Steel scheduling method and device, readable storage medium and program product

Abstract

The invention discloses a steel scheduling method and device, a readable storage medium and a program product, and relates to the technical field of steel machining. The steel scheduling method comprises the following steps: acquiring steel data of to-be-processed steel; establishing a rule configuration model corresponding to the steel to be processed, and establishing a scheduling algorithm model; based on a rule configuration model, performing data processing on the steel data to obtain scheduling task parameters; based on the scheduling algorithm model, data processing is conducted on the scheduling task parameters, steel scheduling information is obtained, and the steel scheduling information represents the arrangement sequence of the to-be-processed steel. The efficiency of steel production scheduling is improved.

Description

Technical Field

[0001] The present application relates to the technical field of steel processing, and in particular to a steel scheduling method, device, readable storage medium and program product. Background Art

[0002] As intelligent manufacturing and automation technologies become increasingly critical in the steel industry, the hot rolling process, a core step in production, has a direct impact on the overall process's economics and competitiveness, thanks to its efficiency and quality. However, traditional hot rolling scheduling methods, which rely on manual experience, are inefficient and struggle to adapt quickly to market changes.

[0003] The hot / cold state of slabs charged to the furnace significantly impacts hot rolling speed and energy consumption. Improper scheduling can lead to energy waste and reduced production efficiency. The human-machine hybrid scheduling model currently used by steel companies is complex and time-consuming, with low hot charging rates. Consequently, existing steel scheduling methods suffer from low efficiency. Summary of the Invention

[0004] The embodiments of the present application provide a steel scheduling method, device, readable storage medium and program product, which are used to solve technical problems such as low efficiency in the prior art.

[0005] A first aspect of an embodiment of the present application provides a steel scheduling method, comprising:

[0006] Obtaining steel material data of steel to be processed;

[0007] Establish a rule configuration model corresponding to the steel to be processed and establish a scheduling algorithm model;

[0008] Based on the rule configuration model, the steel data is processed to obtain the scheduling task parameters;

[0009] Based on the scheduling algorithm model, data processing is performed on the scheduling task parameters to obtain steel scheduling information, wherein the steel scheduling information represents the arrangement order of the steel to be processed.

[0010] The steel scheduling method in this embodiment uses a scheduling algorithm model to quickly and accurately determine the steel scheduling information of the steel to be processed. Compared with manual sorting of the steel to be processed, this embodiment greatly improves the efficiency of steel production sorting while ensuring the accuracy of steel production sorting.

[0011] A second aspect of the embodiments of the present application provides a steel scheduling device, comprising:

[0012] An acquisition unit, used for acquiring steel material data of the steel material to be processed;

[0013] The processing unit is used to establish a rule configuration model corresponding to the steel to be processed and a scheduling algorithm model;

[0014] The processing unit is also used to process the steel data based on the rule configuration model to obtain the scheduling task parameters;

[0015] The processing unit is further used to perform data processing on the scheduling task parameters based on the scheduling algorithm model to obtain steel scheduling information, wherein the steel scheduling information represents the arrangement order of the steel to be processed.

[0016] The steel scheduling device in this embodiment uses a scheduling algorithm model to quickly and accurately determine the steel scheduling information of the steel to be processed. Compared with manual sorting of the steel to be processed, this embodiment greatly improves the efficiency of steel production sorting while ensuring the accuracy of steel production sorting.

[0017] A third aspect of the present application provides another steel scheduling device, comprising a processor and a memory, wherein the memory stores a computer program that, when executed by the processor, implements the steps of the steel scheduling method described in any of the aforementioned embodiments. Therefore, this steel scheduling device possesses all the advantages of the steel scheduling method described in any of the aforementioned embodiments, and further description thereof is omitted.

[0018] A fourth aspect of the present application provides a readable storage medium having a program or instructions stored thereon. When executed by a processor, the program or instructions implement the steps of the steel scheduling method described in any of the aforementioned embodiments. Therefore, the readable storage medium possesses all the beneficial effects of the steel scheduling method described in any of the aforementioned embodiments, and further description thereof is omitted.

[0019] According to a fifth aspect of the present invention, a computer program product is provided, comprising computer instructions. When executed by a processor, the computer instructions implement the steps of the steel scheduling method described in any of the aforementioned embodiments. Therefore, this computer program product possesses all the advantages of the steel scheduling method described in any of the aforementioned embodiments, and further description thereof is omitted. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0021] Figure 1 A flowchart of a steel scheduling method provided in an embodiment of the present application;

[0022] Figure 2 This is a functional module block diagram of the steel scheduling device provided in an embodiment of the present application;

[0023] Figure 3 This is a structural block diagram of the steel scheduling device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to better understand the technical solutions provided by the embodiments of this specification, the technical solutions of the embodiments of this specification are described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of this specification, rather than limitations on the technical solutions of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0025] In this article, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also include elements inherent to such process, method, article or equipment. In the absence of further restrictions, the elements defined by the statement "comprising a ..." do not exclude the presence of other identical elements in the process, method, article or equipment comprising the elements. The term "two or more" includes two or more than two cases.

[0026] In some embodiments, as Figure 1 As shown, an embodiment of the present application provides a steel scheduling method, comprising:

[0027] Step S101, obtaining steel material data of the steel material to be processed;

[0028] Step S102: establishing a rule configuration model corresponding to the steel to be processed and establishing a scheduling algorithm model;

[0029] Step S103: Based on the rule configuration model, the steel data is processed to obtain the scheduling task parameters;

[0030] Step S104: Based on the scheduling algorithm model, data processing is performed on the scheduling task parameters to obtain steel scheduling information.

