Steel defect detection method and device and readable storage medium

Abstract

The invention discloses a steel defect detection method and device and a readable storage medium, and relates to the technical field of steel processing. The steel defect detection method comprises the steps of obtaining a production data set of steel in the machining process of the steel; constructing a knowledge graph corresponding to the steel according to the production data set; based on the knowledge graph, determining a detection model of the steel; and performing defect detection on the steel through the detection model to obtain a detection result of the steel. The steel defect detection accuracy is improved.

Description

Technical Field

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

[0002] During the cold-rolling steel production process, the quality of incoming steel coils varies significantly across various steps. Defective coils can enter the production process, impacting product quality. Currently, quality control of incoming materials at each step faces numerous challenges, including the inability to promptly and accurately identify suspicious materials, a lack of quantitative risk assessment tools, and difficulty implementing effective disposal measures for materials of varying risk levels. This leads to unstable product quality, reduced production efficiency, and increased costs. Existing steel defect detection methods also suffer from technical limitations, including low accuracy. Summary of the Invention

[0003] The embodiments of the present application provide a steel defect detection method, device and readable storage medium, which are used to solve technical problems such as low detection accuracy in the prior art.

[0004] A first aspect of the embodiments of the present application provides a steel defect detection method, comprising:

[0005] During the steel processing, obtain the steel production data set;

[0006] Based on the production data set, build a knowledge graph corresponding to steel;

[0007] Determine the steel detection model based on the knowledge graph;

[0008] The steel is inspected for defects through the inspection model to obtain the inspection results of the steel.

[0009] The steel defect detection method in this embodiment performs defect detection on steel through a knowledge graph and a detection model to obtain the detection results of the steel, thereby ensuring the data accuracy of the detection results and thereby improving the accuracy of steel defect detection.

[0010] A second aspect of the embodiments of the present application provides a steel defect detection device, comprising:

[0011] An acquisition unit, used for acquiring a set of production data of steel materials during the processing of the steel materials;

[0012] A processing unit, used to construct a knowledge graph corresponding to steel materials based on the production data set;

[0013] The processing unit is also used to determine the steel detection model based on the knowledge graph;

[0014] The processing unit is also used to perform defect detection on the steel through the detection model to obtain the detection result of the steel.

[0015] The steel defect detection device in this embodiment performs defect detection on steel through a knowledge graph and a detection model to obtain detection results of the steel, thereby ensuring the data accuracy of the detection results and thereby improving the accuracy of defect detection of steel.

[0016] A third aspect of the present application provides another steel defect detection device, comprising a processor and a memory, wherein the memory stores a computer program that, when executed by the processor, implements the steps of the steel defect detection method described in any of the aforementioned embodiments. Therefore, the steel defect detection device possesses all the beneficial effects of the steel defect detection method described in any of the aforementioned embodiments, and further description thereof is omitted.

[0017] A fourth aspect of the present application provides a readable storage medium having a program or instructions stored thereon. When executed by a processor, the program or instructions implement the steps of the steel defect detection method described in any of the aforementioned embodiments. Therefore, the readable storage medium possesses all the beneficial effects of the steel defect detection method described in any of the aforementioned embodiments, and further description thereof is omitted. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] Figure 1 A flow chart of the steel defect detection method provided in an embodiment of the present application;

[0020] Figure 2 This is a functional module block diagram of the steel defect detection device provided in an embodiment of the present application;

[0021] Figure 3 This is a structural block diagram of the steel defect detection device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to better understand the technical solutions provided by the embodiments of this specification, the technical solutions of the embodiments of this specification are described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of this specification, rather than limitations on the technical solutions of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0023] In this article, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also include elements inherent to such process, method, article or equipment. In the absence of further restrictions, the elements defined by the statement "comprising a ..." do not exclude the presence of other identical elements in the process, method, article or equipment comprising the elements. The term "two or more" includes two or more than two cases.

