A forging furnace charging scheduling method and system based on multi-objective optimization

Abstract

The application provides a kind of based on multi-objective optimization's forging furnace charging scheduling method and system, belong to the field of forging production scheduling.The method includes: obtaining the basic information and operating information of forging billet heating furnace;Obtain the basic information and heating process of the group of to-be-processed forging billets, and number the group of forging billets;The constraint condition of forging furnace charging is constructed;And constraint condition includes furnace capacity constraint, temperature compatibility constraint, holding time compatibility constraint and space filling constraint;With the group of forging billets as the basic scheduling unit, a multi-objective optimization function model is constructed;The multi-objective optimization function model includes minimizing the total number of heating furnace processing batches, minimizing the total working time of heating furnace, minimizing the average holding temperature of heating furnace processing batches;Based on the basic information and operating information of heating furnace, the basic information and heating process of the group of forging billets, combined with constraint condition and multi-objective optimization function model, the generation and iterative optimization of scheduling scheme are carried out.The application improves the feasibility and optimization effect of scheduling scheme.

Description

Technical Field

[0001] This invention belongs to the field of forging production scheduling, specifically relating to a forging furnace loading scheduling method and system based on multi-objective optimization. Background Technology

[0002] With the continuous improvement of manufacturing technology, higher requirements are being placed on energy efficiency, rationality of production organization, and degree of automation in the production process. Steel forging, as a crucial link in the steel manufacturing process, has a significant impact on overall manufacturing costs and energy consumption due to its production efficiency and energy consumption levels. Forging includes various methods such as hot forging, warm forging, and cold forging; among them, hot forging materials have good plasticity and are easy to form, and the process generally includes heating, forging forming, and heat treatment. The heating process is used to raise the temperature of the forging billet to above the recrystallization temperature of steel, and it is a key step in the forging production process, accounting for a large proportion of both the production cycle and energy consumption. Therefore, the rational optimization of the forging furnace loading scheduling process has significant engineering application value.

[0003] In the existing technology, various scheduling modeling and optimization methods have been proposed for the scheduling problem of forging billet heating furnaces. However, most of the existing methods are based on simplified production scenarios and still have certain limitations in practical applications. For example, in the construction of the forging billet charging scheduling model, some existing methods mainly focus on macroscopic constraints such as the furnace volume, lacking consideration of the dynamic changes in the remaining space in the furnace chamber during the billet charging process. This leads to problems such as space conflicts, unreasonable charging sequences, or unusable local remaining space during actual charging. In such cases, manual adjustments by operators based on experience are often required, increasing the difficulty of production organization and resulting in poor consistency of scheduling results. In addition, some existing scheduling methods use a single workpiece as the basic scheduling unit, which is difficult to adapt to the forging production mode characterized by the mixed production of multiple sets of forging billets. Summary of the Invention

[0004] To address the aforementioned issues, this invention provides a forging furnace loading scheduling method and system based on multi-objective optimization. Improvements are made in aspects such as furnace billet loading constraints, batch processing adaptability of multiple billet groups, multi-objective optimization expression, and solution algorithm adaptability, thereby enhancing the feasibility and optimization effect of the scheduling scheme and meeting the application requirements of actual forging production processes.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of the present invention are as follows: In a first aspect, embodiments of the present invention provide a forging furnace charging scheduling method based on multi-objective optimization, the method comprising: Obtain basic information about the forging furnace and collect its operating information. Obtain the basic information and heating process of the forging billet group to be processed, and number the forging billet group; Establish constraints for forging furnace loading; the constraints include furnace volume constraints, temperature compatibility constraints, holding time compatibility constraints, and space loading constraints. A multi-objective optimization function model is constructed using the forging billet group as the basic scheduling unit. The multi-objective optimization function model includes minimizing the total number of processing batches in the heating furnace, minimizing the total working time of the heating furnace, and minimizing the average holding temperature of the processing batches in the heating furnace. Based on the basic information of the heating furnace, its operation information, the basic information of the forging billet group, and the heating process, combined with constraints and a multi-objective optimization function model, a genetic algorithm based on similarity adaptive improvement is used to generate and iteratively optimize the scheduling scheme.

[0006] In a preferred embodiment of the present invention, the basic information of the heating furnace includes parameters such as heating furnace number, rated furnace capacity, effective heating space size, and heating efficiency; wherein, the effective heating space size includes the effective heating space width, height, and depth; and the rated furnace capacity refers to the maximum allowable furnace loading capacity.

[0007] In a preferred embodiment of the present invention, the basic information of the forging billet group includes the type, size and quantity of the forging billet group; the heating process includes the processing path, heating temperature, heating time, holding temperature range and holding time range.

[0008] In a preferred embodiment of the present invention, the furnace volume constraint, temperature compatibility constraint, and holding time compatibility constraint are used to determine whether the forging billets can be combined into the same processing batch for processing.

[0009] In a preferred embodiment of the present invention, the furnace capacity constraint means that the total mass of all forgings in the current heating furnace must not exceed the rated furnace capacity, expressed as: (1) In equation (1), The total mass of the forged billets in batch b of furnace processing. For the capacity of the heating furnace, It represents the number of batches processed in the heating furnace; The temperature compatibility constraint requires that the holding temperature ranges of all forgings within the same batch of processing in the same furnace must overlap to ensure temperature compatibility. The expression is: (2) In equation (2), Let J be the holding temperature range of the j-th forging billet in the b-th batch of processing. The intersection of the holding temperature ranges of forging billets in the same batch is non-empty, which means that the temperature compatibility requirement is met. The heat preservation time compatibility constraint requires that the heat preservation time intervals of all forgings within the same batch of processing in the same furnace must overlap to ensure time compatibility. The expression is: (3) In equation (3), Let J be the holding time interval for the j-th forging billet in the b-th batch of processing. The intersection of the holding time intervals for forging billets in the same batch is non-empty, which means that the time compatibility requirement is met.

[0010] In a preferred embodiment of the present invention, the space filling constraint is used to determine whether the forging billet group can be loaded into the heating furnace under the condition of meeting the process constraints, and to determine the filling position of the forging billet in the effective space of the heating furnace when it can be loaded.

[0011] In a preferred embodiment of the present invention, based on spatial filling constraints, determining whether the forging billet group can be loaded into the heating furnace under the condition of meeting process constraints includes the following steps: Step S301: Establish a three-dimensional coordinate system with respect to the length, width and height of the effective heating space of the heating furnace, and calculate the maximum number of layers that the heating furnace can be filled with. Step S302: Sort the forging billet groups in the same batch of furnace processing according to their size from largest to smallest, calculate the number of layers required for the forging billet group considering the interlayer spacing and transverse spacing, and compare it with the maximum number of layers allowed to be filled in the heating furnace. Step S303: Under the premise that each group of forging billets can be filled, the filling space is constructed layer by layer to complete the initialization of the filling layer; Step S304: Set a length difference threshold in the length direction; load the forging billet, and divide the planar space in a single layer using the main segmentation method. When the length difference between adjacent forging billets exceeds the preset threshold, switch to the secondary segmentation method. Step S305: In the current layer, after each forging billet is loaded, the remaining loading space and the current layer height information are updated in real time. Step S306: Set the remaining height threshold; determine whether the current layer height information meets the remaining height constraint of the heating furnace; if yes, proceed to step S304 to continue filling; if no, determine that the furnace processing batch cannot complete the current forging billet assembly and filling.

