Production optimization control method, control device, equipment and storage medium

Abstract

The invention discloses a production optimization control method and device, equipment and a storage medium, and the method comprises the steps: obtaining candidate production data for producing a target steel grade from an optimization database, optimizing the candidate production data according to a current resource condition and the target cost of the target steel grade, so as to obtain a plurality of optimal parameter groups, each optimal parameter group comprises an optimal steel grade component and an optimal hot rolling process; carrying out fusion processing on the plurality of optimal parameter groups based on a cost optimization strategy so as to obtain fusion sensing information of the current production target steel grade; and current production data are detected in the production process of the target steel grade, and the production process of producing the target steel grade is adjusted according to the deviation between the fused sensing information and the current production data. The technical problem that production and manufacturing of hot-rolled products are not matched with current resource conditions is solved.

Description

Technical Field

[0001] The present invention relates to the field of hot rolling production processes, and particularly to an optimized production control method, control device, equipment and storage medium. Background Art

[0002] The market competition of hot-rolled products has further intensified, and cost optimization in the production of hot-rolled products has become one of the important ways to expand the market and improve profitability of hot-rolled products.

[0003] Currently, on a production line of hot-rolled products, the same steel grade is produced using fixed internal control components and hot-rolling process parameters, resulting in inflexibility in the production process of hot-rolled products. Furthermore, it leads to a mismatch between the production of hot-rolled products and the current resource conditions, and unreasonable utilization of resources. Summary of the Invention

[0004] Embodiments of the present application provide an optimized production control method, control device, equipment and storage medium, which solve the technical problem of the mismatch between the production of hot-rolled products and the current resource conditions in the prior art.

[0005] According to a first aspect of the present application, an optimized production control method is provided, including:

[0006] Obtaining candidate production data of the target steel grade to be produced from a pre-established optimization database, where the candidate production data includes steel grade components and hot-rolling process data of the target steel grade produced by multiple production bases in multiple historical periods;

[0007] Optimizing the candidate production data according to the current resource conditions and the target cost of the target steel grade to obtain multiple optimal parameter groups, where the multiple optimal parameter groups include an optimal steel grade component and an optimal hot-rolling process. The optimal steel grade component includes a set of components required for producing the target steel grade, and the optimal hot-rolling process includes a set of hot-rolling process parameters required for producing the target steel grade;

[0008] Performing fusion processing on the multiple optimal parameter groups based on a cost optimization strategy to obtain fusion perception information for currently producing the target steel grade;

[0009] Detecting current production data during the production process of the target steel grade, and adjusting the production process of the target steel grade according to the deviation between the fusion perception information and the current production data.

[0010] In combination with the first aspect, in some embodiments, the method further includes:

[0011] Preprocessing the obtained cost control materials, where the cost control materials include recorded data during the historical production processes of multiple steel grades;

[0012] Obtain key control information for controlling the production processes of the multiple steel grades from the preprocessed data;

[0013] Establish the optimization database according to the key control information.

[0014] Combined with the first aspect, in some embodiments, the optimizing the candidate production data according to the current resource conditions and the target cost of the target steel grade to obtain multiple optimal parameter groups includes:

[0015] Perform clustering division on the candidate production data based on data differences to obtain multiple clustering division results;

[0016] For each clustering division result, perform optimization solution based on the objective function and constraint conditions corresponding to the data type of the clustering division result to obtain the optimal solution of the clustering division result. The optimal solutions of the multiple clustering division results include the optimal steel grade components and optimal hot rolling processes of the target steel grade at each production base, as well as the optimal steel grade components and optimal hot rolling processes in each historical period.

[0017] Combined with the first aspect, in some embodiments, the fusing and processing the multiple optimal parameter groups based on a cost optimization strategy to obtain fusion perception information for currently producing the target steel grade includes:

[0018] Perform step-by-step association on the multiple optimal parameter groups based on a pre-created scheduling model to obtain multiple perception information groups. Each perception information group is the association result of the process parameters of an optimal steel grade component and an optimal hot rolling process for producing the target steel grade;

[0019] Perform production manufacturing cost accounting for each of the perception information groups to obtain the production manufacturing cost corresponding to each of the perception information groups;

[0020] Determine the fusion perception information for currently producing the target steel grade based on the production manufacturing cost corresponding to each of the perception information groups.

