Steel production scheduling method and system, electronic equipment and storage medium

Abstract

The invention provides a steel production scheduling method and system, electronic equipment and a storage medium, and the method comprises the steps: obtaining the production supply and marketing data, production technology data, rolling line production state parameters and billet stock parameters of a steel production process, building a production planning model, and carrying out the initial production plan scheduling solving according to the production planning model; obtaining an initial production scheduling plan, and solving the initial production scheduling plan based on a large-scale neighborhood search algorithm and a production planning model to obtain an optimal production scheduling plan; according to the method, the production planning model is constructed through the supply and marketing, the process, the rolling line production state and the billet stock, the initial production plan scheduling is performed, and the initial plan is iteratively optimized by means of the neighborhood search algorithm to obtain the optimal production scheduling plan, so that the problem of overall non-optimization caused by existing single-link optimization is solved, and the production efficiency is improved. The production flexibility and response speed of an enterprise under complex production process conditions and a dynamic market environment are improved, and global optimization of a production plan is realized.

Description

Technical Field

[0001] The present application relates to the field of production, and in particular to a steel production scheduling method, system, electronic device and storage medium. Background Art

[0002] In the wire rod manufacturing process of steel enterprises, the three key steps of steelmaking, continuous casting and rolling are closely connected to form a production process system. Among them, changes in any stage may have an impact on other links. Therefore, when planning production, we should not only consider the technical level, but also put the linkage characteristics of the entire production process and market changes under the same decision-making framework for comprehensive consideration. Based on the instability of the market and the rapid change of product profitability, the production scheduling process must be able to quickly adjust the production strategy to ensure the maximization of the company's interests. This requires not only understanding the various limiting factors in the production process, but also having the perception of market changes and being able to accurately determine the production priorities of different products based on the current market trends.

[0003] However, in the process of formulating production plans for most steel companies today, firstly, the complexity of production processes and changes in the market environment have significantly increased the difficulty in pursuing multiple goals at the same time, such as increasing hot charging rates, effectively managing inventory levels, and improving overall production efficiency. Secondly, there is currently a lack of production planning and scheduling methods that can fully integrate steelmaking, continuous casting, rolling processes and market dynamic change analysis, making it impossible to globally achieve adaptive analysis and scheduling of existing production process systems. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a steel production scheduling method, system, electronic device and storage medium to solve the above technical problems.

[0005] The present invention provides a steel production scheduling method, which comprises: obtaining production supply and marketing data, production process data, rolling line production state parameters and billet inventory parameters of a steel production process; constructing a production planning model according to the production supply and marketing data, production process data, rolling line production state parameters and billet inventory parameters, wherein the production planning model takes minimization of maximum out-of-stock time, maximization of minimum inventory duration, minimization of out-of-stock penalty score and maximization of hot charging rate as optimization objective functions, and the production planning model takes process conditions and production time as constraints; performing initial production planning scheduling solution according to the production planning model to obtain an initial production scheduling plan; performing iterative optimization solution on the initial production scheduling plan based on a large-scale neighborhood search algorithm and the production planning model until a preset iterative optimization termination condition is reached to obtain an optimal production scheduling plan, wherein the preset iterative optimization termination condition includes that the number of iterative optimization solutions reaches a preset maximum number of iterative optimization solutions.

[0006] In one embodiment of the present invention, constructing a production planning model based on the production supply and marketing data, production process data, rolling line production status parameters and billet inventory parameters includes: mathematically describing and defining the production line according to the production supply and marketing data, production process data, rolling line production status parameters and billet inventory parameters to obtain mathematical description information of the production line; performing mathematical modeling based on the mathematical description information of the production line to obtain an initial production line model; setting constraints with process conditions and production time as boundaries for the initial production line model according to the mathematical description information of the production line, and constructing an optimization objective function based on the optimization objective to obtain a production planning model.

[0007] In one embodiment of the present invention, the constraints include at least part of the following: one type of steel must be cast during the startup period of each continuous casting machine; the inventory of the type of steel after each shift is equal to the inventory at the end of the previous shift plus the output of the current shift minus the consumption of hot charging or cold charging of the current shift; the total gas consumption per day is less than or equal to the available gas volume of the day; each rolling line can only choose hot charging or cold charging for each specification of products; during hot charging, the production capacity speed of the continuous casting machine is greater than the required hot charging speed; the output of different specifications of each type of steel in each rolling line of each shift does not exceed the maximum production limit of hot charging or cold charging; the cold charging usage of each type of steel does not exceed the maximum limit corresponding to the steel type; each rolling line of each shift produces at most one product; each product of each shift can only be produced on one rolling line at most; the inventory of each specification of product per day is equal to The previous day's surplus plus the current day's hot and cold production minus the estimated sales volume; the initial available gas volume each day is the previous day's surplus gas plus the current day's production gas; the remaining gas volume at the end of each day is equal to the previous day's surplus minus the current day's production minus the current day's consumption; the continuous casting machine and rolling line cannot be used during the shutdown shift; the linear constraint of minimizing the out-of-stock time and maximizing the inventory duration linear constraint; the sum of the non-out-of-stock and out-of-stock penalty variables of each product each day is 1; the out-of-stock penalty score of each product each day is the sum of the penalty score of the non-out-of-stock days and the penalty score of the out-of-stock days; each rolling line in each shift adds a roll change time constraint when changing products; the output of each product in each shift is the maximum output minus the loss output caused by roll change; the production process in any rolling line must meet the continuous minimum production shift restriction.

[0008] In one embodiment of the present invention, the production scheduling plan includes a rolling plan, a pouring plan and a furnace plan. The initial production scheduling solution is performed according to the production planning model to obtain the initial production scheduling plan including: obtaining schedulable shift information, the specification information of the rolled products of the current rolling production, the produced shifts of the current rolled product specifications, the sustainable production days of the rolling line that can produce the specified products, the out-of-stock days of the rolling line that can produce the specified products, and the inventory information of each type of steel billet; determining the corresponding minimum continuous production shift according to the rolled product specification information, and determining the rolling plan in production according to the produced shifts of the current rolled product specifications and the minimum continuous production shift; if there is a product that can produce the specified products of the rolling line with a number of out-of-stock days that is greater than the maximum allowable out-of-stock days corresponding to the product that can produce the specified products, then determining the minimum continuous production shift according to the rolling product specification information; determining the minimum continuous production shift according to the rolling product specification information; determining the rolling plan in production according to the produced shifts and the minimum continuous production shift of the current rolled product specifications; if there is a product that can produce the specified products of the rolling line with a number of out-of-stock days that is greater than the maximum allowable out-of-stock days corresponding to the product that can produce the specified products, then determining the minimum continuous production shift according to the rolling product specification information; ... Prioritize the out-of-stock days to obtain the rolling schedule specification sequence; if there is no product with specifications that can be produced by the rolling line with a number of out-of-stock days greater than the maximum allowable out-of-stock days corresponding to the product with specifications that can be produced, prioritize the product with specifications that can be produced by the rolling line according to the sustainable production days to obtain the rolling schedule specification sequence; schedule shifts are allocated according to the rolling schedule specification sequence and the schedulable shift information to obtain the rolling plan; determine the net demand for steel grades for steelmaking according to the demand for steel billets of each steel grade and the inventory information of steel billets of each steel grade in the rolling plan, and allocate the scheduling shifts for pouring and furnace according to the net demand for steel grades for steelmaking and the schedulable shift information to obtain the pouring plan and furnace plan; solve the rolling plan, pouring plan and furnace plan in the production planning model to determine the initial production scheduling plan.