[0012] As a preferred embodiment of the present invention, the formula for the model of minimizing the total number of processing batches in the heating furnace is as follows: (7) In equation (7), k is the total number of heating furnace processing batches required to complete all the forging blanks; The model for minimizing the total operating time of the heating furnace is as follows: (8) and, (9) (10) In equations (8) to (10), Total completion time It refers to the number of batches processed in the furnace; For furnace processing batches Heating time, For furnace processing batches Insulation time, This represents the total working time for a single furnace batch; m is the total number of forgings in that batch. Forging billet Forging time, This indicates the additional holding time for a single batch of processing in a furnace, which is the first batch of processing time in that batch. Forging time of each forging billet; The model for minimizing the average holding temperature of a batch processed in the heating furnace is expressed as follows: (11) and (12) In equations (11) to (12), This indicates the average holding temperature across all processing batches. The holding temperature for batch b is taken as the average value of the holding temperature range for all batches processed in the furnace. , These are the minimum and maximum values ​​of the holding temperature range for batch b of furnace processing, respectively. This refers to the total number of batches processed in the furnace.

[0013] As a preferred embodiment of the present invention, when using a similarity-adaptive improved genetic algorithm to generate and iteratively optimize the scheduling scheme, the specific steps include: Step S501, Parameter Initialization: Complete the setting of algorithm running parameters and establish an external archive pool to store non-dominant high-quality individuals; Step S502, Encoding and Decoding and Population Initialization: Obtain information on the forging billet group to be processed, heating furnace equipment information and process parameters, represent the allocation relationship between the forging billet group and the batch based on the batch encoding method, and construct the initial population using a hybrid heuristic method in combination with furnace capacity constraints, temperature compatibility constraints, holding time compatibility constraints and space filling constraints; Step S503, Population stratification and archive pool update: Based on the established multi-objective optimization function, the objective function value is calculated for each individual in the population, and the individuals in the population are sorted by non-dominated order based on the objective function value to obtain individuals of different non-dominated levels; the individuals of the first non-dominated level are compared with the individuals in the external archive pool, and the external archive pool is updated according to the dominance relationship and crowding distance. Step S504, Select crossover mutation individuals: Select one individual from both the optimized scheduling scheme group and the normal scheduling scheme group; Step S505, Adaptive parameter adjustment: Calculate the architecture similarity between the two selected scheduling schemes, and adaptively adjust the mutation probability, crossover step size and variable asynchronous length based on the similarity results; Step S506, Crossover and Mutation Operation: Based on the adjusted genetic operator parameters, perform crossover and mutation operations on the two selected parent individuals to generate offspring individuals; Step S507, New Population Generation and Archive Pool Update: Merge the current parent and offspring populations to obtain a mixed population; calculate the objective function value for each individual in the mixed population, and perform non-dominated sorting and crowding distance calculation based on the objective function value to obtain individuals with different non-dominated levels; update high-quality individuals that satisfy the non-dominated relationship and have good distribution to the external archive pool according to the non-dominated sorting results and crowding distance; at the same time, prioritize individuals with lower non-dominated levels and larger crowding distances to form a new generation population; Step S508, Iteration Termination and Result Output: Determine whether the current iteration count has reached the preset maximum iteration count, or whether the non-dominated solution set in the external archive pool has not been significantly updated within several consecutive generations; if not, repeat the above steps; if yes, select the scheduling scheme that meets the actual production needs from the external archive pool as the final forging billet group furnace scheduling scheme output.

[0014] Secondly, embodiments of the present invention also provide a forging furnace charging scheduling system based on multi-objective optimization. The system includes a heating furnace information acquisition module, an order information acquisition module, a constraint condition construction module, a multi-objective optimization function construction module, a scheme optimization module, and a scheduling scheme output module; wherein... The heating furnace information acquisition module is used to acquire basic information about the forging furnace and to collect the furnace's operating information. The order information collection module is used to obtain the basic information and heating process of the forging billet group to be processed, and to number the forging billet group; The constraint construction module is used to construct the constraints for forging furnace loading; the constraints include furnace volume constraints, temperature compatibility constraints, holding time compatibility constraints, and space loading constraints. The multi-objective optimization function construction module is used to construct a multi-objective optimization function model with the forging billet group as the basic scheduling unit; the multi-objective optimization function model includes minimizing the total number of processing batches in the heating furnace, minimizing the total working time of the heating furnace, and minimizing the average holding temperature of the processing batches in the heating furnace. The scheme optimization module is used to generate and iteratively optimize the scheduling scheme based on the basic information of the heating furnace, the operation information, the basic information of the forging billet group and the heating process, combined with the constraints and the multi-objective optimization function model, using a similarity-adaptive improved genetic algorithm. The scheduling scheme output module is used to output the optimized scheduling scheme.

[0015] The solutions of the embodiments of the present invention have the following beneficial effects: The forging furnace scheduling method and system based on multi-objective optimization provided in this invention comprehensively considers production influencing factors, avoids deviations caused by single-objective optimization, and improves the rationality of the scheduling scheme. It considers complex production constraints, allowing temperature, time, and space constraints to participate in the batch formation process, thus improving the rationality of the furnace grouping scheme. Addressing the complex spatial constraints of the heating furnace, a dynamic updating and judgment method for the forging billet filling space of the heating furnace is proposed. By dynamically updating the fillable area, the space for forging billets can be made spatially executable for filling, improving the executability of the scheduling scheme in actual production and the utilization rate of the heating furnace space. Using a similarity-based adaptive improved genetic algorithm, under the condition of satisfying constraints, the established multi-objective scheduling model can be solved more efficiently to obtain a forging billet scheduling scheme that better conforms to process constraints and scheduling objectives. In summary, the method of this invention can improve the rationality and executability of forging production scheduling, which is conducive to reducing worker intervention, reducing the workload and intensity of enterprise production scheduling, and improving the production efficiency and economic benefits of enterprises.

