Hot rolling batch planning method and system based on multi-target model

Abstract

The invention provides a hot rolling batch planning method and system based on a multi-target model, and relates to the technical field of metallurgical hot rolling production line production plan arrangement. Determining a pool to be selected according to the order demand; constructing a multi-target bonus collection vehicle path problem model; setting a target function and a constraint condition of the multi-target bonus collection vehicle path problem model; and under the constraint of the constraint condition, taking a minimization objective function as an objective, solving the multi-objective bonus collection vehicle path problem model through a third-generation multi-objective non-dominated genetic algorithm, outputting a Pareto optimal solution set, and obtaining an optimal hot rolling batch plan in the Pareto optimal solution set according to the preference of the hot rolling batch plan for different objectives. By means of the method, a high-quality hot rolling batch plan can be obtained, and the productivity and benefits of a hot rolling plant are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of production planning and arrangement of metallurgical hot rolling production lines, and in particular to a method and system for compiling hot rolling batch plans based on a multi-objective model. Background Art

[0002] Hot rolling production is one of the main processes in steel production. The molten iron produced by the blast furnace goes through the steelmaking process and is cooled and cut into steel billets on the continuous casting machine. The steel billets are divided into different types according to their use and shape. Among them, slabs are used as raw materials for the hot rolling process. They are continuously rolled at a suitable temperature to form steel coils, steel plates, etc. that meet the order requirements of downstream enterprises. The hot rolling production process is complex. The quality of the hot rolling plan directly affects the production cost, production efficiency and product quality. The hot rolling plan can be divided into rolling units and batch plans. The changes in the rolling process between the pressure rollers are called unit plans, and the changes in the rolling between the support rollers are called batch plans.

[0003] The main task of hot rolling batch planning is to recommend slabs with properties such as steel type, width, quality grade, etc. that meet the order requirements from the virtual slabs to be produced by continuous casting and the current inventory slabs, and provide reasonable arrangements for the loading of the hot rolling process. Reasonable batch planning can improve the efficiency of on-site slab scheduling and reduce the time cost and temperature loss in the process of manual slab selection and scheduling.

[0004] However, existing hot rolling batch planning methods usually use a weighted combination method to transform multiple optimization objectives into a single objective for solution. There is a complex coupling relationship between multiple objectives, which cannot truly reflect the mutual influence of each objective in actual production. The optimization results may deviate from actual needs. The number of objective functions of the optimization model is small, and it fails to fully cover the key factors affecting production efficiency and process quality. In actual production, the mutual constraints between attributes are ignored, and their overall influence is not coordinated. There is a lack of consideration of the coordination between unit optimization and batch planning optimization. The local optimization solution does not meet the overall goal, which affects the execution efficiency and practical feasibility of the hot rolling batch planning. Summary of the Invention

[0005] In order to solve the technical problems that in the existing hot rolling batch planning, multiple optimization objectives are converted into a single objective for solution, the complex coupling relationship between the multiple objectives is ignored, the mutual influence of the various objectives in actual production cannot be truly reflected, and the optimization results may deviate from the actual needs; the number of objective functions of the optimization model is small, and the key factors affecting production efficiency and process quality are not fully covered; in actual production, the mutual constraints between attributes are ignored, their overall influence is not coordinated, and there is a lack of consideration for the coordination between the optimal rolling unit and the optimal batch plan, which affects the execution efficiency and practical feasibility of the hot rolling batch plan, the present invention provides a hot rolling batch planning method and system based on a multi-objective model.

[0006] The technical solutions provided by the embodiments of the present invention are as follows:

[0007] First aspect:

[0008] An embodiment of the present invention provides a method for preparing hot rolling batch planning based on a multi-objective model, comprising:

[0009] S1: Get order requirements;

[0010] S2: Determine the pool to be selected based on order requirements;

[0011] S3: Based on the candidate pool, a multi-objective bonus collection vehicle routing problem model is constructed;

[0012] S4: With the goal of minimizing the attribute jump penalty between adjacent slabs and maximizing the delivery matching bonus, customer priority bonus, total rolling mileage, and rolling unit mileage uniformity, the objective function and constraints of the multi-objective bonus collection vehicle routing problem model are established;

[0013] S5: Under the constraints, with the goal of minimizing the objective function, the multi-objective bonus collection vehicle routing problem model is solved by the third-generation multi-objective non-dominated genetic algorithm, and the Pareto optimal solution set is output;

[0014] S6: According to the preferences of the hot rolling batch plan for different objectives, an optimal hot rolling batch plan is obtained in the Pareto optimal solution set.

[0015] Second aspect:

[0016] An embodiment of the present invention provides a hot rolling batch planning system based on a multi-objective model, comprising:

[0017] processor;

[0018] The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the hot rolling batch planning method based on the multi-objective model as described in the first aspect is implemented.

[0019] The third aspect:

[0020] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for compiling hot rolling batch planning based on a multi-objective model as described in the first aspect is implemented.

