Data processing method and device for steel and iron integrated batch planning, and medium

Abstract

The invention discloses a data processing device and device for steel and iron integrated batch planning, electronic equipment and a storage medium, and relates to the technical field of steel and iron production. The method comprises the steps that process data of a minimum operation object tuple corresponding to steelmaking, continuous casting and hot rolling processes are obtained on the basis of a steel-rolling integrated batch plan, and the process data at least comprise the casting width, the casting thickness, the rolling width and the rolling thickness; establishing parameters of the steel rolling integrated batch plan and a corresponding database, wherein the parameters adopt natural number matrix coding to code particles; generating an initial solution by adopting a particle swarm algorithm based on a non-seed tuple selection method of constraint satisfaction; and moreover, the particles which do not meet the constraint are repaired. The invention further discloses a data processing device for steel and iron integrated batch planning, electronic equipment and a storage medium so as to solve the problems of resource waste and poor planning effect of the existing steel and iron production process by using the particle swarm optimization.

Description

Technical Field

[0001] The present application relates to the technical field of steel production, and in particular to a data processing method, device, equipment and storage medium for integrated steel batch planning. Background Art

[0002] In traditional steel production, production plans for the three major processes of steelmaking, continuous casting and hot rolling are usually formulated and implemented separately, with little consideration given to the connection between production logistics, and the goal pursued is generally only to optimize the local effect of a certain stage. Therefore, the individual formulation of plans for each stage cannot achieve the global optimum, and all of them are at the expense of the interests of other stages to reduce the economic cost of the current stage.

[0003] When the production plans for each stage are formulated separately, when formulating the steelmaking plan, that is, the furnace plan, only the economic cost of the steelmaking stage is considered. It is only necessary to consider combining steel billets with similar steel properties into the same furnace for steelmaking. The goal is to minimize the waste of molten steel. In the subsequent continuous casting stage, it is necessary to consider the connection between the production of the furnaces, and the production sequence of the furnaces needs to comply with the continuity of the continuous casting machine production. If the furnaces with too large differences in steel properties are produced continuously, it will lead to production waste of the continuous casting machine. In the rolling stage, it is necessary to consider the production continuity of specific billet specifications. Billets with too large differences in width or length are not allowed to be produced continuously.

[0004] To sum up, different factors are considered in each process of steel production. If production plans are formulated separately for different stages, it will be limited to the economy of the current stage, which will lead to waste of resources in the entire steel production process and even affect the normal production rhythm. Summary of the invention

[0005] The embodiments of the present application provide a data processing method, device, equipment and storage medium for integrated steel batch planning, which utilizes a particle swarm algorithm to solve the problems of resource waste and poor planning effect in existing steel production processes.

[0006] On the one hand, an embodiment of the present application provides a data processing method for an integrated steel batch plan, comprising: based on an integrated steel-rolling batch plan, obtaining process data of a minimum operation object tuple corresponding to steelmaking, continuous casting and hot rolling processes, the process data comprising at least: casting width, casting thickness, rolling width, rolling thickness; establishing parameters of the integrated steel-rolling batch plan and a corresponding database, the parameters using natural number matrix coding to encode particles; based on a non-seed tuple selection method for constraint satisfaction, using a particle swarm algorithm to generate an initial solution; and, for particles that do not satisfy the constraints, repairing them.

[0007] In a possible embodiment, it also includes: updating the particle swarm algorithm according to the following steps: performing initialization operations based on the encoded particles, including: setting the size of the particle swarm, the maximum number of optimization times, and the evolutionary generation; calculating the fitness value using a neighborhood search algorithm; updating the historical optimal position of the particle so that when the particle evolves to a predetermined generation, the particle is at the historical optimal position; updating the optimal position of the particle swarm so that the particle swarm is at the optimal position of the predetermined generation; when the particle completes the evolution, updating the position and speed of the particle, repairing the infeasible solution, and returning to the fitness value calculation step; otherwise outputting the optimal result of the group.

[0008] In a possible embodiment, repairing an infeasible solution includes: selecting non-seed tuples according to a method for generating an initial solution; and selecting all tuples to convert the infeasible solution into a feasible solution.

[0009] In a possible embodiment, the constraints include at least one of the following: a first constraint: maximizing revenue, and minimizing the number of integrated steel-rolling batch plans, continuous casting penalties, continuous rolling penalties and losses; a second constraint: the minimum and / or maximum weight allowed for the tundish; a third constraint: the maximum number of mold changes allowed within a casting; a fourth constraint: the maximum value allowed for changes in steel grade and delivery time of adjacent elements within a casting; a fifth constraint: the maximum value of changes in rolling width, rolling thickness, rolling hardness and delivery time of adjacent elements in a rolling unit; a sixth constraint: restrictions on the maximum same-width rolling length; a seventh constraint: the minimum and / or maximum length allowed for a rolling unit; an eighth constraint: a element can only be arranged into one integrated steel-rolling batch plan at most; a ninth constraint: a predetermined range of values ​​for variables.

