Cigarette production capacity matching method and system based on improved NSGA-Ⅱ and storage medium
By improving the NSGA-II algorithm to construct a multi-objective optimization model and combining it with an adaptive crossover and mutation mechanism, the problems of mismatch between production capacity and demand, fluctuations in surplus rate, and excessive overtime hours in cigarette equipment production capacity matching were solved, thereby improving equipment utilization and production efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA TOBACCO ZHEJIANG IND CO LTD
- Filing Date
- 2026-03-17
- Publication Date
- 2026-06-23
Smart Images
Figure CN122264388A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of production planning and operation optimization technology, and specifically to a method for optimizing the capacity matching of cigarette equipment based on an improved NSGA-II algorithm. Background Technology
[0002] In cigarette manufacturing enterprises, equipment capacity matching is a crucial link connecting market demand planning and production execution. Its goal is to achieve the rational allocation and efficient utilization of equipment resources while meeting the demand for various cigarette product specifications. As the cigarette market evolves from a single specification to multiple specifications, small batches, and fluctuating demand, traditional capacity allocation methods relying on experience or single-objective optimization are increasingly revealing their shortcomings. Existing technologies often employ cigarette capacity matching methods with the single objective of meeting demand or minimizing the gap, or perform linear or heuristic optimization under simple constraints. These methods typically suffer from the following problems: First, it is difficult to simultaneously control capacity gaps and balance capacity surplus rates, resulting in significant differences in equipment load between different products; second, when capacity is insufficient, there is an over-reliance on overtime to compensate for demand, leading to excessive overtime hours, increased labor costs, and reduced equipment lifespan; third, under multiple specifications and constraints, traditional optimization algorithms are prone to getting trapped in local optima, resulting in insufficient optimization efficiency and solution stability; fourth, the standard NSGA-II algorithm has limitations in initial population diversity and fixed crossover and mutation parameters, making it difficult to adapt to the complex and dynamic production constraints of the cigarette industry.
[0003] Therefore, there is an urgent need for a capacity matching optimization method that can simultaneously consider multiple objectives such as capacity gaps, surplus rate balance, and overtime hours for various cigarette product specifications, and improve optimization efficiency and stability at the algorithm level, so as to meet the actual needs of cigarette companies for refined and intelligent production management. Summary of the Invention
[0004] The purpose of this invention is to provide a capacity matching optimization method for cigarette equipment based on an improved NSGA-II algorithm, in order to solve the problems of low capacity-demand matching degree, large fluctuation of surplus rate, excessive overtime time, and insufficient optimization efficiency of existing cigarette equipment capacity matching methods under multiple specifications and constraints.
[0005] To achieve the above objectives, embodiments of the present invention provide a cigarette production capacity matching method based on the improved NSGA-II, comprising: Obtain basic data on the matching of cigarette production resources and demand; Calculate the constraint parameters for each product based on the aforementioned basic data; A multi-objective optimization model for matching the production capacity of cigarette equipment is constructed based on the aforementioned constraint parameters; The improved NSGA-II algorithm is used to solve the multi-objective optimization model for matching the production capacity of the cigarette equipment, so as to obtain the optimal production capacity matching scheme.
[0006] Optionally, constructing a multi-objective optimization model for matching cigarette equipment capacity based on the constraint parameters includes: Set upper and lower bound constraints on the production capacity of each product, upper limit constraints on the total production capacity of all products, constraints on the surplus rate of all products, and constraints on non-negativity.
[0007] Optionally, constructing a multi-objective optimization model for matching cigarette equipment capacity based on the constraint parameters includes: The optimization objective of minimizing the total gap is obtained according to formula (1). (1) in, For the first Annual demand for this product specification For the first Annual production capacity of each product specification This represents the total number of product specifications.
[0008] Optionally, constructing a multi-objective optimization model for matching cigarette equipment capacity based on the constraint parameters includes: The optimization objective of minimizing the weighted deviation is obtained according to formulas (2) and (3). (2) (3) in, For the first The capacity surplus rate of each product specification For the first Annual demand for this product specification For the first Annual production capacity of each product specification For the first Production capacity weight for each product specification For the first The lower limit of the ideal surplus rate for a certain product specification. This represents the total number of product specifications.
