in the figure, the load balancing efficiency (E) of the five methods on three different production lines is b ) is a schematic diagram of the load balancing efficiency (E b ) is expressed as:

[0101]

[0102] Among them, T t Represents the total processing time of all production equipment on a production line, T represents the cycle time, N m Represents the number of production equipment on a production line.

[0103] from Figures 2 to 4 It can be seen from the figure that the load balancing efficiency (E b ,Too Figures 2 to 4The blue part in the middle achieved better results in almost all production line experiments, and the load balancing efficiency values ​​were close to 1, and exceeded other comparison methods (ABC algorithm, PSO algorithm, GABC algorithm and GCRA algorithm). This not only reflects the adaptability and stability of the method in the configuration of different production lines and task lists, but also further proves its excellent optimization ability in complex production environments. In contrast, other methods failed to achieve the same optimization effect in multiple production line experiments, showing their limitations in dealing with such problems.

[0104] For further reference, Figures 5 to 7 As shown, it is a schematic diagram of the cycle time (T) corresponding to the five methods on three different production lines. The cycle time (T) is also the processing time required by the production equipment with the longest processing time in a production line; in this embodiment, the formula for the cycle time (T) is expressed as:

[0105]

[0106] in, Represents the processing time required by the production equipment m with the longest processing time in a production line.

[0107] from Figures 5 to 7 It can be seen that the production line load balancing method of the present application achieves the lowest cycle time in all production line experiments ( Figures 5 to 7 The blue part in the middle shows excellent performance compared with other comparison methods. The method of this application significantly reduces the cycle time required for production through effective optimization strategies, thereby reducing the order completion time, highlighting its efficiency in handling complex production tasks. In contrast, other methods failed to achieve the same level of optimization effect in most cases, which clearly shows the advantage of the method of this application in optimizing load balancing.

[0108] For further reference, Figures 8 to 10 As shown, it is a schematic diagram of the order completion time (O_Total) corresponding to the five methods on three different production lines. In this embodiment, the formula of the order completion time (O_Total) is expressed as:

[0109]

[0110] Where N represents the number of PCB boards required in the task list, T represents the cycle time, and N m Represents the number of production equipment on a production line. Represents the processing time required by the production equipment m with the longest processing time in a production line.

[0111] from Figures 8 to 10It can be seen that the production line load balancing method of the present application achieves the shortest order completion time in all production line experiments ( Figures 8 to 10 In contrast, the performance of other methods is relatively unstable, and the order completion time in some production line experiments is significantly longer. This shows that the application method has strong stability in optimizing the order completion time, and can effectively improve the operating efficiency of the production line and reduce the total time of order processing. Whether facing different production lines or different task lists, the application method is significantly better than other comparison methods in shortening the order completion time.

[0112] For further reference, Figures 11 to 13 As shown, it is a schematic diagram of the convergence curves corresponding to the five methods on three different production lines. The convergence curve is drawn according to the value of the fitness function; in this embodiment, the drawing parameters of the convergence curve are shown in Table 2 below:

[0113] Table 2

[0114]

[0115]

[0116] Among them, α and β represent two equilibrium parameters, ξ represents the upper limit of the equilibrium constraint, and w max Represents the maximum value of the inertia weight, w min represents the minimum value of inertia weight, c 1,max represents the maximum value of the individual learning factor, c 1,min represents the minimum value of the individual learning factor, c 2,max represents the maximum value of the social learning factor, c 2,min Represents the minimum value of the social learning factor.

[0117] from Figures 11 to 13 It can be seen that the production line load balancing method of the present application shows significant advantages in the optimization process. Specifically, in the first 20 iterations, the fitness value of the method of the present application ( Figures 11 to 13The medium and dark blue curves) drop rapidly, showing an extremely fast convergence speed; within 50 iterations, the method of the present application has been close to the optimal solution. In contrast, other methods converge more slowly within the same number of iterations, and the final fitness values ​​are also higher. The method of the present application not only converges rapidly in the initial iteration stage, but also still shows the ability to continuously optimize in the later iterations, further fine-tuning the accuracy of the fitness value. This is in sharp contrast to other methods: after other methods reach a higher fitness value in the early stage, the convergence speed slows down significantly, and even stagnates. This shows that the method of the present application has stronger global search and local development capabilities throughout the optimization process, can more effectively find excellent solutions, and maintain a high optimization efficiency.