[0010] In a possible embodiment, the parameters are encoded using a natural number matrix encoding for particles, including: representing the position and velocity of each particle as a matrix of natural numbers, and encoding the particles using a matrix of natural numbers; wherein the matrix includes: a vector representing the steel-rolling integrated batch plan to which the tuple belongs, a vector representing the rolling unit to which the tuple belongs, and a vector representing the casting plan to which the tuple belongs.

[0011] In a possible embodiment, a particle swarm algorithm is used to generate an initial solution, including: selecting the vth rolling unit and the uth casting plan of the steel-rolling integrated batch plan; using a non-seed tuple selection method based on constraint satisfaction, the non-seed tuple selection method including: according to the constraints, deleting tuples that cannot be cast in the corresponding steel-rolling integrated batch plan, respectively obtaining the feasible domains of the vth rolling unit and the uth casting plan, thereby generating the initial solution.

[0012] In a possible embodiment, using a particle swarm algorithm to generate an initial solution also includes: using a heuristic method to generate an initial solution to the sorting optimization problem, and constructing two neighborhood structures: an insertion neighborhood and an exchange neighborhood.

[0013] On the one hand, an embodiment of the present application provides a data processing device for steel integrated batch planning, comprising:

[0014] A data receiving module is used to obtain process data of the minimum operation object tuple corresponding to the steelmaking, continuous casting and hot rolling processes based on the steel-rolling integrated batch plan, wherein the process data at least includes: casting width, casting thickness, rolling width and rolling thickness;

[0015] A configuration module, used to establish the parameters of the steel rolling integrated batch plan and the corresponding database, wherein the parameters are encoded by natural number matrix encoding for particles;

[0016] The processing module is used for generating an initial solution by using a particle swarm algorithm based on a non-seed tuple selection method satisfying constraints; and for repairing particles that do not satisfy the constraints.

[0017] On the one hand, an embodiment of the present application provides an electronic device, which includes a processor and a memory, wherein the memory stores program code, and when the program code is executed by the processor, the processor executes any of the above-mentioned data processing methods for integrated steel batch planning.

[0018] On the one hand, the present application provides a computer-readable storage medium, which includes a program code. When the storage medium is run on an electronic device, the program code is used to enable the electronic device to execute any of the above-mentioned data processing methods for steel integrated batch planning.

[0019] The beneficial effects brought by the technical solution provided by the embodiment of the present application include at least one of the following:

[0020] 1. Strategy and model construction of integrated batch planning, overall collaborative optimization: The three stages of steelmaking, continuous casting and hot rolling are regarded as a whole, and the production constraints of each stage are met at the same time. Model construction innovation: An integrated batch planning model is constructed to accurately describe the various complex relationships in the integrated batch planning problem of steel rolling, providing a solid foundation for subsequent solutions and optimization.

[0021] 2. Improvement and discretization of particle swarm optimization algorithm to adapt to problem characteristics: In view of the characteristics of the steel rolling integrated batch planning problem, the particle swarm optimization algorithm has been improved to better adapt to the solution requirements of this problem. Discretization improves efficiency: The algorithm parameters are encoded using natural number matrix coding to encode particles, and the non-seed tuple selection method based on constraint satisfaction is used for discretization, so that the algorithm can directly process integer decision variables, which greatly improves the algorithm's computational efficiency and helps to quickly solve the model within a limited time and generate reasonable integrated batch planning results. This processing method can adapt to the characteristics of the steel rolling integrated batch planning problem and improve the applicability and efficiency of the algorithm.

[0022] 3. Application of constraint satisfaction technology in the initialization and repair process, initialization to ensure feasible solutions: Applying constraint satisfaction technology in the initialization process of the particle swarm algorithm can generate high-quality initial feasible particle swarms according to the process constraints of the problem, improving the initial search efficiency of the algorithm. Repairing enhances robustness: In the process of particle swarm evolution, the infeasible solutions generated are repaired using constraint satisfaction technology, so that the algorithm can make timely adjustments when encountering infeasible solutions, ensuring that the algorithm always searches in the feasible solution space.

[0023] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0025] Figure 1 A schematic diagram of an application scenario of the data processing method for steel integrated batch planning provided in an embodiment of the present application;

[0026] Figure 2 A schematic flow chart of a data processing method for steel integrated batch planning provided in an embodiment of the present application;

[0027] Figure 3 A flow chart of a particle swarm algorithm provided in an embodiment of the present application;

[0028] Figure 4 A module diagram of a data processing device for steel integrated batch planning provided in an embodiment of the present application;

[0029] Figure 5 A schematic diagram of the hardware structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described below in conjunction with the drawings in the embodiment of the present application. Obviously, the described embodiment is only a part of the embodiment of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application. In the absence of conflict, the embodiments in the present application and the features in the embodiments can be arbitrarily combined with each other. In addition, although the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in an order different from that here.

[0031] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the invention described herein can be implemented in sequences other than those illustrated or described herein.