[0024] In some embodiments, as Figure 1 As shown, an embodiment of the present application provides a steel defect detection method, comprising:

[0025] Step S101, during the steel processing process, obtaining a set of steel production data;

[0026] Step S102: constructing a knowledge graph corresponding to steel materials based on the production data set;

[0027] Step S103: determining a steel detection model based on the knowledge graph;

[0028] Step S104: perform defect detection on the steel using the detection model to obtain a detection result of the steel.

[0029] In this embodiment, a steel defect detection method is proposed. During the processing of the steel, a production data set of the steel is obtained, wherein the production data set includes various production indicators of the steel.

[0030] For example, the production data set includes parameters such as contracts, production lines, steelmaking materials, hot-rolled materials, cold-rolled materials, pickling, continuous annealing, and galvanizing.

[0031] Based on the production data set, a knowledge graph corresponding to steel is constructed. The knowledge graph is a graph that uses visualization technology to describe knowledge resources and their carriers, and mines, analyzes, constructs, draws and displays knowledge and the connections between them.

[0032] For example, the knowledge graph may be a knowledge graph that describes the relationships among various properties of steel.

[0033] Based on the knowledge graph, a detection model for steel is determined, where the detection model is a mathematical model used to detect steel defects.

[0034] Exemplarily, the detection model may be a suspicious material risk blocking and risk control model.

[0035] The steel is subjected to defect detection through the detection model to obtain a detection result of the steel, wherein the detection result represents a defect detection result of the steel.

[0036] For example, the detection result may be defective steel in a batch of steel.

[0037] The steel defect detection method in this embodiment performs defect detection on steel through a knowledge graph and a detection model to obtain the detection results of the steel, thereby ensuring the data accuracy of the detection results and thereby improving the accuracy of steel defect detection.

[0038] In some embodiments, the present application provides a method for detecting steel defects, which constructs a knowledge graph corresponding to the steel based on a production data set, including:

[0039] Step S201, determining ontology data and attribute data based on the production data set;

[0040] Step S202: Acquire a first business table corresponding to the ontology data and a second business table corresponding to the attribute data;

[0041] Step S203, determining the association relationship between the ontology data and the attribute data based on the mapping relationship between the first business table and the second business table;

[0042] Step S204: Determine the knowledge graph based on the association relationship between the ontology data and the attribute data.

[0043] In this embodiment, ontology data and attribute data are determined based on the production data set, wherein the ontology data represents the ontology in the knowledge graph and the attribute data represents the attributes in the knowledge graph.

[0044] For example, the ontology data is shown in Table 1.

[0045] Table 1

[0046]

[0047]

[0048]

[0049]

[0050]

[0051] A first business table corresponding to the ontology data and a second business table corresponding to the attribute data are obtained, wherein the first business table is the business table corresponding to the ontology data and the second business table is the business table corresponding to the attribute data.

[0052] The association relationship between the ontology data and the attribute data is determined according to the mapping relationship between the first business table and the second business table.

[0053] For example, the material-side ontology relationship is shown in Table 2.

[0054] Table 2

[0055] subject predicate object contract Contract production line Contract production line Contract production line Contract steelmaking materials Steelmaking materials Steelmaking materials Entrance material Hot rolled materials Hot rolled materials Entrance material Cold rolled materials Contract production line Contract cold rolled materials Cold rolled materials Cold rolled materials Entrance material Cold rolled materials Cold rolled materials Pickling PDA performance Acid-rolled PDA Cold rolled materials Consecutive QDR withdrawal results Continuous withdrawal QDR Cold rolled materials Continuous DAS withdrawal performance Continuous withdrawal DAS Cold rolled materials Roughness performance Roughness Cold rolled materials Galvanized QDR performance Galvanized QDR Cold rolled materials Coating performance coating Cold rolled materials Cold rolling material line determination Cold rolling online judgment

[0056] Determine the knowledge graph based on the association relationship between ontology data and attribute data.

[0057] Exemplarily, the steps of constructing a knowledge graph include:

[0058] The first step is schema design: In a knowledge graph, a schema defines the format of data to be added to the knowledge graph. It serves as metadata for the knowledge graph, describing its entities, attributes, and relationships. Based on actual production processes such as production contracts, production lines, steelmaking materials, hot-rolled materials, cold-rolled materials, pickling, annealing, and galvanizing, we abstract entities, relationships, and attributes to form the material-side knowledge graph schema.