[0031] In this embodiment, a scheduling method for steel is proposed, in which steel data of the steel to be processed is obtained, and a rule configuration model corresponding to the steel to be processed is established, and a scheduling algorithm model is established at the same time, wherein the steel to be processed is the steel to be processed, the rule configuration model is a mathematical model for determining the scheduling rules, and the scheduling algorithm model is a mathematical model for determining the steel scheduling plan.

[0032] Illustratively, the steel materials to be processed may be a plurality of steel slabs from the same batch.

[0033] Exemplarily, the scheduling algorithm model may be a mathematical model including an ant colony algorithm.

[0034] Based on the rule configuration model, the steel data is processed to obtain scheduling task parameters, wherein the scheduling task parameters are relevant parameters of the steel scheduling task.

[0035] Exemplarily, the scheduling task parameters may include scheduling rules.

[0036] Based on the scheduling algorithm model, data processing is performed on the scheduling task parameters to obtain steel scheduling information, wherein the steel scheduling information represents the arrangement order of the steel to be processed.

[0037] For example, the steel scheduling information may indicate a plurality of target steels that need to be sorted among the steels to be processed, and may assign sorting numbers to the plurality of target steels that need to be sorted.

[0038] For example, before the steel to be processed is rolled, the steel scheduling information is used to schedule the steel to be processed.

[0039] The steel scheduling method in this embodiment uses a scheduling algorithm model to quickly and accurately determine the steel scheduling information of the steel to be processed. Compared with manual sorting of the steel to be processed, this embodiment greatly improves the efficiency of steel production sorting while ensuring the accuracy of steel production sorting.

[0040] In some embodiments, embodiments of the present application provide a steel scheduling method, which establishes a scheduling algorithm model, including:

[0041] Step S201: Obtain a preset scheduling algorithm framework, and obtain scheduling decision variables and scheduling auxiliary variables corresponding to the steel to be processed;

[0042] Step S202, determining an optimization objective function and multiple conditional constraint functions based on the scheduling decision variables and the scheduling auxiliary variables;

[0043] Step S203: establishing a scheduling algorithm model based on the scheduling algorithm framework, the optimization objective function, and multiple conditional constraint functions.

[0044] In this embodiment, a preset scheduling algorithm framework is obtained, and scheduling decision variables and scheduling auxiliary variables corresponding to the steel to be processed are obtained, wherein the scheduling algorithm framework includes a preset algorithm for steel scheduling, the scheduling decision variables are the main variables for determining the sorting of steel, and the scheduling auxiliary variables are the auxiliary variables for determining the sorting of steel.

[0045] Exemplarily, the scheduling decision variables include x ij , x ij Indicates that the i-th slab comes before the j-th slab in the schedule.

[0046] Exemplarily, the scheduling auxiliary variables include u i 、f i and y ij ,u i represents the position of the i-th slab in the plan, f i Indicates whether the i-th slab appears in the first 10 slabs (transition section) in the plan, y ij Indicates that the i-th slab is before the j-th slab in the transition section.

[0047] According to the scheduling decision variables and the scheduling auxiliary variables, an optimization objective function and multiple conditional constraint functions are determined, wherein the optimization objective function is the objective function of the scheduling algorithm model, and the conditional constraint function is the constraint function of the scheduling algorithm model.

[0048] Integrate the scheduling algorithm framework, optimization objective function and multiple conditional constraint functions to establish a scheduling algorithm model.

[0049] For example, the optimization objective function may be:

[0050]

[0051] Exemplarily, the multiple conditional constraint functions may include:

[0052]

[0053] f i +f j +x ij ≤2+y ij ×B; (11)

[0054] f i +f j +x ij ≥3-(1-y ij )×B; (12)

[0055]

[0056] Among them, x ij Indicates that the i-th slab is before the j-th slab in the scheduling plan, ui represents the position of the i-th slab in the plan, f i Indicates whether the i-th slab appears in the first 10 slabs (transition section) in the plan, y ij Indicates that the i-th slab in the transition section is before the j-th slab, w i is the slab weight, l i is the slab rolling length, s i 1 is the slab priority score, s ij 2 Slab width jump penalty score, s ij 3 is the penalty score for slab thickness jump, s ij 4 Slab temperature jump penalty score, λ i To optimize the weights of each objective, δ ij is the transition score compensation, D ij k Is the transition from the i-th slab to the j-th slab a restricted type (e.g., transition from tinplate to mild steel, which occurs at most once in the roll schedule), g ij Whether the i-th slab belongs to the j-th same width group, G i is the upper limit of the total kilometers of the i-th same-width group, W i l is the minimum number of blocks at the location of the i-th slab, W i r is the maximum number of blocks at the location of the i-th slab, N is the total number of candidate material blocks, N T is the length of the transition section.

[0057] Equation (1) is the optimization objective of the model, minimizing the priority reward for slabs not included in the plan and the penalty values ​​for changes in various properties of adjacent slabs within the plan. The priority reward for slabs not included in the plan can be calculated by subtracting the priority reward for slabs included in the plan from the sum of the priority rewards of candidate slabs. The sum of the priority rewards of candidate slabs is a fixed constant and is therefore not explicitly included in the formula. In addition to the penalty values ​​corresponding to cumulative rolling width, rolling thickness, and changes in the hot and cold states of slabs, the penalty values ​​for changes in various properties of adjacent slabs within the plan also include compensation values ​​for property changes between slabs in the transition section.

[0058] Formulas (2) and (3) constrain that a slab can appear at most once in the plan; Formulas (4) and (5) constrain that the plan must start from a virtual node and end at a virtual node. Formula (6) constrains that adjacent slabs in the plan must satisfy the slab adjacency matrix calculated in advance according to the plan compilation rules. Formulas (7) and (8) constrain the result to have no sub-loops by constraining the sequence numbers of the slabs included in the plan to increase. Formula (9) constrains the sequence numbers of the slabs to increase continuously. Formula (10) restricts that only the transition segment mark of the slabs with sequence numbers less than 10 can be 1. Formulas (11) and (12) restrict that only when two slabs are adjacent in the transition segment, y ij =1. Equations (13), (14), and (15) restrict the total rolling length, total weight, and number of slabs within the plan to meet capacity constraints. Equation (16) restricts the plan to meet the kilometer constraint of the same width. Equation (17) restricts the position of slabs within the plan to meet the rule constraint. Equation (18) restricts the continuous rolling of special slabs.

