Photovoltaic module production scheduling optimization method and system based on multi-objective optimization
Through multi-objective optimization methods and improved ant colony algorithm, the efficiency and cost problems of traditional photovoltaic module production scheduling methods are solved, energy consumption reduction and inventory management optimization are achieved, and the overall performance of production scheduling is improved.
Patent Information
- Application Number
- CN202411047444.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-01
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-08-01
AI Technical Summary
Traditional photovoltaic module production scheduling methods lack systematicity and optimization capabilities, and are difficult to adapt to complex production environments and diversified optimization goals, resulting in low production efficiency and high cost.
Using a multi-objective optimization method, by obtaining the equipment's rated power, production energy consumption and logistics energy consumption, the objective function of minimizing total energy consumption is constructed, and the inventory turnover rate of raw materials, products in-process and finished products is set, and the weight coefficient is set, and the The improved ant colony algorithm is used to jointly solve it to determine the production scheduling strategy.
It has achieved the reduction of energy consumption and optimization of inventory management, improved the comprehensive performance of production scheduling and enterprise operation efficiency, and balanced energy consumption and inventory management.
Smart Images

Figure CN118569610B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to photovoltaic technology, and in particular to a photovoltaic module production scheduling optimization method and system based on multi-objective optimization. Background Art
[0002] As global energy shortages and environmental pollution become increasingly prominent, photovoltaic power generation, as a clean, renewable energy form, has been widely used and promoted. Photovoltaic modules are the core components of photovoltaic power generation systems, and their production efficiency and quality directly affect the performance and cost of photovoltaic power generation. However, the production process of photovoltaic modules involves multiple processes and equipment, and the production scheduling problem is complex. How to optimize production scheduling to improve production efficiency and reduce production costs has become an important issue facing photovoltaic module manufacturers.
[0003] Traditional photovoltaic module production scheduling mainly relies on manual experience and simple heuristic rules, lacking systematic and optimization capabilities. As the scale of photovoltaic module production continues to expand, traditional scheduling methods are difficult to adapt to the increasingly complex production environment and diversified optimization objectives. Summary of the invention
[0004] The embodiments of the present invention provide a photovoltaic module production scheduling optimization method and system based on multi-objective optimization, which can solve the problems in the prior art.
[0005] According to a first aspect of the embodiments of the present invention,
[0006] Provides a photovoltaic module production scheduling optimization method based on multi-objective optimization, including:
[0007] The rated power of multiple devices in a photovoltaic module production workshop, the production energy consumption of a unit product, and the logistics energy consumption of transporting products in the logistics link are obtained, a first objective function is constructed with the minimum total energy consumption of the photovoltaic module production workshop as the goal, and a first constraint condition corresponding to the first objective function is set according to the first objective function, wherein the first constraint condition includes a production task completion constraint, the production task completion constraint is used to indicate that all production tasks must be completed within a specified time, and task delays or incompleteness are not allowed; equipment capacity constraints, the equipment capacity constraints are used to indicate that the number of processing tasks of each device in each time period cannot exceed its maximum capacity; process sequence constraints, the process sequence constraints are used to indicate that the processing procedures of each production task must be carried out in a predetermined order, and process reversal or skipping is not allowed;
[0008] Determine the raw material inventory turnover rate, work-in-progress inventory turnover rate and finished product inventory turnover rate of the photovoltaic module production workshop respectively, and set corresponding weight coefficients for the raw material inventory turnover rate, the work-in-progress inventory turnover rate and the finished product inventory turnover rate respectively, construct a second objective function with the goal of maximizing the total inventory turnover rate of the photovoltaic module production workshop, and set a second constraint condition corresponding to the second objective function according to the second objective function, wherein the second constraint condition includes an inventory capacity constraint, the inventory capacity constraint is used to indicate that the inventory of each warehouse in each time period cannot exceed its maximum capacity; an inventory balance constraint, the inventory balance constraint is used to indicate that the inventory of each warehouse in each time period must satisfy a material balance relationship, that is, the inventory of the previous time period plus the inventory in the current time period is equal to the inventory of the current time period plus the inventory out of the current time period;
[0009] The first objective function and the second objective function are jointly solved by a multi-objective optimization algorithm to determine a production scheduling strategy for the photovoltaic module production workshop, wherein the multi-objective optimization algorithm is constructed based on an improved ant colony algorithm.
[0010] In an optional embodiment,
[0011] The first objective function is constructed with the goal of minimizing the total energy consumption of the photovoltaic module production workshop, including:
[0012] The first objective function is shown in the following formula:
[0013] ;
[0014] in, E represents the total energy consumption, m Indicates the number of devices. n Indicates the number of processes, p Indicates the number of logistics links, P i Indicates i The rated power of the equipment, t i represents the actual working time of the i-th device in the scheduling cycle, E j represents the energy consumption per unit product of the jth process, Q j represents the product output of the jth process in the scheduling period, E k It represents the energy consumption per unit distance or single transport in the kth logistics link, D k It represents the transportation distance or number of transportation times of the kth logistics link within the scheduling cycle.
[0015] In an optional embodiment,
[0016] Determining the raw material inventory turnover rate, work-in-progress inventory turnover rate, and finished product inventory turnover rate of the photovoltaic module production workshop includes:
[0017] Determine the raw material unit cost of the raw materials stored in the photovoltaic module production workshop within the target scheduling period and the first consumption of the raw materials per unit time, and determine the raw material inventory turnover rate in combination with the raw material inventory of the photovoltaic module production workshop;
[0018] Determine the unit cost of work-in-progress stored in the photovoltaic module production workshop within the target scheduling period, and the second consumption of the work-in-progress per unit time, and determine the work-in-progress inventory turnover rate in combination with the work-in-progress inventory of the photovoltaic module production workshop;
[0019] Determine the unit cost of finished products stored in the photovoltaic module production workshop within the target scheduling cycle and the third consumption of the finished products per unit time, combine the product inventory of the photovoltaic module production workshop, and introduce the product sales return rate and inventory depreciation rate to determine the product inventory turnover rate.