[0009] Optionally, constructing a multi-objective optimization model for matching cigarette equipment capacity based on the constraint parameters includes: The optimization objective of minimizing total overtime hours is obtained based on formulas (4) and (5). (4) (5) in, For the first Annual demand for this product specification For the first Annual production capacity of each product specification For the first The total average output per shift for all models of this product For the production of the first The total number of equipment types for each product For the first type of product The number of models For the first Product No. The daily output of this type of machine. This refers to the standard daily working hours for a single generating unit. This is an indicator function.
[0010] Optionally, the optimal capacity matching scheme is obtained by solving the multi-objective optimization model for cigarette equipment capacity matching based on the improved NSGA-II algorithm, including: An initial solution is generated based on product demand forecast data; The initial solution is adjusted for constraints on single-product output and total capacity to obtain an adjusted seed solution set; Latin hypercube sampling is used to supplement the diversity solutions. The adjusted seed solution set is merged with the diversity solutions generated by Latin hypercube sampling and deduplication is performed to obtain the initial population. Calculate the objective function value for each individual in the current initial population; The individuals are non-dominatedly ranked according to the objective function value; Calculate the crowding distance for each level of individuals; Based on the non-dominated sorting results and the crowding distance, selection, adaptive crossover, adaptive mutation, and environmental selection operations are performed to generate a new generation of population. Determine whether the preset termination condition is met; If the preset termination condition is not met, return to the step of calculating the objective function value of each individual in the current initial population; If the preset termination conditions are met, the optimal capacity matching scheme is output.
[0011] Optionally, the crossover probability of the adaptive crossover operation is dynamically adjusted according to formula (6): (6) in, For crossover probability, The initial crossover probability, The probability of crossover at the end of the period. For the current generation, The maximum number of iterations, For the first indivual fitness value, The average fitness value of the population. This is for adjusting the coefficient.
[0012] Optionally, the mutation probability of the adaptive mutation operation is dynamically adjusted according to formula (7): (7) in, The mutation probability, The initial mutation probability, This represents the probability of late-stage mutation. For the current generation, The maximum number of iterations, For the first indivual fitness value, The average fitness value of the population. This is for adjusting the coefficient.
[0013] On the other hand, the present invention also provides a cigarette production capacity matching system based on an improved NSGA-II, the system including a processor configured to perform any of the methods described above.
[0014] In another aspect, the present invention also provides a computer-readable storage medium storing instructions that, when executed by a processor, implement any of the methods described above.
[0015] The beneficial effects of this invention are: The embodiments of the present invention construct a multi-objective capacity matching model to achieve comprehensive optimization of capacity gap, surplus rate balance and overtime hours, thereby avoiding the resource allocation imbalance problem caused by single-objective optimization.
[0016] The embodiments of the present invention introduce an initial population generation strategy that combines demand prediction seed solution with Latin hypercube sampling, which significantly improves the quality of initial solutions and population diversity, and enhances the convergence speed and stability of the algorithm.
[0017] The embodiments of the present invention employ an adaptive crossover and mutation mechanism based on evolutionary stages and individual fitness, which effectively reduces the risk of the algorithm getting trapped in local optima and improves the accuracy of multi-objective optimization.
[0018] In actual cigarette production scenarios, the embodiments of the present invention can effectively reduce production capacity gaps and overtime hours, balance equipment load for various product specifications, and improve equipment utilization, resulting in significant economic and management benefits.
[0019] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description
[0020] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings: Figure 1 A flowchart illustrating a cigarette production capacity matching method based on an improved NSGA-II according to an embodiment of the present invention; Figure 2 A flowchart illustrating a method for constructing a multi-objective optimization model for matching the production capacity of cigarette equipment based on constraint parameters, according to an embodiment of the present invention; Figure 3 This is a flowchart illustrating a method for solving a multi-objective optimization model for matching the production capacity of cigarette equipment based on an improved NSGA-II algorithm, according to an embodiment of the present invention. Detailed Implementation
[0021] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.