[0021] Combined with the first aspect, in some embodiments, the method further includes:

[0022] Extract multiple key control entities that affect the production process of the target steel grade from the key control information. The key control entities include the component types of the steel grade components and the process parameter types involved in the hot rolling process;

[0023] Define the control relationships between the respective key control entities;

[0024] Construct a cost control knowledge graph by taking each of the key control entities as a graph node of the knowledge graph, and the control relationships between the key control entities as the relationship edges between the graph nodes.

[0025] Determining the fused perception information for currently producing the target steel grade based on the production manufacturing cost corresponding to each perception information group includes:

[0026] Fuse the multiple perception information groups based on the production manufacturing cost corresponding to each perception information group and the cost control knowledge graph to obtain the fused perception information.

[0027] Combined with the first aspect, in some embodiments, adjusting the production process of the target steel grade according to the deviation between the fused perception information and the current production data includes:

[0028] Transmit the fused perception information to multiple control units for controlling the production process of the target steel grade, so that each control unit makes a coordinated adjustment to the production process of producing the target steel grade based on the deviation between the fused perception information and the current production data.

[0029] Combined with the first aspect, in some embodiments, the multiple control units include a reference control unit, a safety control unit, and a path control unit; transmitting the fused perception information to multiple control units for controlling the production process of the target steel grade includes:

[0030] Transmit the fused perception information to the reference control unit, so that the reference control unit generates a reference control instruction and performs local reference control of the target cost based on the reference control instruction, so that the production manufacturing cost of currently producing the target steel grade conforms to the target cost;

[0031] Transmit the fused perception information to the active safety control unit, so that the active safety control unit performs target detection and risk discrimination during the production process of the target steel grade and outputs a risk discrimination result;

[0032] Transmit the fused perception information to the route control unit, so that the route control unit updates the path information based on the fused perception information and re-plans the production path of the target steel grade according to the updated path information.

[0033] According to the second aspect of the present application, a production optimization control device is provided, including:

[0034] An acquisition unit, configured to acquire candidate production data for producing a target steel grade from a pre-established optimization database, where the candidate production data includes steel grade compositions and hot rolling process data of the target steel grade produced by multiple production bases in multiple historical periods;

[0035] An optimization unit, configured to optimize the candidate production data according to current resource conditions and the target cost of the target steel grade to obtain multiple optimal parameter sets, where the multiple optimal parameter sets include an optimal steel grade composition and an optimal hot rolling process, the optimal steel grade composition includes a set of compositions required for producing the target steel grade, and the optimal hot rolling process includes a set of hot rolling process parameters required for producing the target steel grade;

[0036] A fusion unit, configured to perform a fusion process on the multiple optimal parameter sets based on a cost optimization strategy to obtain fusion perception information for currently producing the target steel grade;

[0037] An adjustment unit, configured to detect current production data during the production process of the target steel grade, and adjust the production process of the target steel grade according to the deviation between the fusion perception information and the current production data.

[0038] According to a third aspect of the present application, there is provided an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the program, the production optimization control method according to any embodiment of the first aspect is implemented.

[0039] According to a fourth aspect of the present application, there is provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the production optimization control method according to any embodiment of the first aspect is implemented.

[0040] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0041] Candidate production data for the target steel grade is obtained from a pre-established optimization database, and the candidate production data is optimized according to the current resource conditions and the target cost of the target steel grade to obtain multiple optimal parameter sets, where the multiple optimal parameter sets include the optimal steel grade composition and the optimal hot rolling process; the multiple optimal parameter sets are fused based on a cost optimization strategy to obtain the fusion perception information for the current production of the target steel grade; during the production process of the target steel grade, the current production data is detected, and according to the deviation between the fusion perception information and the current production data, the production process of the target steel grade is adjusted, realizing dynamic adjustment of the fusion perception information according to the changes in resource conditions and the target cost, so that the steel grade composition and the process parameters of the hot rolling process during the production process of the hot rolled product can be dynamically adjusted following the changes in resource conditions, can match the current resource conditions, improve the rationality of resource utilization, and can also reduce the production and manufacturing cost of the hot rolled product. Brief Description of the Drawings

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0043] Figure 1 Shows the flowchart of the production optimization control method according to some embodiments of the present invention;

