Quality judgment method and system for continuous casting and rolling production line, medium and product
By obtaining molten steel and quality monitoring data in the continuous casting and rolling production line and using preset models to make quality judgments, the problem of insufficient product quality risk prevention and control in the continuous casting and rolling production line is solved, accurate prediction of steel coil quality and risk interception are achieved, and the cost of manual inspection is reduced.
Patent Information
- Application Number
- CN202510781946.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-12
- Publication Date
- 2025-09-09
AI Technical Summary
The continuous casting and rolling production line lacks the slab off-line cleaning process in traditional processes, resulting in significant defects in product quality risk prevention and control and a high rate of quality misjudgment.
By acquiring molten steel data, quality monitoring data and continuous casting process parameters, and processing them using a preset continuous casting and rolling quality judgment model, the target quality judgment of each slab is achieved, and the results are associated with the corresponding steel coils.
It achieves accurate prediction of steel coil quality during the uninterrupted production of the entire continuous casting and rolling process, effectively intercepts risky steel coils, and reduces manual inspection costs.
Smart Images
Figure CN120605949A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of continuous casting and rolling, and in particular to a quality determination method, system, medium and product of a continuous casting and rolling production line. Background Art
[0002] Currently, multi-mode continuous casting and rolling lines have achieved significant cost reduction and efficiency gains by shortening the process flow. However, their "molten steel to coil" straight-through production model lacks the traditional slab cleaning process, resulting in significant deficiencies in product quality risk prevention and control. This results in a significantly higher rate of quality misjudgment than traditional lines. Therefore, there is an urgent need to provide full-process quality traceability and accurate judgment for continuous casting and rolling products. Summary of the Invention
[0003] Embodiments of the present invention provide a quality determination method, system, medium and product for a continuous casting and rolling production line.
[0004] In a first aspect, an embodiment of the present invention provides a method for determining the quality of a continuous casting and rolling production line, comprising:
[0005] Obtain the current molten steel data and quality monitoring data in the ladle;
[0006] When the molten steel in the current ladle is continuously cast and rolled, the actual continuous casting process parameters of each slab and the abnormal continuous casting event information are obtained;
[0007] Based on a preset continuous casting and rolling quality determination model, the molten steel data, the quality monitoring data, the actual continuous casting process parameters, and the continuous casting abnormal event information of each slab are processed to obtain a target quality determination result for each slab;
[0008] The steel coil corresponding to each slab is determined, and each steel coil is associated with the target quality determination result of the corresponding slab.
[0009] In some embodiments, obtaining the molten steel data and quality monitoring data in the current ladle includes:
[0010] A data request is sent to the secondary system and the tertiary system of the front-end smelting process of continuous casting and rolling, and the molten steel data and the quality monitoring data fed back by the secondary system and the tertiary system are obtained.
[0011] In some embodiments, the molten steel data in the current ladle includes molten steel composition, molten steel temperature, and charging information.
[0012] In some embodiments, the preset continuous casting and rolling quality determination model is constructed by the following steps:
[0013] Construct an initial continuous casting and rolling quality judgment model;
[0014] Determining a training sample set, wherein each training sample in the training sample set includes sample data and a sample label, the sample data including molten steel data, quality monitoring data, actual continuous casting process parameters, and continuous casting abnormal event information of the corresponding slab during the continuous casting process, and the sample label including a true quality determination result of the corresponding slab;
[0015] The initial continuous casting and rolling quality determination model is iteratively trained based on the training sample set to obtain the preset continuous casting and rolling quality determination model.
[0016] In some embodiments, the sample label includes a first label for indicating whether the quality of the corresponding slab is qualified. When the first label indicates that the quality is abnormal, the sample label further includes a second label for indicating the abnormality level.
[0017] In some embodiments, the second label includes a first level for representing blocking, a second level for representing degradation, and a third level for representing invalidation.
[0018] In some embodiments, determining the steel coil corresponding to each slab and associating each steel coil with the target quality determination result of the corresponding slab includes:
[0019] assigning a real slab identifier and a virtual slab identifier to each of the slabs;
[0020] Establishing a mapping relationship between the virtual slab identifier of each slab and the corresponding target quality determination result;
[0021] For each slab, an actual steel coil identifier is allocated to the steel coil corresponding to the slab, and the actual steel coil identifier is associated with the virtual slab identifier of the slab.