[0022] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application all comply with relevant laws and regulations. In the embodiments of this application, certain existing industry solutions such as software, components, and models may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solution of this application, and do not imply that the applicant has already used or necessarily used such solutions.
[0023] like Figure 1 The diagram shows a flowchart of a cigarette production capacity matching method based on an improved NSGA-II according to an embodiment of the present invention. Figure 1 In this context, the capacity matching method may include the following steps: In step S10, basic data on matching cigarette production resources with demand is obtained; In step S11, the constraint parameters of each product are calculated based on the basic data; In step S12, a multi-objective optimization model for matching the production capacity of cigarette equipment is constructed based on the constraint parameters; In step S13, the multi-objective optimization model for matching the production capacity of cigarette equipment is solved based on the improved NSGA-II algorithm to obtain the optimal production capacity matching scheme.
[0024] In such Figure 1In the cigarette production capacity matching method based on the improved NSGA-II shown, step S10 is used to collect basic data on matching cigarette production resources and demand. In this embodiment, the basic data on matching cigarette production resources and demand includes the annual demand data of cigarette enterprises for each specification of products, equipment configuration and historical production capacity data.
[0025] Step S11 is used to calculate the constraint parameters of each product based on the basic data. In this example, it includes calculating the upper and lower limits of the production capacity, overtime capacity and capacity surplus rate constraint parameters of each product, and determining the weight coefficients of different product specifications through the analytic hierarchy process (AHP).
[0026] Step S12 is used to construct a multi-objective optimization model for matching the production capacity of cigarette equipment based on constraint parameters. In this embodiment, the specific method for constructing the multi-objective optimization model for matching the production capacity of cigarette equipment in step S12 can be of various forms known to those skilled in the art. In one example of the present invention, step S12 may include, for example... Figure 2 The steps shown are described. Figure 2 In this context, step S12 may include: In step S20, constraints are set; In step S21, the optimization objectives are defined according to the constraints: minimizing the total gap, minimizing the weighted deviation, and minimizing the total overtime.
[0027] In such Figure 2 In the method shown, step S20 is used to set constraints. In this embodiment, the constraints include upper and lower bound constraints on the production capacity of each product, upper limit constraints on the total production capacity of all products, surplus rate constraints on all products, and non-negativity constraints. Specifically, the upper and lower bound constraints on the production capacity of a single product are that the annual production volume of each product specification must meet self-production needs and not exceed the upper limit of production capacity under overtime conditions. In this example, the upper and lower bound constraints on the production capacity of a single product are... ,in, Indicates the first Product specifications, For the first Annual demand for this product specification For the first Annual production capacity of each product specification For the first The annual production capacity of a certain product specification under overtime conditions. In this example, =1,2,3,……8.
[0028] The total capacity ceiling constraint means that both the total overtime capacity limit for all products and the fixed total capacity ceiling requirement must be met simultaneously. In this example, the total capacity ceiling constraint is: ; ; in, This represents the total overtime production capacity for all product specifications over one year. This refers to the annual production capacity limit for all product specifications specified by the company.
[0029] The surplus rate constraint means that non-shortage products must control the upper limit of the surplus rate, and all products must meet the lower limit of the surplus rate requirement. In this example, the surplus rate constraint is: ; ; in, For the first Annual capacity surplus rate after product specification optimization This represents the upper limit of historical overcapacity. This is the lower limit of the prescribed capacity surplus rate.
[0030] The non-negativity constraint requires that the annual production capacity of each product specification cannot be negative. ,in, Representing the Product specifications, =1,2,3,……8.
[0031] Step S21 is used to define the optimization objective based on the constraints, minimizing the total gap. Minimize weighted deviation ( ) and minimizing total overtime hours ( This is used to comprehensively characterize the degree of capacity fulfillment, the balance of capacity surplus rates for various products, and production organization costs. Specifically, in this example, the total deficit is minimized as follows: (1) in: This represents the total shortfall for all product specifications. Indicates only when The value is positive if it is positive, otherwise it is 0. For the first Annual demand for this product specification; For the first Annual production capacity of each product specification; Total number of product specifications ( =8).