[0044] Figure 2 Shows the process schematic diagram of the production optimization control method according to some embodiments of the present invention;

[0045] Figure 3 Shows the schematic diagram of the production optimization control system according to some embodiments of the present invention;

[0046] Figure 4 Shows the schematic diagram of the production optimization control device according to some embodiments of the present invention;

[0047] Figure 5 Shows the schematic diagram of the structure of the electronic device according to some embodiments of the present invention. Detailed Embodiments

[0048] By providing a production optimization control method, control device, equipment and storage medium in the embodiments of the present application, the technical problem that the production of hot rolled products in the prior art does not match the current resource conditions is solved. The technical solution of the embodiments of the present application to solve the above technical problem is generally as follows:

[0049] For a certain steel grade, obtain the steel grade composition and hot rolling process data used in producing this steel grade at different bases and in different historical periods; optimize the obtained steel grade composition and hot rolling process data according to the current resource conditions and target cost to obtain multiple optimal parameter groups; select the best production path according to the cost corresponding to each optimal parameter group for the current production of the target steel grade.

[0050] To better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners.

[0051] First, it should be noted that the term "and / or" appearing in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the front and back associated objects.

[0052] As Figure 1 shown, the embodiment of the present invention provides a production optimization control method, including the following steps S101 to S104.

[0053] In step S101: Obtain candidate production data for producing the target steel grade from a pre-established optimization database. The candidate production data includes the steel grade composition and hot rolling process data of the target steel grade produced by multiple production bases in multiple historical periods.

[0054] In some embodiments, the optimization database includes historical production data of multiple steel grades. The historical production data of each steel grade includes the steel grade composition and hot rolling process data of each production base in multiple historical periods for producing this steel grade.

[0055] In some embodiments, preprocess the obtained cost control materials, where the cost control materials include the recorded data in the historical production processes of multiple steel grades; obtain the key control information of the production processes of multiple steel grades from the preprocessed data; establish an optimization database according to the key control information.

[0056] It can be understood that for each steel grade, record data of each process step in the production process of this steel grade is obtained to obtain cost control materials.

[0057] As Figure 2As shown, in some embodiments, cost control data is obtained from a data source by connecting to the data source. The data collection tool and the corresponding data interface are connected to each data source. The connected data sources may include one or more of the following from multiple production bases of multiple steel grades: Programmable Logic Controller (PLC), mixing station, File Transfer Protocol (FTP) log document, L2 database, L3 database, etc.

[0058] It can be understood that the PLC is used to perform real-time control and monitoring on the equipment used in each process step in the hot rolling production line. The L2 database is a process control level database, and the L3 database is a production management level database. The data collected from each data source includes control parameters, historical operation records, fault reports, etc. during the production process. The data cleaning algorithm and the rule engine are used to preprocess the collected data to obtain an optimized database.

[0059] In some embodiments, a distributed database and caching technology can be used to cache the preprocessed data to improve the data processing efficiency and response speed.

[0060] In some embodiments, data reduction can be performed on the optimized database to screen out the core data of each steel grade. The core data includes various core process parameters of the steel grade composition and hot rolling process: hot charging temperature, tapping temperature, cooling mode, hourly output, performance data, etc.

[0061] The resource conditions of different bases and different historical periods are different. The steel grade compositions of the same steel grade can be different. Controlling the difference in steel grade composition is of great significance for cost reduction in each base. The steel grade composition accounts for 50% in the total process cost reduction ratio of a certain steel grade. Under the condition of accurately controlling the steel grade performance, increasing the hot charging temperature, reducing the tapping temperature, and reasonably controlling the in-furnace time can significantly reduce the fuel consumption cost of the steel grade, accounting for 16% in the total process cost reduction ratio of a certain steel grade. The cooling mode and cooling quality determine the water and electricity consumption, performance, and the amount of slab shape rejudgment, accounting for 2% in the total process cost reduction ratio of a certain steel grade. The hourly output directly determines the production efficiency, accounting for 32% in the total process cost reduction ratio of a certain steel grade.

[0062] In step S102: Optimize the candidate production data according to the current resource conditions and the target cost of the target steel grade to obtain multiple optimal parameter groups. The above multiple optimal parameter groups include the optimal steel grade composition and the optimal hot rolling process.