[0021] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0022] In the present invention, the selection pool is determined according to the order requirements, which effectively improves the continuity of the hot rolling process in the upstream and downstream, and provides support for the efficient operation of the overall process of the enterprise. A multi-objective bonus collection vehicle path model is established, which can effectively consider the complex coupling relationship between multiple objectives and truly reflect the mutual influence of various objectives in actual production. By setting multiple objective functions and constraints, the rationality of the rolling plan and the enterprise benefits are improved from multiple angles. By adopting the third-generation multi-objective non-dominated genetic algorithm, a slab arrangement scheme that is more in line with process constraints and planning goals can be obtained at a higher dimension of multiple objectives, which realizes the efficient acquisition of multi-objective optimal hot rolling batch planning results, reduces the pressure and intensity of enterprise production plan formulation and dynamic scheduling, and improves the production efficiency and economic benefits of the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A schematic flow chart of a method for hot rolling batch planning based on a multi-objective model provided by an embodiment of the present invention;

[0025] Figure 2 A schematic diagram of a framework for hot rolling batch planning provided by an embodiment of the present invention;

[0026] Figure 3 A schematic diagram of a process for obtaining a pool of hot rolling batch plans according to an embodiment of the present invention;

[0027] Figure 4 A schematic structural diagram of a hot rolling batch planning system based on a multi-objective model provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0029] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0030] In the embodiments of the present invention, the terms "image" and "picture" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same. The terms "of," "corresponding," and "corresponding" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same.

[0031] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0032] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0033] Reference Manual Figure 1 , which shows a flow chart of a hot rolling batch planning method based on a multi-objective model provided by an embodiment of the present invention.

[0034] Reference Manual Figure 2 , showing a schematic diagram of the framework for hot rolling batch planning provided by an embodiment of the present invention.

[0035] like Figure 2 The matching center classifies the main rolled products, transition products, hot rolled products and tail products according to customer order requirements through information such as process requirements, road rules, priority, jump penalties and transportation routes, and builds a slab pool. The transport vehicles transfer the slabs from different types of slab pools to the corresponding rolling units according to the plan. Each unit contains transition products, main rolled products and tail products. The overall framework coordinates the slab pool and the rolling unit to optimize the arrangement of batch plans and improve the efficiency and quality of hot rolling production.

[0036] An embodiment of the present invention provides a method for preparing hot rolling batch planning based on a multi-objective model, the method comprising:

[0037] S1: Get order requirements.

[0038] Reference Manual Figure 3 , shows a schematic diagram of the process of obtaining the hot rolling batch plan selection pool provided by an embodiment of the present invention.

[0039] like Figure 3Starting from the order production piece plan, through constraint matching of order demand, combined with the data of inventory slabs and continuous casting output virtual slabs, according to hard constraints (such as steel type requirements, width range, thickness range, steel grade, surface quality and hardness range) and soft constraints (such as delivery priority and slab inventory time), qualified slabs to be selected are screened out to form a pool of slabs to be selected. Subsequently, the pool of slabs to be selected is further divided into main rolling material, transition material, hot roll material and tail material slab pool according to the purpose of the slab, providing basic data support for the preparation of hot rolling batch plan.

[0040] S2: Determine the pool to be selected based on order requirements.

[0041] It should be noted that matching the production batch plan with orders issued by the production and marketing system, and determining the selection pool based on the virtual slabs and inventory slabs of the continuous casting and cutting plan can ensure the accuracy of slab selection and the feasibility of the plan, while optimizing resource utilization, reducing unnecessary scheduling interference, and providing high-quality basic data support for the subsequent sequence optimization and batch arrangement of hot rolling plans, effectively improving the execution efficiency of the plan and production quality.

[0042] In a possible implementation, S2 specifically includes:

[0043] S201: Form a production plan based on order requirements.

[0044] It should be noted that by analyzing order demand and formulating a preliminary production plan, we can ensure that production is accurately matched with customer needs, optimize resource allocation, and improve production efficiency and the timeliness of order delivery.

[0045] S202: Divide the production plan into order piece plans.

[0046] It should be noted that by breaking down the production plan into order piece plans, the production tasks for each order can be accurately defined, the accuracy of production scheduling can be improved, resource allocation can be optimized, and the efficient execution and timely delivery of order requirements can be ensured.

[0047] S203: Determine hard constraints and soft constraints of slab requirements.

[0048] S204: According to the order piece plan, combined with hard constraints and soft constraints, determine the slabs to be selected from the inventory slabs and virtual slabs, and form the slab pool with the slabs to be selected.

[0049] It should be noted that by combining order piece planning with hard and soft constraints, it is possible to ensure that the selected slabs strictly meet the process and order requirements, improve the accuracy of the plan, reduce unnecessary screening and scheduling interference, and provide high-quality input for subsequent plans.

[0050] S205: Divide the slab pool according to the types of slabs to be selected to determine the pool to be selected.

[0051] Among them, the types of slabs to be selected include hot rolled materials, tail materials, main rolled materials and transition materials.

[0052] In a possible implementation, the hard constraints specifically include: steel type requirements, width range, thickness range, steel grade, surface quality, and hardness range of the slab.

[0053] Soft constraints specifically include: delivery priority and slab inventory time.

[0054] Among them, hot roll material is the slab used to adjust the temperature of the rolls, finishing material is the slab used to end the rolling unit, main rolled material is the main slab to meet order requirements, and transition material is used to connect slabs of different steel grades or specifications.

[0055] It should be noted that by dividing the pool of slabs to be selected by type, the allocation of slabs can be made more accurate, the functions and roles of different slabs can be clarified, and the rolling unit planning can be ensured to be reasonable and orderly.

[0056] S3: Based on the candidate pool, a multi-objective bonus collection vehicle routing problem model is constructed.

[0057] It should be noted that by constructing a multi-objective bonus collection vehicle routing problem model, comprehensive optimization of multiple objectives can be achieved, which solves the defect of traditional single-objective models that ignore actual complexity. At the same time, it improves the rationality of the plan and the ability to meet customer needs, laying a solid foundation for the subsequent optimization of hot rolling batch plans.

[0058] S4: With the goal of minimizing the attribute jump penalty between adjacent slabs and maximizing the delivery matching bonus, customer priority bonus, total rolling mileage, and rolling unit mileage uniformity, the objective function and constraints of the multi-objective bonus collection vehicle routing problem model are established.