[0032] The following is a brief introduction to the design concept of the embodiment of the present application:

[0033] In today's steel production, the production plans for the three major processes of steelmaking, continuous casting and hot rolling are usually formulated and implemented separately. The plans for each stage cannot achieve global optimization by formulating them separately, and the economic costs of the current stage are reduced at the expense of the interests of other stages. This application proposes to provide an integrated compilation strategy that can coordinate and match the batch plans of each stage, establish an integrated batch planning model for steel, and propose an improved discrete particle swarm algorithm to solve the integrated batch planning model. The integrated batch planning of steel production regards the three different stages of steelmaking, continuous casting and hot rolling as a whole, while satisfying the production constraints of each stage. It is also necessary to consider the constraints of the current stage on the upper / next stage to uniformly formulate production plans, synchronize the plans of the previous and next processes, and ensure that logistics operations are on time, maximizing the hot charging and hot delivery ratio. In addition, the working conditions that may be generated by the data are analyzed; this new method is used to improve the compilation efficiency and optimization degree of the integrated batch planning of steel rolling, thereby improving production efficiency and economic benefits.

[0034] In view of this, the embodiment of the present application provides a data processing method, device, equipment and storage medium for steel integrated batch planning. Among them, the data processing method for steel integrated batch planning includes: based on the steel rolling integrated batch planning, obtaining the process data of the minimum operation object tuple corresponding to the steelmaking, continuous casting and hot rolling processes, the process data at least includes: casting width, casting thickness, rolling width, rolling thickness; establishing the parameters of the steel rolling integrated batch planning and the corresponding database, the parameters use natural number matrix coding to encode particles; based on the non-seed tuple selection method of constraint satisfaction, using the particle swarm algorithm to generate the initial solution; and for the particles that do not meet the constraints, repair them.

[0035] The preferred embodiments of the present application are described below in conjunction with the drawings in the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. In addition, the embodiments and features in the embodiments of the present application may be combined with each other if there is no conflict.

[0036] like Figure 1 , which is a schematic diagram of an application scenario of a data processing method for steel integrated batch planning provided in an embodiment of the present application. In the schematic diagram of the application scenario, a terminal device 101 and a server 102 are included. The terminal device 101 and the server 102 communicate with each other through a communication network.

[0037] The terminal device 101 is an electronic device used by the target object, and the electronic device may be a personal computer, a mobile phone, a tablet computer, a notebook, an e-book reader, a vehicle-mounted terminal, etc. In addition, a client related to the data processing method for the integrated batch plan of steel may be installed on the terminal device 101, and the client may be software (for example, an APP, a browser, etc.), or a web page, a small program, etc. By implementing the data processing method for the integrated batch plan of steel on the terminal device 101, operations related to data processing of the integrated batch plan of steel are performed.

[0038] The server 102 may be an independent physical server or an edge device 102 in the field of cloud computing. It may also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, cloud functions, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (English name: Content Delivery Network, abbreviated as CDN), as well as big data and artificial intelligence platforms.

[0039] There is no restriction on the number of the terminal devices 101 and / or servers 102 .

[0040] It should be noted that the data processing method for the integrated batch plan of steel in the embodiment of the present application can be executed by the terminal device 101 or the server 102 alone, or can be executed jointly by the terminal device 101 and the server 102. For example, when executed jointly by the terminal device 101 and the server 102, the server 102 can provide the terminal device 101 with the process data of the minimum operation object tuple corresponding to the steelmaking, continuous casting and hot rolling processes, and the process data at least includes: casting width, casting thickness, rolling width, rolling thickness. The terminal device 101 can provide the server 102 with the parameters of the integrated batch plan of steel rolling and the corresponding database. When the constraints are met, the server 102 uses the particle swarm algorithm to generate the initial solution based on the non-seed tuple selection method of constraint satisfaction; and for the particles that do not meet the constraints, they are repaired. The terminal device 101 compares the optimal solution or the optimal solution set to determine the only optimal supply plan.

[0041] The following describes the data processing method for steel integrated batch planning provided by the exemplary embodiment of the present application in combination with the above-mentioned application scenarios and with reference to the accompanying drawings. It should be noted that the above-mentioned application scenarios are only shown to facilitate understanding of the spirit and principles of the present application, and the implementation methods of the present application are not subject to any limitations in this regard.

[0042] like Figure 2 , which is a schematic diagram of a data processing method 200 for steel integrated batch planning provided in an embodiment of the present application. In the schematic diagram of the data processing method for steel integrated batch planning, the following steps are shown:

[0043] Step S201, obtaining process data, that is, based on the steel-rolling integrated batch plan, obtaining the process data of the minimum operation object tuple corresponding to the steelmaking, continuous casting and hot rolling processes, the process data at least including: casting width, casting thickness, rolling width, rolling thickness. Using the process data of the minimum operation object tuple, the three stages of steelmaking, continuous casting and hot rolling can be regarded as a whole, and the production restrictions and optimization goals of each stage are comprehensively considered, which changes the traditional mode of making plans for each process separately.