[0009] In one embodiment of the present invention, iterative optimization and solution of the initial production schedule plan based on the large-scale neighborhood search algorithm and the production planning model includes: setting a first optimization operator and a second optimization operator, the first optimization operator is used to adjust the production shift of the rolling product specifications, and the second optimization operator is used to adjust the rolling schedule specification sequence; configuring the selection probability of the first optimization operator and the second optimization operator based on the preset operator calculation weights to obtain operator optimization selection configuration information; solving the initial production schedule plan according to the large-scale neighborhood search algorithm based on the operator optimization selection configuration information to obtain the current optimized production schedule plan, and scoring the current optimized production schedule plan according to the preset scoring criteria to obtain the optimization plan score; updating the preset operator calculation weight according to the optimization plan score, and iteratively optimizing based on the updated preset operator calculation weight until the preset iterative optimization termination condition is reached.

[0010] In one embodiment of the present invention, the first optimization operator includes keeping the total shifts unchanged, reducing the number of continuous production shifts corresponding to the product with the most sustainable production days, and increasing the number of continuous production shifts corresponding to the product specifications with the least sustainable production days; the second optimization operator includes adjusting the order of products with the most out-of-stock days to give priority to production.

[0011] In one embodiment of the present invention, after obtaining the current optimized production schedule, the steel production scheduling method also includes: if the current optimized production schedule does not meet the constraints of the production planning model, the target value of the current optimized production schedule is updated to infinity, and a simulated annealing algorithm is introduced to recalculate with a preset solution probability to solve a second optimized production schedule that meets the constraints of the production planning model.

[0012] An embodiment of the present invention also provides a steel production scheduling system, which includes: a production process parameter acquisition module, which is used to acquire production supply and marketing data, production process data, rolling line production status parameters and billet inventory parameters of the steel production process; a production planning model construction module, which is used to construct a production planning model based on the production supply and marketing data, production process data, rolling line production status parameters and billet inventory parameters, the production planning model takes minimization of maximum out-of-stock time, maximization of minimum inventory duration, minimization of out-of-stock penalty score and maximization of hot loading rate as optimization objective functions, and the production planning model takes process conditions and production time as constraints; a production scheduling plan optimization module, which is used to perform initial production plan scheduling solution according to the production planning model to obtain an initial production scheduling plan; based on a large-scale neighborhood search algorithm and the production planning model, iteratively optimize and solve the initial production scheduling plan until a preset iterative optimization termination condition is reached to obtain an optimal production scheduling plan, and the preset iterative optimization termination condition includes the number of iterative optimization solutions reaching a preset maximum number of iterative optimization times.

[0013] An embodiment of the present invention also provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the electronic device implements a steel production scheduling method as described in any one of the above embodiments.

[0014] An embodiment of the present invention further provides a computer-readable storage medium having computer-readable instructions stored thereon. When the computer-readable instructions are executed by a processor of a computer, the computer executes the steel production scheduling method as described in any one of the above embodiments.

[0015] The present invention provides a steel production scheduling method, system, electronic device and storage medium. The method obtains production supply and marketing data, production process data, rolling line production status parameters and billet inventory parameters of the steel production process and constructs a production planning model. The initial production plan scheduling is solved according to the production planning model to obtain an initial production scheduling plan. The initial production scheduling plan is solved based on a large-scale neighborhood search algorithm and a production planning model to obtain an optimal production scheduling plan. The present invention systematically collects production supply and marketing data, production process data, rolling line production status parameters and billet inventory parameters to provide comprehensive data support for production planning. On this basis, a production scheduling method is constructed to minimize the maximum out-of-stock time and maximize the minimum inventory available. A production planning model with duration, minimizing out-of-stock penalty score and maximizing hot loading rate as the optimization objective function is established, and the actual process conditions and production time are set as the constraints of the model. The model performs initial production planning and scheduling. After generating a preliminary production schedule, the initial schedule is optimized and solved for multiple times based on a large-scale neighborhood search algorithm until the preset iterative optimization termination condition is reached. This effectively solves the scheduling problems caused by the complexity of the production process and the dynamic nature of the market environment in the steel production process, realizes the scientific and intelligent production planning, improves production efficiency and inventory management level, and enhances the company's ability to respond quickly to changes in market demand, thereby achieving overall optimization of the production plan.

[0016] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0018] Figure 1 is a schematic diagram of an exemplary system architecture shown in an exemplary embodiment of the present application;

[0019] Figure 2 is a flow chart of a steel production scheduling method shown in an exemplary embodiment of the present application;

[0020] Figure 3 It is a specific flow chart of generating integrated plan for wire rod steel rolling shown in an exemplary embodiment of the present application;

[0021] Figure 4It is a flowchart of a specific steel enterprise wire rod steel rolling integrated planning method shown in an exemplary embodiment of the present application;

[0022] Figure 5 is a schematic diagram of a steel production scheduling system shown in an exemplary embodiment of the present application;

[0023] Figure 6 It is a structural diagram of a computer system of an electronic device shown in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0024] The following will describe the embodiments of the present invention with reference to the accompanying drawings and specific embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0025] It should be noted that the illustrations provided in the following embodiments are only used to illustrate the basic concept of the present invention in a schematic manner, and thus the illustrations only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0026] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0027] The "and / or" mentioned in this application describes the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0028] Figure 1 It is a schematic diagram of an exemplary system architecture shown in an exemplary embodiment of the present application.