[0063] It should be noted that the optimal steel grade composition is a parameter group including the input amounts of various components required for producing the target steel grade, and the optimal hot rolling process is a parameter group including the parameter values of various process parameters required for the hot rolling process of producing the target steel grade. The target cost of the target steel grade can be formulated and input according to the market conditions. The current resource conditions include the current alloy price and the current energy price.

[0064] In some embodiments, step S102 may include the following steps S1021 - S1022.

[0065] In step S1021: Cluster and partition the obtained candidate production data based on data differences to obtain multiple clustering and partitioning results.

[0066] Cluster and partition the candidate production data based on the differences in bases and data types. Some classes are the steel grade composition data of the target steel grade produced by a production base in multiple historical periods, and some other classes are the hot rolling process data of the target steel grade produced by a production base in multiple historical periods. One production base corresponds to one class of steel grade composition data and one class of hot rolling process data. Cluster and partition the candidate production data based on the differences in time and data types. Some classes are the steel grade composition data of the target steel grade produced by multiple production bases in the same historical period, and some other classes are the hot rolling process data of the target steel grade produced by multiple production bases in the same historical period. One historical period corresponds to one class of steel grade composition data and one class of hot rolling process data.

[0067] In step S1022: For each clustering and partitioning result, optimize based on the objective function corresponding to the data type of this clustering and partitioning result to obtain the optimal solution of this clustering and partitioning result, that is, an optimal set of parameter values. The optimal solutions of multiple clustering and partitioning results include the optimal steel grade composition and the optimal hot rolling process of the target steel grade at each production base, as well as the optimal steel grade composition and the optimal hot rolling process at each historical period.

[0068] In some embodiments, the current resource conditions include the current alloy price and the current energy price. The data types are divided into composition data and process data.

[0069] For the clustering and partitioning result with the data type of composition data, the objective function is to minimize the cost, and the variables include the alloy price (the prices of various elements of the alloy) and functions related to the input amounts of various elements. The constraints adopted include the target cost and various composition constraints. The composition constraints specifically include: the constraints of alloy resources, the constraints of smelting processes, and the constraints of production plan arrangement.

[0070] For the clustering division results of hot rolling process data with a data type, the objective function aims to minimize costs and is a function with variables including energy prices and process parameters. The constraints adopted include the target cost and various process constraints. The process constraints specifically include: constraints on hot charging temperature, tapping temperature, cooling process, performance requirements, and the constraint of using surplus materials, etc.

[0071] In some embodiments, in order to more accurately control the production and manufacturing costs of different thickness specifications of the same steel grade, the optimal steel grade composition of each production base includes the base-optimal composition for different applicable thicknesses, the optimal hot rolling process of each production base includes the base-optimal process for different applicable thicknesses, the optimal steel grade composition of each historical period includes the historical-optimal composition for different applicable thicknesses, and the optimal hot rolling process of each historical period includes the historical-optimal process for different applicable thicknesses.

[0072] For example, for two applicable thicknesses of the target steel grade, 1.4 - 8 and 8.01 - 20.3, it is necessary to determine the base-optimal composition, historical-optimal composition, base-optimal process, and historical-optimal process for each applicable thickness respectively, as shown in Tables 1 and 2 below:

[0073] Table 1. Optimal Composition of the Target Steel Grade

[0074]

[0075] Table 2. Optimal Process of the Target Steel Grade

[0076]

[0077] In step S103: Based on the cost optimization strategy, perform a fusion process on multiple optimal parameter groups to obtain the fusion perception information for the currently produced target steel grade.

[0078] In some embodiments, based on a pre-created scheduling model, perform a step-by-step association on multiple optimal parameter groups to obtain multiple perception information groups. Each perception information group is the association result of the process parameters of an optimal steel grade composition and an optimal hot rolling process for producing the target steel grade; perform production and manufacturing cost accounting for each perception information group to obtain the production and manufacturing cost corresponding to each perception information group. The production and manufacturing cost of each perception information group is equal to the sum of the slab unit price for smelting with the optimal steel grade composition and the hot rolling process cost; based on the production and manufacturing cost corresponding to each perception information group, determine the fusion perception information for the currently produced target steel grade.