[0032] In this example, the weighted deviation is minimized as follows: (2) in: For the first The capacity surplus rate of a certain product specification; For the first Production capacity weight for each product specification; For the first The lower limit of the ideal surplus rate for a certain product specification; Representing the Product specifications, =1,2,3,……8.
[0033] In this example, the total overtime hours are minimized as follows: (4) in: This is a conversion term to convert "ten thousand boxes" into "boxes"; For the first Total average output per machine shift (boxes / shift) for all models of this product. For the production of the first The total number of equipment types for each product; For the first type of product Number of each model (units); For the first Product No. Production per shift (boxes / shift) for this type of machine. The standard daily working hours for a single unit (in this example, it is fixed at 14.67 hours / shift). For indicator functions ( The overtime is calculated only when production capacity is insufficient (1 is used if necessary, 0 otherwise).
[0034] After constructing the multi-objective optimization model for matching the production capacity of cigarette equipment, the improved NSGA-II algorithm is used in step S13 to solve the multi-objective optimization model for matching the production capacity of cigarette equipment to obtain the optimal production capacity matching scheme. In this embodiment, the specific method for solving the multi-objective optimization model for matching the production capacity of cigarette equipment based on the improved NSGA-II algorithm in step S13 can be of various forms known to those skilled in the art. In one example of the present invention, step S13 may include, for example... Figure 3 The steps shown are described. Figure 3 In this context, step S13 may include: In step S30, an initial solution is generated based on the product demand forecast data; In step S31, the initial solution is adjusted for constraints on single-product output and total capacity to obtain the adjusted seed solution set; In step S32, Latin hypercube sampling is used to supplement the diversity solutions. The adjusted seed solution set is merged with the diversity solutions generated by Latin hypercube sampling and deduplication is performed to obtain the initial population. In step S33, the objective function value for each individual in the current initial population is calculated; In step S34, individuals are non-dominated and ranked according to the objective function value; In step S35, the crowding distance for each level of individuals is calculated; In step S36, based on the non-dominated sorting results and crowding distance, selection, adaptive crossover, adaptive mutation, and environmental selection operations are performed to generate a new generation of population. In step S37, it is determined whether the preset termination condition is met; In step S38, if it is determined that the preset termination condition is not met, the process returns to the step of calculating the objective function value of each individual in the current initial population. If the preset termination conditions are met, the optimal capacity matching scheme is output.
[0035] In such Figure 3 In the method shown, initialization settings are required before generating an initial solution that satisfies the preset constraints. Specifically, in this example, the initialization settings include fixing the random seed to ensure the reproducibility of the results, loading the AHP product weight calculation results, basic data such as capacity / equipment / demand, and determining the decision variables (annual capacity). The initial solution is generated by loading product demand forecast data in step S30 after initialization. This initial solution is then used to generate seed solutions that more closely reflect actual demand, based on the product demand forecast data. Step S31 then adjusts the initial solution for single-product output and total capacity constraints to obtain an adjusted seed solution set. Specifically, this adjustment satisfies constraints such as capacity upper and lower bounds and surplus rate, and duplicate solutions are removed to avoid redundancy.
[0036] Step S32 uses Latin hypercube sampling (LHS) to uniformly generate supplementary individuals within the solution space, forming an initial population that balances the relevance of practical needs with the diversity of the solution space, thus ensuring population diversity. Finally, the processed seed solutions are merged with the LHS individuals to form an initial population that balances the relevance of practical needs with the coverage of the solution space, providing a good starting point for subsequent algorithm optimization.
[0037] Step S33 is used to calculate the objective function value of each individual in the current initial population, that is, to perform fitness evaluation and calculate the objective function value of each individual. , , The value is used to impose a penalty on individuals who violate the constraints. In this example, imposing a penalty on an individual who violates the constraints can be achieved by calculating the fitness after the penalty using a penalty function: ,in, The penalty coefficient is... To constrain the total degree of violation.