[0022] In a second aspect, an embodiment of the present invention provides a quality determination device for a continuous casting and rolling production line, comprising:
[0023] The first acquisition module is used to obtain the molten steel data and quality monitoring data in the current ladle;
[0024] The second acquisition module is used to obtain the actual continuous casting process parameters and continuous casting abnormal event information of each slab during the continuous casting process when the molten steel in the current ladle is continuously cast and rolled;
[0025] a quality determination module, configured to process the molten steel data, the quality monitoring data, the actual continuous casting process parameters, and the continuous casting abnormal event information of each slab based on a preset continuous casting and rolling quality determination model to obtain a target quality determination result for each slab;
[0026] The association determination module is used to determine the steel coil corresponding to each slab and associate each steel coil with the target quality determination result of the corresponding slab.
[0027] In the third aspect, the present invention provides a quality determination system for a continuous casting and rolling production line, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the above-mentioned quality determination method for a continuous casting and rolling production line when executing the program.
[0028] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps in the above-mentioned cold-rolled strip quality control method when executed by a processor.
[0029] In a fifth aspect, an embodiment of the present invention provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it is used to load and execute the steps in the above-mentioned quality determination method for the continuous casting and rolling production line.
[0030] The above one or at least one technical solution in the embodiments of the present application has at least the following technical effects:
[0031] In the quality determination method for the continuous casting and rolling production line provided in the embodiment of this specification, the molten steel data and quality monitoring data in the current ladle are obtained, and when the molten steel in the current ladle is continuously cast and rolled, the actual continuous casting process parameters and continuous casting abnormal event information of each slab in the continuous casting process are obtained; based on the preset continuous casting and rolling quality determination model, the molten steel data, quality monitoring data, actual continuous casting process parameters and continuous casting abnormal event information of each slab are processed to obtain the target quality determination result of each slab; the steel coil corresponding to each slab is determined, and each steel coil is associated with the target quality determination result of the corresponding slab. This solution, through the preset continuous casting and rolling quality determination model, can achieve accurate prediction of the quality of the steel coil during the uninterrupted production of the entire continuous casting and rolling process, thereby effectively intercepting steel coils with risks and reducing the cost of manual inspection. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] Figure 1 This is a flow chart of a quality determination method for a continuous casting and rolling production line provided in an embodiment of this specification;
[0033] Figure 2 This is a schematic diagram of a quality determination device for a continuous casting and rolling production line provided in an embodiment of this specification;
[0034] Figure 3 This is a schematic diagram of a quality determination system for a continuous casting and rolling production line provided in an embodiment of this specification. DETAILED DESCRIPTION
[0035] The overall idea of the technical solution of the embodiment of the present application is as follows: obtaining the molten steel data and quality monitoring data in the current ladle; when the molten steel in the current ladle is continuously cast and rolled, obtaining the actual continuous casting process parameters and continuous casting abnormal event information of each slab during the continuous casting process; based on a preset continuous casting and rolling quality judgment model, processing the molten steel data, the quality monitoring data, the actual continuous casting process parameters and the continuous casting abnormal event information of each slab to obtain the target quality judgment result of each slab; determining the steel coil corresponding to each slab, and associating each steel coil with the target quality judgment result of the corresponding slab.
[0036] The solution of the embodiment of this specification, through a preset continuous casting and rolling quality judgment model, can achieve accurate prediction of steel coil quality during the uninterrupted production of the entire continuous casting and rolling process, thereby effectively intercepting risky steel coils and reducing the cost of manual inspection.
[0037] In order to better understand the above technical solutions, the technical solutions of the embodiments of this specification are described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of this specification, rather than limitations on the technical solutions of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.
[0038] First, the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. Furthermore, the character " / " in this document generally indicates an "or" relationship between the associated objects.
[0039] like Figure 1 FIG. 1 is a flow chart of a method for determining the quality of a continuous casting and rolling production line provided in an embodiment of this specification. The method includes the following steps:
[0040] S101: Obtaining the molten steel data and quality monitoring data in the current ladle;
[0041] S102: When the molten steel in the current ladle is continuously cast and rolled, actual continuous casting process parameters of each slab and information on abnormal continuous casting events are obtained;
[0042] S103: Based on a preset continuous casting and rolling quality determination model, the molten steel data, the quality monitoring data, the actual continuous casting process parameters, and the continuous casting abnormal event information of each slab are processed to obtain a target quality determination result for each slab;
[0043] S104: Determine the steel coil corresponding to each slab, and associate each steel coil with the target quality determination result of the corresponding slab.