[0079] It can be understood that based on the cost optimization strategy, one of the perception information groups that minimizes the production and manufacturing cost can be selected from multiple perception information groups as the fused perception information. The fused perception information is used to determine the optimal production path for the currently targeted steel grade, and the production path of the targeted steel grade is re-planned based on the optimal production path to continue the production of the targeted steel grade.

[0080] In some embodiments, the production optimization control method provided by the embodiments of the present invention may further include the following steps: extracting multiple key control entities that affect the targeted steel grade according to the key control information; defining the control relationships between the above-mentioned key control entities; using each key control entity as a graph node of the knowledge graph, and the control relationships between each key control entity as the relationship edges between the graph nodes to construct a cost control knowledge graph.

[0081] Exemplarily, in the constructed cost control knowledge graph, there may be the following knowledge and similar knowledge: Third steelmaking smelting + Second hot rolling + Charging furnace at 700 °C + 110 minutes in-furnace time + Rough rolling exit temperature 1050 °C + Finish rolling temperature 860 °C + Coiling temperature 650 °C + Front-end cooling.

[0082] In some embodiments, key control entities can be extracted from the key control information through methods such as named entity recognition technology, text mining algorithms, and relationship extraction algorithms. The extracted key control entities include the component types of the steel grade components and the process parameter types involved in the hot rolling process. The component types are: C, Si, Mn, P, S, etc., and the process parameter types are hot charging temperature, tapping temperature, cooling mode, hourly output, performance data, operation steps, etc.

[0083] In some embodiments, the extracted key control entities and the control relationships between each key control entity can be verified and supplemented based on the knowledge data of domain experts, which helps to improve the accuracy of the generated cost control knowledge graph.

[0084] In some embodiments, determining the fused perception information of the currently targeted steel grade based on the production and manufacturing cost corresponding to each perception information group may include: fusing multiple perception information groups based on the production and manufacturing cost corresponding to each perception information group and the cost control knowledge graph to obtain the fused perception information.

[0085] Exemplarily, the obtained fused perception information may include various process parameters as shown in Table 3 below:

[0086] Table 3. Process Parameters

[0087] Project Night Day Unit Project Night Day Unit Project Night Day Unit Number of Blocks 266 203 Block Time in Furnace 116 116 Minute Final Rolling Temperature 850 865 ℃ Coil Weight 7198 6233 Ton Average Time in High Temperature Section 92 93 Minute Coiling Temperature 645 655 ℃ Single Weight 27.1 30.7 Ton Furnace Inlet Temperature 701 750 ℃ Lockdown 121 128 Block Roll Change 6 3 Time Furnace Outlet Temperature 1204 1269 ℃ Fault 43 48 Minute Interval 80.7 149.7 Second h < 2.1mm 0 0 Block Hot Charge Ratio 66.3 78.16 ％ Rhythm 162.3 233.6 Second h < 2.1mm 0 0 Ton Yield 99.17 99.58 ％

[0088] It should be noted that h in Table 3 above represents the thickness of the hot-rolled product.

[0089] In step S104: During the production process of the target steel grade, detect the current production data, and adjust the production process of producing the target steel grade according to the deviation between the fusion perception information and the current production data.

[0090] Through the deviation between the fusion perception information and the current production data, the production process is adaptively adjusted to make the steel grade composition and hot rolling process parameters adopted for producing the target steel grade more conform to the fusion perception information, so as to ensure the accurate execution of the established process plan.

[0091] It can be understood that the current production data is real-time monitoring data obtained by real-time monitoring the production process of the target steel grade (the production process includes smelting process and hot rolling process).

[0092] In some embodiments, adjusting the production process of producing the target steel grade according to the deviation between the fusion perception information and the current production data may include: transmitting the fusion perception information to multiple control units for controlling the production of the target steel grade, so that each control unit collaboratively adjusts the production process of producing the target steel grade based on the deviation between the fusion perception information and the current production data.

[0093] In some embodiments, as Figure 2 shown, after optimizing the steel grade composition and hot rolling process of the target steel grade to obtain the fusion perception information; and adjusting the production process of the target steel grade based on the fusion perception information, judge whether the actual production and manufacturing cost of producing the target steel grade meets the target cost. If so, produce the target steel grade based on the optimized steel grade composition and hot rolling process. If not, return to reprocess the data to obtain new fusion perception information.