[0029] Reference Figure 1As shown, the system architecture may include a production control system 110 and a computer device 120. The computer device 120 obtains the production supply and marketing data, production process data, rolling line production state parameters and billet inventory parameters of the steel production process through the production control system 110, and constructs a production planning model based on the production supply and marketing data, production process data, rolling line production state parameters and billet inventory parameters. The production planning model takes the minimization of the maximum out-of-stock time, the maximization of the minimum inventory duration, the minimization of the out-of-stock penalty score and the maximization of the hot charging rate as the optimization objective function, and the production planning model takes the process conditions and production time as the constraints; the initial production plan scheduling is solved according to the production planning model to obtain the initial production scheduling plan; the initial production scheduling plan is iteratively optimized and solved based on the large-scale neighborhood search algorithm and the production planning model until the preset iterative optimization termination condition is reached to obtain the optimal production scheduling plan, and the preset iterative optimization termination condition includes that the number of iterative optimization solutions reaches the preset maximum number of iterative optimization times. The above-mentioned computer device 120 may be at least one of a microcomputer, an embedded computer, a network computer, a single-chip microcomputer, etc.; the above-mentioned production control system 110 is at least used to control steelmaking operations, continuous casting operations and rolling operations.

[0030] Schematically, the computer device 120 obtains the production supply and marketing data, production process data, rolling line production status parameters and billet inventory parameters of the steel production process through the production control system 110 and constructs a production planning model, performs initial production planning scheduling solution according to the production planning model, obtains an initial production scheduling plan, solves the initial production scheduling plan based on a large-scale neighborhood search algorithm and the production planning model, and obtains an optimal production scheduling plan; the present invention provides comprehensive data support for production planning by systematically collecting production supply and marketing data, production process data, rolling line production status parameters and billet inventory parameters, and on this basis, constructs a system to minimize the maximum out-of-stock time and maximize the minimum inventory duration. , minimizing the out-of-stock penalty score and maximizing the hot loading rate as the optimization objective function of the production planning model, and setting the actual process conditions and production time as the constraints of the model. The model performs initial production planning and scheduling. After generating a preliminary production schedule, the initial schedule is optimized and solved for multiple times based on a large-scale neighborhood search algorithm until the preset iterative optimization termination condition is reached. This effectively solves the scheduling problems caused by the complexity of the production process and the dynamic nature of the market environment in the steel production process, realizes the scientific and intelligent production planning, improves production efficiency and inventory management, and enhances the company's ability to respond quickly to changes in market demand, thereby achieving overall optimization of the production plan.

[0031] Figure 2 is a flowchart of a steel production scheduling method shown in an exemplary embodiment of the present application. The steel production scheduling method can be Figure 1The implementation environment may be implemented in other implementation environments, and the above implementation environments are not specifically limited here. Figure 2 As shown, the flowchart of the steel production scheduling method includes at least steps S210 to S240, which are described in detail as follows:

[0032] In step S210, production supply and marketing data, production process data, rolling line production status parameters and billet inventory parameters of the steel production process are obtained.

[0033] In one embodiment of the present application, the above-mentioned steel production process specifically refers to the steelmaking-continuous casting-rolling production process in the steel production system, and the above-mentioned production supply and marketing data include whether each product is allowed to be out of stock, the maximum number of days the product is out of stock, whether the product is efficient, and the estimated daily sales volume of the product; the above-mentioned production process data includes the continuous casting machine start-up and shutdown plan, the rolling line maintenance plan, the production capacity of each rolling line, the time for rolling line roll changing, gas consumption, the corresponding steel grade of the product and other information; the rolling line production status parameters include at least the current rolling line continuous production shift, current product specification information, etc.; the billet inventory parameters include at least the current billet available inventory, product available inventory and other information.

[0034] In step S220, a production planning model is constructed based on production supply and marketing data, production process data, rolling line production status parameters and billet inventory parameters.

[0035] In one embodiment of the present application, the above-mentioned production planning model takes minimizing the maximum out-of-stock time, maximizing the minimum inventory duration, minimizing the out-of-stock penalty score and maximizing the hot loading rate as the optimization objective function, and the above-mentioned production planning model takes process conditions and production time as constraints.

[0036] In one embodiment of the present application, the production planning model uses a mixed integer programming model to describe the production process and market considerations, with the hourly capacity, producible specifications, equipment maintenance time, etc. in the steelmaking-continuous casting-rolling process as constraints, and the furnace and casting operation plans are divided into time segments with a single furnace casting cycle as time segments, and the rolling plan is a production shift as a time segment, and the time segments are discretized into time grids for planning decisions. Mixed integer programming (Mixed Integer Programming, MIP) is a mathematical optimization technique that is mainly used to solve optimization problems that contain both continuous variables and discrete variables. In this model, some variables must take integer values ​​(such as 0 or 1, or any other integer), while other variables can take any real value. MIP problems are usually aimed at finding the optimal combination of a set of decision variables to maximize or minimize a specific objective function while satisfying a series of linear or nonlinear constraints. These constraints reflect business rules and technical limitations in the real world, such as production capacity limits, raw material supply, market demand and other factors.

[0037] The mixed integer programming model is used to scientifically describe the production process of bar products in the steelmaking-continuous casting-rolling production line, as well as the supply and marketing constraints based on market fluctuations. While fully considering the continuous casting of different steel grades, the life of the tundish, the continuous casting start-up and shutdown plan, and batch production to ensure safe and reliable production, the market conditions of products of various specifications are considered globally, and the inventory of various specifications is balanced as much as possible, and more products with better market conditions are produced. In addition, the model ensures that the corresponding furnace plan, casting plan, and rolling plan of steelmaking-continuous casting-rolling can be stably connected and production can be smooth.