[0038] Step S34 is used to perform non-dominated sorting of individuals based on the objective function value, perform non-dominated classification of the population, and determine the frontier ranking of each individual (the first frontier is the current set of optimal solutions).
[0039] Step S35 calculates the crowding distance between individuals within the same front. A larger distance indicates a sparser distribution of individuals in the solution space, thus maintaining population diversity. In this example, the crowding distance for an individual k in the population within the p-th front is calculated. for: ,in, and These represent the maximum and minimum total gap values for all individuals in the current frontier, respectively. and These are the maximum and minimum weighted deviations of all individuals in the current frontier, respectively. and These represent the maximum and minimum total overtime hours for all individuals in the current frontier, respectively.
[0040] Step S36 is used to perform selection, adaptive crossover, adaptive mutation, and environmental selection operations based on the non-dominated ranking results and crowding distance to generate a new generation of population. Environmental selection is achieved through non-dominated ranking and crowding distance calculation, and Pareto optimal solution set is obtained iteratively generation by generation. Among them, the selection operation adopts a binary tournament selection strategy, which combines the frontier ranking of individuals and crowding distance to select the parent population.
[0041] The adaptive crossover operation dynamically adjusts the crossover probability based on the number of generations and individual fitness. In the early stages of evolution, a high probability is used to expand the search range, while in the later stages, a low probability is used for local optimization. The distribution index is adjusted based on the evolutionary stage: a small index in the early stages increases diversity, while a large index in the later stages improves accuracy. Simulated binary crossover is then performed to generate offspring. Specific crossover probabilities are detailed below. Adjust dynamically according to the following formula: (6) in The initial crossover probability, This represents the crossover probability at the end of the period; For the current generation, This represents the maximum number of iterations. For individuals fitness value, This represents the average fitness value of the population. To adjust the coefficients. In this example, the initial crossover probability is set to... The final crossover probability takes the value of The adjustment factor is taken as: Distribution index Adjust according to evolutionary stage, that is, when hour ,when .
[0042] Adaptive mutation dynamically adjusts the mutation probability based on the number of generations and the fitness of individuals. This means increasing the mutation probability of individuals with low fitness to escape local optima, adjusting the distribution index based on the evolutionary stage, and performing multinomial mutation to generate mutated individuals. Specific mutation probabilities... Adjust dynamically according to the following formula: (7) in: The initial mutation probability, This represents the probability of late-stage mutation. In this example, the initial mutation probability is set to... The probability of late-stage mutation is taken as: Distribution index Adjust according to evolutionary stage, that is, when .
[0043] The environmental selection operation merges the parent population, offspring population, and mutated individuals, and selects the optimal individuals to form the next generation population based on non-dominated ranking and crowding.
[0044] Steps S37 and S38 are used for iterative evolution. Steps S33 to S36 are repeated, and the evolutionary progress and current optimal frontier information are output periodically until the preset number of iterations is reached or the population converges. If the preset termination condition is met, the optimal production capacity matching scheme is output. In this example, from the first frontier of the final population, according to… Priority > Priority > The "priority" selection process prioritizes the solution with the best overall performance, calculates optimized capacity gaps, surplus rates, overtime hours, and other indicators, and outputs equipment purchase decision recommendations. In practical applications, based on enterprise management preferences, the solution with the smallest capacity gap, the best balance of surplus rates, and the shortest overtime hours can be prioritized from the optimal solution set as the annual or phased cigarette equipment capacity configuration plan, thereby achieving scientific decision-making and optimized management for the production of multiple cigarette specifications.
[0045] On the other hand, the present invention also provides a cigarette production capacity matching system based on the improved NSGA-II, the system including a processor configured to perform any of the methods described in the cigarette production capacity matching method based on the improved NSGA-II.
[0046] In another aspect, the present invention also provides a computer-readable storage medium storing instructions that, when executed by a processor, implement any of the methods described in the cigarette production capacity matching method based on the improved NSGA-II.