[0094] In some embodiments, the control units for controlling the production process of the target steel grade may include the following three: a reference control unit, a safety control unit, and a path control unit. Transmitting the fusion perception information to multiple control units for controlling the production of the target steel grade, so that each control unit collaboratively adjusts the production process of producing the target steel grade based on the deviation between the fusion perception information and the current production data may include the following multiple steps A1 - A3 executed in parallel and independently:

[0095] Step A1: Transmit the fusion perception information to the reference control unit, so that the reference control unit generates a reference control instruction according to the fusion perception information. The reference control instruction at least includes resource constraints, the base cost and historical cost of the target steel grade; perform reference control on the target cost of producing the target steel grade based on the reference control instruction, so that the actual production and manufacturing cost of producing the target steel grade at the base meets the target cost, and achieve the goal of cost control.

[0096] It is understandable that the benchmark control unit is the local control unit for the target cost. Resource constraints refer to the constraints on various resources required for producing the target steel grade, such as raw materials (iron ore, coke, Si, Mn, P, S, etc.), energy (electricity, gas, etc.), equipment, etc., with limitations set in terms of quantity, quality, acquisition time, etc. The base cost is the production manufacturing cost of the target steel grade in the base, and the historical cost is the production manufacturing cost of the target steel grade in multiple bases in history.

[0097] Step A2: Transmit the fusion perception information to the active safety control unit, so that the active safety control unit performs target detection and risk discrimination based on the fusion perception information and outputs a risk discrimination result.

[0098] It is understandable that target detection is to detect target objects or events related to safety during the process of producing the target steel grade in the base, and judge whether there is a risk according to the detection result. For example: detecting whether the temperature of molten steel and the steel grade components are within the specified range, whether the operating parameters of the continuous casting equipment are normal, whether the size and surface quality of the steel during the rolling process meet the requirements, etc. If not, it indicates that there is a risk.

[0099] Step A3: Transmit the fusion perception information to the route control unit, so that the route control unit updates the path information based on the fusion perception information and re - plans the production path of the target steel grade according to the updated path information, that is, modifies the relevant process parameters of the production path of the target steel grade (refer to the parameter types in Table 3 above, the sequence and time arrangement of each production step, etc.). After the path information is updated, the route control unit will re - plan the entire production path according to the new path information. This includes adjusting the execution sequence, process parameters, and steel grade components of each process step. For example, the production path before re - planning is: secondary steelmaking smelting + secondary hot rolling + charging at 700°C + soaking time of 110 minutes + rough rolling exit temperature of 1050°C + finish rolling final rolling temperature of 860°C + coiling temperature of 650°C + pre - section cooling, and the path after re - planning is: secondary steelmaking smelting + secondary hot rolling + charging at 701°C + soaking time of 116 minutes + rough rolling exit temperature of 1204°C + finish rolling final rolling temperature of 850°C + coiling temperature of 655°C + pre - section cooling.

[0100] According to a production optimization control method provided by an embodiment of the present invention, the production of hot - rolled products with different product specifications is more matched with the current resource conditions, resulting in a reduction in production manufacturing cost ranging from 3% to 15%, and the cost - reduction effect is remarkable.

[0101] Based on the same inventive concept, an embodiment of the present invention provides a system for implementing the above - mentioned production optimization control method, as Figure 3 shown, the system includes five major control modules: a data acquisition module, a data processing module, a data grouping module, a data association module, and a data control module.

[0102] The data acquisition module 301 is used to establish an optimized database for multiple bases and multiple steel grades.

[0103] The data processing module 302 is used to activate the data acquisition module for sensing and acquisition, and obtain the required sensing information from the optimized database, that is, the candidate production data of the target steel grade.

[0104] The data grouping module 303 is used to perform clustering division on the obtained sensing information based on data differences, generate a clustering division result, and for each category in the clustering division result, perform constrained optimization according to the current resource conditions to obtain the following multiple optimal solutions: the optimal base composition, the historical optimal composition, the optimal base process, and the historical optimal process.

[0105] The data association module 304 is used to construct a scheduling model, and perform step-by-step association grouping according to the optimal base composition, the historical optimal composition, the optimal base process, and the historical optimal process obtained through clustering division and constrained optimization by the scheduling model to obtain multiple sensing information groups.