[0059] For example, the scheduling algorithm framework can be an ant colony algorithm (ACO), a heuristic algorithm that simulates the foraging behavior of ants in nature and is particularly suitable for solving combinatorial optimization problems. The basic idea of ​​the ACO is that ants transmit path selection information through pheromones. When exploring a path, each ant makes a choice based on the concentration of pheromones along the path and optimizes the current solution through local search. The details are as follows:

[0060] 1. Basic Principles

[0061] When ants explore the solution space, they simulate the path construction process of real-world problems. In each iteration, ants move between nodes to construct feasible solutions. The path selection depends on the following two factors:

[0062] (1) Pheromone concentration: The higher the amount of pheromone on a path, the greater the probability that the path will be selected.

[0063] (2) Heuristic information: Combined with the actual characteristics of the problem, a heuristic function is used to calculate the potential goodness or badness between nodes.

[0064] When all ants have completed their path selection, the system updates the pheromone concentration based on the quality of the path. The pheromone concentration on high-quality paths increases, while that on low-quality paths gradually decreases. This positive feedback mechanism of pheromones makes future ants more likely to choose high-quality paths.

[0065] 2. Algorithm Process

[0066] The main process of the ant colony algorithm includes the following steps:

[0067] (1) Initialization: Assign an initial pheromone value to each path and define a heuristic function to guide ants to choose a path.

[0068] (2) Path construction: Each ant selects a path based on pheromone concentration and heuristic information until a complete solution is constructed.

[0069] (3) Local search: Local optimization of the solution constructed by each ant, such as node insertion, deletion, and exchange operations, is performed to further improve the quality of the solution.

[0070] (4) Pheromone update: According to the quality of the ants’ solutions, the pheromone concentration on the high-quality paths is increased, and pheromone decay is performed at the same time to avoid falling into the local optimum.

[0071] (5) Iteration: Repeat the process of path construction and pheromone update until the predetermined termination condition is reached (such as the maximum number of iterations or the quality of the solution meets the requirements).

[0072] 3. Local Search and Global Optimization

[0073] The ant colony algorithm not only relies on pheromone-guided global search but also further optimizes the quality of the solution through local search. In each iteration, ants can make local adjustments to the current solution, such as inserting, deleting, and swapping nodes, to find a better solution. This mechanism helps prevent the algorithm from getting stuck in a local optimum and improves solution efficiency.

[0074] 4. Applicability

[0075] The ant colony algorithm is particularly suitable for complex combinatorial optimization problems such as path planning and scheduling optimization. Its dynamic search process combined with global and local optimization enables it to find near-optimal solutions in complex solution spaces.

[0076] The ant colony algorithm for the hot rolling scheduling problem is designed as follows:

[0077] 1. Penalty value design:

[0078] In the design of this embodiment, the specific value of the penalty value is adjusted according to the actual situation. The principles for adjusting the specific value are as follows:

[0079] (1) The higher the priority, the greater the slab priority reward value;

[0080] (2) The penalty value corresponding to the change of rolling width from wide to narrow is 0;

[0081] (3) The penalty value corresponding to the change in rolling width from narrow to wide is positively correlated with the absolute value of the change;

[0082] (4) The penalty value corresponding to the thickness change is positively correlated with the absolute value of the change;

[0083] (5) The absolute value of the penalty for the change in rolling thickness is much smaller than the absolute value of the penalty for the change in rolling width from narrow to wide;

[0084] (6) When materials are in short supply, the absolute value of the penalty corresponding to the change in slab properties should be appropriately increased.

[0085] (7) When there is sufficient material, the penalty value corresponding to the change in slab properties should be appropriately reduced;

[0086] (8)δ ij >0,s ij 2 <0,s ij 3 <0,s ij 4 <0.

[0087] In addition to the above basic principles, the relative size of each parameter value can be adjusted according to actual conditions.

[0088] 2. Prior matrix calculation:

[0089] The prior matrix is ​​determined by the inverse of the penalty value corresponding to the edge;

[0090] Since there are some high-priority slabs that need to transition through a specific type of slab, the prior matrix value of the edge to the specific type of slab takes the maximum value in the matrix.

[0091] 3. Next node selection:

[0092] In addition to the general adjacency matrix constraints, we also need to handle

[0093] Slab position constraints. When constructing the path, record the current number of slab blocks and select candidate nodes that do not violate the constraints.

[0094] Continuous rolling constraint: Count the number of transitions from special materials to other materials. When the number exceeds the limit of 1, no more special materials will be allowed to be added.

[0095] Constraint on the number of kilometers of same width. Pre-calculate all the same-width groups in the candidate slabs. A slab may belong to multiple same-width groups. When constructing the path, update the cumulative rolling kilometers of each same-width group. If the rolling kilometers of a group reaches the upper limit, the slab in that group will not be selected.

[0096] Rolling capacity constraints. When constructing a path, update the values ​​of each capacity constraint attribute, and terminate the path construction when a certain capacity reaches the upper limit.

[0097] 4. Calculation of evaluation indicators:

[0098] The evaluation index directly uses the mathematical model formula (1).

[0099] 5. Local Search Operator Design

[0100] (1) Insertion operator. Slabs to be scheduled are sorted by priority. The first slab is selected and the optimal insertion position (the one that maximizes the improvement in the plan evaluation index after insertion) is traversed through the plan. If there is no suitable insertion position (the index deteriorates after insertion at any position that does not violate the constraints), the slab is skipped.