[0044] The methods provided in the examples of this specification can be applied to continuous casting and rolling production lines. It should be noted that the continuous casting and rolling process involves pouring liquid steel into a continuous casting machine to cast slabs (continuously cast ingots), which are then directly rolled into shape in a hot rolling mill. Since the slabs do not leave the production line during the entire continuous casting and rolling process, the quality assessment methods provided in the examples of this specification can be used to evaluate the internal structure of the final steel coil, such as composition, slag inclusions, and mechanical properties.
[0045] In step S101, the molten steel data in the current ladle may include molten steel composition, molten steel temperature, and charging information. Of course, the molten steel data may also include other data, which is not limited here. The quality monitoring data may be data that affects the quality of the final product. In some embodiments, the quality monitoring data may be quality abnormality code information. Different quality abnormality code information corresponds to different quality issues in the production process. For example, when a certain component in the molten steel exceeds the standard, a corresponding quality abnormality code will be generated. When the molten steel temperature is greater than a preset temperature upper limit, a corresponding quality abnormality code will be generated. If the amount of a certain material added during the charging process is incorrect, a corresponding quality abnormality code will also be generated.
[0046] It should be noted that each steelmaking process corresponds to its own secondary system, which can upload some or all of the data from the corresponding process to the tertiary system. Therefore, in some embodiments, step S101 can be implemented by sending a data request to the secondary and tertiary systems of the preceding continuous casting and rolling smelting process, and obtaining the molten steel data and quality monitoring data fed back by the secondary and tertiary systems.
[0047] In some embodiments, the secondary system of the smelting process preceding continuous casting and rolling can acquire molten steel temperature and quality monitoring data, while the tertiary system can acquire molten steel composition and charging information. To conserve resources, molten steel data and quality monitoring data can be acquired on a heat-by-heat basis. After acquisition, the data can be stored for subsequent use.
[0048] In step S102, during continuous casting and rolling, the actual continuous casting process parameters and abnormal continuous casting event information for each slab during the continuous casting process are monitored. The actual continuous casting process parameters may include parameters during the pouring phase and parameters during the solidification phase. The abnormal continuous casting event information may include, but is not limited to, abnormal temperature, abnormal casting speed, and abnormal pouring events.
[0049] In step S103, the preset continuous casting and rolling quality determination model can be used to process the above-mentioned molten steel data, quality monitoring data, actual continuous casting process parameters and continuous casting abnormal event information to obtain the target quality determination result of each slab.
[0050] The preset continuous casting and rolling quality judgment model can be constructed through the following steps: constructing an initial continuous casting and rolling quality judgment model; determining a training sample set, wherein each training sample in the training sample set includes sample data and sample labels, the sample data includes molten steel data, quality monitoring data, actual continuous casting process parameters, and continuous casting abnormal event information of the corresponding slab during the continuous casting process, and the sample label includes the true quality judgment result of the corresponding slab; iteratively training the initial continuous casting and rolling quality judgment model based on the training sample set to obtain the preset continuous casting and rolling quality judgment model.
[0051] Specifically, the type of the initial continuous casting and rolling quality determination model can be selected according to actual needs and is not limited here. For example, the initial continuous casting and rolling quality determination model can be a neural network model, a support vector machine model, a deep learning model, etc.
[0052] In order to train the initial continuous casting and rolling quality judgment model, a training sample set for the model needs to be constructed. In some embodiments, the model training sample set can be derived from actual data from a continuous casting and rolling production line. For example, on a continuous casting and rolling production line, each slab in the continuous casting process, or each coil in the continuous rolling process, is used as a sample. The molten steel data, quality monitoring data, continuous casting process parameters, and abnormal continuous casting event information of the sample during the actual production process are determined as the sample data of the sample. In some embodiments, to ensure the validity of the sample data, the sample data of each sample can also be preprocessed, for example, by deduplication, correction, and standardization of the sample data.
[0053] In addition, for each sample, the actual instruction judgment result of the slab or coil can be determined through offline quality inspection and used as the sample label for the sample. It should be noted that the sample label can be set according to actual needs. For example, the sample label can include qualified and abnormal. Or, in order to more accurately judge product quality, the sample label can be further divided. For example, qualified cases can be divided into multiple levels, and abnormal cases can also be divided into multiple levels. This is not limited here.
[0054] In some embodiments, the sample label may include a first label for indicating whether the quality of the corresponding slab is qualified. When the first label indicates that the quality is abnormal, the sample label further includes a second label for indicating the abnormality level.