[0020] In an optional embodiment,
[0021] The second objective function is constructed with the goal of maximizing the total inventory turnover rate of the photovoltaic module production workshop, including:
[0022] The second objective function is shown in the following formula:
[0023] ;
[0024] in, R represents the total inventory turnover rate, w 1 , w 2 , w 3 They represent the weight coefficients corresponding to raw material inventory, work-in-progress inventory, and finished product inventory, respectively. R 1 , R 2 , R 3 They represent raw material inventory turnover rate, work-in-progress inventory turnover rate, and finished product inventory turnover rate respectively;
[0025] q , T Represent the quantity of raw materials and the total length of the scheduling cycle, respectively. C lt For the lThe raw materials are t The unit cost of raw materials in a time period, Q lt For the l The raw materials are t The consumption in a period of time, I lt For the l The raw materials are t The inventory at the end of a time period, I l,t-1 For the l The raw materials are t-1 The inventory at the end of a time period, T t is the length of the tth time period;
[0026] r Indicates the number of work in progress. C h Indicates h The unit cost of the product in process, Q h are the consumption or sales volume of the hth type of work-in-process in the scheduling cycle, I h is the average inventory of the hth type of work-in-process during the scheduling cycle;
[0027] s Indicates the quantity of finished products. C gt is the unit cost of the g-th finished product in the t-th time period, Q gt is the sales volume of the g-th finished product in the t-th time period, γ gt is the sales return rate of the g-th finished product in the t-th time period, I gt is the inventory of the g-th finished product at the end of the t-th time period, I g,t-1 is the inventory of the g-th finished product at the end of the t-1 period, δ gt is the inventory depreciation rate of the g-th finished product in the t-th time period.
[0028] In an optional embodiment,
[0029] The first objective function and the second objective function are jointly solved by a multi-objective optimization algorithm to determine the production scheduling strategy of the photovoltaic module production workshop, including:
[0030] Initialize the ant colony, where each ant represents a feasible production scheduling strategy. The ant's path is discretely encoded, and the initial pheromone concentration and heuristic information are set.
[0031] For each ant, a complete ant colony path is constructed according to a state transition rule and a pheromone update rule, wherein the state transition rule is constructed based on pheromone concentration, heuristic information and transition probability, and the pheromone update rule adopts an update strategy based on an adaptive weight, and a first fitness value of the first objective function and a second fitness value of the second objective function of each ant colony path are calculated;
[0032] Determine a comprehensive evaluation value based on the first fitness value and the second fitness value, calculate the pheromone increment based on the comprehensive evaluation value and the total length of the ant colony path, and update each edge in the ant colony path according to the pheromone increment and the introduced pheromone volatility coefficient to determine an updated ant colony path;
[0033] A taboo search algorithm is applied to the updated ant colony path for local search to generate multiple candidate solutions, the candidate fitness value corresponding to each candidate solution and the state of the taboo table are determined, the final candidate solution is determined from the multiple candidate solutions as the current solution, and the current solution is used as the production scheduling strategy of the photovoltaic module production workshop.
[0034] In an optional embodiment,
[0035] Determining a comprehensive evaluation value based on the first fitness value and the second fitness value, and calculating the pheromone increment in combination with the comprehensive evaluation value and the total length of the ant colony path includes:
[0036] ;
[0037] ;
[0038] in, represents the pheromone increment, Q represents the pheromone increment coefficient, Represents the comprehensive evaluation value, Represents the ant colony path Total length;
[0039] m represents the number of objective functions, w i Indicates i The weight coefficient of the objective function, Respectively represent i The maximum and minimum values of the objective function in the current iteration, represents the ant colony path constructed by the k-th ant at the t-th iteration; Represents the ant colony path In the i The fitness value of the objective function.
[0040] In the second aspect of the embodiments of the present application,
[0041] Provide a photovoltaic module production scheduling optimization system based on multi-objective optimization, including:
[0042] The first unit is used to obtain the rated power of multiple devices in a photovoltaic module production workshop, the production energy consumption of a unit product, and the logistics energy consumption of transporting products in the logistics link, construct a first objective function with the minimum total energy consumption of the photovoltaic module production workshop as the goal, and set a first constraint condition corresponding to the first objective function according to the first objective function, wherein the first constraint condition includes a production task completion constraint, the production task completion constraint is used to indicate that all production tasks must be completed within a specified time, and task delays or incompleteness are not allowed; equipment capacity constraints, the equipment capacity constraints are used to indicate that the number of processing tasks of each device in each time period cannot exceed its maximum capacity; process sequence constraints, the process sequence constraints are used to indicate that the processing procedures of each production task must be carried out in a predetermined order, and process reversal or skipping is not allowed;
[0043] The second unit is used to respectively determine the raw material inventory turnover rate, the work-in-process inventory turnover rate and the finished product inventory turnover rate of the photovoltaic module production workshop, and set corresponding weight coefficients for the raw material inventory turnover rate, the work-in-process inventory turnover rate and the finished product inventory turnover rate, respectively, to construct a second objective function with the goal of maximizing the total inventory turnover rate of the photovoltaic module production workshop, and to set a second constraint condition corresponding to the second objective function according to the second objective function, wherein the second constraint condition includes an inventory capacity constraint, the inventory capacity constraint is used to indicate that the inventory of each warehouse in each time period cannot exceed its maximum capacity; an inventory balance constraint, the inventory balance constraint is used to indicate that the inventory of each warehouse in each time period must satisfy a material balance relationship, that is, the inventory of the previous time period plus the incoming inventory of the current time period is equal to the inventory of the current time period plus the outgoing inventory of the current time period;
[0044] The third unit is used to jointly solve the first objective function and the second objective function through a multi-objective optimization algorithm to determine the production scheduling strategy of the photovoltaic module production workshop, wherein the multi-objective optimization algorithm is constructed based on an improved ant colony algorithm.