[0044] Step S202, encode the particles, that is, establish the parameters of the steel rolling integrated batch plan and the corresponding database, and the parameters are encoded by natural number matrix coding. By establishing the parameters and the corresponding database, the efficiency can be discretized to improve: the algorithm is discretized so that the algorithm can directly process integer decision variables, which greatly improves the calculation efficiency of the algorithm, helps to quickly solve the model in a limited time, and generate reasonable integrated batch planning results.

[0045] Step S203, generating an initial solution, that is, using a non-seed tuple selection method based on constraint satisfaction to generate an initial solution using a particle swarm algorithm; and repairing particles that do not satisfy the constraints. Initialization ensures a feasible solution: By applying constraint satisfaction technology during the initialization of the particle swarm algorithm, a high-quality initial feasible particle swarm can be generated based on the process constraints of the problem, thereby improving the initial search efficiency of the algorithm. Repair enhances robustness: During the evolution of the particle swarm, the infeasible solutions generated are repaired using constraint satisfaction technology, so that the algorithm can make timely adjustments when encountering infeasible solutions, ensuring that the algorithm always searches within the feasible solution space.

[0046] In a possible embodiment, it also includes: updating the particle swarm algorithm according to the following steps: performing initialization operations based on the encoded particles, including: setting the size of the particle swarm, the maximum number of optimization times, and the number of evolution generations; calculating the fitness value using the neighborhood search algorithm; updating the historical optimal position of the particle so that when the particle evolves to a predetermined number of generations, the particle is at the historical optimal position; updating the optimal position of the particle swarm so that the particle swarm is at the optimal position of the predetermined number of generations; when the particle completes the evolution, the particle position and speed are updated, the infeasible solution is repaired, and the fitness value calculation step is returned; otherwise, the optimal result of the group is output. Specifically, if Figure 3 The flowchart of the particle swarm algorithm is shown as follows:

[0047] Step 1: Initialization. s 、c 1 、c 2 , ω, population size PopSize, maximum number of optimization times MaxIter and evolutionary generation t = 1, and generate the initial feasible particle swarm.

[0048] Step 2: Calculate the fitness value. Call the neighborhood search algorithm on the particle position X to calculate the fitness value f(X).

[0049] Step 3: Update the historical optimal position of the particle. represents the position of the kth particle when it evolves to the tth generation, P kbest represents the historical optimal position of the kth particle. If t = 1, then Otherwise, if but

[0050] Step 4: Update the optimal position of the group. Let G best represents the optimal position of the group, k∈{1,2,…,PopSize}; if t=1, then Otherwise, if but

[0051] Step 5: Algorithm termination condition. Let t = t + 1. If t < MaxIter, update the positions and velocities of the particles, repair the infeasible solutions, and return to the step of calculating the fitness value; otherwise, output the global optimal result.

[0052] Step 6: Update the positions and velocities of the particles. According to the fitness values and historical optimal positions of the particles, use the discrete particle swarm update formula to update the positions and velocities of the particles. The formula is as follows:

[0053] v id = Int(ωv id + c 1 (p id - x id ) + c 2 (p gd - x id ))

[0054] x id = Mod(|x id + v id |, N)

[0055] where d is the dimensionality of the space, x i = (x i1 , …, x id ), v i = (v i1 , …, v id ), p i = (p i1 , …, p id ) represent the position, velocity, and best position experienced by the i-th particle, p g = (p g1 , …, p gd ) represents the best position experienced by all particles in the particle swarm; ω is the inertia weight, c 1 and c 2 are random numbers between (0, 1); Int() is the rounding function, Mod() represents taking the remainder with N as the modulus, N is the maximum legal value of x id , and its purpose is to prevent the particles from exceeding the boundary. The absolute value in the function ensures non-negativity.

[0056] Step 7: Repair the infeasible solutions. Check the constraints for each particle. If a constraint is violated, repair it and return to the step of calculating the fitness value.

[0057] In this embodiment, through the particle swarm evolution process, the constraint satisfaction technology is used to repair the generated infeasible solutions, enabling the algorithm to adjust in a timely manner when encountering infeasible solutions and ensuring that the algorithm always searches within the feasible solution space.

[0058] In a possible embodiment, repairing an infeasible solution includes: selecting non-seed tuples according to the method of generating the initial solution; until all tuples are selected, so that the infeasible solution is converted into a feasible solution. For example, if the particle swarm generates particles (infeasible solutions) that do not meet the process constraints (such as the weight constraint of the tundish, the number of mold changes within the pouring, the change constraint of the related attributes of adjacent tuples, etc.) during the evolution process, it needs to be repaired. The repair process is: find the seed tuple and the tuple that cannot be rolled. sv Rolling and cannot be cast su Then, non-seed tuples are selected according to the method of generating the initial solution until all tuples are selected, so that the infeasible solution is transformed into a feasible solution.

