Slab rolling process billet calling method, device, equipment and storage medium

Abstract

This application provides a method, apparatus, equipment, and storage medium for billet recall during slab rolling. The method includes: acquiring a slab sequence and determining the set of recallable billets for the currently rolled slab in the slab sequence; determining the stacking cost of each recallable billet in its respective stack; determining the concentration cost of each recallable billet in its respective stack; determining the predicted selection cost of each recallable billet based on the slabs to be rolled in the slab sequence; and determining the target billets to be recalled for the currently rolled slab and the recall order of the target billets from the set of recallable billets based on the current slab's underweight target, stacking cost, concentration cost, and predicted selection cost. This application can effectively avoid frequent stacking and ineffective handling while meeting the current slab's underweight target, thereby improving production efficiency and reducing equipment wear and tear, and lowering production costs during the slab rolling process.

Description

Technical Field

[0001] This application relates to the field of metal processing technology, and in particular to a method, apparatus, equipment and storage medium for billet handling during slab rolling process. Background Technology

[0002] In the hot rolling production process of steel, the slab rolling plan is generally executed sequentially according to the slab sequence. Each slab in the slab sequence usually needs to be called from the warehouse stack to make up for the contract weight deficit and at the same time meet the contract process requirements.

[0003] In related technologies, when calling up steel billets for slab rolling, a simple greedy strategy is generally chosen directly, that is, steel billets are randomly selected for calling based on the current real-time demand, or a more suitable steel billet is evaluated and called through manual judgment.

[0004] While the calling schemes in related technologies can effectively ensure the continuity of production, they only consider the immediate demand for slabs and fail to take into account the cost of using the slabs themselves. This can easily lead to frequent stacking, which severely reduces the production efficiency in the slab rolling process, significantly increases equipment wear and tear, and consequently raises production costs. Summary of the Invention

[0005] This application provides a method, apparatus, equipment, and storage medium for billet recall during slab rolling, which can improve production efficiency and reduce equipment wear during slab rolling, thereby reducing production costs.

[0006] In a first aspect, this application provides a method for billet recall during slab rolling, the method comprising: Obtain the slab sequence and determine the set of callable billets for the currently rolled slab in the slab sequence; Determine the stacking cost of each callable billet in its respective stack. The stacking cost is used to characterize the difficulty of stacking each callable billet when it is retrieved. Determine the concentration cost of each callable billet in its respective stack. The concentration cost is used to characterize the proportion of callable billets in the stack to which each callable billet belongs. Based on the slabs to be rolled in the slab sequence, determine the predicted selection cost for each callable billet. The predicted selection cost is used to characterize the probability that each callable billet is identified as the callable billet corresponding to the slab to be rolled. Based on the current underweight target, stacking cost, concentration cost, and predicted selection cost of the rolled slab, determine the target steel billets to be called for the current rolled slab and the order in which the target steel billets are called from the set of callable steel billets.

[0007] In some possible implementations, the cost of repacking each callable billet in its respective stack is determined, including: The stacking cost of each callable billet in its respective stack is determined based on the number of layers of each callable billet in its stack and the total number of layers in the stack.

[0008] In some possible implementations, the concentration cost of each callable billet in its respective stack is determined, including: Based on the first process parameters of the callable steel billets, determine the same type of steel billets in each stack to which the callable steel billets belong; wherein, the first process parameters include at least steel grade parameters and width parameters; The concentration cost of each callable billet in its stack is determined based on the number of similar billets in the stack to which each callable billet belongs and the total number of billets in the stack to which each callable billet belongs.

[0009] In some possible implementations, the predicted selection cost for each callable billet is determined based on the slabs to be rolled in the slab sequence, including: The prediction window and its length are determined based on the number of slabs to be rolled in the slab sequence. The time decay weight of each slab to be rolled within the prediction window is determined based on the prediction window length. Determine the compatibility score between each slab to be rolled and the available billets within the prediction window; The prediction selection cost for each callable billet is determined based on the prediction window length, the time decay weight of each slab to be rolled, and the compatibility score between each slab to be rolled and the callable billet.