[0059] Among them, the jump penalty values for attributes between adjacent slabs include the jump penalty values for width, thickness, hardness, and steel grade composition between adjacent candidate slabs. Jump penalty values refer to the penalty values caused by the variation (jump) in width, thickness, hardness, and steel grade composition between adjacent slabs. Larger jumps may lead to reduced rolling stability and increased production costs. Delivery bonuses are rewards set for on-time delivery of orders, designed to incentivize the plan to prioritize fulfilling orders with urgent delivery dates. Strategic customer delivery priority bonuses are bonuses set to meet the needs of important customers, giving priority to the completion of strategic customer orders. Rolling mileage represents the total rolling distance completed by the slab during the rolling process in the hot rolling batch plan, reflecting the efficiency of the plan. The average rolling mileage of the rolling unit is the average rolling mileage of each rolling unit, which is used to measure the balance of plan distribution between units.

[0060] It should be noted that by setting objective functions and constraints, multiple objective requirements can be balanced, which not only reduces the impact of changes in adjacent slab properties on process stability, but also meets the priority delivery needs of urgent orders and strategic customer orders, while improving production efficiency and resource utilization, ensuring the rationality of the plan and the effectiveness of execution.

[0061] In a possible implementation, the objective function is specifically:

[0062]

[0063] Among them, min means minimization, F1 means minimizing the width jump penalty value between adjacent candidate slabs, represents the rolling width between candidate slab i and candidate slab j, F2 represents the minimum thickness jump penalty value of adjacent candidate slabs, represents the thickness jump penalty value between candidate slab i and candidate slab j, F3 represents the hardness jump penalty value that minimizes the adjacent candidate slabs, represents the hardness jump penalty value between candidate slab i and candidate slab j, F4 represents the minimum steel grade component jump penalty value between adjacent candidate slabs, represents the penalty value of steel grade composition jump between candidate slab i and candidate slab j, F5 represents the maximum delivery time bonus, Pd i represents the delivery bonus value of slab i, F6 represents the maximum matching strategic customer delivery priority bonus, Pp i represents the order priority bonus value of slab i, F7 represents the total rolling mileage of the maximized hot rolling batch plan, M all Indicates the total rolling mileage of batch rolling, M k represents the kth rolling unit mileage in the batch rolling plan, F8 represents the minimum standard deviation of the rolling mileage of the rolling unit in the batch plan, M avg represents the average rolling mileage of the rolling unit plan in the batch rolling plan, x ijk represents the decision variables of the selected slab i and the selected slab j in the rolling unit k, y ik represents the decision variable of the selected slab i in the rolling unit k. When x ijk = 1, in rolling unit k, the selected slab i is produced immediately after the selected slab j. ijk =0,y ik When =1, the slab i to be selected is in the rolling unit k, V represents the numbered set of the slabs to be selected, V={1,...,n}, i=0,1,...,n, j=1,2,...,n, i≠j, i=0 represents the virtual slab, n represents the total number of slabs to be selected, k=1,2,...,m, m represents the total number of rolling units in the batch rolling plan.

[0064] In a possible implementation, the constraints specifically include:

[0065] Slab allocation constraints:

[0066]

[0067] Virtual slab starting point constraints:

[0068] y 0k =1,k∈K (2)

[0069] Continuity constraints:

[0070]

[0071] Prevent loop constraints:

[0072]

[0073] Minimum rolling length constraints:

[0074]

[0075] Maximum rolling length constraints:

[0076]

[0077] Constraints for rolling slabs of the same width:

[0078] ∑l i ≤Lsw,i∈Vsw ik ,k∈K (7)

[0079] Constraints for slab rolling of the same steel grade:

[0080] ∑l i ≤Lsg b ,i∈Vsg ik ,k∈K (8)

[0081] Width jump constraints:

[0082] 0≤(w i -w j )x ijk ≤W,i,j∈V,k∈K (9)

[0083] Thickness jump constraints:

[0084] |th i -th j |x ijk ≤Th,i,j∈V,k∈K (10)

[0085] Hardness jump constraints:

[0086] |hd i -hd j |x ijk ≤Hd,i,j∈V,k∈K (11)

[0087] Attribute continuity constraints:

[0088] (w i -w j )·|th i -th j |·|hd i -hd j |x ijk =0,i,j∈V,k∈K(12)

[0089] Temperature jump constraints:

[0090] |fot i -fot j |x ijk ≤Fot,i,j∈V,k∈K (13)

[0091] Steel grade transition constraints:

[0092] (c i -c j )x ijk =0>(c i -c j )|hd i -hd j |x ijk =0>|hd i -hd j |x ijk ≠0,i,j∈V,k∈K (14)

[0093] Minimum rolling length constraints:

[0094]

[0095] Among them, l i Indicates the length of the selected slab i, M min and M max They represent the minimum and maximum lengths of the rolling unit, Lsw represents the maximum continuous rolling length of the selected slab with the same width, and Vsw ik Vsg represents the set of slabs with the same width as the slab i in rolling unit k, ik Lsg represents the set of candidate slabs with the same surface grade as the candidate slab i in the k-th rolling unit plan, bIndicates the maximum rolling mileage specified in the rolling constraint of the selected slab with surface grade b within the specified rolling length, Vsg ik represents the set of slabs with the same surface grade as slab i in the kth rolling unit plan, wi and wj represent the widths of slab i and selected slab j respectively, W represents the maximum jump value of the width of the selected slab, and th i and th j They represent the thickness of the selected slab i and the selected slab j respectively, Th represents the maximum jump value of the thickness of the selected slab, hd i and hd j They represent the hardness of the selected slab i and the selected slab j respectively, Hd represents the maximum hardness jump of the selected slab, fot i and fot j They represent the out-of-furnace temperatures of the selected slab i and the selected slab j, Fot represents the maximum jump value of the out-of-furnace temperature of the selected slab, c i and c j Respectively represent the steel composition of the selected slab i and the selected slab j, V k Indicates the number of slabs to be selected in rolling unit k, BPM min Indicates the minimum rolling length of hot rolling batch plan.