[0059] The second step is data mapping, which includes ontology and attribute mapping and relationship mapping.

[0060] Ontology and Attribute Mapping: This process focuses on accurately mapping the entities and their attributes defined in the knowledge graph schema to the corresponding tables and fields in the actual production database. This requires meticulously matching the database table structure of each entity represented by the ontology, while ensuring that the value of each attribute can be accurately extracted or stored in the database field. Data mapping not only ensures data accuracy but also promotes data accessibility and consistency, laying a solid foundation for subsequent data analysis, querying, and knowledge reasoning.

[0061] Relationship mapping: As a complement to data mapping, relationship mapping focuses on parsing and expressing the relationships between tables in the database. These relationships are usually implemented through association fields (such as foreign keys). In the knowledge graph, these relationships are abstracted as edges connecting different ontologies (entities), thereby constructing a complex and rich knowledge network. Relationship mapping requires a deep understanding of the database's design logic, accurately identifying which tables are associated with each other, and how these associations affect the overall structure and meaning of the data. Through relationship mapping, we can reproduce the inherent logic and hierarchical structure of the data in the knowledge graph, providing strong support for complex data analysis and knowledge discovery.

[0062] In some embodiments, an embodiment of the present application provides a steel defect detection method, which obtains a first business table corresponding to the body data and a second business table corresponding to the attribute data, including:

[0063] Step S301: determining a first business table corresponding to the ontology data based on the production data set;

[0064] Step S302: Determine the second business table corresponding to the attribute data according to the first business table and the ontology data.

[0065] In this embodiment, based on the production data set, a first business table corresponding to the ontology data is determined, and then based on the first business table and the ontology data, a second business table corresponding to the attribute data is determined.

[0066] For example, after the schema design is completed, it is connected to the production data source. Through the knowledge graph construction platform, the ontology, attributes and relationships are mapped with the tables and fields in the data source. The data mapping is divided into four steps:

[0067] (1) Connect to the production data source and select the table to be mapped;

[0068] (2) Map the business table where the ontology is located and select the unique primary key of the ontology;

[0069] (3) Map the attributes of the ontology to the fields in the table to confirm the source of the attributes;

[0070] (4) Map the association relationship between ontologies through the association relationship between tables.

[0071] After performing the data mapping in the above four steps, the knowledge graph construction platform will automatically generate SQL statements to query data in the data source, extract knowledge to form NT files, and finally import the NT files into the RDF graph database to form a knowledge graph.

[0072] In some embodiments, an embodiment of the present application provides a steel defect detection method, which determines a steel detection model based on a knowledge graph, including:

[0073] Step S401: determining risk ranges of multiple attribute values ​​of steel materials based on the knowledge graph;

[0074] Step S402: determining multiple numerical processing methods corresponding to multiple attribute value risk ranges, wherein the multiple numerical processing methods correspond to the multiple attribute value risk ranges one-to-one;

[0075] Step S403: determining a steel inspection model based on multiple attribute value risk ranges and multiple numerical processing methods.

[0076] In this embodiment, multiple attribute value risk ranges of steel are determined based on the knowledge graph, wherein the attribute value risk range represents the risk range of the attribute value.

[0077] Determine multiple numerical processing methods corresponding to multiple attribute value risk ranges, wherein the multiple numerical processing methods correspond one-to-one to the multiple attribute value risk ranges, and the numerical processing methods are processing methods for the attribute value risk ranges.

[0078] Determine the steel inspection model based on multiple attribute value risk ranges and multiple numerical processing methods.

[0079] For example, to clarify the risk ranges for each attribute value of a steel coil, the knowledge graph integrates extensive information on the coil's dimensions, curves, shape, and surface defects. The average μ and standard deviation σ for each attribute are calculated. Five score intervals are defined: below 60, 60-70, 70-80, 80-90, and above 90. Each attribute value range is divided into five score intervals, as shown in Table 3.