[0038] In one embodiment of the present application, mathematical description is performed based on production supply and marketing data, production process data, rolling line production status parameters and billet inventory parameters to obtain mathematical description information of the production line. Specifically, model symbols are used to define relevant parameters based on the steelmaking-continuous casting-rolling production process and product market conditions. On the one hand, the available continuous casting machine, rolling line and production scheduling days and other set parameters are mathematically represented, that is, I represents the rolling line set, I j represents the set of rolling lines that can produce product j, J represents the set of product specifications, and J i represents the product set corresponding to rolling line i, S l represents the last shift of the day, the shift number set, C represents the continuous casting machine set, C i represents the set of continuous casting machines available for rolling line i, I c represents the set of rolling lines that can be cast by the continuous casting machine c, S t represents the set of shift numbers for the tth day, T represents the set of production days, L represents the set of steel types, S c represents the set of downtime periods of the continuous casting machine, S i represents the set of rolling mill downtime periods, S last Indicates the last shift in the production schedule; mathematically represents the capacity of each production equipment and the product benefit attributes, that is, s i represents the initial inventory of product j, b l represents the initial stock of steel type l, represents the hot-rolling speed of product j on rolling line i, represents the cold rolling speed of product j on rolling line i, R i represents the average daily sales volume of product i, t s represents the production time of each shift, v h represents the hot-charging gas consumption rate of the rolling line, v c Indicates the cold-charging gas consumption rate of the rolling line, d c represents the hourly capacity of the continuous casting machine c, m t Indicates the remaining gas volume for day t, V c Indicates the storage capacity of the gas tank, m pIndicates the gas output available for rolling line, g t Indicates the maximum available gas on day t, m init Indicates the initial amount of gas, e j represents the efficient penalty coefficient of product j, l j represents the out-of-stock penalty coefficient of product j, f j Indicates the maximum allowable out-of-stock days for product j, min j represents the minimum continuous production shift of product j, min j0 Indicates the minimum shift required for the current production line to produce product j.

[0039] In one embodiment of the present application, a 0-1 variable is used to represent the relevant scheduling decision in the production plan scheduling, u cls ∈{0,1} indicates that the continuous casting machine c supplies steel type in shift s, x ijls ∈{0,1} represents the hot charging process of product j produced by rolling line i with steel grade l in shift s, q ijls ∈{0,1} represents the cold charging process of rolling line i producing product j with steel grade l in shift s, Indicates that the product j1 of rolling line i in shift s is replaced by product j2, g 1jt ∈{0,1} means that product j is penalized on day t (within the allowed out-of-stock time range), g 2jt ∈{0,1} means that product j is penalized on day t (outside the allowed out-of-stock time range); on the other hand, the information such as product inventory, steel inventory, and gas inventory is represented by continuous variables, that is, y ijls ∈R + represents the output of hot charging of product j produced by rolling line i with steel grade l in shift s, r ijls ∈R + represents the cold charge of product j produced by rolling line i with steel grade l in shift s, p jt ∈R represents the available inventory of product j at t, b ls ∈R + represents the inventory of steel type l in shift s, k t ∈R + Indicates the available gas quantity at the beginning of day t, m t ∈R + Indicates the available gas quantity at the end of day t, h i ∈R means that the maximum out-of-stock days of rolling line i is minimized, o i ∈R represents the maximum inventory duration of rolling line i that can be minimized, g jt ∈R represents the penalty score of product j on day t.

[0040] In one embodiment of the present application, mathematical modeling is performed based on the mathematical description information of the production line to obtain an initial production line model, constraints with process conditions and production time as boundaries are set for the initial production line model according to the mathematical description information of the production line, and an optimization objective function is constructed based on the optimization goal to obtain a production planning model.

[0041] Among them, the optimization objective function based on the optimization goal can be characterized as:

[0042] A. Minimize the maximum out-of-stock time;

[0043]

[0044] B. The duration of minimum inventory can be maximized;

[0045]

[0046] C. Minimize the out-of-stock penalty score;

[0047]

[0048] D. Maximize the hot loading rate;

[0049]

[0050] In one embodiment of the present application, the above-mentioned constraints include at least part of the following: one type of steel must be cast during each continuous casting machine startup period;

[0051] The inventory of each type of steel after the end of each shift is equal to the inventory at the end of the previous shift plus the output of the current shift minus the consumption of hot charging or cold charging in the current shift; the total gas consumption per day is less than or equal to the available gas volume of the day; each rolling line can only choose hot charging or cold charging for each specification of products; during hot charging, the production capacity speed of the continuous casting machine is greater than the required hot charging speed; the output of different specifications of each type of steel in each rolling line of each shift does not exceed the maximum production limit of hot charging or cold charging; the cold charging usage of each type of steel does not exceed the maximum limit corresponding to the steel type; each rolling line in each shift produces at most one product; each product in each shift can only be produced on one rolling line at most; the inventory of each specification of product per day is equal to the previous day's surplus plus the output of hot charging and cold charging on the day minus the estimated Sales volume; the initial available gas volume each day is the remaining gas of the previous day plus the gas produced on that day; the remaining gas volume at the end of each day is equal to the remaining volume of the previous day minus the output of that day minus the consumption of that day; the continuous casting machine and rolling line cannot be used during the shutdown shift; the linear constraint of minimizing the out-of-stock time and maximizing the linear constraint of the inventory duration; the sum of the non-out-of-stock and out-of-stock penalty variables of each product every day is 1; the out-of-stock penalty score of each product every day is the sum of the penalty score of the non-out-of-stock days and the penalty score of the out-of-stock days; each rolling line in each shift adds a roll change time constraint when changing products; the output of each product in each shift is the maximum output minus the loss output caused by roll change; the production process in any rolling line must meet the continuous minimum production shift restriction.

[0052] Specifically, the above constraints can be expressed as follows based on the aforementioned definitions and variables:

[0053] (1) In any shift, any continuous casting machine, one type of steel must be cast during the start-up period;

[0054]

[0055] (2) The inventory of any steel type in any shift is equal to the surplus of the previous shift plus the output of the current shift minus the consumption of hot and cold loads in the current shift;

[0056]

[0057] (3) On any given day, the gas consumption of all products, including cold and hot loads, shall not exceed the available gas for that day;

[0058]

[0059] (4) Any shift, any rolling line, any specification, can only be hot loaded or cold loaded;

[0060]

[0061] (5) For any shift, any rolling line, any steel grade, when hot charging is required, the capacity of the continuous casting machine must be greater than that of hot charging;

[0062]

[0063] (6) The output of any shift, any rolling line, any steel grade, and any specification is less than the maximum limit for hot charging or cold charging;

[0064]

[0065] (7) For any shift and any steel grade, the amount of cold loading used cannot exceed the maximum steel grade limit;

[0066]

[0067] (8) Any shift and any rolling line can produce at most one product;

[0068]

[0069] (9) Any product in any shift can only be produced on one rolling line at most;

[0070]

[0071] (10) Balanced inventory limit for each specification: the daily inventory is the previous day's surplus plus the current day's hot and cold production, minus the estimated sales volume;

[0072]

[0073] (11) On any given day, the initial available gas volume is the remaining gas from the previous day plus the gas produced on that day;

[0074]

[0075] (12) On any given day, the maximum amount of gas initially available shall not exceed the gas tank capacity;

[0076]

[0077] (13) On any given day, the remaining gas volume is the previous day’s remaining volume minus the current day’s production volume, minus the current day’s consumption volume;

[0078]