[0101] (2) Delete operator. Traverse the plan and try to delete the current slab. If the plan evaluation index improves after deletion and the plan still meets all constraints, execute the deletion; otherwise, skip it.

[0102] (3) Exchange operator.

[0103] Traverse the plan and try to find the best candidate slab to replace the current slab. If the plan evaluation index is improved after the replacement and the plan still meets all constraints, delete it, otherwise skip it.

[0104] (4) Interval removal operator.

[0105] Find the widest negative return interval in the plan and try to remove all slabs in it. If the constraints are not violated, remove it; otherwise, skip it and try to remove other negative return intervals narrower than this interval.

[0106] (5) Twin ant operator.

[0107] Select the best results and find the position where the rolling width becomes wider.

[0108] The result of the first step is cropped according to the width change position, and all steel coils after the width change position are deleted.

[0109] Using the series of plans obtained in the second step as the initial solution of the ants, a group of ants is constructed to perform the ant colony algorithm. For these ants, when constructing the path, it is forbidden to select a slab with a rolling width wider than the last slab in the initial solution.

[0110] In some embodiments, embodiments of the present application provide a method for scheduling steel products, which establishes a rule configuration model corresponding to the steel products to be processed, including:

[0111] Step S301, obtaining priority marking rules and adjacency rules corresponding to the steel to be processed;

[0112] Step S302: Establish a rule configuration model based on the priority marking rule and the adjacency rule.

[0113] In this embodiment, the priority marking rule and adjacency rule corresponding to the steel to be processed are obtained, wherein the priority marking rule is a rule for marking the priority of the steel, and the adjacency rule is a rule for determining the adjacency relationship of the steel.

[0114] A rule configuration model is established based on priority marking rules and adjacency rules.

[0115] For example, the scheduling rules are summarized as follows:

[0116] 1. Hard rules. These are quantifiable constraints that must be strictly met during planning. These rules are used in scheduling systems to ensure physical feasibility and process requirements for production.

[0117] (1) Slab position constraint;

[0118] Rules: The specific location of slabs in the plan must meet certain requirements. For example, hot rolled steel must be placed in the 1st and 2nd blocks of the plan, and high-strength steel must be placed after the 12th block.

[0119] Purpose: When the slab is rolled, it will affect the state of the roller. In order to ensure that the state of the roller during the rolling of slabs of different materials and specifications meets the slab production requirements.

[0120] (2) Rules for continuous rolling of adjacent slabs;

[0121] Rule content: The adjacent slabs must meet the requirements of width, thickness, hardness, steel grade and other property changes, and the changes must meet the rule restrictions to ensure stable and continuous rolling.

[0122] Purpose: To avoid abnormal equipment load or production interruption caused by sudden changes in properties during rolling.

[0123] (3) Constraints on the number of kilometers of the same width;

[0124] Rules content: The cumulative rolling kilometers of slabs with the same rolling width within the plan must meet specific requirements.

[0125] Purpose: During slab rolling, wear of the rollers creates "marks" on the slab edges. If the cumulative rolling mileage of a slab with the same planned width is too long, the "marks" on the rollers deepen, affecting slab rolling.

[0126] (4) Roll period capacity constraints;

[0127] Rules content: The maximum total weight and maximum total rolling length of each rolling period cannot exceed the predetermined capacity limit.

[0128] Purpose: To ensure that the quantity and specifications of slabs in the rolling period are within a controllable range, avoid production overload, and ensure the normal operation of the equipment.

[0129] (5) Continuous rolling constraints;

[0130] Rules: Certain types of slabs, such as tinplate and pickled plate, must be rolled continuously without any other types of slabs mixed in.

[0131] Purpose: To prevent mixed rolling of different materials and ensure the rolling quality and process consistency of these special types of slabs.

[0132] 2. Flexible rules

[0133] Soft rules are those that lack strict quantification. These rules often include vague boundary descriptions such as "try to the best of your ability," "as far as possible," and "relatively." Despite these vague boundaries, planning must consider soft rules while meeting the rigid rules.

[0134] (1) Plan the rolling width change trend of the corresponding slab sequence;

[0135] 1. Rule Content: The rolling width of the main part of the plan should change from wide to narrow as much as possible. The rolling width of the transition section (the first section of the plan, the length of which is not fixed according to actual production) can change from narrow to wide, but the change trend should be as consistent as possible (i.e., avoid narrow to wide and then narrow again). The transition section ends after the widest slab is reached, and the subsequent slab rolling width must still meet the requirement of wide to narrow.

[0136] 2. Purpose: To reduce production instability caused by width changes during rolling, ensure smooth production, quickly transition to wider coils, and avoid "marks" on the rolls that affect production.

[0137] (2) As close as possible to the upper limit of capacity constraints;

[0138] 1. Rule content: Try to arrange the total weight and total rolling length during the rolling period to be close to the capacity limit.

[0139] 2. Purpose: To make full use of the rolling capacity of the rollers and improve production efficiency.

[0140] (3) Prioritize high-priority materials;

[0141] 1. Rule content: Try to arrange high-priority materials into the roll schedule.

[0142] 2. Purpose: To ensure that high-priority orders are completed as quickly as possible to meet customer delivery needs.

[0143] (4) Arrange as few "negative priority" materials as possible;

[0144] 1. Rule content: For some specific slabs, it is necessary to minimize their arrangement in the schedule due to reasons such as lack of order demand. They should only be used when other slabs cannot be continuously rolled and need to be transitioned through these special slabs.

[0145] 2. Purpose: To prioritize urgent or important material orders and reduce the frequency of producing low-priority materials.

[0146] (5) Reduce the change in the cold rolling state of adjacent slabs;

[0147] 1. Rule content: Minimize the changes in the cold rolling state of adjacent slabs.