[0059] In a possible embodiment, multiple constraints can be designed to cooperate with the particle swarm algorithm to generate an initial solution. The constraint can include at least one of the following:

[0060] The first constraint is to maximize the revenue and minimize the number of steel-rolling integrated batch plans, continuous casting penalty, continuous rolling penalty and loss. In some embodiments, the following formula can be used:

[0061]

[0062] This formula represents the maximization of the profit function, minimization of the steel rolling integration batch planning number, continuous casting penalty function, continuous rolling penalty function and loss function. Where: c i and q i are the profit function of the tuple included in the plan and the loss function of the tuple not included in the plan; when tuple j is the direct successor of tuple i, the penalty functions of continuous casting and continuous rolling are and y suij is a Boolean variable whose value is 1 if tuple j is the direct successor of tuple i in the u-th casting plan of the s-th steel-rolling integrated batch plan, otherwise it is 0.

[0063] Second constraint: minimum and / or maximum weight allowed for the intermediate package; in some embodiments, the following formula may be used:

[0064]

[0065] This formula represents the minimum and / or maximum weight allowed for a tundish. min represents the minimum weight of tuple i, x suvi Represents a Boolean variable. If the i-th tuple is in the u-th casting plan of the s-th steel-rolling integrated batch plan and the v-th rolling plan, the value is 1, otherwise it is 0. i represents the casting width of tuple i, TW maxRepresents the maximum weight of tuple i, where i represents the tuple sequence number.

[0066] Third constraint: the maximum number of mold changes allowed within a casting cycle; in some embodiments, the following formula can be used:

[0067]

[0068] Among them, y suij is a Boolean variable. If tuple j is the direct successor of tuple i in the u-th pouring plan of the s-th steel-rolling integrated batch plan, the value is 1, otherwise it is 0; D MT The maximum number of steel grade changes in adjacent elements in the pouring plan, dimensionless quantity; sW i and sW j Respectively represent the casting width of tuple i and tuple j; sT i and sT j Represent the casting thickness of tuple i and tuple j respectively.

[0069] Fourth constraint: the maximum value of the allowed variation of steel grade and delivery time of adjacent elements within a casting; in some embodiments, the following formula can be used:

[0070]

[0071] Among them, SG i and SG j Represents the steel grade of tuple i and tuple j respectively; D SG It represents the maximum value of the steel grade change allowed for adjacent elements in the pouring plan, a dimensionless quantity; D i and D j Denote the delivery time of tuple i and tuple j respectively, dimensionless quantity; D d It represents the maximum allowable variation of the delivery time, a dimensionless quantity. suij is a Boolean variable whose value is 1 if tuple j is the direct successor of tuple i in the u-th casting plan of the s-th steel-rolling integrated batch plan, otherwise it is 0.

[0072] The fifth constraint condition: represents the maximum value of the rolling width change, rolling thickness change, rolling hardness change and delivery time change of adjacent elements in the rolling unit; in some embodiments, the following formula can be used:

[0073]

[0074] Among them, cW i and cW j Denote the rolling width of group i and group j respectively; D cW Indicates the maximum value of the width variation allowed for adjacent groups in the rolling unit, in mm; cT i and cTj Denote the rolling thickness of group i and group j respectively; D cT are the maximum allowable thickness variation of adjacent groups in the rolling unit, in mm; cR i and cR j Represents the steel grade of tuple i and tuple j, dimensionless quantity; D cR D is the maximum value of the hardness variation allowed between adjacent groups in the rolling unit, a dimensionless quantity; i and D j Denote the delivery time of tuple i and tuple j respectively, dimensionless quantity; D d The maximum allowable variation of the delivery time of adjacent groups in the rolling unit, dimensionless quantity; z suij is a Boolean variable whose value is 1 if tuple j is the direct successor of tuple i in the vth rolling plan of the sth integrated steel-rolling batch plan, and 0 otherwise.

[0075] Sixth constraint: Limitation on the maximum same-width rolling length; in some embodiments, the following formula may be used:

[0076]

[0077] Among them, x suvi is a Boolean variable. If the i-th tuple is in the u-th casting plan of the s-th steel-rolling integrated batch plan and the v-th rolling plan, the value is 1, otherwise it is 0; cL i is the rolling length of tuple i; The rolling width of the element in the rolling unit is cW i Maximum rolling length of the same width, in m; cW i and represent the rolling width and rolling thickness of element i respectively.

[0078] Seventh constraint: the minimum and / or maximum length allowed for the rolling unit; in some embodiments, the following formula may be used:

[0079]

[0080] Among them, RL min is the rolling length of the tuple, the minimum length allowed by the rolling unit, in m; x suvi is a Boolean variable. If the i-th tuple is in the u-th casting plan of the s-th steel-rolling integrated batch plan and the v-th rolling plan, the value is 1, otherwise it is 0; cL i is the rolling length of element i, in m; RL max The maximum length allowed for the rolling unit, in meters.