[0079] (14) Continuous casting machines and rolling lines cannot be used during shutdown shifts;

[0080]

[0081] (17) Maximum and minimum out-of-stock time linearization constraints;

[0082]

[0083] (18) Maximum and minimum inventory sustainable linearization constraints;

[0084]

[0085] (19) Linearization of out-of-stock days penalty;

[0086] (20-1) On any day, the sum of the non-out-of-stock / out-of-stock penalty variables for any product is 1;

[0087]

[0088] (20-2) On any day, the out-of-stock penalty score for any product is the sum of the penalty score for non-out-of-stock days and the penalty score for out-of-stock days;

[0089]

[0090] (21) Constraints on product roll change in any shift, any rolling line;

[0091]

[0092] (22) For any shift and any product, the output is the maximum output minus the output loss from roller change;

[0093]

[0094] (23) Any rolling line producing any product must meet the minimum continuous production shift;

[0095] Among them, for the first shift, the model needs to consider the previous continuous production shifts of the product. If the previous continuous production shifts are less than the minimum continuous production shift, it is necessary to continue scheduling production until the minimum shift condition is met.

[0096] If the previous continuous production shifts have satisfied the minimum production shift, this constraint need not be considered.

[0097]

[0098] When it is not the first shift, the model scheduling needs to consider the minimum continuous production shift for each product. When the model decides to produce a certain product, if the subsequent free shifts meet the minimum continuous shift requirement, they will be directly occupied. If not, the remaining shifts will be occupied.

[0099]

[0100] In step S230, an initial production schedule is solved according to the production planning model to obtain an initial production schedule.

[0101] In one embodiment of the present application, the above-mentioned production scheduling plan includes a rolling plan, a pouring plan and a furnace plan.

[0102] In one embodiment of the present application, the schedulable shift information, the specification information of the rolled product of the current rolling production, the produced shifts of the current rolled product specifications, the sustainable production days of the products of the rolling line that can produce the specifications, the out-of-stock days of the products of the rolling line that can produce the specifications, and the inventory information of each type of steel billet are obtained, and the corresponding minimum continuous production shift is determined according to the rolled product specification information, and the rolling plan in production is determined according to the produced shifts of the current rolled product specifications and the minimum continuous production shift. Among them, the calculation method of the sustainable production days of the products of the rolling line that can produce the specifications is the ratio of the available inventory of a certain product specification to the average daily sales volume of the corresponding product specification.

[0103] In one embodiment of the present application, before determining the corresponding minimum continuous production shift according to the rolling product specification information, the production planning model is further encoded. The solution of the rolling plan is represented by symbolic encoding, and each node represents a production shift of a specification.

[0104] In one embodiment of the present application, based on the continuous production shifts of the product currently being produced by each rolling line, the minimum continuous production shift that satisfies the product is scheduled first.

[0105] In one embodiment of the present application, if there are days when the number of days out of stock of the specifications that the rolling line can produce is greater than the maximum allowable days out of stock of the corresponding specifications that the rolling line can produce, priority is sorted according to the days out of stock of the specifications that the rolling line can produce, and a rolling scheduling specification sequence is obtained; if there are no days when the number of days out of stock of the specifications that the rolling line can produce is greater than the maximum allowable days out of stock of the corresponding specifications that the rolling line can produce, priority is sorted according to the sustainable production days of the specifications that the rolling line can produce, and a rolling scheduling specification sequence is obtained.

[0106] In one embodiment of the present application, a scheduling shift is allocated according to the rolling schedule specification sequence and the schedulable shift information to obtain a rolling plan, the net demand for steel grades is determined according to the billet demand for each steel grade and the billet inventory information for each steel grade in the rolling plan, and the scheduling shifts for pouring and furnace are allocated according to the net demand for steel grades and the schedulable shift information to obtain a pouring plan and a furnace plan, and the rolling plan, the pouring plan and the furnace plan are solved in the production planning model to determine the initial production scheduling plan. Among them, the determination of the net demand for steel grades is determined according to the absolute value of the difference between the billet demand for each steel grade and the billet inventory information for each steel grade in the rolling plan. Scheduling shift allocation for pouring and furnace according to the net demand for steel grades and schedulable shift information includes preparing furnace plans from front to back based on production shifts. When scheduling each shift, priority is given to steel grades with the largest net demand for steel grades, and the conditions for continuous casting of different steel grades must be met until all shifts are scheduled.

[0107] In step S240, the initial production schedule is iteratively optimized and solved based on the large-scale neighborhood search algorithm and the production planning model until the preset iterative optimization termination condition is reached to obtain the optimal production schedule.

[0108] In one embodiment of the present application, the above-mentioned preset iterative optimization termination condition includes that the number of iterative optimization solutions reaches a preset maximum number of iterative optimization solutions. Large Neighborhood Search (LNS) is a meta-heuristic optimization algorithm, which is mainly used to solve complex combinatorial optimization problems, especially showing good solving ability when facing large-scale problems. The basic idea of ​​LNS is to start from the current solution, destroy (Destroy) part of the structure of the current solution, and then reconstruct (Repair) a new solution based on the remaining structure. This process creates a "neighborhood", that is, a series of possible new solutions.

[0109] In one embodiment of the present application, a first optimization operator and a second optimization operator are set, the first optimization operator is used to adjust the production shifts of the rolling product specifications, and the second optimization operator is used to adjust the rolling schedule specification sequence. The first optimization operator includes keeping the total shifts unchanged, reducing the number of continuous production shifts corresponding to the product with the most sustainable production days, and increasing the number of continuous production shifts corresponding to the product specifications with the least sustainable production days; the second optimization operator includes adjusting the order of the products with the most out-of-stock days to give priority to production. Among them, the first optimization operator and the second optimization operator are neighborhood operators, and the adaptive large-scale neighborhood search algorithm needs to design 2 or more destruction-repair operators so that selection can be made based on operator weights in each round of iteration.

[0110] In one embodiment of the present application, the selection probabilities of the first optimization operator and the second optimization operator are configured based on the preset operator calculation weights to obtain operator optimization selection configuration information, and the initial production schedule is solved according to the large-scale neighborhood search algorithm based on the operator optimization selection configuration information to obtain the current optimized production schedule. Among them, the destruction operator and the repair operator need to be used correspondingly, that is, only the initial weights of the first optimization operator and the second optimization operator need to be configured based on the preset operator calculation weights. The above-mentioned preset operator calculation weights can be set according to the efficiency principle of the optimization process, and the initial weights can be set according to experimental data or empirical data to improve the initial optimization effect.