[0148] 2. Purpose: To avoid frequent state transitions, reduce production adjustment time and improve efficiency.

[0149] (6) Without affecting the rolling width trend, slabs with the same rolling thickness should be distributed as concentratedly as possible;

[0150] 1. Rule content: Try to make the thickness change of adjacent slabs smooth and without sudden changes.

[0151] 2. Purpose: To avoid the influence of large thickness variation on the stability of rolling process and product quality.

[0152] Standardized scheduling issues

[0153] The specific rule parameters vary greatly depending on the type of rolled slab and the process requirements of the rolling mill. The present invention converts the specific rules into data required for subsequent algorithms.

[0154] In addition, considering that when inventory is relatively tight, if planning is strictly carried out according to the constraints of the normal mode, it is easy to obtain a shorter plan or a plan that poorly meets the flexible rules. The present invention adds a "breakpoint mode" scheduling rule based on the existing rules.

[0155] Breakpoint mode: allows a certain number of transition slabs to be set between adjacent slabs to ensure a smooth transition between slabs with different properties. The minimum number of transition slabs should be less than the set value (for example, when the width change does not exceed 50, a minimum of 4 transition slabs are required to transition from a 1200mm slab to a 1000mm slab). Breakpoint mode relaxes the constraints to ensure a longer result and better compliance with flexible rules. Although such a plan cannot be directly produced for the time being, manual intervention, calling material filling breakpoints, and other means can quickly obtain a plan that can be used as a production reference.

[0156] After completing the rule configuration, process the candidate slab data, which mainly includes the following parameters:

[0157] 1. Slab priority.

[0158] 2. An adjacency matrix indicating whether any two slabs can appear consecutively in the plan (slabs that are consecutive in the plan in normal mode are rolled continuously during production, while in breakpoint mode manual intervention is required, but this is not distinguished when the plan is compiled).

[0159] 3. The location range of the slab within the plan is limited.

[0160] 4. Planned transition length.

[0161] 5. Restrictions on the number of kilometers of the same width within the plan.

[0162] 6. Planned capacity.

[0163] 7. Types of steel that need to be continuously rolled within the plan.

[0164] When computers process flexible rules, they cannot rely on experience and intuition like humans do when planning. Instead, they must use quantifiable and calculable methods.

[0165] The present invention processes flexible rules by setting the following centralized parameters:

[0166] 1. Priority level rewards for slabs.

[0167] 2. If two slabs appear consecutively in the plan, the penalty value corresponding to the change in their properties is applied.

[0168] 3. The property changes of the slabs in the transition section and the non-transition section are considered differently, and a compensation value is given to the property changes of two slabs appearing continuously in the transition section.

[0169] 1. In actual production and during the promotion of intelligent scheduling technology, the specific priority determination rules for materials to be processed and other rules may change. Therefore, it is particularly important to design a rule framework that is highly versatile and easy to maintain. The following describes the rule configuration framework designed by this invention.

[0170] The rule configuration framework is configured based on the table structure and configures the data processing process by parsing the table.

[0171] (1) Constant table

[0172] Header: 1) English identifier; 2) value; 3) Chinese identifier;

[0173] The constant table stores key values ​​used in rule configuration that are not specific to the slab or intermediate calculation results. Its English identifiers begin with the letters "#p" and are unique. The Chinese identifiers are brief descriptions of the constants, such as "Hot Forming Entry Width Variation Range."

[0174] (2) Single slab attribute value calculation table

[0175] Table header: 1) English identifier; 2) attribute name; 3) operation type; 4) operation parameters; 5) Chinese identifier.

[0176] The single slab attribute value calculation table configures various single slab value calculation operations required for data processing. English identifiers begin with "#s" and are unique. Chinese identifiers are brief descriptions of the operation, such as "entry width" as a Chinese identifier.

[0177] There are three types of operations: value, value fragment, and value inclusion. The value operation directly returns the value corresponding to the slab attribute name configured for the operation, and its operation parameter must be empty. The value fragment returns a segment of the string type value corresponding to the attribute name, and its operation parameter is an index range. The value inclusion determination determines whether the attribute name contains the operation parameter and returns the determination result.

[0178] Operation parameters must be set according to the standard. For value operations, the operation parameter is empty; for value fragment operations, the operation parameter is an index range, such as "[2,4]"; for value inclusion checks, the operation parameter is a character type. Operation parameters can also be set to existing parameters in the constant table by filling in the corresponding identifier.

[0179] (3) Double slab attribute value calculation table

[0180] Table header: 1) English identifier; 2) Operation type; 3) Operand one; 4) Operand two; 5) Chinese identifier.

[0181] The double slab attribute value operation table configures various attribute value operations for paired slabs required for data processing. English identifiers begin with "#d" and are unique.

[0182] The most commonly used operation type for double slabs is "difference." This operation calculates the difference between operand one and operand two and returns the difference. Operand one and operand two can be identifiers for operations defined in the single slab attribute value operation table, constants in the constant table, or nested operations defined in other double slab attribute value operation tables (they cannot call themselves, as this will result in an infinite loop). It's important to note that double slab value operations involve two slabs, and the order of the two slabs affects the operation. Single slab attribute value operations, on the other hand, only involve one slab.

[0183] Operation rules: If the operation designated as operand one by default is a single slab attribute value operation, it is performed on the first slab; if the operation designated as operand two by default is a single slab attribute value operation, it is performed on the second slab; double slab attribute value operations are nested and the order of the slabs is not changed; modify the identifier of the operation and add "[1]" or "[2]" to specify the slab, for example, "get entrance width [1]" means to get the "entrance width" attribute of the first slab.

[0184] (4) Value determination operation table

[0185] Table header: 1) English identifier; 2) Operation type; 3) Operand one; 4) Operand two; 5) Chinese identifier.