[0096] Specifically, constraint (1) indicates that a slab can only be arranged in one rolling unit plan at most, constraint (2) indicates that virtual slab 0 must be arranged in each rolling unit plan, constraint (3) ensures that each slab is connected to another slab before and after it, constraint (4) ensures that a loop is formed. If an order has been assigned to a certain rolling unit, then an order should be assigned to the position before and after it, constraints (5) and (6) indicate that the length of the rolling unit plan has minimum and maximum restrictions, constraint (7) indicates that the total length of continuous rolling of slabs of the same width in the rolling unit plan is limited, and constraint (8) ensures surface quality, etc. Slabs of higher grades must be rolled within the specified rolling length. Constraints (9) to (11) indicate that the jumps in rolling width, rolling thickness, and hardness of adjacent slabs within the unit plan are restricted. Constraint (12) indicates that the same rolling thickness, rolling width, and steel type must be continuous during main material production scheduling, and simultaneous changes are not allowed. Constraint (13) indicates that when transitioning between steel types, the constraint of similar steel type composition must first be met. If the constraint of similar steel type composition is not met, different steel types of the same hardness level can be selected, and finally the hardness level can be crossed. Constraint (14) indicates the limit on the jump value of the furnace temperature. Constraint (15) indicates the avoidance of sub-loops.

[0097] S5: Under the constraints, with the goal of minimizing the objective function, the multi-objective bonus collection vehicle routing problem model is solved by the third-generation multi-objective non-dominated genetic algorithm, and the Pareto optimal solution set is output.

[0098] Among them, the third-generation multi-objective non-dominated genetic algorithm is an advanced multi-objective optimization algorithm that can solve the non-dominated optimal solution set (Pareto optimal solution) between multiple complex objectives and is widely used in complex optimization problems.

[0099] It should be noted that by solving the multi-objective bonus collection vehicle routing problem model, multiple Pareto optimal solution sets can be generated for selection, which meets the requirements of production stability and order priority, while improving resource utilization and customer satisfaction, and providing flexible and high-quality hot rolling batch planning solutions for actual production.

[0100] In a possible implementation, S5 specifically includes:

[0101] S501: Setting initial parameters of the third generation multi-objective non-dominated genetic algorithm, wherein the initial parameters specifically include: population size, maximum number of iterations, crossover rate and mutation rate.

[0102] S502: Based on the constraint conditions, the population is initialized using a bundle satisfaction strategy to obtain an initial population.

[0103] When solving the problem, due to the complex coupling relationship between multiple objectives of the hot rolling batch planning, a multi-objective algorithm is used to obtain the non-dominated optimal solution, and NSGA-III, which has better optimization capabilities in multi-objective dimensions, is used to solve the hot rolling batch planning problem with complex multi-objective coupling relationships.

[0104] In a possible implementation, S502 specifically includes:

[0105] S5021: In the population, select the candidate slab that meets the requirements of the largest rolling width and the highest surface grade as the first slab of the main rolling material planned for the rolling unit, and place it after the virtual slab No. 0.

[0106] Among them, the main rolled material is the core slab of each rolling unit in the hot rolling batch plan. As the starting slab of the rolling unit, it plays a leading role in the plan.

[0107] S5022: From the remaining slabs to be selected, select the slabs of the same steel grade that meet the constraints (9) to (13), and randomly select one of the three slabs of the same steel grade that meet the constraints and have the smallest sum of width, thickness and hardness penalties between them and the last slab of the currently scheduled rolling unit plan, and schedule it in the plan until the constraints (6) to (8) are not met or there are no slabs of the same steel grade to be scheduled.

[0108] S5023: When S5022 is terminated due to violation of constraint (6), a new rolling unit plan is established. When S5022 is terminated due to violation of constraint (7) to constraint (8) or no slabs of the same steel grade are available for selection, transition slabs and follow-up slabs are selected from different steel grades according to the steel grade transition constraint until constraint (6) to constraint (8) is violated or no slabs of the same steel grade are available for selection, so as to complete the first rolling unit. At this time, if the transition and the formulation of the first rolling unit cannot be completed while satisfying constraints (5) to constraints (14), the first rolling unit is abandoned and steps S5021-S5022 are repeated.

[0109] Among them, the transition slab is a slab that connects different steel grades or properties, which is used to reduce the impact of property jumps between adjacent slabs in the rolling unit on process stability. The follow-up slab is used to continue to build a new slab of the rolling unit after the transition slab to ensure that the rolling unit meets integrity and continuity.

[0110] S5024: Add virtual slab No. 0 to the last position of the first rolling unit and check whether the first rolling unit meets the constraints (1) to (5). If so, retain the first rolling unit and repeat steps S5021-S5023 to establish a second rolling unit until there are no more available slabs to be selected or the remaining slabs cannot form a new rolling unit. If not, abandon the first rolling unit and repeat steps S5021-S5023.

[0111] S5025: Determine whether the last rolling unit in the batch plan meets the constraint condition (5). If not, discard it. Then determine whether the batch plan meets the constraint condition (15). If so, complete the batch plan formulation and form the population individual gene by encoding the corresponding relationship between the slab and the gene. If not, adjust the rolling unit combination to meet the above conditions to form the rolling batch plan.