[0045] According to a third aspect of the embodiments of the present invention,
[0046] An electronic device is provided, comprising:
[0047] processor;
[0048] a memory for storing processor-executable instructions;
[0049] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.
[0050] According to a fourth aspect of the embodiments of the present invention,
[0051] A computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the aforementioned method is implemented.
[0052] This application obtains the rated power of production equipment, the production energy consumption of unit products, and the energy consumption of logistics links, and constructs the first objective function with the minimum total energy consumption as the goal to optimize the production scheduling strategy, which can effectively reduce energy consumption in the production process, improve energy utilization efficiency, and achieve energy conservation and emission reduction. By determining the raw material inventory turnover rate, work-in-progress inventory turnover rate, and finished product inventory turnover rate respectively, and setting the corresponding weight coefficients, and constructing the second objective function with the goal of maximizing the total inventory turnover rate, it is possible to optimize the inventory structure, reduce inventory backlogs, speed up capital turnover, and improve inventory management level and enterprise operation efficiency.
[0053] The multi-objective optimization of production scheduling is realized. By jointly solving the first objective function (minimizing total energy consumption) and the second objective function (maximizing total inventory turnover rate) through the multi-objective optimization algorithm, a balance can be achieved between energy consumption and inventory management, multi-objective optimization of production scheduling can be achieved, and the comprehensive performance of production scheduling can be improved. By improving the ant colony algorithm to construct a multi-objective optimization algorithm, and using the intelligent search ability and global optimization characteristics of the ant colony algorithm, the complexity and multi-objective characteristics of the production scheduling problem can be effectively handled, the convergence speed of the optimization algorithm and the quality of the solution can be improved, and efficient and accurate production scheduling optimization can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS
[0054] Figure 1 A schematic diagram of a process flow of a photovoltaic module production scheduling optimization method based on multi-objective optimization according to an embodiment of the present invention;
[0055] Figure 2 It is a structural schematic diagram of a photovoltaic module production scheduling optimization system based on multi-objective optimization according to an embodiment of the present invention. DETAILED DESCRIPTION
[0056] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0057] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.
[0058] Figure 1 FIG. 1 is a flow chart of a photovoltaic module production scheduling optimization method based on multi-objective optimization according to an embodiment of the present invention. Figure 1 As shown, the method includes:
[0059] S101. Obtain the rated power of multiple devices in the photovoltaic module production workshop, the production energy consumption of the unit product, and the logistics energy consumption of the product in the logistics link, and construct a first objective function with the goal of minimizing the total energy consumption of the photovoltaic module production workshop;
[0060] For example, in order to obtain the total energy consumption of a photovoltaic module production workshop, it is first necessary to conduct a comprehensive energy consumption survey and statistics on the equipment in the production workshop. By consulting the equipment's technical parameter table, energy consumption monitoring report and other materials, or using tools such as an online energy consumption monitoring system and a portable energy consumption measuring instrument, key energy consumption indicators such as the rated power, actual operating power, and energy efficiency level of each device can be obtained. For complex production equipment, it is also necessary to analyze its energy consumption composition, identify the main energy consumption sources and energy consumption links, and provide a basis for subsequent energy consumption calculation and optimization.
[0061] On the basis of obtaining equipment energy consumption data, it is necessary to further analyze the production process of each photovoltaic module product to clarify the equipment type, quantity, processing time and other factors involved. Through production management data such as production orders, process routes, equipment processing logs, combined with equipment energy consumption data, it is possible to calculate the various energy consumptions such as electricity, heat, fuel, etc. required to produce a unit of product. In order to improve the accuracy of the calculation, it is necessary to fully consider factors such as the actual load rate and energy efficiency level of the equipment, and if necessary, corrections and verifications can be made through actual measurements.
[0062] In addition to energy consumption in the production process, it is also necessary to consider the energy consumption of photovoltaic module products in the logistics process. By conducting energy consumption surveys and statistics on logistics equipment and handling tools in the production workshop, obtaining parameters such as their rated power and operating time, the energy consumption level of handling unit products in the logistics process can be calculated. At the same time, it is also necessary to analyze factors such as product logistics routes and inventory strategies, optimize logistics networks and scheduling methods, and reduce unnecessary energy consumption.
[0063] After obtaining complete production energy consumption and logistics energy consumption data, the total energy consumption model of the photovoltaic module production workshop can be constructed. This model needs to comprehensively consider factors such as the production quantity, production process, equipment energy consumption, and logistics energy consumption of various products to accurately quantify the total energy consumption level within a production scheduling cycle. At the same time, it is also necessary to combine the total energy consumption model with other production management goals, such as production efficiency, delivery time, inventory level, etc., to construct a multi-objective optimization model to seek the optimal balance between energy consumption and other goals.
[0064] Finally, it is necessary to select a suitable optimization algorithm to solve the objective function of minimizing total energy consumption. Considering the complexity and multi-objective characteristics of the photovoltaic module production scheduling problem, traditional precise algorithms are difficult to work, and intelligent optimization algorithms such as improved ant colony algorithms, genetic algorithms, and particle swarm algorithms need to be adopted. By rationally designing the algorithm's encoding, decoding, fitness evaluation, evolutionary operation and other mechanisms, the total energy consumption target can be efficiently solved and dynamically optimized, providing production managers with the best production scheduling strategy and achieving energy saving and efficiency improvement in the photovoltaic module manufacturing process.