[0186] The header of the value determination operation table is essentially the same as the double-slab attribute value operation table. The difference between the two is that the value determination operation can be performed on a single slab or a pair of slabs. If the operand is a single-slab attribute value operation, the slabs must be specified; if the operand is a double-slab attribute value operation, the slab order remains unchanged. Its English identifier begins with "#j".

[0187] The main types of value determination operations include "belongs to," "equals," "interval," "less than," "greater than," "less than or equal to," and "greater than or equal to." Here, we briefly explain "belongs to" and "interval." The second operand of "belongs to" is a list-type data, represented by a string separated by ","; the second operand of "interval" is a numeric interval "[minimum value, maximum value]." It returns true if the operand is within the range, otherwise it returns false.

[0188] (5) Joint operation table

[0189] Table header: 1) English identifier; 2) Operation type; 3) Operand list; 4) Chinese identifier.

[0190] A join operation forms the criteria for a specific rule by organizing value-determination operations. There are three types of operations: AND, OR, and NOT. The operand list for AND and OR is a list of identifiers for the value-determination or join operation, while the operand list for NOT is an identifier for a single operation. English identifiers begin with "#u."

[0191] Note that the joint operation is performed on pairs of slabs. Therefore, for the various operation identifiers in the operand list, if the operation is performed on a single slab, "[1]" or "[2]" is appended to the identifier to specify the slab.

[0192] Based on the above table, you can complete the configuration of most rules. The following uses priority marking rules and adjacency rules as examples to illustrate.

[0193] (1) Priority marking rules

[0194] Priority marking rules analyze the properties of a single slab and determine its priority based on the set parameters.

[0195] Therefore, a single priority marking rule can be described by (decision condition, priority): when the slab attributes meet the determination condition, the corresponding priority is assigned.

[0196] First define the priority marking rule table

[0197] Table header: 1) Identifier; 2) Decision condition; 3) Priority. Decision condition is the operation defined in the value decision operation table or the joint operation table.

[0198] For example, there is a rule as follows: when the slab's inventory time is greater than 10 days, its priority is 3.

[0199] First, configure the single coil calculation table as shown in Table 1, the constant table as shown in Table 2, the attribute determination table as shown in Table 3, and the priority marking rule table as shown in Table 4:

[0200] Table 1

[0201] English identifier Attribute Name Operation type Operation parameters Chinese identifiers #s1 Time in library Value Retrieval time

[0202] Table 2

[0203] English identifier value Chinese identifiers #p1 10 Time in library3

[0204] Table 3

[0205]

[0206] Table 4

[0207] Identifier Judgment conditions Priority #r1 #j1[1] 3

[0208] (2) adjacency rules;

[0209] Adjacency rules analyze the properties of paired slabs to determine whether they can be rolled continuously. A single adjacency rule is a binary tuple consisting of (trigger condition, judgment condition). Given two slabs, continuous rolling is assumed to be possible. If the two slabs meet an adjacency rule's trigger condition but not its judgment condition, continuous rolling is prohibited. In other words, the necessary and sufficient condition for continuous rolling of two slabs is to test the trigger condition and judgment condition for any adjacency rule against the two slabs, and either the trigger condition is false or the judgment condition is true.

[0210] For example, there is a rule that states that if either slab is high-strength steel, the difference in rolled width between the two slabs cannot exceed 80. High-strength steel refers to slabs whose grade code's third to sixth digits are "60DP," "80DP," "A0DP," or "A2DP."

[0211] Define the adjacency rule table:

[0212] Header: 1) Identifier; 2) Trigger condition; 3) Decision condition.

[0213] First, configure the single coil calculation table as shown in Table 5, the constant table as shown in Table 6, the double coil attribute value calculation table as shown in Table 7, the attribute determination table as shown in Table 8, the joint calculation table as shown in Table 9, and the rule table as shown in Table 10:

[0214] Table 5

[0215]

[0216] Table 6

[0217]

[0218] Table 7

[0219]

[0220]

[0221] Table 8

[0222]

[0223] Table 9

[0224]

[0225] Table 10

[0226] Identifier Trigger Conditions Judgment conditions #r2 #u1 #j3

[0227] The consideration of whether two slabs can be rolled continuously generally involves multiple slabs. For any two slabs, the rule table is traversed. Currently, continuous rolling is allowed only when there is no rule that determines that the two cannot be rolled continuously.

[0228] 2. Breakpoint Mode Adjacency Determination Method

[0229] In the breakpoint mode, whether two slabs can appear continuously in the plan depends on the minimum number of slabs that can be inserted between the two to ensure continuous rolling.

[0230] 1. Determine which rules cause the two slabs to not be rolled continuously;

[0231] 2. Calculate the minimum number of slabs that need to be inserted between two slabs under each rule;

[0232] 3. For the results of step 2, take the maximum value to determine whether the two slabs can appear continuously in the planned seeding.

[0233] For step 2, since each rule has different forms, the calculation is too complex and not very useful for human reference. Therefore, we select rules with relatively simple logic to design the breakpoint pattern.

[0234] Taking the rolling width transition rule of high-strength steel as an example, the absolute value of the rolling width difference between two slabs is divided by 80 and taken downward to calculate the minimum number of slabs that need to be inserted between the two slabs.

[0235] In some embodiments, embodiments of the present application provide a steel scheduling method, which processes steel data based on a rule configuration model to obtain scheduling task parameters, including:

[0236] Step S401, setting steel material data as first input data;

[0237] Step S402: inputting first input data into the rule configuration model to obtain first output data output by the rule configuration model;

[0238] Step S403: determining the scheduling task parameters according to the first output data.

[0239] In this embodiment, the steel material data is set as the first input data, wherein the first input data is the input data of the rule configuration model.