[0055] Specifically, when the offline quality inspection of a slab is qualified, the sample label corresponding to the slab is the first label; when the offline quality inspection of the slab is abnormal, the sample label corresponding to the slab is the second label.
[0056] In some embodiments, in abnormal situations, further classification may be performed, that is, the second label includes a first level for representing blocking, a second level for representing degradation, and a third level for representing scrapping.
[0057] Specifically, slab blocking refers to a restrictive measure taken during the production process to prevent slabs from entering subsequent production processes or entering the market due to potential risks in their quality or condition. Blocked slabs require further inspection, processing, or evaluation to determine whether they can be unblocked and continue to be used, or whether they require other treatment, such as downgrading or scrapping.
[0058] Slab downgrading refers to the process of reducing a slab from a high-grade use to a lower-grade use, even though it may have defects or quality issues and, despite not meeting the original quality standards, still possesses some value. This downgrading process allows defective slabs to be effectively utilized, reducing resource waste.
[0059] Slab rejection occurs when a slab's quality problems are so severe that no repair or treatment can bring it back to usable standards, requiring it to be treated as scrap. For example, a slab may contain severe internal cracks, shrinkage cavities, substandard composition, or other significant defects that severely impact the performance and safety of the final product and cannot be eliminated through normal rolling or other processing steps.
[0060] By performing offline quality inspection on the slab, if the slab is abnormal, it can be further determined which of the above situations the slab belongs to, and then the abnormality level of the slab can be determined.
[0061] The above method can be used to construct a training sample set for the model, and the initial continuous casting and rolling quality judgment model can be iteratively trained based on the training sample set. When the number of iterations reaches a preset number, or the output accuracy of the trained continuous casting and rolling quality judgment model reaches a preset accuracy, the model is considered to have completed training, and the final model is used as the preset continuous casting and rolling quality judgment model and put into use.
[0062] After obtaining the molten steel data, quality monitoring sentence by sentence, and actual continuous casting process parameters and continuous casting abnormal event information corresponding to the current continuous casting and rolling production line, the target quality judgment result of each slab is output based on the preset continuous casting and rolling quality judgment model.
[0063] In some embodiments, after obtaining the target quality determination results for each slab, the target quality determination results can be uploaded to the three-level system for data recording. It should be noted that the three-level system can record data using preset fields. For example, the recorded information may include a and b, where a is used to indicate whether the quality is abnormal. A value of a is "no" indicates acceptable quality, and a value of a is "yes" indicates abnormal quality. b indicates different abnormality levels. When a is "yes" and b is 1, it indicates a first-level blockade. When a is "yes" and b is 2, it indicates a second-level downgrade. When a is "yes" and b is 3, it indicates a third-level scrapping.
[0064] In step S104, since the slabs are directly coiled in the continuous casting and rolling process, in order to ensure the consistency of the quality of the coils, the target quality judgment result of each slab needs to be matched to the corresponding steel coil.
[0065] In some embodiments, step S104 can be implemented by the following steps: assigning an actual slab identification and a virtual slab identification to each of the slabs; establishing a mapping relationship between the virtual slab identification of each of the slabs and the corresponding target quality judgment result; for each of the slabs, assigning an actual steel coil identification to the steel coil corresponding to the slab, and associating the actual steel coil identification with the virtual slab identification of the slab.
[0066] Specifically, each slab is assigned its own actual slab identifier and virtual slab identifier. For example, the actual slab identifier of a slab is AA, and its virtual slab identifier is aa. When this slab is produced as a steel coil through rolling, it is assigned an actual steel coil identifier 11. Then, the actual slab identifier AA, the virtual slab identifier aa and the actual steel coil identifier 11 are associated. In this way, the actual slab identifier and the actual steel coil identifier can be connected through the virtual slab identifier, thereby achieving matching between the slab and the steel coil.
[0067] In the embodiments of this specification, in order to obtain the corresponding slab quality information through the actual steel coil identification, the target quality determination result of each slab can also be associated with the virtual slab identification. When the quality information of a steel coil needs to be obtained, the corresponding virtual slab identification can be determined through the actual steel coil identification of the steel coil, and then the corresponding target quality determination result can be determined based on the virtual slab identification. In some embodiments, all data during the production of the slab can also be associated with the virtual slab identification. For example, the above-mentioned molten steel data, quality monitoring data, actual continuous casting process parameters, and continuous casting abnormal event information are all associated with the virtual slab identification. Then, all information about the corresponding slab can be obtained through the actual steel coil identification of the steel coil.