[0010] In some possible implementations, the slab sequence is obtained, and the set of callable billets for the currently rolled slab in the slab sequence is determined, including: Obtain the slab sequence and determine the second process parameters of the steel billet to be called in the current rolling slab in the slab sequence; the second process parameters include at least one of steel grade parameters, width parameters, thickness parameters, and length parameters; According to the second process parameters, a target billet cluster is determined in the preset billet cluster, and the target billet cluster is determined as the set of billets that can be called up for the current rolled slab; wherein, the preset billet cluster is obtained by dividing the available billets in the slab rolling process according to at least one of the billet's steel grade parameters, width parameters, thickness parameters and length parameters.

[0011] In some possible implementations, based on the current underweight target of the rolled slab, the stacking cost, the concentration cost, and the predicted selection cost, the target steel billets to be called for the current rolled slab and the order in which the target steel billets are called are determined from the set of callable steel billets, including: Based on the current underweight target of rolled slabs, determine the quantitative weight unit; Obtain the weight of the target billet and convert the weight of the callable billet into a quantized weight based on the quantized weight unit; Based on the current underweight target of the rolled slab, the quantified weight of the available steel billets, the stacking cost, the concentration cost, and the predicted selection cost, a quantified dynamic programming solution is performed to obtain the target steel billets that need to be called for the current rolled slab and the order in which the target steel billets are called.

[0012] Secondly, this application provides a billet handling device during the slab rolling process, the device comprising: The slab sequence acquisition module is used to acquire the slab sequence and determine the set of callable steel billets for the currently rolled slab in the slab sequence. The stacking cost determination module is used to determine the stacking cost of each callable billet in its respective stack. The stacking cost is used to characterize the stacking difficulty of each callable billet when it is retrieved. The concentration cost determination module is used to determine the concentration cost of each callable billet in its respective stack. The concentration cost is used to characterize the proportion of callable billets in the stack to which each callable billet belongs. The Predicted Selection Cost Determination Module is used to determine the predicted selection cost of each callable billet based on the slabs to be rolled in the slab sequence. The predicted selection cost is used to characterize the probability that each callable billet is determined as the callable billet corresponding to the slab to be rolled. The call order determination module is used to determine the target steel billets to be called for the current rolled slab and the call order of the target steel billets from the set of callable steel billets, based on the current underweight target, stacking cost, concentration cost, and predicted selection cost of the current rolled slab.

[0013] Thirdly, this application provides an electronic device, which includes: a processor and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the billet recall method in the slab rolling process as described above.

[0014] Fourthly, this application provides a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement the billet recall method in the slab rolling process described above.

[0015] Fifthly, this application provides a computer program product in which instructions, when executed by a processor of an electronic device, cause the electronic device to perform the billet calling method in the slab rolling process as described above.

[0016] The billet recall method, apparatus, equipment, and storage medium provided in this application embodiment acquire a billet sequence and determine the set of recallable billets for the currently rolled slab in the sequence. Then, it determines the stacking cost, concentration cost, and predicted selection cost for each recallable billet. Based on the current underweight target, stacking cost, concentration cost, and predicted selection cost of the currently rolled slab, it determines the target billets to be recalled for the current rolled slab and the recall order of the target billets from the set of recallable billets. This allows for the representation of the stacking difficulty of each recallable billet, the proportion of recallable billets in the stack to which each recallable billet belongs, and the probability that each recallable billet is identified as the corresponding recallable billet for the slab to be rolled as quantifiable cost data. Under the premise of meeting the current underweight target of the rolled slab, it effectively avoids frequent stacking and ineffective handling based on the stacking cost, thereby improving production efficiency and reducing equipment wear during the slab rolling process, and ultimately reducing production costs. It can also combine concentration cost to select the optimal stacking to optimize the billet calling sequence, further avoiding frequent stacking and ineffective handling, and improving the continuous rolling efficiency of the current slab. On this basis, combining the predicted selection cost can help to fully consider the subsequent rolling needs of the slab sequence and further optimize the billet calling sequence, thereby improving the overall production efficiency of the hot rolling process of steel. Attached Figure Description

[0017] This application can be better understood from the following description of specific embodiments in conjunction with the accompanying drawings, wherein: Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings, wherein the same or similar reference numerals denote the same or similar features.