[0118] Corresponding to the production line load balancing method in the above embodiment, Fig.14 A schematic diagram of the composition of a production line load balancing device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0119] refer to Fig.14 , the load balancing device of the production line includes:

[0120] The acquisition unit 101 is used to acquire a task list.

[0121] The initialization unit 102 is used to perform initialization task allocation for multiple production equipment on the production line according to the task list and generate multiple initial allocation plans.

[0122] The initial evaluation unit 103 is used to evaluate the fitness of multiple initial allocation schemes and select an initial allocation scheme with the best fitness as the initial optimized allocation scheme.

[0123] The search unit 104 is used to search and update multiple initial allocation schemes according to the initial optimized allocation scheme, and generate corresponding multiple search optimized allocation schemes.

[0124] The search evaluation unit 105 is used to select a search optimization allocation scheme with the best fitness, compare the fitness with the initial optimization allocation scheme, and obtain a search determination scheme.

[0125] The advanced unit 106 is used to perform advanced updates on multiple search optimization allocation schemes according to the search determination scheme, and generate corresponding multiple advanced optimization allocation schemes.

[0126] The advanced evaluation unit 107 is used to select an advanced optimization allocation scheme with the best fitness, compare the fitness with the search determination scheme, and obtain the advanced determination scheme.

[0127] It should be noted that since the above-mentioned production line load balancing device is based on the same concept as the embodiment of the method of the present application, its specific functions, the process of each module realizing its respective functions and the technical effects brought about can be specifically referred to the description of the embodiment shown in the above-mentioned production line load balancing method, and will not be repeated here.

[0128] Based on the same inventive concept, the present application also provides an electronic device, which includes a processor, a memory and a communication circuit, and 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.

[0129] See also Fig.15 The electronic device described in the embodiment of the present application may specifically include a processor 210 and a memory 220. The memory 220 is coupled to the processor 210.

[0130] The processor 210 is used to control the operation of the electronic device. The processor 210 may also be referred to as a CPU (Central Processing Unit). The processor 210 may be an integrated circuit chip having the ability to process signals. The processor 210 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. A general-purpose processor may be a microprocessor or the processor 210 may also be any conventional processor, etc.

[0131] The memory 220 is used to store computer programs, and may be a RAM, a ROM, or other types of storage terminals. Specifically, the memory 220 may include one or more computer-readable storage media, which may be non-transitory or transient. The memory 220 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage terminals, flash memory storage terminals. In some embodiments, the non-transitory computer-readable storage medium in the memory 220 is used to store at least one program code.

[0132] The processor 210 is used to execute the computer program stored in the memory 220 to implement the methods described in the various method embodiments of the present application.

[0133] In some embodiments, the electronic device may further include: a peripheral terminal interface 230 and at least one peripheral terminal. The processor 210, the memory 220 and the peripheral terminal interface 230 may be connected via a bus or a signal line. Each peripheral terminal may be connected to the peripheral terminal interface 230 via a bus, a signal line or a 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.

[0134] The peripheral terminal interface 230 may be used to connect at least one peripheral terminal related to I / O (Input / output) to the processor 210 and the memory 220. In some embodiments, the processor 210, the memory 220, and the peripheral terminal interface 230 are integrated on the same chip or circuit board; in some other implementations, any one or two of the processor 210, the memory 220, and the peripheral terminal interface 230 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.

[0135] The radio frequency circuit 240 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 240 communicates with the communication network and other IoT devices through electromagnetic signals, and the radio frequency circuit 240 is the communication circuit of the electronic device. The radio frequency circuit 240 converts the electrical signal into an electromagnetic signal for transmission, or converts the received electromagnetic signal into an electrical signal. Optionally, the radio frequency 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 identity module card, and the like. The radio frequency circuit 240 can communicate with other terminals through at least one wireless communication protocol. The wireless communication protocol includes, but is not limited to: the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 240 may also include circuits related to NFC (Near Field Communication), which is not limited in this application.