[0240] Inputting first input data into the rule configuration model to obtain first output data output by the rule configuration model, wherein the first output data is output data of the rule configuration model.

[0241] Determine the scheduling task parameters according to the first output data.

[0242] In some embodiments, embodiments of the present application provide a steel scheduling method, which processes the scheduling task parameters based on a scheduling algorithm model to obtain steel scheduling information, including:

[0243] Step S501, obtaining algorithm control parameters of the scheduling algorithm model;

[0244] Step S502, setting the scheduling task parameters and algorithm control parameters as second input data;

[0245] Step S503, inputting the second input data into the scheduling algorithm model to obtain second output data output by the scheduling algorithm model;

[0246] Step S504: Determine steel material scheduling information based on the second output data.

[0247] In this embodiment, an algorithm control parameter of the scheduling algorithm model is obtained, wherein the algorithm control parameter is a control parameter of the scheduling algorithm model.

[0248] The scheduling task parameters and the algorithm control parameters are set as second input data, wherein the second input data is input data of the scheduling algorithm model.

[0249] The second input data is input into the scheduling algorithm model to obtain second output data output by the scheduling algorithm model, wherein the second output data is the output data of the scheduling algorithm model.

[0250] Steel material scheduling information is determined based on the second output data.

[0251] In some embodiments, an embodiment of the present application provides a steel scheduling method, further comprising:

[0252] Step S601, performing data verification processing on the steel scheduling information to obtain the verification result of the steel scheduling information;

[0253] Step S602: If the verification result is executable, schedule the steel to be processed according to the steel scheduling information.

[0254] In this embodiment, data verification processing is performed on the steel scheduling information to obtain a verification result of the steel scheduling information, wherein the verification result indicates the feasibility of the steel scheduling information.

[0255] Exemplarily, the verification result may be executable or not executable.

[0256] If the verification result is executable, the steel to be processed is scheduled according to the steel scheduling information.

[0257] In some embodiments, as Figure 2 As shown, an embodiment of the present application provides a steel scheduling device 700, comprising:

[0258] An acquisition unit 702 is used to acquire steel material data of the steel material to be processed;

[0259] Processing unit 704 is used to establish a rule configuration model corresponding to the steel to be processed and establish a scheduling algorithm model;

[0260] The processing unit 704 is further used to process the steel data based on the rule configuration model to obtain scheduling task parameters;

[0261] The processing unit 704 is further configured to perform data processing on the scheduling task parameters based on the scheduling algorithm model to obtain steel scheduling information, wherein the steel scheduling information represents the arrangement order of the steel to be processed.

[0262] In this embodiment, a steel scheduling device 700 is proposed to obtain steel data of the steel to be processed, establish a rule configuration model corresponding to the steel to be processed, and establish a scheduling algorithm model at the same time, wherein the steel to be processed is the steel to be processed, the rule configuration model is a mathematical model for determining the scheduling rules, and the scheduling algorithm model is a mathematical model for determining the steel scheduling plan.

[0263] Illustratively, the steel materials to be processed may be a plurality of steel slabs from the same batch.

[0264] Exemplarily, the scheduling algorithm model may be a mathematical model including an ant colony algorithm.

[0265] Based on the rule configuration model, the steel data is processed to obtain scheduling task parameters, wherein the scheduling task parameters are relevant parameters of the steel scheduling task.

[0266] Exemplarily, the scheduling task parameters may include scheduling rules.

[0267] Based on the scheduling algorithm model, data processing is performed on the scheduling task parameters to obtain steel scheduling information, wherein the steel scheduling information represents the arrangement order of the steel to be processed.

[0268] For example, the steel scheduling information may indicate a plurality of target steels that need to be sorted among the steels to be processed, and may assign sorting numbers to the plurality of target steels that need to be sorted.

[0269] For example, before the steel to be processed is rolled, the steel scheduling information is used to schedule the steel to be processed.

[0270] The steel scheduling method in this embodiment uses a scheduling algorithm model to quickly and accurately determine the steel scheduling information of the steel to be processed. Compared with manual sorting of the steel to be processed, this embodiment greatly improves the efficiency of steel production sorting while ensuring the accuracy of steel production sorting.

[0271] In some embodiments, an embodiment of the present application provides a steel scheduling device 700, further comprising:

[0272] The processing unit 704 is further configured to obtain a preset scheduling algorithm framework and obtain scheduling decision variables and scheduling auxiliary variables corresponding to the steel to be processed;

[0273] The processing unit 704 is further configured to determine an optimization objective function and a plurality of conditional constraint functions based on the scheduling decision variables and the scheduling auxiliary variables;

[0274] The processing unit 704 is further configured to establish a scheduling algorithm model based on the scheduling algorithm framework, the optimization objective function, and the plurality of conditional constraint functions.

[0275] In some embodiments, an embodiment of the present application provides a steel scheduling device 700, further comprising:

[0276] The processing unit 704 is further configured to obtain a priority marking rule and an adjacency rule corresponding to the steel material to be processed;

[0277] The processing unit 704 is further configured to determine an optimization objective function and a plurality of conditional constraint functions based on the scheduling decision variables and the scheduling auxiliary variables;

[0278] The processing unit 704 is further configured to establish a scheduling algorithm model based on the scheduling algorithm framework, the optimization objective function, and the plurality of conditional constraint functions.

[0279] In some embodiments, an embodiment of the present application provides a steel scheduling device 700, further comprising:

[0280] The processing unit 704 is further configured to obtain a priority marking rule and an adjacency rule corresponding to the steel material to be processed;

[0281] The processing unit 704 is further configured to establish a rule configuration model based on the priority marking rule and the adjacency rule.