[0112] S5026: Repeat or parallelize steps S5021-S5025 according to the number of populations to obtain an initial population represented by multiple feasible rolling batch plans.

[0113] It should be noted that the constraint satisfaction strategy initializes the population to ensure the diversity and feasibility of the population, providing a high-quality initial solution for subsequent optimization. At the same time, it improves the solution efficiency of the algorithm and the actual executability of the plan, meeting the needs of multi-objective optimization.

[0114] S503: Evaluate the individuals in the initial population, determine the objective function value and constraint violation of the individuals, eliminate the individuals that violate the constraints, and increase the proportion of better individuals in the population to obtain a better population.

[0115] S504: The optimal population is used as the parent population, and a crossover operation and a two-stage mutation operation are performed to generate a child population.

[0116] In a possible implementation, the crossover operation specifically includes:

[0117] Two individuals are randomly selected from the population individuals representing the batch plan to perform a crossover operation, and the attributes of the gene segments to be crossed, namely the length and starting position of the slab group, are randomly determined.

[0118] Determine whether the connection positions of the two crossover individuals at the two ends of the exchanged slab group meet the constraints (9) to (13). If so, complete the crossover operation; otherwise, reselect the length and starting position of the slab group until the crossover operation is completed.

[0119] It should be noted that the crossover operation is the key link in generating a new population, which effectively increases the search direction in the population space and improves the algorithm's ability to quickly search and optimize. At the same time, the constraint satisfaction strategy ensures the feasibility of the solution and provides high-quality optimization results for the hot rolling plan.

[0120] In one possible implementation, the two-stage mutation operation specifically includes:

[0121] In random individuals, whether to mutate is determined according to the set mutation probability. If mutation occurs, the mutation point slab is randomly selected and confirmed.

[0122] The first phase mutation operation is specifically to determine whether there is a slab in the candidate pool that meets the constraints (9) to (13). If so, the mutation point slab is replaced with the slab in the candidate pool that meets the constraints. Otherwise, the second phase is entered.

[0123] The second stage mutation operation is specifically as follows: when there is a similar slab that meets the constraints (9) to (12) after the mutation point slab, the mutation point slab participates in the mutation as a similar slab group, and selects a rolling unit outside the mutation point in the hot rolling batch plan to find another group of similar slab groups that meet the constraints (9) to (12) with the mutation point slab for swapping. When there is no similar slab group, or there is no similar slab group in another rolling unit, no mutation is performed.

[0124] Determine whether the individuals after the first or second stage mutation meet the constraints (1) to (15). If so, complete the mutation operation; otherwise, reselect the mutation point slab for mutation operation.

[0125] It should be noted that the mutation operation effectively maintains the diversity of the population and improves the global optimization capability. At the same time, the constraint satisfaction strategy can ensure that the generated hot rolling batch plan is more in line with actual production needs and optimization goals.

[0126] S505: Fusing the parent population and the offspring population to generate a mixed population, and evaluating the individuals in the mixed population to determine the objective function value of the individuals.

[0127] S506: Using the objective function value, perform non-dominated sorting on the individuals of the mixed population to obtain individuals of different non-dominated levels.

[0128] It should be noted that non-dominated sorting of mixed populations can retain high-quality solutions in multi-objective optimization, ensure the trade-off between objectives, comprehensively evaluate the pros and cons of individuals, provide a diverse set of optimal solutions, and offer more feasible and efficient options for hot rolling batch planning.

[0129] S507: retaining individuals whose non-dominance levels are lower than a preset non-dominance level, and selecting the next generation population based on the reference point selection mechanism.

[0130] It should be noted that this step ensures that the diversity and balance of high-quality solutions are retained during the optimization process, effectively improves the uniformity of solution distribution, and provides a better Pareto frontier for multi-objective optimization, thereby improving the practical feasibility and flexibility of hot rolling batch planning.

[0131] S508: Repeat steps S503 to S507 until the maximum number of iterations is reached or the quality of the solution cannot be effectively improved.

[0132] S509: Output the Pareto optimal solution set.

[0133] In the present invention, starting from the initialization of the population, by generating the offspring population and merging the parent and offspring individuals, target evaluation, crossover and mutation operations are performed, and at the same time, fast non-dominated sorting and reference point selection are optimized based on constraint satisfaction to generate the next generation population. This process is iterated until the maximum number of iterations is reached or the termination condition is met, and finally the optimal solution set is output. This process ensures the population diversity and the global optimality of the solution, which helps to achieve multi-objective optimization needs.

[0134] S6: According to the preferences of hot rolling batch plan for different objectives, the optimal hot rolling batch plan is obtained in the Pareto optimal solution set.

[0135] Specifically, according to the preferences of hot rolling planners for different objectives, the optimal solution with target bias is obtained in the Pareto optimal solution set, and according to the correspondence between genes and slabs, the optimal solution is decoded into the optimal hot rolling batch plan output.