[0016] Of course, implementing any product or method of the present invention does not necessarily require achieving all of the advantages described above at the same time. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the forging furnace scheduling method based on multi-objective optimization as described in an embodiment of the present invention; Figure 2 This is a schematic diagram of the heating process of the forging billet in the heating furnace provided in an embodiment of the present invention; Figure 3This is a schematic diagram of the method for determining the furnace loading space of forging billets in an embodiment of the present invention; Figure 4 This is the chromosome coding scheme in the embodiments of the present invention; Figure 5 This is a flowchart of the similarity-adaptive improved genetic algorithm in an embodiment of the present invention; Figure 6 This is a flowchart of the hybrid heuristic algorithm in an embodiment of the present invention; Figure 7 This is a schematic diagram of the cross operation in an embodiment of the present invention; Figure 8 This is a schematic diagram of the mutation operation in an embodiment of the present invention; Figure 9 This is a schematic diagram comparing the total number of processing batches of the heating furnace according to an embodiment of the present invention; Figure 10 This is a schematic diagram comparing the total working time of the heating furnace according to an embodiment of the present invention. Figure 11 This is a schematic diagram showing the comparison curves of the average holding temperature results of the heating furnace processing batches according to an embodiment of the present invention. Detailed Implementation

[0019] After discovering the aforementioned problems, the inventors of this application conducted a detailed study on the existing forging furnace loading scheduling process. The study found that in forging furnace loading scheduling, in addition to macroscopic constraints such as the furnace capacity, it is also necessary to consider the changes in the internal space and layout constraints of the furnace during the billet loading process. This allows the generated scheme to directly realize furnace loading without manual adjustment. Simultaneously, the generated scheme improves the utilization rate of the furnace space, thereby increasing production efficiency and saving energy consumption. Furthermore, when multiple sets of billets are produced in a mixed manner, each set typically contains several billets of the same specifications but varying quantities. The billets within a set must be processed as a whole and cannot be separated. In this case, if a single workpiece is still used as the basic scheduling unit, it can easily lead to unreasonable combinations of billet specifications within the furnace, thus affecting the efficiency of subsequent forging and logistics processes.

[0020] Meanwhile, in solving multi-objective scheduling problems, existing methods often transform multiple optimization objectives into a single objective through weighted summation. However, the objectives involved in furnace scheduling, such as completion time, number of processing batches, and heating temperature, typically have complex coupling relationships. Simple single-objective processing cannot fully reflect actual production needs and can easily lead to scheduling results deviating from the engineering application objectives. Furthermore, although intelligent optimization methods such as genetic algorithms have been introduced into solving scheduling problems, traditional algorithms still suffer from slow convergence speed and unstable solution set quality when faced with complex constraints and large solution space in forging billet furnace loading scheduling. Targeted improvements are needed based on specific application scenarios.

[0021] It should be noted that the defects in the above-mentioned prior art solutions are all results obtained by the inventors after practice and careful research. Therefore, the discovery process of the above problems and the solutions proposed by the embodiments of the present invention in the following text should be considered as contributions made by the inventors to the present invention.

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. It should be noted that, without conflict, the embodiments and features in the embodiments of the present invention can also be combined with each other.

[0023] It should be noted that similar reference numerals and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In the description of the embodiments of the present invention, the terms "first," "second," "third," "fourth," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance. In addition, sometimes a subscript such as W1 may be written in a non-subscript form such as W1, and their meanings are consistent unless the distinction is emphasized.

[0024] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0025] Following the above in-depth analysis, this invention provides a multi-objective optimization-based forging furnace loading scheduling method and system. Here, "furnace loading" refers to a billet heating furnace, typically a bogie-type heating furnace. Based on the obtained heating furnace equipment parameters and billet order information, this invention constructs a multi-objective scheduling model with heating furnace operating time, batch quantity, and average holding temperature per batch as optimization objectives. The scheduling scheme is constrained and controlled by actual production constraints such as furnace capacity, temperature, time, and space loading. To address the spatial complexity of the bogie-type heating furnace loading process, a billet loading judgment method is proposed to ensure the executability of the scheduling results in actual production. Furthermore, an adaptive improved genetic algorithm based on similarity is proposed to solve the multi-objective scheduling model, improving the quality and speed of billet grouping furnace scheduling optimization. This invention can effectively obtain high-quality bogie-type heating furnace billet grouping furnace scheduling schemes, improve heating furnace space utilization, shorten production cycles, reduce the average operating temperature of the heating furnace to reduce energy consumption, and effectively improve the capacity and efficiency of the forging workshop.

[0026] like Figure 1 As shown, the forging furnace scheduling method based on multi-objective optimization includes the following steps: Step S1: Obtain basic information about the forging furnace and collect its operating information.

[0027] In this step, the basic information of the heating furnace includes parameters such as the heating furnace number, rated furnace capacity, effective heating space dimensions, and heating efficiency; wherein, the effective heating space dimensions include the effective heating space width, height, and depth; and the rated furnace capacity refers to the maximum allowable furnace loading capacity.

[0028] The operational information includes the furnace's historical operating time, furnace availability time, and fault status information.

[0029] Step S2: Obtain the basic information and heating process of the forging billet group to be processed, and number the forging billet group.

[0030] In this step, the basic information of the forging billet group includes the type, size, and quantity of the forging billets. The heating process includes process parameters such as processing path, heating temperature, heating time, holding temperature range, and holding time range.

[0031] Step S3: Construct the constraints for forging furnace loading; the constraints include furnace volume constraints, temperature compatibility constraints, holding time compatibility constraints, and space loading constraints.

[0032] In this step, the furnace capacity constraint, temperature compatibility constraint, and holding time compatibility constraint are used to determine whether the forging billets can be combined into the same processing batch for processing; the space filling constraint is used to determine whether the forging billet group can be loaded into the heating furnace under the condition of meeting the process constraints, and to determine the filling position of the forging billets in the effective space of the heating furnace when loading is possible.

[0033] The furnace capacity constraint means that the total mass of all forgings currently in the heating furnace must not exceed the rated furnace capacity, expressed as: (1) In equation (1), The total mass of the forged billets in batch b of furnace processing. For the capacity of the heating furnace, It represents the number of batches processed in the heating furnace.

[0034] The temperature compatibility constraint requires that the holding temperature ranges of all forgings within the same batch of processing in the same furnace must overlap to ensure temperature compatibility. The expression is: (2) In equation (2), Let J be the holding temperature range for the j-th forging billet in the b-th batch of processing. The intersection of the holding temperature ranges for forging billets in the same batch is non-empty, which means that the temperature compatibility requirements are met.

[0035] The heat preservation time compatibility constraint requires that the heat preservation time intervals of all forgings within the same batch of processing in the same furnace must overlap to ensure time compatibility. The expression is: (3) In equation (3), Let J be the holding time interval for the j-th forging billet in the b-th batch of processing. The intersection of the holding time intervals for forging billets in the same batch is non-empty, which means that the time compatibility requirement is met.

[0036] The spatial loading constraints refer to the specific requirements of the trolley-type heating furnace for loading forging billets in the same batch: the loading direction is consistent with the length direction of the heating furnace, a layered placement pattern is adopted, layers are separated by shims, and a certain interval must be reserved between transverse forging billets within the same layer. Although this loading method sacrifices some space, it can improve heating efficiency and temperature uniformity, while reserving gaps to facilitate subsequent robotic arm grasping of forging billets.