[0065] Exemplarily, a first constraint condition corresponding to the first objective function can be set according to the first objective function, wherein the first constraint condition includes a production task completion constraint, which is used to indicate that all production tasks must be completed within a specified time, and task delays or incompleteness are not allowed; an equipment capacity constraint, which is used to indicate that the number of processing tasks of each equipment in each time period cannot exceed its maximum capacity; and a process sequence constraint, which is used to indicate that the processing procedures of each production task must be performed in a predetermined order, and process reversal or skipping is not allowed.
[0066] In an optional embodiment,
[0067] The first objective function is constructed with the goal of minimizing the total energy consumption of the photovoltaic module production workshop, including:
[0068] The first objective function is shown in the following formula:
[0069] ;
[0070] in, Erepresents the total energy consumption, m Indicates the number of devices. n Indicates the number of processes, p Indicates the number of logistics links, P i Indicates i The rated power of the equipment, t i represents the actual working time of the i-th device in the scheduling cycle, E j represents the energy consumption per unit product of the jth process, Q j represents the product output of the jth process in the scheduling period, E k It represents the energy consumption per unit distance or single transport in the kth logistics link, D k It represents the transportation distance or number of transportation times of the kth logistics link within the scheduling cycle.
[0071] Through the above detailed technical solution, the equipment energy consumption, production energy consumption and logistics energy consumption data of the photovoltaic module production workshop can be accurately obtained, and the first objective function can be constructed with the minimum total energy consumption as the goal. This objective function quantifies the energy consumption level of the production scheduling plan, and provides important evaluation indicators and optimization directions for subsequent multi-objective optimization. At the same time, by optimizing and solving this objective function, the production scheduling strategy with the highest energy utilization efficiency can be obtained, realizing energy conservation, emission reduction and cost savings in the photovoltaic module manufacturing process.
[0072] S102. Determine the raw material inventory turnover rate, the work-in-progress inventory turnover rate, and the finished product inventory turnover rate of the photovoltaic module production workshop, respectively, and set corresponding weight coefficients for the raw material inventory turnover rate, the work-in-progress inventory turnover rate, and the finished product inventory turnover rate, respectively, and construct a second objective function with the goal of maximizing the total inventory turnover rate of the photovoltaic module production workshop;
[0073] In an optional embodiment,
[0074] Determining the raw material inventory turnover rate, work-in-progress inventory turnover rate, and finished product inventory turnover rate of the photovoltaic module production workshop includes:
[0075] Determine the raw material unit cost of the raw materials stored in the photovoltaic module production workshop within the target scheduling period and the first consumption of the raw materials per unit time, and determine the raw material inventory turnover rate in combination with the raw material inventory of the photovoltaic module production workshop;
[0076] Determine the unit cost of work-in-progress stored in the photovoltaic module production workshop within the target scheduling period, and the second consumption of the work-in-progress per unit time, and determine the work-in-progress inventory turnover rate in combination with the work-in-progress inventory of the photovoltaic module production workshop;
[0077] Determine the unit cost of finished products stored in the photovoltaic module production workshop within the target scheduling cycle and the third consumption of the finished products per unit time, combine the product inventory of the photovoltaic module production workshop, and introduce the product sales return rate and inventory depreciation rate to determine the product inventory turnover rate.
[0078] For example, in order to optimize the inventory management of a photovoltaic module production workshop and improve inventory turnover efficiency, it is necessary to determine the inventory turnover rates of raw materials, work-in-progress and finished products respectively. Inventory turnover rate is an important indicator for measuring inventory management efficiency, reflecting the turnover speed of inventory funds and the utilization efficiency of inventory assets.
[0079] First of all, to determine the inventory turnover rate of raw materials, it is necessary to comprehensively consider the unit cost and consumption rate of raw materials. By collecting and analyzing data such as raw material purchase contracts, warehouse invoices, and warehouse outvoices, the purchase cost, inventory quantity, and consumption quantity of each raw material can be accurately obtained. At the same time, it is also necessary to combine information such as production plans and bills of materials to predict the consumption of raw materials within a scheduling cycle. After mastering the unit cost, inventory quantity, and consumption rate of raw materials, the turnover times and turnover days of raw material inventory can be calculated to evaluate the efficiency and rationality of raw material inventory management.
[0080] Secondly, to determine the turnover rate of work-in-process inventory, it is necessary to pay attention to the production cost and processing speed of the work-in-process. By collecting and analyzing data such as production work orders, material requisition records, and completed warehousing records, the unit cost and quantity of each work-in-process can be calculated. At the same time, it is also necessary to predict the consumption rate and turnover rate of work-in-process based on factors such as production progress and equipment capacity. By comparing the inventory volume, production cost, and consumption rate of work-in-process, the rationality and risk level of the work-in-process inventory can be evaluated, production scheduling and material distribution strategies can be optimized, and the backlog of work-in-process and capital occupation can be reduced.
[0081] Finally, in order to determine the finished product inventory turnover rate, in addition to considering the production cost and sales speed of the finished product, it is also necessary to introduce factors such as sales return rate and inventory depreciation rate. By analyzing data such as sales orders, delivery records, and return records, the unit cost, inventory quantity, and sales quantity of each finished product can be accurately calculated. At the same time, it is also necessary to collect and evaluate quality indicators such as the return rate and scrap rate of finished products to reasonably predict the actual consumption rate of finished products. After comprehensively considering the finished product inventory, sales speed, return rate, and depreciation rate, the turnover times and turnover days of the finished product inventory can be calculated, the efficiency and risk level of finished product inventory management can be evaluated, and sales strategies and inventory control measures can be optimized.
[0082] Exemplarily, a second constraint condition corresponding to the second objective function can be set according to the second objective function, wherein the second constraint condition includes an inventory capacity constraint, which is used to indicate that the inventory quantity of each warehouse in each time period cannot exceed its maximum capacity; and an inventory balance constraint, which is used to indicate that the inventory quantity of each warehouse in each time period must satisfy the material balance relationship, that is, the inventory quantity of the previous time period plus the inventory quantity in the current time period is equal to the inventory quantity in the current time period plus the inventory quantity out of the current time period.