[0018] Figure 1 This is a flowchart of a billet calling method in the slab rolling process provided in some embodiments of this application; Figure 2 This is a schematic diagram of the billet calling device in the slab rolling process provided in some embodiments of this application; Figure 3 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0019] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0020] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0021] In hot-rolled steel production, the rolling schedule consists of several slab sequences. Each slab requires one or more billets to be retrieved from the storage stack to make up for contract shortages and meet process parameters such as steel grade, width, thickness, and length. Related technologies often employ simple greedy strategies or manual operations to retrieve billets. While these methods ensure production continuity, they often lead to frequent stacking, i.e., removing upper billets to retrieve deeper ingots. This easily results in a large amount of inefficient handling, production waiting, and equipment load, thus severely reducing production efficiency and increasing production costs in the slab rolling process. Traditional precise global optimization techniques, such as mixed-integer linear programming (MILP), suffer from high computational costs and difficulty in real-time deployment at large scales, resulting in low practicality.

[0022] To address the aforementioned problems, embodiments of this application provide a method, apparatus, equipment, and storage medium for billet retrieval during slab rolling. The billet retrieval method provided in this application embodiment is described below.

[0023] Figure 1 This illustration shows a flowchart of a billet calling method in the slab rolling process according to an embodiment of this application. Figure 1As shown, the method includes the following steps: S101 to S105.

[0024] S101: Obtain the slab sequence and determine the set of callable billets for the currently rolled slab in the slab sequence.

[0025] S102: Determine the stacking cost of each callable billet in its respective stack. The stacking cost is used to characterize the difficulty of stacking each callable billet when it is retrieved.

[0026] S103: Determine the concentration cost of each callable billet in its stack. The concentration cost is used to characterize the proportion of callable billets in the stack to which each callable billet belongs.

[0027] S104: Based on the slabs to be rolled in the slab sequence, determine the predicted selection cost for each callable billet. The predicted selection cost is used to characterize the probability that each callable billet is identified as the callable billet corresponding to the slab to be rolled.

[0028] S105: Based on the current underweight target, stacking cost, concentration cost, and predicted selection cost of the rolled slab, determine the target steel billet to be called for the current rolled slab and the order in which the target steel billets are called from the set of callable steel billets.

[0029] Therefore, by representing the difficulty of repacking each available billet during retrieval, the proportion of available billets in the stack to which each available billet belongs, and the probability that each available billet is identified as the available billet corresponding to the slab to be rolled, as quantifiable cost data, and under the premise of meeting the current underweight target of the rolled slab, the repacking cost can effectively avoid frequent repacking and ineffective handling, thereby improving the production efficiency and reducing equipment wear in the slab rolling process, and thus reducing production costs. Furthermore, by combining the concentration cost to select the optimal stacking and optimize the billet retrieval order, the phenomenon of frequent repacking and ineffective handling can be further avoided, improving the continuous rolling efficiency of the current rolled slab. On this basis, further combining the predicted selection cost helps to fully consider the subsequent rolling needs of the slab sequence and further optimize the billet retrieval order, improving the overall production efficiency of the hot rolling steel production process.

[0030] In some implementations, determining the stacking cost of each callable billet in its respective stack includes: The stacking cost of each callable billet in its respective stack is determined based on the number of layers of each callable billet in its stack and the total number of layers in the stack.

[0031] In a practical implementation, the number of layers of each callable billet in its stack and the total number of layers in the stack can be obtained, thereby calculating the stacking cost of each callable billet in its stack.

[0032] In some examples, stacking can be set up. Current height, i.e., total number of floors, is Set up stacks The bottom layer of steel billets has one layer. Following a bottom-up order, the steel billets located in the stack can be retrieved. The Layer. Therefore, when the callable billet is selected, the layers on it must be removed. The number of steel billets to be stacked is called the number of stacked billets, which can be calculated according to the following formula (1): (1) in, The cost of retrieving billet i from its stack; For the stack to which billet i can be called The total number of floors; The number of layers in the stack to which the callable billet i belongs.

[0033] Based on this, to make the cost of stacking between different stacks comparable, the maximum stacking height, i.e., the maximum number of layers, can be introduced. The stacking cost is obtained by normalizing the number of stacked billets. The stacking cost of each callable billet in its stack can be calculated according to the following formula (2): (2) in, The cost of retrieving billet i from its stack; The number of stack blocks that can be called up, billet i, are flipped in its stack; This represents the maximum stacking height, i.e., the maximum number of layers.