[0068] In the embodiments of this specification, in order to realize the quality determination method of the above-mentioned continuous casting and rolling production line, a lightweight standard three-layer development framework can be built, including an interface layer (User Interface, UI), a business logic layer (Business Logic Layer, BLL) and a data access layer (Data Access Layer, DAL). At the same time, a database layer and a platform layer can be established, wherein the database layer can provide an Oracle relational database, which should provide a variety of database access interfaces and be compatible with a variety of hardware systems, support various development framework technologies, support a variety of network protocols, support column storage, data compression, materialized views and other optimization options for online transaction analysis scenarios, and can configure a data guard system (master and backup), automatically and quickly recover from faults, and have powerful disaster recovery capabilities. The platform layer can be regarded as the cornerstone of business service development, providing data communication middleware with secondary and above systems and a first-level data communication middleware based on the OPC (OLE for Process Control, OLE for process control) protocol, and has real-time data collection, analysis, storage and efficient and stable IPC functions.
[0069] Specifically, the interface layer establishes communication links with the secondary and tertiary systems of the upstream smelting process. Through the data access layer, information such as molten steel temperature and quality anomaly codes from the secondary smelting model, as well as composition information and charging information from the tertiary system, can be retrieved at the heat level. The retrieved data is stored in the database layer for subsequent use. In some embodiments, this architecture can be deployed in the continuous casting process to collect various data, perform quality judgment calculations, and display and upload the results.
[0070] In summary, the scheme of the embodiments of this specification, by acquiring molten steel data and quality monitoring data in real time, can achieve real-time perception of molten steel quality risks and accurate prediction of steel coil performance under the condition of uninterrupted production throughout the entire continuous casting and rolling process. It can also lock in the occurrence of defects in real time during the production process, and ensure that defective products are not released to the downstream through blocking and other means. Through online monitoring of molten steel data, the interception rate of the risk of exceeding the inclusion standard can be improved, and the occurrence of defects such as surface cracks, slag inclusions, and composition segregation can be reduced. In addition, through the preset continuous casting and rolling quality judgment model, the accuracy of the prediction of the mechanical properties of hot-rolled steel coils can be improved, and the losses caused by quality misjudgment can be reduced. At the same time, due to the full-process quality traceability and intelligent decision-making, the time for handling abnormal working conditions is effectively shortened, the frequency of manual sampling is reduced, and the labor cost is reduced.
[0071] Based on the same inventive concept, the embodiment of this specification also provides a quality determination device for a continuous casting and rolling production line, such as Figure 2 As shown, the device includes:
[0072] The first acquisition module 201 is used to obtain the molten steel data and quality monitoring data in the current ladle;
[0073] The second acquisition module 202 is used to obtain the actual continuous casting process parameters and continuous casting abnormal event information of each slab during the continuous casting process when the molten steel in the current ladle is continuously cast and rolled;
[0074] The quality determination module 203 is configured to process the molten steel data, the quality monitoring data, the actual continuous casting process parameters, and the continuous casting abnormal event information of each slab based on a preset continuous casting and rolling quality determination model to obtain a target quality determination result for each slab;
[0075] The association determination module 204 is configured to determine the steel coil corresponding to each slab and associate each steel coil with the target quality determination result of the corresponding slab.
[0076] Regarding the above-mentioned device, the specific implementation of each step has been described in detail in the embodiment of the quality determination method for the continuous casting and rolling production line provided in the embodiment of the specification, and will not be elaborated here.
[0077] In some implementations, the first acquisition module 201 is configured to:
[0078] A data request is sent to the secondary system and the tertiary system of the front-end smelting process of continuous casting and rolling, and the molten steel data and the quality monitoring data fed back by the secondary system and the tertiary system are obtained.
[0079] In some embodiments, the molten steel data in the current ladle includes molten steel composition, molten steel temperature, and charging information.
[0080] In some embodiments, the preset continuous casting and rolling quality determination model is constructed by the following steps:
[0081] Construct an initial continuous casting and rolling quality judgment model;
[0082] Determining a training sample set, wherein each training sample in the training sample set includes sample data and a sample label, the sample data including molten steel data, quality monitoring data, actual continuous casting process parameters, and continuous casting abnormal event information of the corresponding slab during the continuous casting process, and the sample label including a true quality determination result of the corresponding slab;
[0083] The initial continuous casting and rolling quality determination model is iteratively trained based on the training sample set to obtain the preset continuous casting and rolling quality determination model.