[0136] The display screen 250 is used to display the UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 250 is a touch display screen, the display screen 250 also has the ability to collect touch signals on the surface or above the surface of the display screen 250. The touch signal can be input to the processor 210 as a control signal for processing. At this time, the display screen 250 can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the display screen 250 can be one, set on the front panel of the electronic device; in other embodiments, the display screen 250 can be at least two, respectively set on different surfaces of the electronic device or in a folding design; in other embodiments, the display screen 250 can be a flexible display screen, set on a curved surface or a folding surface of the electronic device. Even, the display screen 250 can also be set to a non-rectangular irregular shape, that is, a special-shaped screen. The display screen 250 can be made of materials such as LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode, organic light-emitting diode).

[0137] 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, and convert the sound waves into electrical signals and input them into the processor 210 for processing, or input them into the radio frequency circuit 240 to achieve voice communication. For the purpose of stereo acquisition or noise reduction, there may be multiple microphones, which are respectively arranged in different parts of the electronic device. The microphone may also be an array microphone or an omnidirectional acquisition microphone. The speaker is used to convert the electrical signal from the processor 210 or the radio frequency circuit 240 into sound waves. The speaker may be a traditional film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert the electrical signal into sound waves audible to humans, but also convert the electrical signal into sound waves inaudible to humans for purposes such as ranging. In some embodiments, the audio circuit 260 may also include a headphone jack.

[0138] The power supply 270 is used to power various components in the electronic device. The power supply 270 can be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the 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 through a wired line, and a wireless rechargeable battery is a battery that is charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0139] For a detailed description of the functions and execution processes of each functional module or component in the electronic device embodiment of the present application, reference can be made to the description in the above-mentioned method embodiments of the present application, which will not be repeated here.

[0140] In the several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the various embodiments of the electronic devices described above are only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0141] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0142] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0143] Based on the same inventive concept, the present application also provides a computer-readable storage medium storing a computer program, which can be executed by a processor to implement the above-mentioned production line load balancing method.

[0144] See also Fig.16 , if the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium 300. Based on this understanding, the technical solution of the present application is essentially 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, and the computer software product is stored in a storage medium, including several instructions / computer programs to enable an IoT device (which can be a personal computer, server, or network terminal, etc.) or a processor (processor) to perform all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical disks, and electronic terminals such as computers, mobile phones, laptops, tablet computers, cameras, etc. having the above-mentioned storage media.

[0145] The description of the execution process of the program data in the computer-readable storage medium can refer to the description in the above-mentioned method embodiments of the present application, and will not be repeated here.

[0146] It can be seen that the present invention discloses a method, device, equipment and medium for load balancing of a production line. The method includes the following steps: the first step is to obtain a task list, and according to the task list, respectively perform task initialization allocation for multiple production equipment on the production line to generate multiple initial allocation schemes; the second step is to evaluate the fitness of multiple initial allocation schemes, and select an initial allocation scheme with the best fitness as the initial optimization allocation scheme; the third step is to search and update multiple initial allocation schemes according to the initial optimization allocation scheme, and generate multiple corresponding search optimization allocation schemes; and select a search optimization allocation scheme with the best fitness, and compare the fitness with the initial optimization allocation scheme to obtain a search determination scheme; the fourth step is to perform advanced updates on multiple search optimization allocation schemes according to the search determination scheme, and generate multiple corresponding advanced optimization allocation schemes; and select an advanced optimization allocation scheme with the best fitness, and compare the fitness with the search determination scheme to obtain an advanced determination scheme; the fifth step is to iteratively execute the third and fourth steps according to the advanced determination scheme until the target number of iterations is reached, and generate a target determination scheme. This application performs task initialization allocation for multiple production equipment according to the task list, generates multiple initial allocation plans; and performs multiple global, local and advanced updates on the initial allocation plan, optimizes the initial allocation plan, and screens out the final target determination plan. Through the two-way information exchange mechanism, this application can avoid falling into the local optimum, while accelerating the optimization process and achieving an effective balance between the global and local. This method can dynamically adjust the task allocation according to the actual load of the production line to ensure the load balance of each production equipment. It shows significant results in improving production efficiency and balancing the workload of each production equipment. At the same time, it has good scalability and is suitable for PCB production lines of different sizes.