[0083] By determining the inventory turnover rates of raw materials, work-in-progress, and finished products respectively, the inventory management level of the photovoltaic module production workshop can be comprehensively evaluated. The improvement of inventory turnover rate means faster turnover of inventory funds, reduced inventory risks, and improved efficiency of capital utilization. In order to further optimize inventory management, it is also necessary to combine production plans, sales forecasts, supply chain collaboration and other factors to dynamically adjust inventory strategies and goals, balance inventory costs, service levels and risk levels, and achieve refined and intelligent inventory management. At the same time, it is also necessary to establish a sound inventory monitoring and early warning mechanism to promptly discover and solve inventory abnormalities, continuously improve inventory management processes and performance, and provide strong guarantees for the efficient operation of photovoltaic module production workshops.
[0084] In an optional embodiment,
[0085] The second objective function is constructed with the goal of maximizing the total inventory turnover rate of the photovoltaic module production workshop, including:
[0086] The second objective function is shown in the following formula:
[0087] ;
[0088] in, R represents the total inventory turnover rate, w 1 , w 2 , w3 They represent the weight coefficients corresponding to raw material inventory, work-in-progress inventory, and finished product inventory, respectively. R 1 , R 2 , R 3 They represent raw material inventory turnover rate, work-in-progress inventory turnover rate, and finished product inventory turnover rate respectively;
[0089] q , T Represent the quantity of raw materials and the total length of the scheduling cycle, respectively. C lt For the l The raw materials are t The unit cost of raw materials in a time period, Q lt For the l The raw materials are t The consumption in a period of time, I lt For the l The raw materials are t The inventory at the end of a time period, I l,t-1 For the l The raw materials are t-1 The inventory at the end of a time period, T t is the length of the tth time period;
[0090] r Indicates the number of work in progress, C h Indicates h The unit cost of the product in process, Q h are the consumption or sales volume of the hth type of work-in-process in the scheduling cycle, I h is the average inventory of the hth type of work-in-process during the scheduling cycle;
[0091] s Indicates the quantity of finished products. C gt is the unit cost of the g-th finished product in the t-th time period, Q gt is the sales volume of the g-th finished product in the t-th time period, γ gt is the sales return rate of the g-th finished product in the t-th time period, I gt is the inventory of the g-th finished product at the end of the t-th time period, Ig,t-1 is the inventory of the g-th finished product at the end of the t-1 period, δ gt is the inventory depreciation rate of the g-th finished product in the t-th time period.
[0092] S103. The first objective function and the second objective function are jointly solved by a multi-objective optimization algorithm to determine a production scheduling strategy for the photovoltaic module production workshop, wherein the multi-objective optimization algorithm is constructed based on an improved ant colony algorithm.
[0093] In an optional embodiment,
[0094] The first objective function and the second objective function are jointly solved by a multi-objective optimization algorithm to determine the production scheduling strategy of the photovoltaic module production workshop, including:
[0095] Initialize the ant colony, where each ant represents a feasible production scheduling strategy. The ant's path is discretely encoded, and the initial pheromone concentration and heuristic information are set.
[0096] For each ant, a complete ant colony path is constructed according to a state transition rule and a pheromone update rule, wherein the state transition rule is constructed based on pheromone concentration, heuristic information and transition probability, and the pheromone update rule adopts an update strategy based on an adaptive weight, and a first fitness value of the first objective function and a second fitness value of the second objective function of each ant colony path are calculated;
[0097] Determine a comprehensive evaluation value based on the first fitness value and the second fitness value, calculate the pheromone increment based on the comprehensive evaluation value and the total length of the ant colony path, and update each edge in the ant colony path according to the pheromone increment and the introduced pheromone volatility coefficient to determine an updated ant colony path;
[0098] A taboo search algorithm is applied to the updated ant colony path for local search to generate multiple candidate solutions, the candidate fitness value corresponding to each candidate solution and the state of the taboo table are determined, the final candidate solution is determined from the multiple candidate solutions as the current solution, and the current solution is used as the production scheduling strategy of the photovoltaic module production workshop.
[0099] In an optional embodiment,
[0100] Determining a comprehensive evaluation value based on the first fitness value and the second fitness value, and calculating the pheromone increment in combination with the comprehensive evaluation value and the total length of the ant colony path includes:
[0101] ;
[0102] in, represents the pheromone increment, Q represents the pheromone increment coefficient, Represents the comprehensive evaluation value, Represents the ant colony path Total length;
[0103] m represents the number of objective functions, w i Indicates i The weight coefficient of the objective function, Respectively represent i The maximum and minimum values of the objective function in the current iteration, represents the ant colony path constructed by the k-th ant at the t-th iteration; Represents the ant colony path In the i The fitness value of the objective function.
[0104] For example, after determining the two objective functions of minimizing the total energy consumption of the photovoltaic module production workshop and maximizing the inventory turnover rate, it is necessary to further jointly solve these two objective functions through a multi-objective optimization algorithm to determine the optimal production scheduling strategy. Considering the complexity, multi-objective and dynamic nature of the photovoltaic module production scheduling problem, traditional precise algorithms are difficult to meet actual needs, and intelligent optimization algorithms need to be used to solve it.
[0105] Among them, the ant colony algorithm is an intelligent optimization algorithm that simulates the foraging behavior of ant colonies. It has the advantages of parallel search, positive feedback mechanism, distributed computing, etc., and is suitable for solving complex combinatorial optimization problems. In order to further improve the performance and adaptability of the ant colony algorithm, it can be improved and expanded, and strategies such as adaptive mechanisms and taboo search can be introduced to enhance the algorithm's global search capability and convergence speed.