[0136] In the present invention, the close connection between hot rolling batch planning and upstream continuous casting process and downstream production orders is taken into consideration. By combining order matching with virtual slabs and inventory slabs, a slab pool for batch planning is established in combination with soft and hard constraint screening, which creates an efficient and reasonable basis for the formulation of batch plans, effectively improves the continuity of hot rolling processes in upstream and downstream, and provides support for the efficient operation of the overall process of the enterprise. The rolling batch planning problems are summarized and reasonably simplified, and a multi-objective bonus collection vehicle path model based on hot rolling batch planning is established. The model extracts the key constraints and more comprehensive evaluation goals in actual hot rolling production, and can effectively consider the complex coupling relationship between multiple goals. The algorithm sets multiple slab attribute jump penalty objective functions, fully considering the different effects of different slab attribute jumps on plan execution and process results, and taking into account the coordination problem between the optimal compilation of rolling units and the optimal batch plan. Objective functions are established for the rolling unit length and the total rolling length of the batch plan respectively. Taking into account the enterprise benefits and business strategy design, the delivery date and strategic customer priority bonus objective functions are set to improve the rationality of the rolling plan and the enterprise benefits from multiple angles. In solving the hot rolling batch planning problem, the algorithm uses NSGA-III to obtain the non-dominated optimal solution, and obtains a slab arrangement scheme that is more in line with the process constraints and planning goals in a higher dimension of multiple objectives. Taking into account the rule constraints of hot rolling batch planning and the characteristics of the VRP problem, initialization and crossover mutation operators that meet the characteristics of the problem are designed at the constraint satisfaction and path optimization levels. While ensuring the diversity of the population, the iteration efficiency of the population in path optimization is effectively improved, and the results of multi-objective optimal hot rolling batch planning are obtained more efficiently, which ultimately greatly reduces the pressure and intensity of the enterprise's production planning and dynamic scheduling work, and improves the enterprise's production efficiency and economic benefits.

[0137] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0138] In the present invention, the selection pool is determined according to the order requirements, which effectively improves the continuity of the hot rolling process in the upstream and downstream, and provides support for the efficient operation of the overall process of the enterprise. A multi-objective bonus collection vehicle path model is established, which can effectively consider the complex coupling relationship between multiple objectives and truly reflect the mutual influence of various objectives in actual production. By setting multiple objective functions and constraints, the rationality of the rolling plan and the enterprise benefits are improved from multiple angles. By adopting the third-generation multi-objective non-dominated genetic algorithm, a slab arrangement scheme that is more in line with process constraints and planning goals can be obtained at a higher dimension of multiple objectives, which realizes the efficient acquisition of multi-objective optimal hot rolling batch planning results, reduces the pressure and intensity of enterprise production plan formulation and dynamic scheduling, and improves the production efficiency and economic benefits of the enterprise.

[0139] Reference Manual Figure 4, showing a structural schematic diagram of a hot rolling batch planning system based on a multi-objective model provided by the present invention.

[0140] The present invention further provides a hot rolling batch planning system 20 based on a multi-objective model, which is applied to the above-mentioned hot rolling batch planning method based on a multi-objective model, comprising:

[0141] Processor 201.

[0142] The memory 202 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 201 , the method for preparing hot rolling batch planning based on a multi-objective model as described in the method embodiment is implemented.

[0143] The hot rolling batch planning system 20 based on the multi-objective model provided by the present invention can execute the above-mentioned hot rolling batch planning method based on the multi-objective model and achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0144] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0145] In the present invention, the selection pool is determined according to the order requirements, which effectively improves the continuity of the hot rolling process in the upstream and downstream, and provides support for the efficient operation of the overall process of the enterprise. A multi-objective bonus collection vehicle path model is established, which can effectively consider the complex coupling relationship between multiple objectives and truly reflect the mutual influence of various objectives in actual production. By setting multiple objective functions and constraints, the rationality of the rolling plan and the enterprise benefits are improved from multiple angles. By adopting the third-generation multi-objective non-dominated genetic algorithm, a slab arrangement scheme that is more in line with process constraints and planning goals can be obtained at a higher dimension of multiple objectives, which realizes the efficient acquisition of multi-objective optimal hot rolling batch planning results, reduces the pressure and intensity of enterprise production plan formulation and dynamic scheduling, and improves the production efficiency and economic benefits of the enterprise.

[0146] It should be understood that the processor in the embodiments of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0147] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0148] The above embodiments can be implemented in whole or in part through software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function according to the embodiments of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired method (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available media can be magnetic media (such as floppy disks, hard disks, tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0149] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0150] In this disclosure, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0151] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0152] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0153] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0154] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, and can be electrical, mechanical, or other forms.

[0155] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0156] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0157] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, and other media that can store program codes.

[0158] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for compiling hot rolling batch planning based on a multi-objective model as described in the method embodiment is implemented.

[0159] The computer-readable storage medium provided by the present invention can realize the steps and effects of the hot rolling batch planning method based on the multi-objective model of the above method embodiment. To avoid repetition, the present invention will not go into details.

[0160] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0161] In the present invention, the selection pool is determined according to the order requirements, which effectively improves the continuity of the hot rolling process in the upstream and downstream, and provides support for the efficient operation of the overall process of the enterprise. A multi-objective bonus collection vehicle path model is established, which can effectively consider the complex coupling relationship between multiple objectives and truly reflect the mutual influence of various objectives in actual production. By setting multiple objective functions and constraints, the rationality of the rolling plan and the enterprise benefits are improved from multiple angles. By adopting the third-generation multi-objective non-dominated genetic algorithm, a slab arrangement scheme that is more in line with process constraints and planning goals can be obtained at a higher dimension of multiple objectives, which realizes the efficient acquisition of multi-objective optimal hot rolling batch planning results, reduces the pressure and intensity of enterprise production plan formulation and dynamic scheduling, and improves the production efficiency and economic benefits of the enterprise.

[0162] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

[0163] There are a few points to note:

[0164] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention. Other structures may refer to conventional designs.

[0165] (2) For the sake of clarity, the thickness of layers or regions in the drawings used to describe the embodiments of the present invention are exaggerated or reduced, that is, these drawings are not drawn to scale. It is understood that when an element such as a layer, film, region, or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or intervening elements may be present.

[0166] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to form new embodiments.