[0047] The beneficial effects of this invention are: This invention proposes a capacity matching optimization method for cigarette equipment based on an improved NSGA-II algorithm, aiming to solve problems such as resource waste, excessive overtime, uneven equipment load, and low optimization efficiency caused by fluctuations in capacity demand for multiple product specifications, and to achieve accurate matching between capacity and market demand.
[0048] First, a multi-objective capacity matching optimization model is constructed. The annual production capacity of each specification of cigarette product is used as the decision variable. Taking into account actual production constraints, upper and lower bound constraints on individual product capacity, a total capacity ceiling constraint, a capacity surplus rate constraint, and non-negativity constraints are set. Regarding optimization objectives, three core objective functions are simultaneously defined: minimizing the total capacity gap, used to characterize the overall degree to which capacity meets market demand; minimizing the weighted deviation, used to measure the deviation of each product's capacity surplus rate from the preset ideal lower limit, avoiding excessive surplus for individual products and improving the rationality and balance of surplus rate allocation; and minimizing total overtime time, used to reflect production organization costs and equipment load pressure. Through multi-objective collaborative optimization, the resource allocation imbalance problem caused by single-objective optimization is avoided.
[0049] Secondly, an improved NSGA-II multi-objective evolutionary algorithm is introduced to solve the model. The algorithm improvement is reflected in two key aspects: In the population initialization phase, a dual generation strategy combining demand forecast seed solutions and Latin hypercube sampling is employed. On one hand, a demand-oriented seed solution is constructed based on product demand forecast data and adjusted to meet various constraints, ensuring the initial solution closely reflects actual production needs. On the other hand, Latin hypercube sampling is used to uniformly generate supplementary individuals within the solution space, ensuring population diversity and preventing initial solution clustering. The seed solution and LHS individuals are then merged to form an initial population that balances relevance to actual demand with solution space coverage, laying the foundation for efficient optimization in the future.
[0050] In the evolutionary iteration phase, an adaptive crossover and mutation mechanism based on the evolutionary stage and individual fitness is designed. The crossover and mutation probabilities are dynamically adjusted according to the current generation and individual fitness. An adaptive simulated binary crossover and polynomial mutation strategy is employed to maintain strong global exploration capabilities in the early stages of evolution and enhance local exploration accuracy in the later stages, effectively reducing the risk of getting trapped in local optima and improving the accuracy and stability of multi-objective optimization. Simultaneously, environment selection is achieved through non-dominated sorting and crowding distance calculation, iteratively obtaining a uniformly distributed and convergent Pareto optimal solution set generation by generation.
[0051] Ultimately, the optimal capacity configuration scheme with the best overall performance is selected from the Pareto optimal solution set, and the corresponding key indicators such as capacity gap, surplus rate of each product, and overtime hours are output, providing quantitative decision support for enterprises to formulate cigarette equipment configuration schemes and production plans.
[0052] In practical applications, this method can effectively reduce production capacity gaps and overtime hours, balance equipment load for various product specifications, significantly improve equipment utilization and production efficiency, reduce resource waste, and bring significant economic and management benefits to cigarette production management.
[0053] With the transformation of cigarette production towards intelligent and digital manufacturing, the implementation of this invention has broad prospects. By improving the capacity matching optimization method of the NSGA-II algorithm, enterprises can improve production management efficiency, reduce overtime costs, and enhance equipment load balancing, thereby reducing production costs and increasing equipment utilization. The application of this technology will significantly improve the accuracy of production planning, bringing higher economic and management benefits. It is expected that after large-scale application, this method will reduce manual intervention, increase production response speed, and drive technological progress in the industry, possessing strong market competitiveness. As the industry develops towards intelligent manufacturing, implementing this technology will help increase enterprise capacity and further enhance market position.
[0054] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0055] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0056] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0057] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0058] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0059] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0060] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0061] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0062] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.
Claims
1. A cigarette production capacity matching method based on the improved NSGA-II, characterized in that, The capacity matching method includes: Obtain basic data on the matching of cigarette production resources and demand; Calculate the constraint parameters for each product based on the aforementioned basic data; A multi-objective optimization model for matching the production capacity of cigarette equipment is constructed based on the aforementioned constraint parameters; The improved NSGA-II algorithm is used to solve the multi-objective optimization model for matching the production capacity of the cigarette equipment, so as to obtain the optimal production capacity matching scheme.