[0111] After that, it also includes updating the global optimal solution. If the current solution is better than the current global optimal solution, it is updated, otherwise no operation is performed.

[0112] In one embodiment of the present application, the current optimized production schedule plan is scored according to a preset scoring standard to obtain an optimization plan score, the preset operator calculation weight is updated according to the optimization plan score, and iterative optimization is performed based on the updated preset operator calculation weight until the preset iterative optimization termination condition is reached. Specifically, for each round of neighborhood operator perturbation, the generated plan will be scored, and the neighborhood operator weight will be updated based on the score.

[0113]

[0114] ρ=αρ+(1-α)v

[0115] Among them, v is the score of the neighborhood operator in this round of iteration, v1, v2, and v3 represent the scores in different situations, ρ is the weight update function of different neighborhood operators, and α is the sensitivity attenuation parameter of the operator performance change.

[0116] Based on the above-mentioned encoded model nodes, each node represents the casting cycle of a furnace, and each steelmaking furnace will cast the corresponding small steel grade. All nodes are combined to form a casting plan. Based on the start-up and shutdown plan, the corresponding casting plan is generated, and then the net production demand of various steel grade slabs in the rolling plan needs to be considered. The missing steel grades need to be produced by continuous casting machines. By inserting the steelmaking furnace into the casting plan, the rolling plan requirements are met.

[0117] Specifically, it includes furnace demand adjustment and furnace position adjustment, among which, furnace demand adjustment includes selecting the steel type with the largest total demand for rolled steel billets, randomly increasing the number of furnaces of the corresponding steel type, with the maximum limit being the total demand for steel billets / maximum furnace capacity, and rounding up if it is less than a full furnace. And the number of furnaces of the least scarce steel type is removed accordingly to ensure that the number of furnaces meets the maximum number of furnaces in the casting. Furnace position adjustment includes inserting the newly added steel type furnaces in the furnace demand adjustment back into the casting, traversing each position in the casting and calculating the target value, and selecting the position with the smallest target value as the final insertion position.

[0118] In one embodiment of the present application, after obtaining the current optimized production schedule, if the current optimized production schedule does not satisfy the constraints of the production planning model, the target value of the current optimized production schedule is updated to infinity, and a simulated annealing algorithm is introduced to recalculate with a preset solution probability to obtain a second optimized production schedule that satisfies the constraints of the production planning model. The preset solution probability is Where T>0 is the temperature, f(w) is the target value calculation function, and w i and w b is the new solution and the current optimal solution. The simulated annealing algorithm (SA) is a heuristic global optimization method that imitates the physical phenomenon of metal annealing, that is, the process of finding the global optimal solution or the near-optimal solution by gradually lowering the temperature. In the optimization problem, the simulated annealing algorithm starts from an initial solution. Under given temperature conditions, the algorithm randomly selects a candidate solution in the solution space. If the new candidate solution is worse than the current solution, the new solution is accepted; if the new candidate solution is not as good as the current solution, then a probability function is used to decide whether to accept the new solution, which is related to the temperature. As the algorithm proceeds, the temperature gradually decreases, and the probability of accepting a worse solution also decreases. This allows the algorithm to explore a wide area of ​​the solution space in the early stage, and to focus more on improving the good solutions that have been found in the later stage. Through this mechanism, the simulated annealing algorithm can avoid falling into the local optimal solution to a certain extent and has a strong global search capability.

[0119] In one embodiment of the present application, after the optimal production schedule is obtained, it is sent to a terminal page and displayed visually for reference and adjustment by relevant technical personnel.

[0120] Reference Figure 3 As shown, Figure 3 FIG. 1 is a flow chart showing a specific wire rod steel rolling integrated plan generation process according to an exemplary embodiment of the present application. Figure 3As shown, in a specific embodiment of the present application, the production department will formulate a one-week production start-up and shutdown plan and a rolling line maintenance plan in advance based on the maintenance of the continuous casting machine, obtain production process parameters and market fluctuations from the front end, and obtain real-time production information and inventory information, with the optimization goals of maximizing the hot charging rate, minimizing the difference in the number of sustainable days of each product (i.e., inventory balance), and minimizing the number of days of product shortages, and generate an integrated plan for rolling, furnaces, and castings. If there is an equipment failure in the production process, the equipment maintenance plan is adjusted, or the market product benefits fluctuate, the above input data will be updated after re-maintenance at the front end, and an optimal plan will be calculated.

[0121] Reference Figure 4 As shown, Figure 4 This is a flowchart of a specific steel enterprise wire rod steel rolling integrated planning method shown in an exemplary embodiment of the present application. Figure 4 As shown in the figure, after the supply and marketing personnel fill in the supply and marketing constraint related parameters according to the market situation of each product, the production personnel fill in the production process constraints on the front-end page, such as the start-up and shutdown plan, the production capacity of each rolling line, the product switching time and other parameters. The algorithm model obtains the current production performance data from the production system through the interface, such as the previous production shifts of each product. Obtain logistics information from the logistics system, such as the current inventory of each product. Based on the production constraints such as the start-up and shutdown plan of the continuous casting machine, the maximum furnace weight, the continuous casting of different steel grades, and the supply and marketing constraints such as product benefits and the maximum number of days out of stock of products, a mixed integer programming model is established with the goals of maximizing the hot charging rate and balancing inventory. The model is solved by an adaptive large-scale neighborhood search algorithm to obtain the optimal furnace plan, casting plan, and rolling plan. The production planner will issue each plan to the corresponding production department after reviewing and adjusting it at the front end of the system, and the production system will execute the plan modified and adjusted by the production planner.

[0122] The present invention provides a steel production scheduling method, system, electronic device and storage medium. The method obtains production supply and marketing data, production process data, rolling line production status parameters and billet inventory parameters of the steel production process and constructs a production planning model. The initial production plan scheduling is solved according to the production planning model to obtain an initial production scheduling plan. The initial production scheduling plan is solved based on a large-scale neighborhood search algorithm and a production planning model to obtain an optimal production scheduling plan. The present invention systematically collects production supply and marketing data, production process data, rolling line production status parameters and billet inventory parameters to provide comprehensive data support for production planning. On this basis, a production scheduling method is constructed to minimize the maximum out-of-stock time and maximize the minimum inventory available. A production planning model with duration, minimizing out-of-stock penalty score and maximizing hot loading rate as the optimization objective function is established, and the actual process conditions and production time are set as the constraints of the model. The model performs initial production planning and scheduling. After generating a preliminary production schedule, the initial schedule is optimized and solved for multiple times based on a large-scale neighborhood search algorithm until the preset iterative optimization termination condition is reached. This effectively solves the scheduling problems caused by the complexity of the production process and the dynamic nature of the market environment in the steel production process, realizes the scientific and intelligent production planning, improves production efficiency and inventory management level, and enhances the company's ability to respond quickly to changes in market demand, thereby achieving overall optimization of the production plan.