[0037] In one executable embodiment, based on spatial filling constraints, determining whether the forging billet group can be loaded into the heating furnace under the condition of satisfying process constraints includes the following steps: Step S301: Establish a three-dimensional coordinate system with respect to the length, width and height of the effective heating space of the heating furnace, and calculate the maximum number of layers that the heating furnace can be filled with. Step S302: Sort the forging billet groups in the same batch of furnace processing according to their size from largest to smallest, calculate the number of layers required for the forging billet group considering the interlayer spacing and transverse spacing, and compare it with the maximum number of layers allowed to be filled in the heating furnace. Step S303: Under the premise that each group of forging billets can be filled, the filling space is constructed layer by layer to complete the initialization of the filling layer; Step S304: Set a length difference threshold in the length direction; load the forging billet, and divide the planar space in a single layer using the main segmentation method. When the length difference between adjacent forging billets exceeds the preset threshold, switch to the secondary segmentation method. Step S305: In the current layer, after each forging billet is loaded, the remaining loading space and the current layer height information are updated in real time. Step S306: Set the remaining height threshold; determine whether the current layer height information meets the remaining height constraint of the heating furnace; if yes, proceed to step S304 to continue filling; if no, determine that the current forging batch cannot complete the current forging billet assembly and filling.

[0038] In one feasible implementation, the process of determining whether the forging billet group can be loaded into the heating furnace under the condition of meeting process constraints is as follows: Coordinate system establishment: A three-dimensional coordinate system is established with the length, width, and height of the effective heating space of the heating furnace as the x, y, and z axes, respectively.

[0039] Forging billet sorting and feasibility prediction of single-group forging billet loading: For n groups of forging billets allocated to the same heating furnace processing batch, sort them from largest to smallest according to the length and width of the forging billets; determine whether each group of forging billets has the space feasibility to be loaded into the heating furnace alone without considering loading with other forging billets, specifically including the calculation of the maximum number of loading layers, single layer capacity and required number of loading layers; Maximum number of layers: The maximum number of layers of this type of forging billet that can be placed in the height direction of the heating furnace.

[0040] (4)

[0041] In equation (4), The effective heating space height of the heating furnace, Forging billet high, The height of the gap between layers. This represents the maximum number of layers.

[0042] Single-layer filling capacity calculation: Multiply the quantity that can be placed in the width direction of the heating furnace by the quantity that can be placed in the length direction.

[0043] (5)

[0044] In equation (5), The effective heating space width and length of the heating furnace, Forging billet Width and length, This refers to the required spacing between the forging blanks in the width and length directions. It is a single layer that can accommodate forging billets The capacity.

[0045] Required number of filling layers calculation: The minimum number of layers required to accommodate this group of forgings.

[0046] (6)

[0047] In equation (6), For the first The number of forged billets The number of layers required to fill the i-th group of forging billets.

[0048] If the required number of layers is greater than the maximum number of layers, that is This group exceeds the volume of the heating furnace.

[0049] Filling layer initialization: After assessing the feasibility of single-assembly filling, the filling layer is established. The initial length of the layer and width These are respectively equal to the length and width of the effective heating space of the heating furnace, and the floor height. The data is updated in real time based on the height of the forging billet added during the loading process.

[0050] Spatial Division and Forging Billet Loading: During the loading process, a spatial division strategy combining primary and secondary division methods is adopted for the current loading plane. Let the dimensions of the current loading plane be... Forging billet to be loaded Size is When the forging billet When it can be placed into the filling plane: the specific method of primary and secondary segmentation is as follows: Main Segmentation Method: Prioritizing the width direction of the heating furnace for loading, the loading plane is divided along the width direction based on the diagonal coordinates of the forging billet, thus dividing the loading plane into... and Two subplanes, such as Figure 2 As shown in (a); Secondary segmentation method: Taking the length of the heating furnace as the segmentation direction, the forging blank is segmented along the length direction according to the diagonal coordinates, dividing the filling plane into... and Two subplanes, such as Figure 2 As shown in (b); During the filling process, the primary segmentation method is used first. When the dimensional difference in the length direction between the forged billet to be filled and the previously filled forged billet exceeds a preset threshold, it is determined that the dimensional difference is too large. At this time, the secondary segmentation method is switched to perform spatial segmentation, and then the primary segmentation method is used again for filling. The filling result using only the primary segmentation method is as follows: Figure 2 As shown in (c), the filling result using a combination of primary and secondary segmentation is as follows: Figure 2 As shown in (d).

[0051] Loading status update: After each forging billet loading is completed, the current loading layer's height, remaining fillable planar space, and other information are updated in real time; if the current loading layer cannot accommodate more forging billets, the spatial coordinate information of the forging billets within that layer is saved, and that layer is added to the layer set. At the same time, update the remaining available height space of the heating furnace.

[0052] Loading Termination Judgment: Determine if there are still forging blanks to be loaded: If there are forging blanks to be loaded, determine if the remaining forging blanks meet the remaining height constraint of the heating furnace. If they do, continue loading; if they do not, determine that the current processing batch is not spatially feasible; if there are no forging blanks to be loaded, determine that the current processing batch is spatially feasible.

[0053] By adopting the above-mentioned method for filling and judging forging billets, the space utilization rate of the heating furnace can be improved while meeting the filling constraints of the trolley-type heating furnace. At the same time, the spatial coordinate position of each forging billet in the heating furnace can be determined, thus providing the basic conditions for realizing automated filling and intelligent scheduling of forging billets.

[0054] Step S4: Using the forging billet group as the basic scheduling unit, construct a multi-objective optimization function model; the multi-objective optimization function model includes minimizing the total number of processing batches in the heating furnace, minimizing the total working time of the heating furnace, and minimizing the average holding temperature of the processing batches in the heating furnace.

[0055] In this step, the formula for minimizing the total number of processing batches in the heating furnace is as follows: (7) In equation (7), k is the total number of heating furnace processing batches required to complete all the forging blanks.

[0056] like Figure 3 As shown, the heating process of the forging billet in the furnace includes the process from loading the billet into the furnace to heating to the initial forging temperature. This involves both a heating stage and a holding stage within the furnace. The standard processing time for a single batch of forging billets also includes both heating and holding times. Since different forging billets in the same furnace require different heating and holding times, the longest heating time required for forging billets in the same furnace is the furnace heating time, and the longest holding time required is the furnace holding time.