[0080] Table 3

[0081] Score range Attribute value range Below 60 points x<μ-3σ、μ+3σ<x 60-70 points μ-3σ<=x<μ-2σ、μ+2σ <x<=μ+3σ 70-80 points μ-2σ<=x<μ-1.5σ、μ+1.5σ <x<=μ+2σ 80-90 points μ-1.5σ<=x<μ-1σ、μ+1σ <x<=μ+1.5σ 90 points or above μ-1σ<=x<=μ+1σ

[0082] In some embodiments, embodiments of the present application provide a steel defect detection method, which determines a detection model based on multiple attribute value risk ranges and multiple numerical processing methods, including:

[0083] Step S501, determining suspicious material risk rules based on multiple attribute value risk ranges and multiple value processing methods;

[0084] Step S502: Input suspicious material risk rules into the knowledge graph to obtain a detection model.

[0085] In this embodiment, suspicious material risk rules are determined based on multiple attribute value risk ranges and multiple numerical value processing methods, wherein the suspicious material risk rules represent risk rules corresponding to suspicious materials in steel.

[0086] For example, the knowledge graph identifies attribute value ranges within five score intervals. Expert experience then adjusts these attribute value ranges and formulates a treatment approach. The process manager then identifies reviewers and early warning positions. Ultimately, the numerical treatment approach, or treatment rules, is derived. The risk blocking and risk control rules for suspicious materials in process are then entered into the predictive model knowledge graph.

[0087] In some embodiments, a method for detecting steel defects is provided in an embodiment of the present application. The method performs defect detection on steel to obtain a steel detection result, including:

[0088] Step S601, obtaining material parameters of steel;

[0089] Step S602: Detecting the material parameters using the detection model to obtain detection results.

[0090] In this embodiment, material parameters of the steel are acquired, and the material parameters are detected and processed by a detection model to obtain detection results, wherein the material parameters are real-time parameters of the steel.

[0091] Exemplarily, the steps of suspicious material prediction include:

[0092] (1) Obtain prediction models from knowledge graphs.

[0093] (2) Risk prediction is performed before going online. The processes involved are before pickling, before annealing, and before galvanizing. The current attribute information of the steel coil material, such as thickness tolerance, width tolerance, outer diameter, convexity, wedge shape, centerline offset, local high point of the contour, protective slag, scarring, surface warping, pits, foreign matter intrusion, delamination, thickness, uncut edge width, cut edge width, length, and inner diameter, is obtained from the material knowledge graph. The rule information of each attribute is obtained from the prediction model. The rule engine is executed in the Java code to predict suspicious materials and the prediction results are pushed to the staff on the job.

[0094] (3) Recommend treatment measures. Recommend treatment measures for each attribute of the steel coil material. Post personnel need to pay attention to the treatment measures for attributes below 90 points.

[0095] In some embodiments, a method for detecting steel defects is provided in an embodiment of the present application. After performing defect detection on the steel using a detection model to obtain a steel detection result, the method further includes:

[0096] Step S701, after the steel material has completed the processing process, obtaining the production qualification result of the steel material;

[0097] Step S702: Compare the qualified production result and the test result to determine the detection accuracy of the detection model.

[0098] In this embodiment, after the steel material completes the processing process, the production qualification result of the steel material is obtained, wherein the production qualification result indicates the final production qualification status of the steel material.

[0099] Compare the qualified production results and the test results to determine the detection accuracy of the detection model, where the detection accuracy represents the detection accuracy of the detection model.

[0100] For example, monthly forecast accuracy statistics are used. The knowledge graph is then used to query the prediction results for cold-hardened coils and the final qualified status of the coils, grouped by month. The forecast accuracy is then calculated based on these results. Based on these comparisons, the range of coil attribute values ​​within each score interval is adjusted in a timely manner.

[0101] In some embodiments, as Figure 2 As shown, in an embodiment of the present application, a steel defect detection device 800 is provided, comprising:

[0102] An acquisition unit 802 is used to acquire a set of production data of the steel during the processing of the steel;

[0103] Processing unit 804 is used to construct a knowledge graph corresponding to steel materials based on the production data set;

[0104] The processing unit 804 is further configured to determine a steel material detection model based on the knowledge graph;

[0105] The processing unit 804 is further configured to perform defect detection on the steel material using the detection model to obtain a detection result of the steel material.