[0081] Eighth constraint: A tuple can be arranged into at most one steel rolling integrated batch plan; in some embodiments, the following formula can be used:

[0082]

[0083] Among them, x suvi is a Boolean variable. If the i-th tuple is in the u-th casting plan of the s-th steel-rolling integrated batch plan and the v-th rolling plan, the value is 1, otherwise it is 0; U is the casting plan set, U={1,2,…,u,…,N U}; V is the rolling plan set, V = {1,2,…,v,…,N V}; S is the steel rolling integrated batch plan set, S = {1,2,…,s,…,N s}.

[0084] Ninth constraint: Predetermined range of variables. In some embodiments, the following formula may be used:

[0085] x suvi ,y suij , z suij ∈{0,1}, (9)

[0086] Among them, x suvi is a Boolean variable. If the i-th tuple is in the u-th casting plan of the s-th steel-rolling integrated batch plan and the v-th rolling plan, the value is 1, otherwise it is 0; suij is a Boolean variable. If tuple j is the direct successor of tuple i in the u-th pouring plan of the s-th steel-rolling integrated batch plan, the value is 1, otherwise it is 0; suij is a Boolean variable whose value is 1 if tuple j is the direct successor of tuple i in the vth rolling plan of the sth integrated steel-rolling batch plan, and 0 otherwise.

[0087] In a possible embodiment, the parameters are encoded using natural number matrix coding for particles, including: representing the position and speed of each particle as a matrix of natural numbers, and encoding the particles using a matrix of natural numbers; wherein the matrix includes: a vector representing the steel rolling integrated batch plan to which the tuple belongs, a vector representing the rolling unit to which the tuple belongs, and a vector representing the casting plan to which the tuple belongs. For example: natural number matrix coding can be used to encode particles, and the position and speed of each particle are represented as a matrix of natural numbers A 3×NI , where each element corresponds to the steel rolling integrated batch plan, rolling unit and pouring plan to which the tuple belongs. 11 ,a 12 ,…,a 1NI ) represents the steel rolling integrated batch plan to which the tuple belongs, a1i ∈{0,1,2,…,N s},i∈{1,2,…,N I}, such as a 15 =3 means that tuple 5 belongs to the third steel rolling integrated batch plan. 21 ,a 22 ,…,a 2NI ) indicates the rolling unit to which the tuple belongs, a 2i ∈{1,2,…,v,…,N pV},i∈{1,2,…,N I}. Vector(a 31 ,a 32 ,…,a 3NI ) indicates the pouring plan to which the tuple belongs, a 3i ∈{1,2,…,u,…,N PU}), (i∈{1,2,…,N I}.

[0088] In a possible embodiment, a particle swarm algorithm is used to generate an initial solution, including: selecting the vth rolling unit and the uth casting plan of the steel rolling integrated batch plan; using a non-seed tuple selection method based on constraint satisfaction, the non-seed tuple selection method includes: according to the constraints, deleting the tuples that cannot be cast in the corresponding steel rolling integrated batch plan, respectively obtaining the feasible domains of the vth rolling unit and the uth casting plan, thereby generating the initial solution. For example, you can let roll sv and cast su They represent the vth rolling unit and the uth casting plan of the sth steel rolling integrated batch plan. First, for each roll sv and cast su Select a seed tuple, and the tuples other than the seed tuple are called non-seed tuples. The non-seed tuple selection method based on constraint satisfaction is adopted, that is, whenever in roll sv After adding a tuple to the , constraint propagation is performed according to the constraints (such as the rolling width, thickness, hardness, delivery time change limit of adjacent tuples), and its feasible domain is recalculated, and the tuples that cannot be cast in their corresponding steel rolling integrated batch plan are deleted from the feasible domain. su The feasible domain of roll sv and cast su The tuple with the smallest penalty value is selected from the feasible domain to generate the initial feasible solution.

[0089] In a possible embodiment, the particle swarm algorithm is used to generate an initial solution, and it further includes: using a heuristic method to generate an initial solution for the sorting optimization problem, and constructing two neighborhood structures, namely, an insertion neighborhood and a swap neighborhood. In this way, according to the characteristics of the problem, two neighborhood structures, namely, an insertion neighborhood and a swap neighborhood, are constructed. By searching within these neighborhoods, a local optimal solution can be quickly found, thereby improving the search efficiency of the algorithm and accelerating the convergence speed of the algorithm. For example, the neighborhood search (NSRC) algorithm for optimizing the rolling order and casting order (i.e., the process of calculating the particle fitness value) is as follows:

[0090] Step 1: Generate an initial solution. Based on the particle position encoding, an initial solution roll sv and cast su .

[0091] Step 2: Select a neighborhood structure. The neighborhood structure NS′ k ∈{IN, SN}, and k max is the number of neighborhood structures; k = 1 indicates the selection of IN, and k = 2 indicates the selection of SN; initially, k = 1.

[0092] Step 3: Algorithm parameters. Let MaxIter be the maximum number of optimization iterations, Count be the counter, Φ 0 represent the initial solution roll sv or cast su , and Φ best represent the current optimal solution. If the tuple sequence is a rolling unit, the evaluation function Otherwise Initially, Count = 1, and Φ best = Φ 0 .