[0034] In this embodiment, by determining the stacking cost of each callable billet in its stack based on the number of layers of each callable billet in its stack and the total number of layers of the stack, the stacking cost of each callable billet in its stack can be directly reflected, thus reflecting the number of upper-layer billets that may need to be removed when the billet is taken. This allows the stacking cost to truly reflect the difficulty of taking the billet, thereby enabling subsequent billet taking decisions to prioritize the use of billets with lower taking costs and reduce the probability of stacking operations and ineffective handling.

[0035] In some embodiments, determining the concentration cost of each callable billet in its respective stack includes: Based on the first process parameters of the callable steel billets, determine the same type of steel billets in each stack to which the callable steel billets belong; wherein, the first process parameters include at least steel grade parameters and width parameters; The concentration cost of each callable billet in its stack is determined based on the number of similar billets in the stack to which each callable billet belongs and the total number of billets in the stack to which each callable billet belongs.

[0036] In practice, the same type of billet can be determined in each stack of callable billets based on the steel type parameters and width parameters of the callable billet. The concentration cost of each callable billet in its stack can be calculated based on the number of the same type of billets in each stack and the total number of billets in each stack.

[0037] In some examples, a compatibility determination function for similar steel billets, is_compatible(k,i), can be defined. This function can be set to return 1 if any other steel billet i in the stack to which the callable steel billet k belongs is of the same steel type as the callable steel billet k and its width is within the tolerance range; otherwise, it returns 0.

[0038] Based on this, the quantity of the same type of billet in the stack to which each callable billet belongs can be calculated according to the following formula (3): (3) in, The quantity of the same type of billet in the stack to which billet i belongs; This refers to any other billet in the stack to which the billet belongs.

[0039] Furthermore, the total number of layers in the stack s to which billet i belongs is set to... The concentration cost of callable billets in their respective stacks can be calculated using the following formula (4): (4) in, The concentration cost of callable billet i in its stack s; The quantity of the same type of billet in the stack to which billet i belongs; The total number of stacks s to which the callable billet i belongs.

[0040] It should be noted that, if ,but This refers to the situation when no data has been generated for the hot billet stack. The smaller this concentration cost index, the more concentrated the similar billets in the stack where the callable billets are located are, which is beneficial for subsequent continuous rolling. Whenever a billet is removed or transferred from the stack, causing a change in the stack structure, the concentration cost of the callable billets in that stack can be locally updated.

[0041] In this embodiment, the concentration cost of each callable billet in its stack is determined based on the number of similar billets in the stack to which each callable billet belongs and the total number of billets in the stack. This allows for the priority selection of billets with a relatively high concentration of similar billets for use, thereby improving the efficiency of continuous rolling and the utilization rate of billets.

[0042] In some embodiments, determining the predicted selection cost for each callable billet based on the slabs to be rolled in the slab sequence includes: The prediction window and its length are determined based on the number of slabs to be rolled in the slab sequence. The time decay weight of each slab to be rolled within the prediction window is determined based on the prediction window length. Determine the compatibility score between each slab to be rolled and the available billets within the prediction window; The prediction selection cost for each callable billet is determined based on the prediction window length, the time decay weight of each slab to be rolled, and the compatibility score between each slab to be rolled and the callable billet.

[0043] In practical applications, the prediction window and its length can be determined based on the number of slabs to be rolled in the slab sequence; the time decay weight of each slab to be rolled within the prediction window can be determined based on the prediction window length; the compatibility score between each slab to be rolled and the available steel billet can be determined; and then, based on the prediction window length, the time decay weight of each slab to be rolled, and the compatibility score between each slab to be rolled and the available steel billet, the prediction selection cost of each available steel billet can be calculated.