[0167] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A hot rolling batch planning method based on a multi-objective model, characterized in that: include: S1: Get order requirements; S2: Determine the pool to be selected based on the order requirements; S3: Based on the candidate pool, construct a multi-objective bonus collection vehicle routing problem model; S4: With the goal of minimizing the attribute jump penalty between adjacent slabs and maximizing the delivery matching bonus, customer priority bonus, total rolling mileage, and rolling unit mileage uniformity, the objective function and constraints of the multi-objective bonus collection vehicle routing problem model are established; S5: Under the constraints of the constraints, with the goal of minimizing the objective function, solving the multi-objective bonus collection vehicle routing problem model by a third-generation multi-objective non-dominated genetic algorithm, and outputting a Pareto optimal solution set; S6: According to the preferences of the hot rolling batch plan for different objectives, an optimal hot rolling batch plan is obtained in the Pareto optimal solution set.

2. The hot rolling batch planning method based on the multi-objective model according to claim 1 is characterized in that: The S2 specifically includes: S201: Forming a production plan based on the order requirements; S202: Divide the production plan into order piece plans; S203: Determine hard constraints and soft constraints of slab demand; S204: determining slabs to be selected from the inventory slabs and virtual slabs according to the order piece schedule and in combination with the hard constraints and the soft constraints, and forming a slab pool from the slabs to be selected; S205: Dividing the slab pool according to the types of the slabs to be selected to determine a pool to be selected; The types of slabs to be selected include hot rolled materials, tail materials, main rolled materials and transition materials.

3. The hot rolling batch planning method based on the multi-objective model according to claim 2 is characterized in that: The hard constraints specifically include: steel type requirements, width range, thickness range, steel grade, surface quality and hardness range of the slab; The soft constraints specifically include: delivery priority and slab inventory time.

4. The method for hot rolling batch planning based on a multi-objective model according to claim 1, characterized in that: The objective function is specifically: Among them, min means minimization, F1 means minimizing the width jump penalty value between adjacent candidate slabs, represents the rolling width between candidate slab i and candidate slab j, F2 represents the minimum thickness jump penalty value of adjacent candidate slabs, represents the thickness jump penalty value between candidate slab i and candidate slab j, F3 represents the hardness jump penalty value that minimizes the adjacent candidate slabs, represents the hardness jump penalty value between candidate slab i and candidate slab j, F4 represents the minimum steel grade component jump penalty value between adjacent candidate slabs, represents the penalty value of steel grade composition jump between candidate slab i and candidate slab j, F5 represents the maximum delivery time bonus, Pd i represents the delivery bonus value of slab i, F6 represents the maximum matching strategic customer delivery priority bonus, Pp i represents the order priority bonus value of slab i, F7 represents the total rolling mileage of the maximized hot rolling batch plan, M all Indicates the total rolling mileage of batch rolling, M k represents the kth rolling unit mileage in the batch rolling plan, F8 represents the minimum standard deviation of the rolling mileage of the rolling unit in the batch plan, M avg represents the average rolling mileage of the rolling unit plan in the batch rolling plan, x ijk represents the decision variables of the selected slab i and the selected slab j in the rolling unit k, y ik represents the decision variable of the selected slab i in the rolling unit k. When x ijk = 1, in rolling unit k, the selected slab i is produced immediately after the selected slab j. ijk =0,y ik When =1, the slab i to be selected is in the rolling unit k, V represents the numbered set of the slabs to be selected, V={1,,n}, i=0,1,,n, j=1,2,...,n, i≠j, i=0 represents the virtual slab, n represents the total number of slabs to be selected, k=1,2,,m, m represents the total number of rolling units in the batch rolling plan.

5. The method for hot rolling batch planning based on a multi-objective model according to claim 4, characterized in that: The constraints specifically include: Slab allocation constraints: Virtual slab starting point constraints: and 0k =1,k∈K (2) Continuity constraints: Prevent loop constraints: Minimum rolling length constraints: Maximum rolling length constraints: Constraints for rolling slabs of the same width: ∑l i ≤Lsw,i∈Vsw ik ,k∈K (7) Constraints for slab rolling of the same steel grade: ∑l i ≤Lsg b ,i∈Vsg ik ,k∈K (8) Width jump constraints: 0≤(w i -w j )x ijk ≤W,i,j∈V,k∈K (9) Thickness jump constraints: |th i -th j |x ijk Th,i,j∈V,k∈K (10) Hardness jump constraints: |hd i -hd j |x ijk Hd,i,j∈V,k∈K (11) Attribute continuity constraints: (w i -w j )·|th i -th j |·|hd i -hd j |x ijk =0,i,j∈V,k∈K (12) Temperature jump constraints: |foot i -Foot j |x ijk Foot,i,j∈V,k∈K (13) Steel grade transition constraints: (c i -c j )x ijk =0(c i -c j )|hd i -hd j |x ijk =0>|hd i -hd j |x ijk ≠0,i,j∈V,k∈K (14) Minimum rolling length constraints: Among them, l i Indicates the length of the selected slab i, M min and M max They represent the minimum and maximum lengths of the rolling unit, Lsw represents the maximum continuous rolling length of the selected slab with the same width, and Vsw ik Vsg represents the set of slabs with the same width as the slab i in rolling unit k, ik Lsg represents the set of candidate slabs with the same surface grade as the candidate slab i in the k-th rolling unit plan, b Indicates the maximum rolling mileage specified in the rolling constraint of the selected slab with surface grade b within the specified rolling length, Vsg ik represents the set of slabs with the same surface grade as slab i in the kth rolling unit plan, wi and wj represent the widths of slab i and selected slab j respectively, W represents the maximum jump value of the width of the selected slab, and th i and th j They represent the thickness of the selected slab i and the selected slab j respectively, Th represents the maximum jump value of the thickness of the selected slab, hd i and hd j They represent the hardness of the selected slab i and the selected slab j respectively, Hd represents the maximum hardness jump of the selected slab, fot i and fot j They represent the out-of-furnace temperatures of the selected slab i and the selected slab j, Fot represents the maximum jump value of the out-of-furnace temperature of the selected slab, c i and c j Respectively represent the steel composition of the selected slab i and the selected slab j, V k Indicates the number of slabs to be selected in rolling unit k, BPM min Indicates the minimum rolling length of hot rolling batch plan.