[0057] The actual working time of the heating furnace consists of the rated heating time, the rated holding time, and the additional holding waiting time. The additional holding waiting time is due to the fact that the forging billet needs to be held in the heating furnace until it is ready for the forging process before it can be removed from the furnace, thus incurring additional holding time. Therefore, the model for minimizing the total working time of the heating furnace is as follows: (8) and, (9) (10) In equations (8) to (10), Total completion time It refers to the number of batches processed in the furnace; For furnace processing batches Heating time, For furnace processing batches Insulation time, This represents the total working time for a single furnace batch; m is the total number of forgings in that batch. Forging billet Forging time, This indicates the additional holding time for a single batch of processing in a furnace, which is the first batch of processing time in that furnace. Forging time of each forging billet.

[0058] The model for minimizing the average holding temperature of a batch processed in the heating furnace is expressed as follows: (11) and (12) In equations (11) to (12), This indicates the average holding temperature across all processing batches. The holding temperature for batch b is taken as the average value of the holding temperature range for all batches processed in the furnace. , These are the minimum and maximum values ​​of the holding temperature range for batch b of furnace processing, respectively. This refers to the total number of batches processed in the furnace.

[0059] Forging is a hot working process, and temperature is one of the most important factors in the entire process. Reducing the completion time while lowering the operating temperature of the heating furnace can effectively reduce energy consumption. The multi-objective model described above is used in the evaluation stage of scheduling schemes. Objective values ​​are calculated for each scheduling scheme, serving as the basis for classifying the merits of the scheduling schemes and selecting the final scheduling scheme.

[0060] Step S5: Based on the basic information of the heating furnace, the operation information, the basic information of the forging billet group, and the heating process, combined with the constraints and the multi-objective optimization function model, a genetic algorithm based on similarity adaptive improvement is used to generate and iteratively optimize the scheduling scheme.

[0061] In this step, when using a similarity-adaptive improved genetic algorithm to generate and iteratively optimize the scheduling scheme, such as... Figure 4 As shown, it specifically includes: Step S501, parameter initialization: Complete the setting of algorithm running parameters and establish an external archive pool to store non-dominated high-quality individuals.

[0062] Initialization parameters include maximum number of iterations, population size, initial mutation probability, initial crossover step size, initial mutation step size, and establishment of an external archive pool.

[0063] Step S502, Encoding and Decoding and Population Initialization: Obtain information on the forging billet group to be processed, heating furnace equipment information and process parameters, represent the allocation relationship between the forging billet group and the furnace batch based on the encoding method of the furnace processing batch, and construct the initial population using a hybrid heuristic method in combination with the furnace capacity constraint, temperature compatibility constraint, holding time compatibility constraint and space filling constraint.

[0064] In one possible implementation, an encoding method such as Figure 5 As shown, in an exemplary embodiment, for an order containing 10 sets of forging blanks, under the premise of meeting production constraints, the forging blank sets are divided into 5 processing batches for sequential processing. Each individual corresponds to an allocation scheme of forging blank sets and processing batches. Each coded segment in the individual corresponds to a processing batch. The coded segment contains the forging blank set number and sequence allocated to that processing batch.

[0065] During the decoding process, each processing batch is analyzed sequentially according to the batch coding order of the furnace, and the feasibility of the scheme is judged based on the established forging furnace loading scheduling model and constraints. Within the same heating furnace processing batch, different forging billet groups can only be processed after the previous group of forging billets has been completely forged, in order to avoid process overlap.

[0066] In one possible implementation, a hybrid approach to constructing the initial population involves the following specific process: Figure 6 As shown, assuming there are a total of Forging billets, the initialization population methods include: (1) Assign a unique number to each forging billet group and store all numbers in the set Q to be sorted. Randomly shuffle the order of the numbers in set Q. (2) Initialize the total processing batch set F and create a new current processing batch object f; the furnace capacity, space size and other parameters of the current processing batch object are determined by the corresponding heating furnace information, and its processing temperature and time interval are initially empty; (3) Randomly generate a value in the interval If the number is less than the set value, random selection is used; if it is greater than the set value, greedy selection is used. (4) Under the random selection strategy, select forging billet groups sequentially from the shuffled set Q, and determine whether they meet the furnace capacity constraint, temperature compatibility constraint, holding time compatibility constraint and space filling constraint. If the above constraints are met, add the forging billet group to the current furnace batch and delete the forging billet group from the set Q, and execute step (5); if any constraint is not met, add it to the set Q′ and delete the forging billet group from the set Q; if there is no forging billet group to select, execute step (7). Under the greedy selection strategy, a set of candidate forging billet groups that can be added to the current furnace processing batch and meet the constraints are selected. The remaining forging billet groups are deleted from Q and added to the set to be sorted Q′. If the set of candidate forging billet groups is not empty, they are sorted according to the difference between the heating time and holding time required by each candidate forging billet group and the time parameter corresponding to the current furnace batch. The forging billet group with the smallest difference is selected to be added to the current furnace batch. When there are multiple forging billet groups with the same difference, the forging billet group with the larger weight is selected to be added to the current furnace batch and the forging billet group is deleted from the set to be sorted Q. Step (5) is executed. If the set of candidate forging billet groups is empty, step (7) is executed. (5) After the current furnace processing batch is added to the forging billet group, the parameters of the current processing batch are updated in real time, including the remaining furnace capacity, holding temperature range, holding time range and remaining available space information, and the layer height and the remaining height space of the heating furnace are updated at the same time. (6) Determine the set If there are still unfinished forging billet groups, continue to execute the above steps (3) to (5); otherwise, add the current furnace processing batch to the furnace processing batch set F and execute step (8). (7) If there are no more workpieces to be loaded into the batch processed in this furnace, add the batch to the total furnace batch set F; (8) Reassign the set Q′ to be processed to the set Q. If the set Q is not empty, create a new furnace processing batch object and repeat steps (3) to (7). If the set Q is empty, generate a complete individual based on the total furnace batch set F. (9) Repeat the above process until an initial population that meets the population size requirements is generated.

[0067] Step S503, Population Stratification and Archive Pool Update: Based on the established multi-objective optimization function, the objective function value is calculated for each individual in the population, and the individuals are sorted by non-dominated status based on the objective function value to obtain individuals with different non-dominated levels. The individuals with the first non-dominated level are compared with the individuals in the external archive pool, and the external archive pool is updated according to the dominance relationship and crowding distance.

[0068] Based on the non-dominance level, the population is divided into a superior scheduling scheme group and a normal scheduling scheme group. The superior scheduling scheme group consists of individuals with the first dominance level and non-dominance individuals in the external archive pool, while the normal scheduling scheme group includes all other individuals except those in the superior scheduling scheme group.

[0069] Step S504, Select crossover mutation individuals: Select one individual from both the optimized scheduling scheme group and the normal scheduling scheme group.

[0070] It should be noted that by performing non-dominated sorting on the population, the merits of the scheduling schemes under multiple optimization objectives such as the number of batches processed in the furnace, the total working time of the heating furnace, and the average holding temperature can be comprehensively evaluated, and a diverse set of non-dominated solutions can be formed. Individuals are selected from the optimal scheduling scheme group and the ordinary scheduling scheme group for cross-mutation, which can retain the characteristics of the excellent scheduling schemes and introduce the difference information in the ordinary scheduling schemes. This can improve the population diversity while ensuring the quality of the solutions, and guide the direction of population evolution.