[0044] In some examples, the prediction window length can be set to... , The value of can be the number of slabs to be rolled in the slab sequence, or it can be adjusted according to computational efficiency requirements. The value can be adjusted; and a compatibility score determination function can be set. This function can be set to detect when a slab to be rolled is detected. The currently rolled slab can be used as a slab to be rolled. If the billet is its own callable billet, return 1; otherwise, return 0. The time decay weight of each billet to be rolled can also be determined according to the following formula (5): (5) in, This represents the position of the slab to be rolled within the prediction window; The time decay weight is the weight corresponding to the slab to be rolled at position t, where 1 ≤ t ≤ ; The time decay factor, The larger the value of the t-value, the further back in the roll position it is; that is, the larger the t-value, the smaller the weight of the slab to be rolled. >0.

[0045] Based on this, the predicted selection cost for each callable billet can be determined according to the following formula (6): (6) in, The predicted selection cost for callable billet i; The time decay weight is the slab to be rolled at position t. To predict the window length; To predict the compatibility score between the slab to be rolled (b) and the callable billet (i) within the window.

[0046] The higher the predicted selection cost of callable billet i, the higher the probability that callable billet i will be required by other slabs in the future. As the slab rolling plan progresses, for example, after the rolling of 10 slabs has been completed, the predicted selection cost can be updated on a rolling basis.

[0047] In this embodiment, the predicted selection cost of each callable billet is determined based on the prediction window length, the time decay weight of each slab to be rolled, and the compatibility score between each slab and the callable billet. This quantifies the likelihood that a callable billet will be subsequently used by other slabs, allowing for the avoidance of prematurely calling billets that are more needed later. This helps to fully consider the subsequent rolling requirements of the slab sequence, further optimize the billet calling order, and improve the overall production efficiency of the hot rolling steel production process.

[0048] In some embodiments, obtaining a slab sequence and determining the set of callable billets for the currently rolled slab in the slab sequence includes: Obtain the slab sequence and determine the second process parameters of the steel billet to be called in the current rolling slab in the slab sequence; the second process parameters include at least one of steel grade parameters, width parameters, thickness parameters, and length parameters; According to the second process parameters, a target billet cluster is determined in the preset billet cluster, and the target billet cluster is determined as the set of billets that can be called up for the current rolled slab; wherein, the preset billet cluster is obtained by dividing the available billets in the slab rolling process according to at least one of the billet's steel grade parameters, width parameters, thickness parameters and length parameters.

[0049] In practical implementation, in order to improve computational efficiency, the available steel billets during the slab rolling process can be pre-divided into clusters based on at least one of the steel grade parameters, width parameters, thickness parameters, and length parameters of the steel billet, thus obtaining a preset steel billet cluster. Specifically, rule-based classification, such as width interval division or the K-Means clustering algorithm, can be used to achieve clustering.

[0050] After obtaining the slab sequence, the second process parameters of the steel billets required for the current rolling slab in the sequence can be determined. These second process parameters include at least one of steel grade parameters, width parameters, thickness parameters, and length parameters. Based on these second process parameters, a target steel billet cluster can be determined from a preset steel billet cluster, and this target steel billet cluster can be defined as the set of callable steel billets for the current rolling slab. Therefore, when determining the target steel billets to be called, only the steel billets within the target steel billet cluster can be considered for cost calculations, ignoring incompatible clusters outside the target steel billet cluster. This significantly reduces the search space, improves the rationality of determining the set of callable steel billets, and helps improve the overall production efficiency in the slab rolling process.

[0051] In some embodiments, based on the current underweight target of the rolled slab, the stacking cost, the concentration cost, and the predicted selection cost, the target steel billets to be called for the current rolled slab and the calling order of the target steel billets are determined from the set of callable steel billets, including: Based on the current underweight target of rolled slabs, determine the quantitative weight unit; Obtain the weight of the target billet and convert the weight of the callable billet into a quantized weight based on the quantized weight unit; Based on the current underweight target of the rolled slab, the quantified weight of the available steel billets, the stacking cost, the concentration cost, and the predicted selection cost, a quantified dynamic programming solution is performed to obtain the target steel billets that need to be called for the current rolled slab and the order in which the target steel billets are called.

[0052] In practical implementation, the total cost function can be obtained by weighted summing of the stacking cost, concentration cost, and predicted selection cost of the callable steel billets according to the following formula (7): (7) in, The total cost of the callable billet i; The cost of stacking callable billet i; The concentration cost of the callable steel billet i; The predicted selection cost for callable billet i; This is a weighting coefficient, the value of which can be determined based on experience or optimization experiments. For example: .