6. The method for hot rolling batch planning based on a multi-objective model according to claim 5, characterized in that: The S5 specifically includes: S501: Setting initial parameters of the third-generation multi-objective non-dominated genetic algorithm, wherein the initial parameters specifically include: population size, maximum number of iterations, crossover rate, and mutation rate; S502: Based on the constraint conditions, the population is initialized using a constraint satisfaction strategy to obtain an initial population; S503: Evaluate the individuals in the initial population, determine the objective function values and constraint violation conditions of the individuals, remove the individuals that violate the constraints, and increase the proportion of better individuals in the population to obtain a better population; S504: Using the selected population as the parent population, performing a crossover operation and a two-stage mutation operation to generate a child population. S505: Fusing the parent population and the offspring population to generate a mixed population, and evaluating individuals in the mixed population to determine the objective function value of the individual; S506: Using the objective function value, perform non-dominated sorting on the individuals of the mixed population to obtain individuals of different non-dominated levels; S507: retaining individuals whose non-dominance levels are lower than the preset non-dominance levels, and selecting the next generation population based on the reference point selection mechanism; S508: Repeat steps S503 to S507 until the maximum number of iterations is reached or the quality of the solution cannot be effectively improved; S509: Output the Pareto optimal solution set.

7. The method for hot rolling batch planning based on a multi-objective model according to claim 6, characterized in that: The S502 specifically includes: S5021: Select the candidate slab that meets the requirements of the largest rolling width and the highest surface grade in the population as the first slab of the main rolling material planned for the rolling unit, and place it after the virtual slab No. 0; S5022: Select the same steel grade slabs that meet the constraints (9) to (13) from the remaining slabs to be selected, and randomly select one of the three slabs to be selected that has the smallest sum of width, thickness, and hardness penalties between the last slab in the current rolling unit plan and the remaining slabs to be selected, and place it in the plan until the constraints (6) to (8) are not met or there are no slabs of the same steel grade to be selected; S5023: When S5022 is terminated due to violation of constraint (6), a new rolling unit plan is established. When S5022 is terminated due to violation of constraint (7), constraint (8) or no slabs of the same steel grade are available for selection, transition slabs and subsequent slabs are selected from different steel grades according to the steel grade transition constraint until constraints (6) to (8) are violated or no slabs of the same steel grade are available for selection, so as to complete the first rolling unit. At this time, if the transition and the first rolling unit cannot be completed while satisfying constraints (5) to (14), the first rolling unit is abandoned and steps S5021-S5022 are repeated. S5024: Add virtual slab No. 0 to the last position of the first rolling unit, and check whether the first rolling unit meets the constraints (1) to (5); if so, retain the first rolling unit and repeat steps S5021-S5023 to establish subsequent rolling units until there is no accessible slab to be selected or the remaining slabs to be selected cannot form a new rolling unit; if not, abandon the first rolling unit and repeat steps S5021-S5023; S5025: Determine whether the last rolling unit in the batch plan meets the constraint condition (5). If not, discard it and determine whether the batch plan meets the constraint condition (15). If so, complete the batch plan formulation and form the population individual gene through the corresponding relationship between the slab and the gene encoding; if not, adjust the rolling unit combination to meet the above conditions to form the rolling batch plan; S5026: Repeat or parallelize steps S5021-S5025 according to the number of populations to obtain an initial population represented by multiple feasible rolling batch plans.

8. The method for hot rolling batch planning based on a multi-objective model according to claim 6, characterized in that: The crossover operation specifically includes: Randomly selecting two individuals from the population individuals representing the batch plan to perform a crossover operation, and randomly determining the attributes of the gene segments to be crossed, namely, the length and starting position of the slab group; Determine whether the connection positions of the two crossover individuals at the two ends of the exchanged slab group meet the constraints (9) to (13); if so, complete the crossover operation; otherwise, reselect the length and starting position of the slab group until the crossover operation is completed.

9. The method for hot rolling batch planning based on a multi-objective model according to claim 6, characterized in that: The two-stage mutation operation specifically includes: Selecting whether to mutate among the random individuals according to a set mutation probability, and if mutation occurs, randomly selecting and confirming the mutation point slab; The first stage mutation operation is specifically as follows: determine whether there is a slab in the candidate pool that meets the constraints (9) to (13); if so, replace the mutation point slab with the slab in the candidate pool that meets the constraints; otherwise, enter the second stage; The second stage mutation operation is specifically as follows: when there is a similar slab that meets the constraints (9) to (12) after the mutation point slab, the mutation point slab is used as a similar slab group to participate in the mutation, and a rolling unit outside the mutation point is selected in the hot rolling batch plan to find another similar slab group that meets the constraints (9) to (12) with the mutation point slab to perform the swap operation; when there is no similar slab group, or there is no similar slab group in another rolling unit, no mutation is performed; Determine whether the individual after mutation in the first stage or the second stage meets the constraints (1) to (15); if so, complete the mutation operation; otherwise, reselect the mutation point slab for mutation operation.

10. A hot rolling batch planning system based on a multi-objective model, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method for preparing hot rolling batch plan based on a multi-objective model according to any one of claims 1 to 9 is implemented.

Images