[0106] Specifically, we first need to initialize an ant colony, where each ant represents a feasible production scheduling strategy. The ant path is coded in a discrete manner, where each node represents a production task or operation, and the edges between nodes represent the order and dependency of tasks. At the same time, we also need to set the initial pheromone concentration and heuristic information to guide the ants' search direction and explore new solution spaces.
[0107] During the ant colony search process, each ant gradually builds a complete path according to the state transition rule and pheromone update rule. The state transition rule determines the direction of the ant's next move and the node selection based on the pheromone concentration, heuristic information and transition probability of the current node. The pheromone update rule adopts an adaptive weight-based update strategy to dynamically adjust the release amount and volatilization speed of pheromones according to the quality of the solution to accelerate the convergence of the algorithm. At the same time, it is also necessary to calculate the fitness value of each ant colony path on the two objective functions of minimizing total energy consumption and maximizing inventory turnover rate, as a basis for evaluating the quality of the solution and selecting the next generation of populations.
[0108] In order to balance the trade-offs and considerations among multiple objectives, it is necessary to construct a comprehensive evaluation function based on the energy consumption fitness value and the inventory fitness value, taking into account the importance and priority of different objectives. At the same time, it is also necessary to combine the total length of the ant colony path, pheromone concentration and other factors to calculate the pheromone increment of each edge, and update the path according to the pheromone volatility coefficient to obtain a new ant colony path and solution set.
[0109] On the basis of the ant colony algorithm, the taboo search algorithm can also be introduced to perform local search and improvement on the current optimal solution. By defining the taboo table and the set of candidate solutions, the optimal path is perturbed and the domain search is performed in each iteration of the ant colony search to generate multiple candidate solutions. By evaluating the fitness value and taboo table status of the candidate solution, the optimal candidate solution is selected as the current solution, and the taboo table and the global optimal solution are updated. This hybrid strategy combining the ant colony algorithm and the taboo search can improve the local search capability and the quality of the solution while ensuring the global convergence of the algorithm.
[0110] Finally, after multiple rounds of iteration and optimization, the optimal path obtained from the ant colony search is the optimal production scheduling strategy for the photovoltaic module production workshop. This strategy comprehensively considers the two goals of minimizing total energy consumption and maximizing inventory turnover, and achieves a good balance in production efficiency, energy consumption, inventory management, etc., providing strong decision-making support for the production and operation management of enterprises.
[0111] Specifically, the Multi-Objective Ant Colony Optimization Algorithm (MOACO) is a heuristic optimization algorithm based on swarm intelligence. It simulates the behavior of ants in finding food and uses the positive feedback mechanism of pheromones to solve multi-objective optimization problems. The Tabu Search Algorithm (TS) is a meta-heuristic algorithm based on local search. By introducing taboo tables and candidate tables, it avoids the search from falling into local optimality while ensuring the quality and diversity of the solution.
[0112] This paper proposes a composite optimization method based on MOACO and TS algorithms, combining the advantages of the two algorithms to improve the efficiency and accuracy of solving multi-objective optimization problems. The specific algorithm flow is as follows:
[0113] Step 1: Initialize the ant colony. Each ant represents a feasible production scheduling plan. The ant's path can be discretely encoded.
[0114] Step 2: For each ant, a complete path is constructed according to the state transition rule and pheromone update rule, and its fitness value on the energy consumption minimization objective function and inventory turnover rate objective function is calculated.
[0115] Step 3: According to the fitness value, update the pheromone concentration on each path, and make global and local corrections to the pheromone.
[0116] Step 4: For each ant's constructed path, apply the TS algorithm to perform local search. Specifically, starting from the current path, several candidate paths are generated according to certain domain movement rules. Among the candidate paths, the path with the highest fitness value that is not in the taboo table is selected as the new current path. If all candidate paths are in the taboo table, the path with the highest fitness value is selected as the new current path and added to the taboo table.
[0117] Step 5: Repeat steps 2 to 4 until the termination condition is met, such as reaching the maximum number of iterations or the convergence degree of the ant colony meets the requirements.
[0118] Step 6: Perform non-dominated sorting and congestion calculation on the paths constructed by the final ant colony to obtain the Pareto optimal solution set as the solution to the multi-objective optimization problem.
[0119] This composite optimization method combines the positive feedback mechanism of the MOACO algorithm and the taboo search strategy of the TS algorithm, which can improve the convergence speed and robustness of the algorithm while ensuring the quality of the solution. By introducing the taboo table and candidate table, it can effectively jump out of the local optimum and expand the search range; by adopting non-dominated sorting and congestion calculation, it can maintain the diversity of solutions and avoid premature convergence. At the same time, this method also has strong adaptability and flexibility. According to the characteristics of the actual problem, the algorithm's parameter settings, transfer rules, update strategies, etc. can be appropriately adjusted to obtain better optimization performance.
[0120] In addition, in the multi-objective ant colony algorithm, each ant represents a feasible production scheduling strategy, and a complete ant colony path is constructed through state transition rules and pheromone update rules. Among them, the state transition rule determines the node selection strategy of the ant in the path construction process, and the pheromone update rule reflects the learning and optimization mechanism of the algorithm.
[0121] In terms of pheromone updating, this paper proposes an updating strategy based on adaptive weights. Traditional ant colony algorithms usually use fixed pheromone release and volatility coefficients, which are difficult to adapt to the dynamic changes of the problem. The adaptive weight strategy dynamically adjusts the parameters of pheromone updating according to the quality of the solution to accelerate the convergence of the algorithm. After each round of iteration, it is necessary to evaluate the fitness value of each ant colony path on the two objective functions of minimizing total energy consumption and maximizing inventory turnover. Among them, the first fitness value is the inverse of the first objective function, and the second fitness value is the inverse of the second objective function.