[0053] Based on this, to avoid the excessively large state space of traditional dynamic programming, an adaptive quantization dynamic programming method can be used to solve for the target steel billets required for the current rolled slab and the order in which they are called. This significantly reduces the computational scale while maintaining approximate accuracy. Specifically, the allowable error can be determined first. For example, you can Set to 1%; and can be based on the current underweight target of the rolled slab. The conversion to obtain the quantification unit can be carried out according to the following formula (8): (8) Where q is the unit of quantification; This is the precision control constant; The current target for underweight rolled slabs This is the allowable error.

[0054] Furthermore, the weight of the callable steel billet j can be rounded to the nearest integer. The integer multiples of , and in the quantized state space, the following formula (9) is used to solve the problem using dynamic programming: (9) in, The total weight of the steel billet shall not exceed The minimum cost corresponding to the selected slab; The currently set total weight; For callable steel billets Quantified weight For callable steel billets The total cost.

[0055] Enumeration can be done from 0 To the underweight target The solution is obtained by recursion, and finally... The desired solution is to ensure that the total weight of the steel billet is not less than [amount missing]. Under the premise of minimizing the total cost corresponding to the current rolled slab, the target steel billets to be called and their calling order are determined from the set of callable steel billets to minimize the total cost corresponding to the current rolled slab. It should be noted that in practical applications, the recursive solution process can also be performed in parallel during the calling process. That is, it is not necessary to determine all the target steel billets to be called and their calling order in advance. Instead, the target steel billets selected for each call can be determined synchronously with the slab process.

[0056] In this embodiment, by determining the quantization unit based on the current underweight target of the rolled slab and quantifying the weight of the available steel billets, and then combining the stacking cost, concentration cost and predicted selection cost to perform quantization dynamic programming solution, the system can find the combination and order of steel billets that meet the underweight requirement and have the minimum total cost in a small quantization state space. Thus, the target steel billets to be called and the calling order of the target steel billets are obtained with a low computational cost, avoiding the waste of computational resources.

[0057] Based on the billet calling method in the slab rolling process provided in the above embodiments, this application also provides a specific implementation of the billet calling device in the slab rolling process.

[0058] Please refer to the following examples.

[0059] First see Figure 2 The billet calling device 200 in the slab rolling process provided in this application embodiment includes the following modules: The slab sequence acquisition module 201 is used to acquire the slab sequence and determine the set of callable steel billets for the currently rolled slab in the slab sequence. The stacking cost determination module 202 is used to determine the stacking cost of each callable steel billet in its respective stack. The stacking cost is used to characterize the stacking difficulty of each callable steel billet when it is picked up. The concentration cost determination module 203 is used to determine the concentration cost of each callable billet in its respective stack. The concentration cost is used to characterize the proportion of callable billets in the stack to which each callable billet belongs. The prediction selection cost determination module 204 is used to determine the prediction selection cost of each callable billet based on the slabs to be rolled in the slab sequence. The prediction selection cost is used to characterize the probability that each callable billet is determined as the callable billet corresponding to the slab to be rolled. The call order determination module 205 is used to determine the target steel billets to be called for the current rolled slab and the call order of the target steel billets from the set of callable steel billets, based on the current underweight target, stacking cost, concentration cost and predicted selection cost of the current rolled slab.

[0060] As one implementation of this application, the stacking cost determination module 202 includes: The stacking cost determination submodule is used to determine the stacking cost of each callable billet in its respective stack based on the number of layers of each callable billet in its respective stack and the total number of layers of the respective stack.

[0061] As one implementation of this application, the concentration cost determination module 203 includes: The similar billet determination submodule is used to determine similar billets of the callable billet in each stack to which the callable billet belongs, based on the first process parameters of the callable billet; wherein, the first process parameters include at least steel grade parameters and width parameters; The concentration cost determination submodule is used to determine the concentration cost of each callable billet in its stack based on the number of similar billets in the stack to which each callable billet belongs and the total number of billets in the stack to which each callable billet belongs.