[0093] Step 4: Neighborhood search.

[0094] Generate a new solution Φ best in the NS′ k neighborhood of the current optimal solution Φ new .

[0095] If f(Φ new ) < f(Φ best ), then update Φ best , and Count = Count + 1.

[0096] If Count < MaxIter, go to (1); otherwise, go to Step 5.

[0097] Step 5: Condition judgment. If k < k max, then Count=1, k=k+1, go to step 2; otherwise, select the unoptimized rolling unit or casting plan as the initial solution, Count=1, k=1, go to step 2.

[0098] Step 6: Calculate the fitness value of the particle. Calculate the fitness value of the particle based on the optimized rolling unit and pouring schedule, as well as the objective function. In the process of calculating the fitness value of the particle, the neighborhood search method is introduced to help the algorithm find the optimal solution or approximate optimal solution more quickly in the global scope, improve the optimization performance of the algorithm, and make the final integrated batch plan more reasonable and efficient.

[0099] refer to Figure 4 , which is a module diagram of a data processing device 400 for steel integrated batch planning provided in an embodiment of the present application, referring to Figure 4 The device includes: a data receiving module 402, a configuration module 404, and a processing module 406. Among them:

[0100] The data receiving module 402 is used to obtain the process data of the minimum operation object tuple corresponding to the steelmaking, continuous casting and hot rolling processes based on the steel-rolling integrated batch plan, wherein the process data at least includes: casting width, casting thickness, rolling width and rolling thickness;

[0101] Configuration module 404, used to establish the parameters of the steel rolling integrated batch plan and the corresponding database, wherein the parameters are encoded by natural number matrix encoding for particles;

[0102] The processing module 406 is used to generate an initial solution based on the non-seed tuple selection method of constraint satisfaction by using a particle swarm algorithm; and to repair particles that do not satisfy the constraints.

[0103] Based on the same inventive concept, an electronic device is also provided in the embodiment of the present application, and the electronic device can realize the function of the data processing device of the aforementioned steel integrated batch plan, referring to Figure 5 , the electronic device comprises:

[0104] At least one processor 501, and a memory 502 connected to the at least one processor 501. The specific connection medium between the processor 501 and the memory 502 is not limited in the embodiment of the present application. Figure 5 In the example, the processor 501 and the memory 502 are connected via a bus 500. The bus 500 is Figure 5 The connections between other components are shown in bold lines, and are not intended to be limiting. The bus 500 can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, Figure 5Only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. Alternatively, the processor 501 can also be called a controller, and there is no limitation on the name.

[0105] In the embodiment of the present application, the memory 502 stores instructions that can be executed by at least one processor 501. The at least one processor 501 can execute the data processing method for steel integrated batch planning discussed above by executing the instructions stored in the memory 502. The processor 501 can implement Figure 4 The functions of each module in the device shown.

[0106] Among them, the processor 501 is the control center of the device, and can use various interfaces and lines to connect the various parts of the entire control device. By running or executing instructions stored in the memory 502 and calling data stored in the memory 502, the various functions of the device and processing data, the device can be monitored as a whole.

[0107] In one possible design, the processor 501 may include one or more processing units, and the processor 501 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the modem processor may not be integrated into the processor 501. In some embodiments, the processor 501 and the memory 502 may be implemented on the same chip, and in some embodiments, they may also be implemented separately on separate chips.

[0108] The processor 501 may be a general-purpose processor, such as a central processing unit (CPU), a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and may implement or execute the methods, steps, and logic diagrams disclosed in the embodiments of the present application. A general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the data processing method for the steel integrated batch plan disclosed in the embodiments of the present application may be directly embodied as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0109] The memory 502 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules. The memory 502 may include at least one type of storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory, a random access memory (Random Access Memory, RAM), a static random access memory (Static Random Access Memory, SRAM), a programmable read-only memory (Programmable Read Only Memory, PROM), a read-only memory (Read Only Memory, ROM), an electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), a magnetic memory, a disk, an optical disk, etc. The memory 502 is any other medium that can be used to carry or store a desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 502 in the embodiment of the present application can also be a circuit or any other device that can realize a storage function, for storing program instructions and / or data.

[0110] By programming the processor 501, the code corresponding to the data processing method for the steel integrated batch plan described in the above embodiment can be fixed into the chip, so that the chip can execute the data processing method when running. Figure 2 The steps of the data processing method for steel integrated batch planning in the embodiment shown are as follows: How to design and program the processor 501 is a technology well known to those skilled in the art and will not be described in detail here.

[0111] Based on the same inventive concept, an embodiment of the present application also provides a storage medium, which stores computer instructions. When the computer instructions are executed on a computer, the computer executes the data processing method for steel integrated batch planning discussed above.

[0112] In some possible implementations, various aspects of the data processing method for integrated steel batch planning provided in the present application can also be implemented in the form of a program product, which includes program code. When the program product is run on an apparatus, the program code is used to enable the control device to execute the steps of the data processing method for integrated steel batch planning according to various exemplary embodiments of the present application described above in this specification.