[0106] The data control module 305 is used to determine the production manufacturing cost for each sensing information group in the multiple sensing information groups respectively, perform fusion based on the production manufacturing cost corresponding to each sensing information group to obtain fused sensing information, and transmit the fused sensing information to multiple control units for collaborative control of the production process of the target steel grade.

[0107] Based on the same inventive concept, an embodiment of the present invention provides a production optimization control device, as Figure 4 shown, the production optimization control device includes:

[0108] The acquisition unit 401 is used to obtain candidate production data for producing the target steel grade from a pre-established optimized database, and the candidate production data includes the steel grade composition and hot rolling process data of the target steel grade produced by multiple production bases in multiple historical periods.

[0109] The optimization unit 402 is used to optimize the candidate production data according to the current resource conditions and the target cost of the target steel grade to obtain multiple optimal parameter groups, and each optimal parameter group includes an optimal steel grade composition and an optimal hot rolling process.

[0110] The fusion unit 403 is used to perform fusion processing on the multiple optimal parameter groups based on a cost optimization strategy to obtain fused sensing information for currently producing the target steel grade.

[0111] The adjustment unit 404 is used to detect current production data during the production process of the target steel grade, and adjust the production process of producing the target steel grade according to the deviation between the fused sensing information and the current production data.

[0112] Figure 5 The structural schematic diagram of an electronic device according to some embodiments of the present invention is shown. As Figure 5 shown, an embodiment of the present invention provides an electronic device, including a memory 504, a processor 502, and a computer program stored on the memory 504 and executable on the processor 502. When the processor 502 executes the program, it implements the production optimization control method described in any of the above embodiments.

[0113] Among them, in Figure 5 , the bus architecture (represented by bus 500), the bus 500 may include any number of interconnected buses and bridges. The bus 500 links various circuits including one or more processors represented by the processor 502 and a memory represented by the memory 504 together. The bus 500 can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, etc., which are well known in the art. Therefore, further description thereof will not be provided herein. The bus interface 505 provides an interface between the bus 500 and the receiver 501 and the transmitter 503. The receiver 501 and the transmitter 503 may be the same element, i.e., a transceiver, providing a unit for communicating with various other devices on the transmission medium. The processor 502 is responsible for managing the bus 500 and general processing, while the memory 504 can be used to store data used by the processor 502 when performing operations.

[0114] Based on the same inventive concept, an embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the production optimization control method described in any of the above embodiments.

[0115] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 each flow or multiple flows and / or blocks Figure 1 each block or multiple blocks.

[0116] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means that implement the function specified in one or more of the processes and / or blocks Figure 1 one or more of the processes and / or blocks Figure 1 specified in the block or blocks.

[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the function specified in one or more of the processes and / or blocks Figure 1 one or more of the processes and / or blocks Figure 1 specified in the block or blocks.

[0118] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn of the basic inventive concept. Therefore, the appended claims are intended to be construed to cover the preferred embodiments as well as all changes and modifications that fall within the scope of the present invention.

[0119] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn of the basic inventive concept. Therefore, the appended claims are intended to be construed to cover the preferred embodiments as well as all changes and modifications that fall within the scope of the present invention.

[0120] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A production optimization control method, characterized in that, Including: Obtaining candidate production data of the target steel grade from a pre-established optimization database, where the candidate production data includes steel grade compositions and hot rolling process data of the target steel grade produced by multiple production bases in multiple historical periods; Optimizing the candidate production data according to the current resource conditions and the target cost of the target steel grade to obtain multiple optimal parameter groups, where the multiple optimal parameter groups include the optimal steel grade composition and the optimal hot rolling process; Performing a fusion process on the multiple optimal parameter groups based on a cost optimization strategy to obtain the fusion perception information for currently producing the target steel grade; Detecting the current production data during the production process of the target steel grade, and adjusting the production process of the target steel grade according to the deviation between the fusion perception information and the current production data.

2. The production optimization control method according to claim 1, wherein Also including: Preprocessing the obtained cost control materials, where the cost control materials include recorded data during the historical production processes of multiple steel grades; Obtaining the key control information for controlling the production processes of the multiple steel grades from the preprocessed data; Establishing the optimization database according to the key control information.