[0062] As one implementation of this application, the prediction selection cost determination module 204 includes: The prediction window determination submodule is used to determine the prediction window and its length based on the number of slabs to be rolled in the slab sequence. The time decay weight determination submodule is used to determine the time decay weight of each slab to be rolled within the prediction window based on the prediction window length. The compatibility score determination submodule is used to determine the compatibility score between each slab to be rolled and the callable billets within the prediction window; The Predicted Selection Cost Determination Submodule is used to determine the predicted selection cost of each callable billet based on the prediction window length, the time decay weight of each billet to be rolled, and the compatibility score between each billet to be rolled and the callable billet.

[0063] As one implementation of this application, the slab sequence acquisition module 201 includes: The slab sequence acquisition submodule is used to acquire the slab sequence and determine the second process parameters of the steel billet to be called for the currently rolled slab in the slab sequence; the second process parameters include at least one of the following: steel grade parameters, width parameters, thickness parameters, and length parameters. The callable billet set determination submodule is used to determine the target billet cluster in the preset billet cluster according to the second process parameters, and to determine the target billet cluster as the callable billet set of the current rolled slab; wherein, the preset billet cluster is obtained by dividing the available billets in the slab rolling process according to at least one of the billet's steel grade parameters, width parameters, thickness parameters and length parameters.

[0064] As one implementation of this application, the call order determination module 205 includes: The quantification weight unit determination submodule is used to determine the quantification weight unit based on the current underweight target of the rolled slab; The quantized weight conversion submodule is used to obtain the weight of the target steel billet and convert the weight of the callable steel billet into a quantized weight according to the quantized weight unit. The quantized dynamic programming solution submodule is used to perform quantized dynamic programming solution based on the current underweight target of the rolled slab, the quantized weight of the available steel billets, the stacking cost, the concentration cost, and the predicted selection cost, so as to obtain the target steel billets to be called for the current rolled slab and the calling order of the target steel billets.

[0065] Each module in the billet calling device in the slab rolling process provided in this application embodiment can realize each step in the billet calling method in the above-mentioned slab rolling process and achieve the corresponding effect. For the sake of brevity, it will not be described in detail here.

[0066] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown.

[0067] The electronic device may include a processor 301 and a memory 302 storing computer program instructions.

[0068] Specifically, the processor 301 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0069] Memory 302 may include mass storage for data or instructions. For example, and not limitingly, memory 302 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 302 may include removable or non-removable or fixed media. Where appropriate, memory 302 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 302 is non-volatile solid-state memory.

[0070] Memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible, non-transitory, computer-readable storage media, such as memory devices, encoded with software including computer-executable instructions, and when the software is executed by one or more processors, it is operable to perform the operations described with reference to the billet recall method in a slab rolling process according to any embodiment of this disclosure.

[0071] The processor 301 reads and executes the computer program instructions stored in the memory 302 to implement any of the billet recall methods in the slab rolling process described in the above embodiments.

[0072] In one example, the electronic device may also include a communication interface 303 and a bus 310. For example, Figure 3 As shown, the processor 301, memory 302, and communication interface 303 are connected through bus 310 and complete communication with each other.

[0073] The communication interface 303 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0074] Bus 310 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 310 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0075] Furthermore, in conjunction with the billet retrieval method during the slab rolling process described in the above embodiments, this application embodiment can provide a computer storage medium for implementation. This computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the billet retrieval methods during the slab rolling process described in the above embodiments.

[0076] This application also provides a computer program product, including a computer program that, when executed, implements any of the billet calling methods in the slab rolling process described in the above embodiments.

[0077] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0078] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0079] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0080] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0081] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for billet transfer during slab rolling, characterized in that, The method includes: Obtain the slab sequence and determine the set of callable steel billets for the currently rolled slab in the slab sequence; Determine the stacking cost of each of the callable billets in its respective stack, the stacking cost being used to characterize the difficulty of stacking each of the callable billets when it is retrieved; Determine the concentration cost of each callable billet in its respective stack, the concentration cost being used to characterize the proportion of each callable billet in its respective stack; Based on the slabs to be rolled in the slab sequence, a predicted selection cost is determined for each of the callable billets, the predicted selection cost being used to characterize the probability that each of the callable billets is determined to be the callable billet corresponding to the slab to be rolled; Based on the current underweight target of the rolled slab, the stacking cost, the concentration cost, and the predicted selection cost, the target steel billets to be called for the current rolled slab and the calling order of the target steel billets are determined from the set of callable steel billets.