[0122] Figure 2 FIG. 1 is a schematic diagram of a photovoltaic module production scheduling optimization system based on multi-objective optimization according to an embodiment of the present invention. Figure 2 As shown, the system comprises:
[0123] The first unit is used to obtain the rated power of multiple devices in a photovoltaic module production workshop, the production energy consumption of a unit product, and the logistics energy consumption of transporting products in the logistics link, construct a first objective function with the minimum total energy consumption of the photovoltaic module production workshop as the goal, and set a first constraint condition corresponding to the first objective function according to the first objective function, wherein the first constraint condition includes a production task completion constraint, the production task completion constraint is used to indicate that all production tasks must be completed within a specified time, and task delays or incompleteness are not allowed; equipment capacity constraints, the equipment capacity constraints are used to indicate that the number of processing tasks of each device in each time period cannot exceed its maximum capacity; process sequence constraints, the process sequence constraints are used to indicate that the processing procedures of each production task must be carried out in a predetermined order, and process reversal or skipping is not allowed;
[0124] The second unit is used to respectively determine the raw material inventory turnover rate, the work-in-process inventory turnover rate and the finished product inventory turnover rate of the photovoltaic module production workshop, and set corresponding weight coefficients for the raw material inventory turnover rate, the work-in-process inventory turnover rate and the finished product inventory turnover rate, respectively, to construct a second objective function with the goal of maximizing the total inventory turnover rate of the photovoltaic module production workshop, and to set a second constraint condition corresponding to the second objective function according to the second objective function, wherein the second constraint condition includes an inventory capacity constraint, the inventory capacity constraint is used to indicate that the inventory of each warehouse in each time period cannot exceed its maximum capacity; an inventory balance constraint, the inventory balance constraint is used to indicate that the inventory of each warehouse in each time period must satisfy a material balance relationship, that is, the inventory of the previous time period plus the incoming inventory of the current time period is equal to the inventory of the current time period plus the outgoing inventory of the current time period;
[0125] The third unit is used to jointly solve the first objective function and the second objective function through a multi-objective optimization algorithm to determine the production scheduling strategy of the photovoltaic module production workshop, wherein the multi-objective optimization algorithm is constructed based on an improved ant colony algorithm.
[0126] According to a third aspect of the embodiments of the present invention,
[0127] An electronic device is provided, comprising:
[0128] processor;
[0129] a memory for storing processor-executable instructions;
[0130] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.
[0131] A fourth aspect of the embodiments of the present invention is:
[0132] A computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the aforementioned method is implemented.
[0133] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.
[0134] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.
Claims
1. A photovoltaic module production scheduling optimization method based on multi-objective optimization, characterized in that: include: The rated power of multiple devices in a photovoltaic module production workshop, the production energy consumption of a unit product, and the logistics energy consumption of transporting products in the logistics link are obtained, a first objective function is constructed with the minimum total energy consumption of the photovoltaic module production workshop as the goal, and a first constraint condition corresponding to the first objective function is set according to the first objective function, wherein the first constraint condition includes a production task completion constraint, the production task completion constraint is used to indicate that all production tasks must be completed within a specified time, and task delays or incompleteness are not allowed; equipment capacity constraints, the equipment capacity constraints are used to indicate that the number of processing tasks of each device in each time period cannot exceed its maximum capacity; process sequence constraints, the process sequence constraints are used to indicate that the processing procedures of each production task must be carried out in a predetermined order, and process reversal or skipping is not allowed; Determine the raw material inventory turnover rate, work-in-progress inventory turnover rate and finished product inventory turnover rate of the photovoltaic module production workshop respectively, and set corresponding weight coefficients for the raw material inventory turnover rate, the work-in-progress inventory turnover rate and the finished product inventory turnover rate respectively, construct a second objective function with the goal of maximizing the total inventory turnover rate of the photovoltaic module production workshop, and set a second constraint condition corresponding to the second objective function according to the second objective function, wherein the second constraint condition includes an inventory capacity constraint, the inventory capacity constraint is used to indicate that the inventory of each warehouse in each time period cannot exceed its maximum capacity; an inventory balance constraint, the inventory balance constraint is used to indicate that the inventory of each warehouse in each time period must satisfy a material balance relationship, that is, the inventory of the previous time period plus the inventory in the current time period is equal to the inventory of the current time period plus the inventory out of the current time period; The first objective function and the second objective function are jointly solved by a multi-objective optimization algorithm to determine a production scheduling strategy for the photovoltaic module production workshop, wherein the multi-objective optimization algorithm is constructed based on an improved ant colony algorithm; The first objective function is constructed with the goal of minimizing the total energy consumption of the photovoltaic module production workshop, including: The first objective function is shown in the following formula: ; Among them, E represents the total energy consumption, m represents the number of equipment, n represents the number of processes, p represents the number of logistics links, and P i represents the rated power of the i-th device, t i represents the actual working time of the i-th device in the scheduling cycle, E j represents the energy consumption per unit product of the jth process, Q j represents the product output of the jth process in the scheduling period, E k represents the energy consumption per unit distance or single transport in the kth logistics link, D k It represents the transportation distance or number of handling times of the kth logistics link in the scheduling period; The second objective function is constructed with the goal of maximizing the total inventory turnover rate of the photovoltaic module production workshop, including: The second objective function is shown in the following formula: Among them, R represents the total inventory turnover rate, w1, w2, w3 represent the weight coefficients corresponding to raw material inventory, work-in-progress inventory and finished product inventory, R1, R2, R3 represent the raw material inventory turnover rate, work-in-progress inventory turnover rate and finished product inventory turnover rate respectively; q and T represent the quantity of raw materials and the total length of the scheduling cycle respectively. lt is the unit cost of the lth raw material in the tth time period, Q lt is