3. The production optimization control method according to claim 2, wherein The optimizing the candidate production data according to the current resource conditions and the target cost of the target steel grade to obtain multiple optimal parameter groups includes: Performing clustering division on the candidate production data based on data differences to obtain multiple clustering division results; For each clustering division result, performing an optimization solution based on the objective function and constraint conditions corresponding to the data type of the clustering division result to obtain the optimal solution of the clustering division result, where the optimal solutions of the multiple clustering division results include the optimal steel grade composition and the optimal hot rolling process of the target steel grade at each production base, as well as the optimal steel grade composition and the optimal hot rolling process in each historical period.

4. The production optimization control method according to claim 3, wherein The performing a fusion process on the multiple optimal parameter groups based on a cost optimization strategy to obtain the fusion perception information for currently producing the target steel grade includes: Performing step-by-step association on the multiple optimal parameter groups based on a pre-created scheduling model to obtain multiple perception information groups, where each perception information group is the association result of the process parameters of an optimal steel grade composition and an optimal hot rolling process for producing the target steel grade; Performing production manufacturing cost accounting for each of the perception information groups to obtain the production manufacturing cost corresponding to each perception information group; Determining the fusion perception information for currently producing the target steel grade based on the production manufacturing cost corresponding to each perception information group.

5. The production optimization control method according to claim 4, wherein Also including: Extracting multiple key control entities that affect the production process of the target steel grade from the key control information, where the key control entities include the composition types of the steel grade composition and the process parameter types involved in the hot rolling process; Defining the control relationships between the key control entities; Constructing a cost control knowledge graph with each of the key control entities as the graph nodes of the graph and the control relationships between the key control entities as the relationship edges between the graph nodes; The determining the fusion perception information for currently producing the target steel grade based on the production manufacturing cost corresponding to each perception information group includes: Fusing the multiple sets of perception information based on the production manufacturing cost corresponding to each set of perception information and the cost control knowledge graph to obtain the fused perception information.

6. The production optimization control method according to claim 1, characterized in that, Adjusting the production process of the target steel grade according to the deviation between the fused perception information and the current production data, including: Transmitting the fused perception information to multiple control units for controlling the production process of the target steel grade, so that each control unit collaboratively adjusts the production process of producing the target steel grade based on the deviation between the fused perception information and the current production data.

7. The production optimization control method according to claim 6, characterized in that The multiple control units include a reference control unit, a safety control unit, and a path control unit; Transmitting the fused perception information to multiple control units for controlling the production process of the target steel grade, including: Transmitting the fused perception information to the reference control unit, so that the reference control unit generates a reference control instruction and performs local reference control of the target cost based on the reference control instruction, so that the production manufacturing cost of currently producing the target steel grade conforms to the target cost; Transmitting the fused perception information to the active safety control unit, so that the active safety control unit performs target detection and risk discrimination during the production process of the target steel grade based on the fused perception information and outputs a risk discrimination result; Transmitting the fused perception information to the route control unit, so that the route control unit updates the path information based on the fused perception information and re-plans the production path of the target steel grade according to the updated path information.

8. A production optimization control device, characterized in that, Including: An acquisition unit for acquiring candidate production data for producing the target steel grade from a pre-established optimization database, where the candidate production data includes the steel grade composition and hot rolling process data of the target steel grade produced by multiple production bases in multiple historical periods; An optimization unit for optimizing the candidate production data according to the current resource conditions and the target cost of the target steel grade to obtain multiple optimal parameter sets, where the multiple optimal parameter sets include an optimal steel grade composition and an optimal hot rolling process, the optimal steel grade composition includes a set of components required for producing the target steel grade, and the optimal hot rolling process includes a set of hot rolling process parameters required for producing the target steel grade; A fusion unit for performing a fusion process on the multiple optimal parameter sets based on a cost optimization strategy to obtain the fused perception information for currently producing the target steel grade; An adjustment unit for detecting the current production data during the production process of the target steel grade and adjusting the production process of the target steel grade according to the deviation between the fused perception information and the current production data.

9. An electronic device, characterized in that, Including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the production optimization control method according to any one of claims 1-8 when executing the program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program, when executed by the processor, implements the production optimization control method according to any one of claims 1-8.

Images