[0071] Step S505, Adaptive parameter adjustment: Calculate the architectural similarity between the two selected scheduling schemes, and adaptively adjust the mutation probability, crossover step size, and variable asynchronous length based on the similarity results.

[0072] In one possible implementation, the parameters are adaptively adjusted based on the structural similarity between the two selected scheduling schemes. When the similarity between the selected schemes is higher than a set value, the mutation probability, crossover step size, and variable asynchrony length are increased; when the similarity between the selected schemes is lower than the set value, a smaller mutation probability, crossover step size, and variable asynchrony length are selected.

[0073] Similarity calculation formula: (13) In equation (13), For the similarity between two entities, This represents the number of furnace processing batches in two entities that contain the same set of forging billet group numbers. The order of the forging billet group numbers within the furnace batch is not considered. For the number of batches processed in the furnace for the first individual, This refers to the number of batches processed in the furnace for the second individual.

[0074] Adaptive mutation probability formula: (14) In equation (14), The mutation probability, This represents the maximum mutation probability. This represents the minimum probability of mutation. For similarity threshold, The steepness coefficient of the adjustment function is used to control the sensitivity of the mutation probability to changes in similarity.

[0075] Cross-variable asynchronous length: (15) In equation (15), Cross step size, maximum cross step size ratio Minimum cross step size ratio , This is the steepness coefficient of the adjustment function.

[0076] (16)

[0077] In equation (16), For variable asynchronous length, the maximum variable asynchronous length ratio Minimum variable asynchronous length ratio , This is the steepness coefficient of the adjustment function.

[0078] It should be noted that when the similarity between scheduling schemes is high, the perturbation intensity is increased to enhance the multidimensionality of the scheduling optimization process; when the similarity between scheduling schemes is low, the perturbation intensity is reduced to maintain the existing high-quality scheduling scheme.

[0079] Step S506, Crossover and Mutation Operation: Based on the adjusted genetic operator parameters, perform crossover and mutation operations on the two selected parent individuals to generate offspring individuals.

[0080] In the cross operation, based on the cross step size, a portion of the furnace processing batches are selected from the two parent scheduling schemes as cross segments, and the cross segments in one parent are inherited to the corresponding child. Then, complete furnace batches that do not contain duplicate forging groups are selected from the other parent and added to the child. For forging groups that have not yet been arranged, the hybrid heuristic method is used to redistribute them, and the reconstructed furnace batches are added to the child scheduling scheme, thereby ensuring that each forging group appears only once in the child scheduling scheme and is arranged.

[0081] In one possible implementation, such as Figure 7The diagram shows a crossover. Assuming the crossover step size is 2, the crossover segments selected in scheduling scheme C1 are (2,7,10) and (3). The furnace batches selected in C1 are placed into Ch1. The complete furnace batches (1,6,12) in scheduling scheme C2 that do not contain the forging billet group in the crossover segment selected in C1 are placed into Ch1. The remaining segments in C2 are (9), (4,8), (11) and (5). The remaining forging billet groups are re-assembled according to the heuristic method. The results (5,9) and (4,8,11) are added to Ch1 to obtain the offspring Ch1. Similarly, the crossover segments (2,9) and (10,11) are selected in individual C2. Ch2 can be obtained by following the same steps.

[0082] In one possible implementation, such as Figure 7 As shown, assuming the cross step size is determined to be 2, and the cross segments selected in scheduling scheme C1 are (2,7,10) and (3), then the cross segments are first placed into the offspring Ch1. Then, scheduling scheme C2 is traversed, and complete furnace batches that do not contain forging groups 2, 7, 10, and 3, such as (1,6,12), are added to the offspring Ch1. For the remaining unarranged forging groups in scheduling scheme C2, such as (9), (4,8), (11), and (5), a hybrid heuristic furnace grouping method is used to reconstruct (5,9) and (4,8,11), and these are added to the offspring Ch1, thus obtaining the complete offspring Ch1. Similarly, cross segments (2,9) and (10,11) can be selected from scheduling scheme C2, and the offspring Ch2 can be generated according to the same steps. It should be noted that during the generation of offspring, if the reconstructed furnace batch does not meet the furnace capacity constraints, temperature compatibility constraints, holding time compatibility constraints, or space filling constraints, the hybrid heuristic furnace grouping method will continue to be used to repair the unarranged forging billet groups until an offspring scheduling scheme that meets the constraints is generated.

[0083] In the mutation operation, based on the mutation probability and the mutation time, some furnace batches in the offspring scheduling scheme are split and reassembled to form a new scheduling scheme.

[0084] In one possible implementation, such as Figure 8 The mutation diagram shown determines the mutation probability and the variable asynchrony length. For scheduling schemes Ch1 and Ch2, it is determined whether mutation needs to be performed. If the random number is less than the mutation probability, the mutation operation is performed. In the scheduling scheme M that needs to be mutated, the processing batches (3,5) and (2,9) with a variable asynchrony length of 2 are randomly selected. The remaining processing batches that are not selected are directly retained to the offspring. The forging billet groups in the selected processing batches are put back into the set to be arranged in a random order. The combination is redistributed according to the heuristic method. The result is merged with the remaining processing batches in M ​​to obtain the new scheduling scheme M'.

[0085] It should be noted that during the reconfiguration process, it is still necessary to determine the furnace capacity constraints, temperature compatibility constraints, holding time compatibility constraints, and space loading constraints to ensure that the scheduling scheme obtained after the mutation is still a feasible scheme.

[0086] It should be noted that the crossover and mutation operation is the core step in generating a new scheduling scheme population. It effectively expands the population search dimension, improves the algorithm's ability to quickly find the best solution, and satisfies the constraints, thus ensuring the feasibility of the scheduling scheme.

[0087] Step S507, New Population Generation and Archive Pool Update: The current parent and offspring populations are merged to obtain a mixed population; the objective function value is calculated for each individual in the mixed population, and non-dominated sorting and crowding distance calculation are performed based on the objective function value to obtain individuals with different non-dominated levels. According to the non-dominated sorting results and crowding distance, high-quality individuals that satisfy the non-dominated relationship and have good distribution are updated to the external archive pool; at the same time, individuals with lower non-dominated levels and larger crowding distances are preferentially selected to form a new generation of population.

[0088] It should be noted that this step ensures the diversity and balance of high-quality solutions are preserved during the optimization process, thereby improving the practical feasibility and flexibility of the forging scheduling scheme.

[0089] Step S508, Iteration Termination and Result Output: Determine whether the current iteration count has reached the preset maximum iteration count, or whether the non-dominated solution set in the external archive pool has not been significantly updated within several consecutive generations; if not, repeat the above steps; if yes, select the scheduling scheme that meets the actual production needs from the external archive pool as the final forging billet group furnace scheduling scheme output.