2. The capacity matching method according to claim 1, characterized in that, The multi-objective optimization model for matching the production capacity of cigarette equipment, based on the aforementioned constraint parameters, includes: Set upper and lower bound constraints on the production capacity of each product, upper limit constraints on the total production capacity of all products, constraints on the surplus rate of all products, and constraints on non-negativity.
3. The capacity matching method according to claim 1, characterized in that, The multi-objective optimization model for matching the production capacity of cigarette equipment, based on the aforementioned constraint parameters, includes: The optimization objective of minimizing the total gap is obtained according to formula (1). ，（1） in, For the first Annual demand for this product specification For the first Annual production capacity of each product specification This represents the total number of product specifications.
4. The capacity matching method according to claim 1, characterized in that, The multi-objective optimization model for matching the production capacity of cigarette equipment, based on the aforementioned constraint parameters, includes: The optimization objective of minimizing the weighted deviation is obtained according to formulas (2) and (3). ，（2） ，（3） in, For the first The capacity surplus rate of each product specification For the first Annual demand for this product specification For the first Annual production capacity of each product specification For the first Production capacity weight for each product specification For the first The lower limit of the ideal surplus rate for a certain product specification. This represents the total number of product specifications.
5. The capacity matching method according to claim 1, characterized in that, The multi-objective optimization model for matching the production capacity of cigarette equipment, based on the aforementioned constraint parameters, includes: The optimization objective of minimizing total overtime hours is obtained based on formulas (4) and (5). ，（4） ，（5） in, For the first Annual demand for this product specification For the first Annual production capacity of each product specification For the first The total average output per shift for all models of this product For the production of the first The total number of equipment types for each product For the first type of product The number of models For the first Product No. The daily output of this type of machine. This refers to the standard daily working hours for a single generating unit. This is an indicator function.
6. The capacity matching method according to claim 1, characterized in that, The multi-objective optimization model for matching the production capacity of cigarette equipment is solved based on the improved NSGA-II algorithm to obtain the optimal production capacity matching scheme, including: An initial solution is generated based on product demand forecast data; The initial solution is adjusted for constraints on single-product output and total capacity to obtain an adjusted seed solution set; Latin hypercube sampling is used to supplement the diversity solutions. The adjusted seed solution set is merged with the diversity solutions generated by Latin hypercube sampling and deduplication is performed to obtain the initial population. Calculate the objective function value for each individual in the current initial population; The individuals are non-dominatedly ranked according to the objective function value; Calculate the crowding distance for each level of individuals; Based on the non-dominated sorting results and the crowding distance, selection, adaptive crossover, adaptive mutation, and environmental selection operations are performed to generate a new generation of population. Determine whether the preset termination condition is met; If the preset termination condition is not met, return to the step of calculating the objective function value of each individual in the current initial population; If the preset termination conditions are met, the optimal capacity matching scheme is output.
7. The capacity matching method according to claim 6, characterized in that, The crossover probability of the adaptive crossover operation is dynamically adjusted according to formula (6): ，（6） in, For crossover probability, The initial crossover probability, The probability of crossover at the end of the period. For the current generation, The maximum number of iterations, For the first indivual fitness value, The average fitness value of the population. This is for adjusting the coefficient.
8. The capacity matching method according to claim 6, characterized in that, The mutation probability of the adaptive mutation operation is dynamically adjusted according to formula (7): ，（7） in, The mutation probability, The initial mutation probability, This represents the probability of late-stage mutation. For the current generation, The maximum number of iterations, For the first indivual fitness value, The average fitness value of the population. This is for adjusting the coefficient.
9. A cigarette production capacity matching system based on an improved NSGA-II, characterized in that, The system includes a processor configured to perform the method as described in any one of claims 1 to 8.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed by a processor, implement the method as described in any one of claims 1 to 8.