[0084] In some embodiments, the sample label includes a first label for indicating whether the quality of the corresponding slab is qualified. When the first label indicates that the quality is abnormal, the sample label further includes a second label for indicating the abnormality level.
[0085] In some embodiments, the second label includes a first level for representing blocking, a second level for representing degradation, and a third level for representing invalidation.
[0086] In some implementations, the association determination module 204 is configured to:
[0087] assigning a real slab identifier and a virtual slab identifier to each of the slabs;
[0088] Establishing a mapping relationship between the virtual slab identifier of each slab and the corresponding target quality determination result;
[0089] For each slab, an actual steel coil identifier is allocated to the steel coil corresponding to the slab, and the actual steel coil identifier is associated with the virtual slab identifier of the slab.
[0090] Based on the same inventive concept, the embodiment of the present invention also provides a quality determination system for a continuous casting and rolling production line, such as Figure 3 The system includes a memory 304, a processor 302, and a computer program stored in the memory 304 and executable on the processor 302. When the processor 302 executes the program, any one of the methods for determining the quality of a continuous casting and rolling production line is implemented.
[0091] Among them, Figure 3 In the embodiment of the present invention, a bus architecture (represented by bus 300) is shown. Bus 300 may include any number of interconnected buses and bridges, and bus 300 links together various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same component, namely a transceiver, which provides a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 may be used to store data used by processor 302 when performing operations.
[0092] Based on the same inventive concept, an embodiment of this specification provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned method for determining the quality of the continuous casting and rolling production line.
[0093] Based on the same inventive concept, an embodiment of this specification provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it is used to load and execute the steps of the quality determination method for the continuous casting and rolling production line.
[0094] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and implementations are within the scope and spirit of the present invention and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hardwiring, or a combination of any of these. Furthermore, each functional unit may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit.
[0095] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.
[0096] The units described as separate components may or may not be physically separate, and the components of the control device may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0097] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.
[0098] The foregoing description is merely an embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of the claims.
Claims
1. A method for determining the quality of a continuous casting and rolling production line, characterized in that: include: Obtain the current molten steel data and quality monitoring data in the ladle; When the molten steel in the current ladle is continuously cast and rolled, the actual continuous casting process parameters of each slab and the abnormal continuous casting event information are obtained; Based on a preset continuous casting and rolling quality determination model, the molten steel data, the quality monitoring data, the actual continuous casting process parameters, and the continuous casting abnormal event information of each slab are processed to obtain a target quality determination result for each slab; The steel coil corresponding to each slab is determined, and each steel coil is associated with the target quality determination result of the corresponding slab.
2. The method according to claim 1, wherein The acquisition of the current molten steel data and quality monitoring data in the ladle includes: A data request is sent to the secondary system and the tertiary system of the front-end smelting process of continuous casting and rolling, and the molten steel data and the quality monitoring data fed back by the secondary system and the tertiary system are obtained.
3. The method according to claim 1, wherein The molten steel data in the current ladle includes molten steel composition, molten steel temperature and charging information.
4. The method according to claim 1, wherein The preset continuous casting and rolling quality judgment model is constructed by the following steps: Construct an initial continuous casting and rolling quality judgment model; Determining a training sample set, wherein each training sample in the training sample set includes sample data and a sample label, the sample data including molten steel data, quality monitoring data, actual continuous casting process parameters, and continuous casting abnormal event information of the corresponding slab during the continuous casting process, and the sample label including a true quality determination result of the corresponding slab; The initial continuous casting and rolling quality determination model is iteratively trained based on the training sample set to obtain the preset continuous casting and rolling quality determination model.
5. The method according to claim 4, wherein The sample label includes a first label for indicating whether the quality of the corresponding slab is qualified. When the first label indicates that the quality is abnormal, the sample label also includes a second label for indicating the abnormality level.
6. The method according to claim 5, wherein The second label includes a first level for representing blocking, a second level for representing demotion, and a third level for representing abandonment.
7. The method according to claim 1, wherein Determining the steel coil corresponding to each slab and associating each steel coil with the target quality determination result of the corresponding slab includes: assigning a real slab identifier and a virtual slab identifier to each of the slabs; Establishing a mapping relationship between the virtual slab identifier of each slab and the corresponding target quality determination result; For each slab, an actual steel coil identifier is allocated to the steel coil corresponding to the slab, and the actual steel coil identifier is associated with the virtual slab identifier of the slab.
8. A quality determination system for a continuous casting and rolling production line, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the program.
9. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the computer program is configured to load and execute the method according to any one of claims 1 to 7.