2. The billet transfer method in the slab rolling process according to claim 1, characterized in that, Determining the stacking cost for each of the callable billets in its respective stack includes: The stacking cost of each callable billet in its respective stack is determined based on the number of layers of each callable billet in its respective stack and the total number of layers of the respective stack.

3. The billet transfer method in the slab rolling process according to claim 1, characterized in that, Determining the concentration cost of each of the callable billets in its respective stack includes: Based on the first process parameters of the callable steel billet, steel billets of the same type as the callable steel billet are determined in each stack to which the callable steel billet belongs; wherein, the first process parameters include at least steel grade parameters and width parameters; The concentration cost of each callable billet in its stack is determined based on the number of similar billets in the stack to which each callable billet belongs and the total number of billets in the stack to which each callable billet belongs.

4. The billet transfer method in the slab rolling process according to claim 1, characterized in that, Based on the slabs to be rolled in the slab sequence, determine the predicted selection cost for each of the callable slabs, including: The prediction window and its length are determined based on the number of slabs to be rolled in the slab sequence. The time decay weight of each slab to be rolled within the prediction window is determined based on the prediction window length. Determine the compatibility score between each of the slabs to be rolled and the available steel billets within the prediction window; The prediction selection cost for each callable billet is determined based on the prediction window length, the time decay weight of each slab to be rolled, and the compatibility score between each slab to be rolled and the callable billet.

5. The billet transfer method in the slab rolling process according to claim 1, characterized in that, Obtain the slab sequence and determine the set of callable billets for the currently rolled slab in the slab sequence, including: Obtain the slab sequence and determine the second process parameters of the steel billet to be called for the current rolling slab in the slab sequence; the second process parameters include at least one of steel grade parameters, width parameters, thickness parameters, and length parameters; According to the second process parameters, a target billet cluster is determined in the preset billet cluster, and the target billet cluster is determined as the set of billets that can be called up for the current rolled slab; wherein, the preset billet cluster is obtained by dividing the available billets in the slab rolling process according to at least one of the billet's steel grade parameters, width parameters, thickness parameters and length parameters.

6. The billet transfer method in the slab rolling process according to claim 1, characterized in that, Based on the current underweight target of the rolled slab, the stacking cost, the concentration cost, and the predicted selection cost, the target steel billets to be called for the current rolled slab and the calling order of the target steel billets are determined from the set of callable steel billets, including: Based on the current underweight target of the rolled slab, determine the quantified weight unit; Obtain the weight of the target steel billet, and convert the weight of the callable steel billet into a quantized weight according to the quantized weight unit; Based on the current underweight target of the rolled slab, the quantified weight of the available steel billets, the stacking cost, the concentration cost, and the predicted selection cost, a quantified dynamic programming solution is performed to obtain the target steel billets to be called for the current rolled slab and the calling order of the target steel billets.

7. A billet handling device in the slab rolling process, characterized in that, The device includes: The slab sequence acquisition module is used to acquire the slab sequence and determine the set of callable steel billets for the currently rolled slab in the slab sequence. The stacking cost determination module is used to determine the stacking cost of each callable steel billet in its respective stack, wherein the stacking cost is used to characterize the stacking difficulty of each callable steel billet when it is retrieved. The concentration cost determination module is used to determine the concentration cost of each callable billet in its respective stack, wherein the concentration cost is used to characterize the proportion of each callable billet in the stack to which it belongs; The prediction selection cost determination module is used to determine the prediction selection cost of each callable billet based on the slabs to be rolled in the slab sequence. The prediction selection cost is used to characterize the probability that each callable billet is determined to be the callable billet corresponding to the slab to be rolled. The call order determination module is used to determine the target steel billets to be called for the current rolled slab and the call order of the target steel billets from the set of callable steel billets, based on the underweight target of the current rolled slab, the stacking cost, the concentration cost, and the predicted selection cost.

8. An electronic device, characterized in that, The electronic device includes: a processor and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the billet recall method in the slab rolling process as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the billet recall method in the slab rolling process as described in any one of claims 1-6.

10. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device performs the functions as described in claim 1.

6. The billet calling method in the slab rolling process as described in any one of the above.

Images