[0123] On the other hand, the mixed integer programming model is used to scientifically describe the production process of bar products in the steelmaking-continuous casting-rolling production line, as well as the supply and marketing constraints based on market fluctuations. While fully considering the continuous casting of different steel grades, the life of the tundish, the continuous casting start-up and shutdown plan, and batch production to ensure safe and reliable production, the market conditions of products of various specifications are considered globally, and the inventory of various specifications is balanced as much as possible, and more products with better market conditions are produced. In addition, the model ensures that the corresponding furnace plan, casting plan, and rolling plan of steelmaking-continuous casting-rolling can be stably connected and production can be smooth.

[0124] Based on the integrated model of bar steel rolling in steel plant production line, it quickly takes into account the current steelmaking-continuous casting-rolling production situation and market product fluctuations, and finds the best solution in a very short time through an adaptive large-scale neighborhood search algorithm. It can adapt to the dynamic changes in steel plant production and fluctuations in supply and marketing conditions.

[0125] The following describes a system embodiment of the present application, which can be used to execute the steel production scheduling method in the above embodiment of the present application. For details not disclosed in the system embodiment of the present application, please refer to the above embodiment of the steel production scheduling method of the present application.

[0126] Figure 5is a schematic diagram of a steel production scheduling system shown in an exemplary embodiment of the present application. The system can be applied to Figure 2 The method implementation process shown in the figure can be based on Figure 1 The system is executed in the implementation environment shown in the figure, and may also be applicable to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the system is applicable.

[0127] like Figure 5 As shown, the exemplary steel production scheduling system includes: a production process parameter acquisition module 501, a production planning model construction module 502, and a production scheduling plan optimization module 503.

[0128] Among them, the production process parameter acquisition module 501 is used to obtain the production supply and marketing data, production process data, rolling line production status parameters and billet inventory parameters of the steel production process; the production planning model construction module 502 is used to construct a production planning model based on the production supply and marketing data, production process data, rolling line production status parameters and billet inventory parameters. The production planning model takes minimization of the maximum out-of-stock time, maximization of the minimum inventory duration, minimization of the out-of-stock penalty score and maximization of the hot loading rate as the optimization objective function, and the production planning model takes process conditions and production time as constraints; the production scheduling plan optimization module 503 is used to perform initial production planning and scheduling solution according to the production planning model to obtain an initial production scheduling plan; based on the large-scale neighborhood search algorithm and the production planning model, the initial production scheduling plan is iteratively optimized and solved until the preset iterative optimization termination condition is reached to obtain the optimal production scheduling plan. The preset iterative optimization termination condition includes the number of iterative optimization solutions reaching the preset maximum number of iterative optimization times.

[0129] An embodiment of the present application also provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by one or more processors, the electronic device implements the steel production scheduling method provided in the above-mentioned embodiments.

[0130] Figure 6 is a schematic diagram of the structure of a computer system of an electronic device according to an exemplary embodiment of the present application. It should be noted that: Figure 6 The computer system 600 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0131] like Figure 6As shown, computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to the program stored in a read-only memory (ROM) 602 or the program loaded from the storage part to a random access memory (RAM) 603, such as the method in the above embodiment. In RAM 603, various programs and data required for system operation are also stored. CPU 601, ROM 602 and RAM 603 are connected to each other via a bus. Input / output (I / O) interface 605 is also connected to bus 604.

[0132] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section performs communication processing via a network such as the Internet. A drive is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed so that a computer program read therefrom is installed into the storage section 608 as needed.

[0133] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 609, and / or installed from a removable medium 611. When the computer program is executed by a central processing unit (CPU) 601, various functions defined in the system of the present application are executed.

[0134] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. A computer program contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0135] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. Among them, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0136] In the corresponding drawings of the above embodiments, connecting lines may indicate the connection relationship between the various components to indicate more constituent signal paths (constituent_signalpath) and / or one or more ends of some lines may have arrows to indicate the main information flow direction. Connecting lines, as a mark, are not a limitation to the scheme itself, but the use of these lines in combination with one or more exemplary embodiments helps to connect circuits or logic units more easily. Any represented signal (determined by design requirements or preferences) may actually include one or more signals that can be transmitted in either direction and implemented with any appropriate type of signal scheme.

[0137] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0138] Another aspect of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. The computer-readable storage medium may be included in the electronic device described in the above embodiment, or may exist independently without being assembled into the electronic device.

[0139] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0140] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation methods of the present application.

[0141] It should be noted that the present application can be used in many general or special computing system environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like.

[0142] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application.

[0143] It should be understood that the above content of the present application is only a preferred exemplary embodiment of the present application and is not intended to limit the implementation scheme of the present application. Ordinary technicians in this field can easily make corresponding changes or modifications based on the main concept and spirit of the present application. Therefore, the scope of protection of the present application should be the scope of protection required by the claims.

Claims

1. A steel production scheduling method, characterized in that: The steel production scheduling method comprises: Obtain production supply and marketing data, production process data, rolling line production status parameters and billet inventory parameters of the steel production process; A production planning model is constructed according to the production supply and marketing data, production process data, rolling line production status parameters and billet inventory parameters, wherein the production planning model takes minimization of maximum out-of-stock time, maximization of minimum inventory duration, minimization of out-of-stock penalty score and maximization of hot charging rate as optimization objective functions, and the production planning model takes process conditions and production time as constraints; Solving the initial production plan scheduling according to the production planning model to obtain an initial production scheduling plan; The initial production schedule is iteratively optimized and solved based on a large-scale neighborhood search algorithm and the production planning model until a preset iterative optimization termination condition is reached to obtain an optimal production schedule. The preset iterative optimization termination condition includes that the number of iterative optimization solutions reaches a preset maximum number of iterative optimization times.

2. The steel production scheduling method according to claim 1, characterized in that: Constructing a production planning model based on the production supply and marketing data, production process data, rolling line production status parameters and billet inventory parameters includes: A mathematical description is performed based on the production supply and marketing data, production process data, rolling line production status parameters and billet inventory parameters to obtain mathematical description information of the production line; Perform mathematical modeling based on the mathematical description information of the production line to obtain an initial production line model; The initial production line model is set with constraints based on process conditions and production time as boundaries according to the mathematical description information of the production line, and an optimization objective function is constructed based on the optimization goal to obtain a production planning model.