[0090] It should be noted that by solving the multi-objective forging billet loading scheduling model, multiple Pareto optimal or near-Pareto optimal scheduling schemes can be obtained, which production personnel can choose according to actual production needs. This achieves a comprehensive balance between reducing the number of furnace processing batches, shortening the total working time of the heating furnace, and reducing the average holding temperature, thereby improving production efficiency and reducing energy consumption.

[0091] To verify the effectiveness of this embodiment, computer simulation was used. The simulation was implemented using the Python programming language, and an existing multi-objective optimization method was selected for comparison. Multiple independent experiments were conducted under the same parameter conditions to compare and analyze the optimization effects. The main parameters were set as follows: maximum number of iterations 200, population size 100, mutation probability range... Initial crossover step size range Variable asynchronous length ratio Create an external archive pool of size 50.

[0092] The simulation case study data for the forged billets is shown in Table 1: Table 1

[0093] The specifications of the heating furnace are as follows: Furnace capacity: 80t, effective heating area: 5.4 (length) 2.6 (width) 2.4 (height) / m.

[0094] Table 2

[0095] To more clearly illustrate the effects of the present invention, such as Figures 9-11 The optimization process trends of this embodiment and other methods are compared, with the blue curve representing the optimization curve of the present invention. The first, second, and third optimization objectives are the furnace working time, the number of furnace batches, and the average holding temperature per batch, respectively. Table 2 shows the specific simulation results. As can be seen from the table and the optimization curve, under the same conditions, this embodiment exhibits superior optimization effects in terms of the number of furnace batches, completion time, and convergence speed. The simulation results show that, by adopting the method of the present invention, while satisfying the space, temperature, and process constraints of the furnace, the number of furnace batches and the overall completion time are effectively reduced, and the scheduling scheme exhibits good stability, indicating that the method of the present invention has good engineering applicability.

[0096] Based on the same approach, this invention also provides a forging furnace charging scheduling system based on multi-objective optimization. The system includes a heating furnace information acquisition module, an order information acquisition module, a constraint condition construction module, a multi-objective optimization function construction module, a scheme optimization module, and a scheduling scheme output module. The heating furnace information acquisition module is used to acquire basic information about the forging furnace and to collect the furnace's operating information. The order information collection module is used to obtain the basic information and heating process of the forging billet group to be processed, and to number the forging billet group; The constraint construction module is used to construct the constraints for forging furnace loading; the constraints include furnace volume constraints, temperature compatibility constraints, holding time compatibility constraints, and space loading constraints. The multi-objective optimization function construction module is used to construct a multi-objective optimization function model with the forging billet group as the basic scheduling unit; the multi-objective optimization function model includes minimizing the total number of processing batches in the heating furnace, minimizing the total working time of the heating furnace, and minimizing the average holding temperature of the processing batches in the heating furnace. The scheme optimization module is used to generate and iteratively optimize the scheduling scheme based on the basic information of the heating furnace, the operation information, the basic information of the forging billet group and the heating process, combined with the constraints and the multi-objective optimization function model, using a similarity-adaptive improved genetic algorithm. The scheduling scheme output module is used to output the optimized scheduling scheme.

[0097] The system or device for executing the method in this embodiment of the invention can be a terminal or a server. The system includes a processor, a memory, and / or a transceiver, etc., and is connected via a communication bus. Each module can be implemented by a processor, a memory, and / or a transceiver, etc. The processor can be, but is not limited to, one or more microprocessors (MPUs), central processing units (CPUs), network processors (NPs), digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), and other programmable logic devices, discrete gates, transistor logic devices, discrete hardware components, etc., or can be configured to implement one or more integrated circuits of this invention. The processor can perform various functions by running or executing software programs in the memory and calling data in the memory. The memory includes Random Access Memory (RAM), Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Compact Disc Read-Only Memory (CD-ROM), and / or Non-Volatile Memory (NVM), etc. The transceiver is used to communicate with network devices or terminal devices, and includes a receiver and a transmitter. The memory and transceiver can be integrated with the processor or exist independently.

[0098] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0099] It should also be noted that the forging furnace charging scheduling system based on multi-objective optimization described in this embodiment corresponds to the forging furnace charging scheduling method based on multi-objective optimization. The description and limitations of the method also apply to the system, and will not be repeated here.

[0100] It should be understood that, in various embodiments of the present invention, the sequence number of each process does not imply 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.

[0101] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed, and is not intended to limit the scope of the claimed invention, but merely to illustrate preferred embodiments of the invention. Those skilled in the art should understand that the scope of the invention is not limited to the specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the inventive concept. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

Claims

1. A forging furnace charging scheduling method based on multi-objective optimization, characterized in that, The method includes: Obtain basic information about the forging furnace and collect its operating information. Obtain the basic information and heating process of the forging billet group to be processed, and number the forging billet group; Establish constraints for forging furnace loading; the constraints include furnace volume constraints, temperature compatibility constraints, holding time compatibility constraints, and space loading constraints. A multi-objective optimization function model is constructed using the forging billet group as the basic scheduling unit. The multi-objective optimization function model includes minimizing the total number of processing batches in the heating furnace, minimizing the total working time of the heating furnace, and minimizing the average holding temperature of the processing batches in the heating furnace. Based on the basic information of the heating furnace, its operation information, the basic information of the forging billet group, and the heating process, combined with constraints and a multi-objective optimization function model, a genetic algorithm based on similarity adaptive improvement is used to generate and iteratively optimize the scheduling scheme.

2. The method according to claim 1, characterized in that, The basic information of the heating furnace includes parameters such as the heating furnace number, rated furnace capacity, effective heating space dimensions, and heating efficiency; wherein, the effective heating space dimensions include the effective heating space width, height, and depth; and the rated furnace capacity refers to the maximum allowable furnace loading capacity.

3. The method according to claim 1, characterized in that, The basic information of the forging billet group includes the type, size and quantity of the forging billet group; the heating process includes the processing path, heating temperature, heating time, holding temperature range and holding time range.

4. The method according to claim 1, characterized in that, The furnace volume constraint, temperature compatibility constraint, and holding time compatibility constraint are used to determine whether forging billets can be combined into the same processing batch for processing.