[0113] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may 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 may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0114] 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 processor, or other programmable data processing device to generate 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 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0115] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate 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 A function specified in one or more boxes.

[0116] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0117] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A data processing method for steel integrated batch planning, characterized in that: include: Based on the steel-rolling integrated batch plan, process data of the minimum operation object tuple corresponding to the steelmaking, continuous casting and hot rolling processes are obtained, wherein the process data at least includes: casting width, casting thickness, rolling width and rolling thickness; Establishing parameters of the steel rolling integrated batch plan and a corresponding database, wherein the parameters are encoded by natural number matrix encoding for particles; Based on the constraint-satisfied non-seed tuple selection method, a particle swarm algorithm is used to generate the initial solution; and the particles that do not meet the constraints are repaired.

2. The data processing method for steel integrated batch planning according to claim 1, characterized in that: Also includes: Follow these steps to update the Particle Swarm Optimization algorithm: Initialization operations are performed based on the encoded particles, including: setting the size of the particle swarm, the maximum number of optimization times, and the number of evolution generations; Calculate the fitness value using the neighborhood search algorithm; Updating the historical optimal position of the particle so that when the particle evolves to a predetermined generation, the particle is at the historical optimal position; Updating the optimal position of the particle swarm so that the particle swarm is in a predetermined algebraic optimal position; When the particle completes the evolution, the particle's position and velocity are updated, the infeasible solution is repaired, and the fitness value calculation step is returned; otherwise, the optimal result of the group is output.

3. The data processing method for steel integrated batch planning according to claim 2, characterized in that: Repair infeasible solutions, including: Select non-seed tuples according to the method of generating initial solutions; Until all tuples are selected, the infeasible solution is transformed into a feasible solution.

4. The data processing method for steel integrated batch planning according to claim 1, characterized in that: The constraints include at least one of the following: The first constraint is to maximize the profit and minimize the number of batch plans for steel-rolling integration, continuous casting penalty, continuous rolling penalty and loss; Second constraint: minimum and / or maximum weight allowed for the intermediate package; The third constraint condition: the maximum number of mold changes allowed within a pouring cycle; The fourth constraint condition: the maximum value of the allowed variation of steel grade and delivery time of adjacent elements within a casting; The fifth constraint condition: represents the maximum value of the rolling width change, rolling thickness change, rolling hardness change and delivery time change of adjacent elements in the rolling unit; The sixth constraint condition: the limit on the maximum rolling length of the same width; Seventh constraint: minimum and / or maximum length allowed for the rolling unit; The eighth constraint: A tuple can be arranged into at most one steel rolling integrated batch plan; Ninth constraint: predetermined range of values ​​of the variable.

5. The data processing method for steel integrated batch planning according to claim 1, characterized in that: The parameters are encoded using natural number matrix encoding for particles, including: The position and velocity of each particle are represented as a matrix of natural numbers, and the particles are encoded using the matrix of natural numbers; wherein the matrix includes: a vector representing the steel-rolling integrated batch plan to which the tuple belongs, a vector representing the rolling unit to which the tuple belongs, and a vector representing the casting plan to which the tuple belongs.

6. The data processing method for steel integrated batch planning according to claim 1, characterized in that: The particle swarm algorithm is used to generate the initial solution, including: Select the vth rolling unit and the uth pouring schedule of the steel rolling integrated batch plan; A non-seed tuple selection method based on constraint satisfaction is adopted, and the non-seed tuple selection method includes: according to the constraints, deleting the tuples that cannot be cast in the corresponding steel-rolling integrated batch plan, and obtaining the feasible domains of the vth rolling unit and the uth casting plan respectively, thereby generating the initial solution.

7. The data processing method for steel integrated batch planning according to claim 6, characterized in that: The particle swarm algorithm is used to generate the initial solution, which also includes: A heuristic method is used to generate the initial solution of the sorting optimization problem, and two neighborhood structures, insertion neighborhood and exchange neighborhood, are constructed.

8. A data processing device for steel integrated batch planning, characterized in that: include: A data receiving module is used to obtain process data of the minimum operation object tuple corresponding to the steelmaking, continuous casting and hot rolling processes based on the steel-rolling integrated batch plan, wherein the process data at least includes: casting width, casting thickness, rolling width and rolling thickness; A configuration module, used to establish the parameters of the steel rolling integrated batch plan and the corresponding database, wherein the parameters are encoded by natural number matrix encoding for particles; The processing module is used to generate an initial solution based on a non-seed tuple selection method based on constraint satisfaction and adopt a particle swarm algorithm; and to repair particles that do not satisfy the constraints.

9. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores program codes, and when the program codes are executed by the processor, the processor executes the data processing method for steel integrated batch planning as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The method comprises a program code, and when the storage medium is run on an electronic device, the program code is used to enable the electronic device to execute the data processing method for steel integrated batch planning as claimed in any one of claims 1 to 7.

Images