3. The steel production scheduling method according to claim 2, characterized in that: The constraints include at least one of the following: Each continuous casting machine must cast one type of steel during its startup period; the inventory of a type of steel after each shift is equal to the inventory at the end of the previous shift plus the output of the current shift minus the consumption of hot charging or cold charging of the current shift; the total gas consumption per day is less than or equal to the available gas volume of the day; each rolling line can only choose hot charging or cold charging for each specification of products; during hot charging, the production capacity speed of the continuous casting machine is greater than the required hot charging speed; the output of different specifications of each type of steel in each rolling line of each shift does not exceed the maximum production limit of hot charging or cold charging; the cold charging usage of each type of steel does not exceed the maximum limit corresponding to the steel type; each rolling line in each shift produces at most one product; each product in each shift can only be produced on one rolling line at most; the inventory of each specification of product per day is equal to the previous day's surplus plus the current day's hot charging and cold charging. The initial available gas volume each day is the remaining gas of the previous day plus the gas produced on that day; the remaining gas volume at the end of each day is equal to the remaining volume of the previous day minus the production volume of that day minus the consumption of that day; the continuous casting machine and rolling line cannot be used during the shutdown shift; the linear constraint of minimizing the out-of-stock time and maximizing the linear constraint of the inventory duration; the sum of the non-out-of-stock and out-of-stock penalty variables of each product every day is 1; the out-of-stock penalty score of each product every day is the sum of the penalty score of the number of non-out-of-stock days and the penalty score of the number of out-of-stock days; each rolling line in each shift adds a roll change time constraint when changing products; the output of each product in each shift is the maximum output minus the loss output caused by roll change; the production process in any rolling line must meet the continuous minimum production shift restriction.

4. The steel production scheduling method according to claim 1, characterized in that: The production schedule includes a rolling schedule, a pouring schedule and a furnace schedule. The initial production schedule is solved according to the production planning model to obtain the initial production schedule including: Obtain information on schedulable shifts, specifications of rolled products currently being produced, the shifts that have been produced for the current rolled product specifications, the number of sustainable production days that the rolling line can produce products of the specifications, the number of days that the rolling line can be out of stock for products of the specifications, and inventory information of billets of various steel types; Determine the corresponding minimum continuous production shift according to the rolled product specification information, and determine the rolling plan in production according to the produced shifts and the minimum continuous production shift of the current rolled product specifications; If there is a situation where the number of days out of stock of a product of a specification that can be produced by the rolling line is greater than the maximum allowable number of days out of stock of the product of the specification that can be produced, then the priority is sorted according to the number of days out of stock of the product of the specification that can be produced by the rolling line, and the rolling schedule specification sequence is obtained; if there is no situation where the number of days out of stock of a product of a specification that can be produced by the rolling line is greater than the maximum allowable number of days out of stock of the product of the specification that can be produced, then the priority is sorted according to the sustainable production days of the product of the specification that can be produced by the rolling line, and the rolling schedule specification sequence is obtained; According to the rolling schedule specification sequence and the schedulable shift information, the scheduling shift is allocated to obtain a rolling plan; Determine the net demand for steel grades for steelmaking according to the demand for steel billets of each steel grade and the inventory information of steel billets of each steel grade in the rolling plan, and allocate the scheduling shifts of pouring and furnace according to the net demand for steel grades for steelmaking and the schedulable shift information to obtain a pouring plan and a furnace plan; Based on the rolling plan, pouring plan and furnace plan, a solution is performed in the production planning model to determine the initial production scheduling plan.

5. The steel production scheduling method according to claim 4, characterized in that: Iteratively optimizing and solving the initial production schedule based on the large-scale neighborhood search algorithm and the production planning model includes: Setting a first optimization operator and a second optimization operator, wherein the first optimization operator is used to adjust the production shift of the rolling product specification, and the second optimization operator is used to adjust the rolling schedule specification sequence; Calculate the selection probabilities of the first optimization operator and the second optimization operator based on the preset operator weights to obtain operator optimization selection configuration information; Solving the initial production schedule according to the large-scale neighborhood search algorithm based on the operator optimization selection configuration information to obtain a current optimized production schedule, and scoring the current optimized production schedule according to a preset scoring standard to obtain an optimized plan score; The preset operator calculation weight is updated according to the optimization plan score, and iterative optimization is performed based on the updated preset operator calculation weight until a preset iterative optimization termination condition is reached.

6. The steel production scheduling method according to claim 5, characterized in that: The first optimization operator includes keeping the total shifts unchanged, reducing the number of continuous production shifts corresponding to the product with the most sustainable production days, and increasing the number of continuous production shifts corresponding to the product specifications with the least sustainable production days; the second optimization operator includes adjusting the order of products with the most out-of-stock days to give priority to production.

7. The steel production scheduling method according to claim 5, characterized in that: After obtaining the current optimized production schedule, the steel production scheduling method further includes: If the current optimized production schedule does not meet the constraints of the production planning model, the target value of the current optimized production schedule is updated to infinity, and a simulated annealing algorithm is introduced to recalculate with a preset solution probability to obtain a second optimized production schedule that meets the constraints of the production planning model.

8. A steel production scheduling system, characterized in that: The steel production scheduling system comprises: The production process parameter acquisition module is used to obtain the production supply and marketing data, production process data, rolling line production status parameters and billet inventory parameters of the steel production process; A production planning model building module is used to build a production planning model according to the production supply and marketing data, production process data, rolling line production status parameters and billet inventory parameters. The production planning model takes minimization of maximum out-of-stock time, maximization of minimum inventory duration, minimization of out-of-stock penalty score and maximization of hot charging rate as optimization objective functions, and the production planning model takes process conditions and production time as constraints; The production scheduling optimization module is used to perform an initial production planning solution according to the production planning model to obtain an initial production scheduling plan; based on a large-scale neighborhood search algorithm and the production planning model, the initial production scheduling plan is iteratively optimized and solved until a preset iterative optimization termination condition is reached to obtain an optimal production scheduling plan, wherein the preset iterative optimization termination condition includes the number of iterative optimization solutions reaching a preset maximum number of iterative optimization times.

9. An electronic device, characterized in that: It comprises a processor, a memory and a communication bus; the communication bus is used to connect the processor and the memory; the processor is used to execute the computer program stored in the memory to implement the steel production scheduling method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is used to enable a computer to execute the steel production scheduling method as described in any one of claims 1-7.

Images