5. The method according to any one of claims 1 to 4, characterized in that, The furnace capacity constraint means that the total mass of all forgings currently in the heating furnace must not exceed the rated furnace capacity, expressed as: ，(1) In equation (1), The total mass of the forged billets in batch b of furnace processing. For the capacity of the heating furnace, It represents the number of batches processed in the heating furnace; The temperature compatibility constraint requires that the holding temperature ranges of all forgings within the same batch of processing in the same furnace must overlap to ensure temperature compatibility. The expression is: ，(2) In equation (2), Let J be the holding temperature range of the j-th forging billet in the b-th batch of processing. The intersection of the holding temperature ranges of forging billets in the same batch is non-empty, which means that the temperature compatibility requirement is met. The heat preservation time compatibility constraint requires that the heat preservation time intervals of all forgings within the same batch of processing in the same furnace must overlap to ensure time compatibility. The expression is: ，(3) In equation (3), Let J be the holding time interval for the j-th forging billet in the b-th batch of processing. The intersection of the holding time intervals for forging billets in the same batch is non-empty, which means that the time compatibility requirement is met.

6. The method according to claim 1, characterized in that, The space filling constraint is used to determine whether the forging billet group can be loaded into the heating furnace under the condition of meeting the process constraints, and to determine the filling position of the forging billet in the effective space of the heating furnace when it can be loaded.

7. The method according to claim 6, characterized in that, Based on spatial filling constraints, the steps to determine whether the forging billet group can be loaded into the heating furnace under the condition of meeting process constraints include: Step S301: Establish a three-dimensional coordinate system with respect to the length, width and height of the effective heating space of the heating furnace, and calculate the maximum number of layers that the heating furnace can be filled with. Step S302: Sort the forging billet groups in the same batch of furnace processing according to their size from largest to smallest, calculate the number of layers required for the forging billet group considering the interlayer spacing and transverse spacing, and compare it with the maximum number of layers allowed to be filled in the heating furnace. Step S303: Under the premise that each group of forging billets can be filled, the filling space is constructed layer by layer to complete the initialization of the filling layer; Step S304: Set a length difference threshold in the length direction; load the forging billet, and divide the planar space in a single layer using the main segmentation method. When the length difference between adjacent forging billets exceeds the preset threshold, switch to the secondary segmentation method. Step S305: In the current layer, after each forging billet is loaded, the remaining loading space and the current layer height information are updated in real time. Step S306: Set the remaining height threshold; determine whether the current layer height information meets the remaining height constraint of the heating furnace; if yes, proceed to step S304 to continue filling; if no, determine that the furnace processing batch cannot complete the current forging billet assembly and filling.

8. The method according to claim 1, characterized in that, The formula for the model that minimizes the total number of processing batches in the heating furnace is as follows: ，(7) In equation (7), k is the total number of heating furnace processing batches required to complete all the forging blanks; The model for minimizing the total operating time of the heating furnace is as follows: ，(8) and, ，(9) ，(10) In equations (8) to (10), Total completion time It refers to the number of batches processed in the furnace; For furnace processing batches Heating time, For furnace processing batches Insulation time, This indicates the total working time for a single batch of processing in a single furnace; m is the total number of forging blanks in this processing batch. Forging billet Forging time, This indicates the additional holding time for a single batch of processing in a furnace, which is the first batch of processing time in that batch. Forging time of each forging billet; The model for minimizing the average holding temperature of a batch processed in the heating furnace is expressed as follows: ，(11) and ，(12) In equations (11) to (12), This indicates the average holding temperature across all processing batches. The holding temperature for batch b is taken as the average value of the holding temperature range for all batches processed in the furnace. , These are the minimum and maximum values ​​of the holding temperature range for batch b of furnace processing, respectively. This refers to the total number of batches processed in the furnace.

9. The method according to claim 1, characterized in that, When using a similarity-adaptive improved genetic algorithm to generate and iteratively optimize scheduling schemes, the specific steps include: Step S501, Parameter Initialization: Complete the setting of algorithm running parameters and establish an external archive pool to store non-dominant high-quality individuals; Step S502, Encoding and Decoding and Population Initialization: Obtain information on the forging billet group to be processed, heating furnace equipment information and process parameters, represent the allocation relationship between the forging billet group and the batch based on the batch encoding method, and construct the initial population using a hybrid heuristic method in combination with furnace capacity constraints, temperature compatibility constraints, holding time compatibility constraints and space filling constraints; Step S503, Population stratification and archive pool update: Based on the established multi-objective optimization function, the objective function value is calculated for each individual in the population, and the individuals in the population are sorted by non-dominated order based on the objective function value to obtain individuals of different non-dominated levels; the individuals of the first non-dominated level are compared with the individuals in the external archive pool, and the external archive pool is updated according to the dominance relationship and crowding distance. Step S504, Select crossover mutation individuals: Select one individual from both the optimized scheduling scheme group and the normal scheduling scheme group; Step S505, Adaptive parameter adjustment: Calculate the architecture similarity between the two selected scheduling schemes, and adaptively adjust the mutation probability, crossover step size and variable asynchronous length based on the similarity results; Step S506, Crossover and Mutation Operation: Based on the adjusted genetic operator parameters, perform crossover and mutation operations on the two selected parent individuals to generate offspring individuals; Step S507, New Population Generation and Archive Pool Update: Merge the current parent and offspring populations to obtain a mixed population; calculate the objective function value for each individual in the mixed population, and perform non-dominated sorting and crowding distance calculation based on the objective function value to obtain individuals with different non-dominated levels; update high-quality individuals that satisfy the non-dominated relationship and have good distribution to the external archive pool according to the non-dominated sorting results and crowding distance; at the same time, prioritize individuals with lower non-dominated levels and larger crowding distances to form a new generation population; Step S508, Iteration Termination and Result Output: Determine whether the current iteration count has reached the preset maximum iteration count, or whether the non-dominated solution set in the external archive pool has not been significantly updated within several consecutive generations; if not, repeat the above steps; if yes, select the scheduling scheme that meets the actual production needs from the external archive pool as the final forging billet group furnace scheduling scheme output.

10. A forging furnace charging scheduling system based on multi-objective optimization, characterized in that, The system includes a heating furnace information acquisition module, an order information acquisition module, a constraint construction module, a multi-objective optimization function construction module, a scheme optimization module, and a scheduling scheme output module; wherein... The heating furnace information acquisition module is used to acquire basic information about the forging furnace and to collect the furnace's operating information. The order information acquisition module is used to obtain the basic information and heating process of the forging billet group to be processed, and to number the forging billet group; The constraint construction module is used to construct the constraints for forging furnace loading; the constraints include furnace volume constraints, temperature compatibility constraints, holding time compatibility constraints, and space loading constraints. The multi-objective optimization function construction module is used to construct a multi-objective optimization function model with the forging billet group as the basic scheduling unit; the multi-objective optimization function model includes minimizing the total number of processing batches in the heating furnace, minimizing the total working time of the heating furnace, and minimizing the average holding temperature of the processing batches in the heating furnace. The scheme optimization module is used to generate and iteratively optimize the scheduling scheme based on the basic information of the heating furnace, the operation information, the basic information of the forging billet group and the heating process, combined with the constraints and the multi-objective optimization function model, using a similarity-adaptive improved genetic algorithm. The scheduling scheme output module is used to output the optimized scheduling scheme.

Images