[0147] The above are only embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structural transformations made using the contents of the present invention's specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A production line load balancing method, characterized in that: Includes steps: The first step is to obtain a task list, and according to the task list, respectively perform task initialization allocation on multiple production equipment on the production line to generate multiple initial allocation plans; The second step is to evaluate the fitness of the multiple initial allocation plans, and select the initial allocation plan with the best fitness as the initial optimized allocation plan; The third step is to search and update multiple initial allocation plans according to the initial optimization allocation plan to generate multiple corresponding search optimization allocation plans; and selecting the search optimization allocation scheme with the best fitness, and comparing the fitness with the initial optimization allocation scheme to obtain the search determination scheme; The fourth step is to perform advanced updates on the plurality of search optimization allocation schemes according to the search determination scheme, and generate a plurality of corresponding advanced optimization allocation schemes; and selecting the advanced optimization allocation scheme with the best fitness, and comparing the fitness with the search determination scheme to obtain the advanced determination scheme; The fifth step is to iteratively execute the third and fourth steps according to the advanced determination plan until the target number of iterations is reached to generate a target determination plan.

2. The production line load balancing method according to claim 1, characterized in that: The initialization allocation of tasks to multiple production equipment on the production line according to the task list specifically includes: randomly allocating the first-category components to a plurality of first-category production devices; randomly allocating the second-category components to a plurality of second-category production devices; The third category components are randomly distributed to a plurality of the first category production equipment or the second category production equipment.

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

4. The production line load balancing method according to claim 3, characterized in that: The global search update includes: Performing a global search on a plurality of the initial allocation schemes; According to the initial optimized allocation scheme and the global search parameter, the position of the element in each of the initial allocation schemes is adjusted, and the plurality of initial allocation schemes are updated.

5. The production line load balancing method according to claim 3, characterized in that: The local search update includes: Performing a local search on a plurality of the initial allocation schemes; According to the initial optimized allocation scheme and the local search parameters, the position of the element in each of the initial allocation schemes is adjusted, and the multiple initial allocation schemes are updated.

6. The production line load balancing method according to claim 1, characterized in that: The step of performing advanced updating on the plurality of search optimization allocation schemes according to the search determination scheme specifically includes: According to the initial allocation scheme, the search determination scheme and the advanced parameters, adjusting the moving speed of the elements in each of the search optimization allocation schemes; According to the moving speed, the position of the element in each of the search optimization allocation schemes is adjusted, and multiple search optimization allocation schemes are updated.

7. The production line load balancing method according to claim 1, characterized in that: The task list includes a plurality of different types of workpieces, the quantity of each type of the workpieces, the processing time of each type of the workpieces, and the constraints of each type of the workpieces.

8. A production line load balancing device, characterized in that: include: An acquisition unit, used to acquire a task list; An initialization unit, configured to perform initialization assignment of tasks to a plurality of production equipment on the production line according to the task list, and generate a plurality of initial assignment plans; An initial evaluation unit, used 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; A search unit, configured to search and update a plurality of the initial allocation schemes according to the initial optimization allocation scheme, and generate a plurality of corresponding search optimization allocation schemes; A search evaluation unit, configured to select the search optimization allocation scheme with the best fitness, compare the fitness with the initial optimization allocation scheme, and obtain a search determination scheme; An advanced unit, used for performing advanced updates on the plurality of search optimization allocation schemes according to the search determination scheme, and generating a plurality of corresponding advanced optimization allocation schemes; The advanced evaluation unit is used to select the advanced optimization allocation scheme with the best fitness, compare the fitness with the search determination scheme, and obtain the advanced determination scheme.

9. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images