[0106] In this embodiment, a steel defect detection device 800 is proposed. During the processing of the steel, a production data set of the steel is obtained, wherein the production data set includes various production indicators of the steel.

[0107] For example, the production data set includes parameters such as contracts, production lines, steelmaking materials, hot-rolled materials, cold-rolled materials, pickling, continuous annealing, and galvanizing.

[0108] Based on the production data set, a knowledge graph corresponding to steel is constructed. The knowledge graph is a graph that uses visualization technology to describe knowledge resources and their carriers, and mines, analyzes, constructs, draws and displays knowledge and the connections between them.

[0109] For example, the knowledge graph may be a knowledge graph that describes the relationships among various properties of steel.

[0110] Based on the knowledge graph, a detection model for steel is determined, where the detection model is a mathematical model used to detect steel defects.

[0111] Exemplarily, the detection model may be a suspicious material risk blocking and risk control model.

[0112] The steel is subjected to defect detection through the detection model to obtain a detection result of the steel, wherein the detection result represents a defect detection result of the steel.

[0113] For example, the detection result may be defective steel in a batch of steel.

[0114] The steel defect detection device 800 in this embodiment performs defect detection on steel through a knowledge graph and a detection model to obtain detection results of the steel, thereby ensuring the data accuracy of the detection results and thereby improving the accuracy of defect detection on steel.

[0115] In some embodiments, an embodiment of the present application provides a steel defect detection device 800, further comprising:

[0116] The processing unit 804 is further configured to determine the ontology data and the attribute data based on the production data set;

[0117] The processing unit 804 is further configured to obtain a first business table corresponding to the ontology data and a second business table corresponding to the attribute data;

[0118] The processing unit 804 is further configured to determine an association relationship between the ontology data and the attribute data based on a mapping relationship between the first business table and the second business table;

[0119] Determine the knowledge graph based on the association relationship between ontology data and attribute data.

[0120] In some embodiments, an embodiment of the present application provides a steel defect detection device 800, further comprising:

[0121] The processing unit 804 is further configured to determine a first business table corresponding to the ontology data based on the production data set;

[0122] The processing unit 804 is further configured to determine the second business table corresponding to the attribute data according to the first business table and the ontology data.

[0123] In some embodiments, an embodiment of the present application provides a steel defect detection device 800, further comprising:

[0124] The processing unit 804 is further configured to determine risk ranges of multiple attribute values ​​of the steel material based on the knowledge graph;

[0125] The processing unit 804 is further configured to determine multiple numerical processing methods corresponding to the multiple attribute value risk ranges, wherein the multiple numerical processing methods correspond to the multiple attribute value risk ranges in a one-to-one manner;

[0126] The processing unit 804 is further configured to determine a steel material detection model based on multiple attribute value risk ranges and multiple numerical processing methods.

[0127] In some embodiments, an embodiment of the present application provides a steel defect detection device 800, further comprising:

[0128] The processing unit 804 is further configured to determine a suspicious material risk rule based on the multiple attribute value risk ranges and the multiple value processing methods;

[0129] The processing unit 804 is further configured to input the suspicious material risk rules into the knowledge graph to obtain a detection model.

[0130] In some embodiments, an embodiment of the present application provides a steel defect detection device 800, further comprising:

[0131] The processing unit 804 is further used to obtain material parameters of the steel;

[0132] The processing unit 804 is further configured to perform detection processing on the material parameters through the detection model to obtain detection results.

[0133] In some embodiments, an embodiment of the present application provides a steel defect detection device 800, further comprising:

[0134] The processing unit 804 is further used to obtain a qualified result of the steel material after the steel material completes the processing process;

[0135] The processing unit 804 is further configured to compare the generated qualified result with the detection result to determine the detection accuracy of the detection model.