[0282] In some embodiments, an embodiment of the present application provides a steel scheduling device 700, further comprising:

[0283] The processing unit 704 is further configured to set the steel material data as the first input data;

[0284] The processing unit 704 is further configured to input the first input data into the rule configuration model to obtain first output data output by the rule configuration model;

[0285] The processing unit 704 is further configured to determine a scheduling task parameter according to the first output data.

[0286] In some embodiments, an embodiment of the present application provides a steel scheduling device 700, further comprising:

[0287] The processing unit 704 is further configured to obtain algorithm control parameters of the scheduling algorithm model;

[0288] The processing unit 704 is further configured to set the scheduling task parameters and the algorithm control parameters as second input data;

[0289] The processing unit 704 is further configured to input the second input data into the scheduling algorithm model to obtain second output data output by the scheduling algorithm model;

[0290] The processing unit 704 is further configured to determine steel scheduling information based on the second output data.

[0291] In some embodiments, an embodiment of the present application provides a steel scheduling device 700, further comprising:

[0292] The processing unit 704 is further configured to perform data verification processing on the steel scheduling information to obtain a verification result of the steel scheduling information;

[0293] The processing unit 704 is further configured to schedule the steel to be processed according to the steel scheduling information when the verification result indicates that the steel is executable.

[0294] In some embodiments, as Figure 3 As shown, a steel scheduling device 800 is provided. The steel scheduling device 800 includes a processor 802 and a memory 804. The memory 804 stores a computer program that, when executed by the processor 802, implements the steps of the steel scheduling method described in any of the aforementioned embodiments. Therefore, the steel scheduling device 800 possesses all the benefits of the steel scheduling method described in any of the aforementioned embodiments, and will not be further elaborated upon here.

[0295] In some embodiments, a readable storage medium is provided on which a program is stored. When the program is executed by a processor, the steps of the steel scheduling method in any of the above embodiments are implemented, thereby having all the beneficial technical effects of the steel scheduling method in any of the above embodiments.

[0296] In one embodiment of the present application, a computer program product includes computer instructions that, when executed by a processor, implement the steps of the steel scheduling method described in any of the above-described embodiments. Therefore, this computer program product possesses all the benefits of the steel scheduling method described in any of the above-described embodiments.

[0297] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0298] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-readable program code.

[0299] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, 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, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0300] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0301] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0302] An embodiment of the present application further provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device executes the process of the steel scheduling method.

[0303] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. 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 a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)).

[0304] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0305] In the several embodiments provided in this application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0306] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0307] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0308] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0309] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

[0310] Although the preferred embodiments of this specification have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of this specification.

[0311] Obviously, those skilled in the art may make various changes and modifications to this specification without departing from the spirit and scope of this specification. Thus, if such changes and modifications fall within the scope of the claims of this specification and their equivalents, this specification is intended to include such changes and modifications.

Claims

1. A method for scheduling steel products, characterized in that: The method comprises: Obtaining steel material data of steel to be processed; Establishing a rule configuration model corresponding to the steel to be processed and establishing a scheduling algorithm model; Based on the rule configuration model, the steel data is processed to obtain scheduling task parameters; Based on the scheduling algorithm model, the scheduling task parameters are processed to obtain steel scheduling information, wherein the steel scheduling information represents the arrangement order of the steel to be processed.

2. The method according to claim 1, characterized in that: The establishing of the scheduling algorithm model comprises: Obtaining a preset scheduling algorithm framework, and obtaining scheduling decision variables and scheduling auxiliary variables corresponding to the steel to be processed; Determining an optimization objective function and a plurality of conditional constraint functions according to the scheduling decision variables and the scheduling auxiliary variables; The scheduling algorithm model is established based on the scheduling algorithm framework, the optimization objective function and the plurality of conditional constraint functions.

3. The method according to claim 1, characterized in that The step of establishing a rule configuration model corresponding to the steel material to be processed includes: Obtaining priority marking rules and adjacency rules corresponding to the steel material to be processed; The rule configuration model is established based on the priority marking rule and the adjacency rule.

4. The method according to claim 1, characterized in that: The step of processing the steel data based on the rule configuration model to obtain scheduling task parameters includes: Setting the steel material data as first input data; Inputting the first input data into the rule configuration model to obtain first output data output by the rule configuration model; The scheduling task parameters are determined according to the first output data.

5. The method according to claim 1, characterized in that The step of performing data processing on the scheduling task parameters based on the scheduling algorithm model to obtain steel scheduling information includes: Obtaining algorithm control parameters of the scheduling algorithm model; Setting the scheduling task parameter and the algorithm control parameter as second input data; Inputting the second input data into the scheduling algorithm model to obtain second output data output by the scheduling algorithm model; The steel material scheduling information is determined according to the second output data.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: Performing data verification processing on the steel scheduling information to obtain a verification result of the steel scheduling information; When the verification result is executable, the steel to be processed is scheduled according to the steel scheduling information.

7. A steel scheduling device, characterized in that: The device comprises: An acquisition unit, used for acquiring steel material data of the steel material to be processed; A processing unit, used to establish a rule configuration model corresponding to the steel to be processed and a scheduling algorithm model; The processing unit is further used to process the steel data based on the rule configuration model to obtain scheduling task parameters; The processing unit is further used to perform data processing on the scheduling task parameters based on the scheduling algorithm model to obtain steel scheduling information, wherein the steel scheduling information represents the arrangement order of the steel to be processed.

8. A steel scheduling device, characterized in that: include: processor; A memory, wherein a program or instruction is stored in the memory, and when the processor executes the program or instruction in the memory, the steps of the steel scheduling method as claimed in any one of claims 1 to 6 are implemented.

9. A readable storage medium, characterized in that: The readable storage medium stores programs or instructions, and when the programs or instructions are executed by the processor, the steps of the steel scheduling method as described in any one of claims 1 to 6 are implemented.

10. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the steel scheduling method described in any one of claims 1 to 6 are implemented.

Images