the consumption of the lth raw material in the tth time period, I lt is the inventory of the lth raw material at the end of the tth time period, I l,t-1 is the inventory of the lth raw material at the end of the t-1th time period, T t is the length of the tth time period; r represents the number of work in progress, C h represents the unit cost of the hth work-in-progress product, Q h are the consumption or sales volume of the hth work-in-process in the scheduling cycle, I h is the average inventory of the hth type of work-in-process during the scheduling cycle; s represents the quantity of finished products, C gt is the unit cost of the g-th finished product in the t-th time period, Q gt is the sales volume of the g-th finished product in the t-th time period, γ gt is the sales return rate of the g-th finished product in the t-th time period, I gt is the inventory of the g-th finished product at the end of the t-th time period, I g,t-1 is the inventory of the g-th finished product at the end of the t-1th time period, δ gt is the inventory depreciation rate of the g-th finished product in the t-th time period; The first objective function and the second objective function are jointly solved by a multi-objective optimization algorithm to determine the production scheduling strategy of the photovoltaic module production workshop, including: Initialize the ant colony, where each ant represents a feasible production scheduling strategy. The ant's path is discretely encoded, and the initial pheromone concentration and heuristic information are set. For each ant, a complete ant colony path is constructed according to a state transition rule and a pheromone update rule, wherein the state transition rule is constructed based on pheromone concentration, heuristic information and transition probability, and the pheromone update rule adopts an update strategy based on an adaptive weight, and a first fitness value of the first objective function and a second fitness value of the second objective function of each ant colony path are calculated; Determine a comprehensive evaluation value based on the first fitness value and the second fitness value, calculate the pheromone increment based on the comprehensive evaluation value and the total length of the ant colony path, and update each edge in the ant colony path according to the pheromone increment and the introduced pheromone volatility coefficient to determine an updated ant colony path; Applying a taboo search algorithm to perform local search on the updated ant colony path to generate multiple candidate solutions, determining a candidate fitness value corresponding to each candidate solution and a state of a taboo table, determining a final candidate solution from the multiple candidate solutions as a current solution, and using the current solution as a production scheduling strategy for the photovoltaic module production workshop; Determining a comprehensive evaluation value based on the first fitness value and the second fitness value, and calculating the pheromone increment in combination with the comprehensive evaluation value and the total length of the ant colony path includes: ; in, represents the pheromone increment, Q represents the pheromone increment coefficient, Represents the comprehensive evaluation value, Represents the ant colony path Total length; m represents the number of objective functions, w i represents the weight coefficient of the i-th objective function, Respectively represent the maximum and minimum values of the i-th objective function in the current iteration, represents the ant colony path constructed by the k-th ant at the t-th iteration; Represents the ant colony path The fitness value on the i-th objective function.
2. The method according to claim 1, characterized in that Determining the raw material inventory turnover rate, work-in-progress inventory turnover rate, and finished product inventory turnover rate of the photovoltaic module production workshop includes: Determine the raw material unit cost of the raw materials stored in the photovoltaic module production workshop within the target scheduling period and the first consumption of the raw materials per unit time, and determine the raw material inventory turnover rate in combination with the raw material inventory of the photovoltaic module production workshop; Determine the unit cost of work-in-progress stored in the photovoltaic module production workshop within the target scheduling period, and the second consumption of the work-in-progress per unit time, and determine the work-in-progress inventory turnover rate in combination with the work-in-progress inventory of the photovoltaic module production workshop; Determine the unit cost of finished products stored in the photovoltaic module production workshop within the target scheduling cycle and the third consumption of the finished products per unit time, combine the product inventory of the photovoltaic module production workshop, and introduce the product sales return rate and inventory depreciation rate to determine the product inventory turnover rate.
3. A photovoltaic module production scheduling optimization system based on multi-objective optimization, used to implement the method described in any one of claims 1 to 2, characterized in that: include: The first unit is used to obtain the rated power of multiple devices in a photovoltaic module production workshop, the production energy consumption of a unit product, and the logistics energy consumption of transporting products in the logistics link, construct a first objective function with the minimum total energy consumption of the photovoltaic module production workshop as the goal, and set a first constraint condition corresponding to the first objective function according to the first objective function, wherein the first constraint condition includes a production task completion constraint, the production task completion constraint is used to indicate that all production tasks must be completed within a specified time, and task delays or incompleteness are not allowed; equipment capacity constraints, the equipment capacity constraints are used to indicate that the number of processing tasks of each device in each time period cannot exceed its maximum capacity; process sequence constraints, the process sequence constraints are used to indicate that the processing procedures of each production task must be carried out in a predetermined order, and process reversal or skipping is not allowed; The second unit is used to respectively determine the raw material inventory turnover rate, the work-in-process inventory turnover rate and the finished product inventory turnover rate of the photovoltaic module production workshop, and set corresponding weight coefficients for the raw material inventory turnover rate, the work-in-process inventory turnover rate and the finished product inventory turnover rate, respectively, to construct a second objective function with the goal of maximizing the total inventory turnover rate of the photovoltaic module production workshop, and to set a second constraint condition corresponding to the second objective function according to the second objective function, wherein the second constraint condition includes an inventory capacity constraint, the inventory capacity constraint is used to indicate that the inventory of each warehouse in each time period cannot exceed its maximum capacity; an inventory balance constraint, the inventory balance constraint is used to indicate that the inventory of each warehouse in each time period must satisfy a material balance relationship, that is, the inventory of the previous time period plus the incoming inventory of the current time period is equal to the inventory of the current time period plus the outgoing inventory of the current time period; The third unit is used to jointly solve the first objective function and the second objective function through a multi-objective optimization algorithm to determine the production scheduling strategy of the photovoltaic module production workshop, wherein the multi-objective optimization algorithm is constructed based on an improved ant colony algorithm.
4. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the method described in any one of claims 1 to 2.
5. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 2 is implemented.