[0136] In some embodiments, as Figure 3 As shown, a steel defect detection device 900 is proposed. The steel defect detection device 900 includes a processor 902 and a memory 904. The memory 904 stores a computer program. When executed by the processor 902, the computer program implements the steps of the steel defect detection method in any of the above-mentioned embodiments. Therefore, the steel defect detection device 900 has all the beneficial effects of the steel defect detection method in any of the above-mentioned embodiments, and will not be further described here.

[0137] In some embodiments, a readable storage medium is provided on which a program is stored. When the program is executed by a processor, the steps of the steel defect detection method in any of the above embodiments are implemented, thereby having all the beneficial technical effects of the steel defect detection method in any of the above embodiments.

[0138] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0139] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-readable program code.

[0140] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0141] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0142] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0143] An embodiment of the present application further provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device executes the process of the steel defect detection method.

[0144] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)).

[0145] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0146] In the several embodiments provided in this application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0147] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0148] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0149] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0150] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

[0151] Although the preferred embodiments of this specification have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of this specification.

[0152] Obviously, those skilled in the art may make various changes and modifications to this specification without departing from the spirit and scope of this specification. Thus, if such changes and modifications fall within the scope of the claims of this specification and their equivalents, this specification is intended to include such changes and modifications.

Claims

1. A steel defect detection method, characterized in that: The method comprises: During the processing of the steel material, obtaining a production data set of the steel material; Constructing a knowledge graph corresponding to the steel material based on the production data set; Determining a detection model for the steel based on the knowledge graph; The steel is subjected to defect detection using the detection model to obtain a detection result of the steel.

2. The method according to claim 1, characterized in that The step of constructing a knowledge graph corresponding to the steel material based on the production data set includes: Determining ontology data and attribute data based on the production data set; Obtaining a first business table corresponding to the ontology data and a second business table corresponding to the attribute data; determining an association relationship between the ontology data and the attribute data according to a mapping relationship between the first business table and the second business table; The knowledge graph is determined based on the association relationship between the ontology data and the attribute data.

3. The method according to claim 2, characterized in that The obtaining of the first business table corresponding to the ontology data and the second business table corresponding to the attribute data includes: Determining the first business table corresponding to the ontology data based on the production data set; The second business table corresponding to the attribute data is determined according to the first business table and the ontology data.

4. The method according to claim 1, wherein Determining the steel detection model based on the knowledge graph includes: Determining risk ranges of multiple attribute values ​​of the steel material based on the knowledge graph; Determining multiple numerical processing methods corresponding to the multiple attribute value risk ranges, wherein the multiple numerical processing methods correspond to the multiple attribute value risk ranges one by one; Based on the multiple attribute value risk ranges and the multiple numerical processing methods, a detection model for the steel material is determined.

5. The method according to claim 4, characterized in that The determining of the steel inspection model based on the plurality of attribute value risk ranges and the plurality of numerical processing methods includes: determining suspicious material risk rules based on the plurality of attribute value risk ranges and the plurality of value processing methods; The suspicious material risk rules are input into the knowledge graph to obtain a detection model.

6. The method according to claim 1, characterized in that The method of performing defect detection on the steel material by using the detection model to obtain a detection result of the steel material includes: Obtaining material parameters of the steel; The material parameters are detected and processed by the detection model to obtain the detection results.

7. The method according to any one of claims 1 to 6, characterized in that After performing defect detection on the steel material using the detection model to obtain the detection result of the steel material, the method further includes: After the steel material completes the processing process, obtaining the production qualification result of the steel material; Compare the qualified production result with the test result to determine the detection accuracy of the detection model.

8. A steel defect detection device, characterized in that: The device comprises: An acquisition unit, configured to acquire a set of production data of the steel during the processing of the steel; A processing unit, configured to construct a knowledge graph corresponding to the steel material based on the production data set; The processing unit is further configured to determine a detection model for the steel material based on the knowledge graph; The processing unit is further configured to perform defect detection on the steel material using the detection model to obtain a detection result of the steel material.

9. A steel defect detection device, characterized in that: include: processor; A memory, wherein a program or instruction is stored in the memory, and when the processor executes the program or instruction in the memory, the steps of the steel defect detection method according to any one of claims 1 to 7 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the steel defect detection method according to any one of claims 1 to 7 are implemented.

Images