Cold-rolled sheet metal yield strength prediction model construction method and related equipment

The cold-rolled metal sheet yield strength prediction model is constructed through deep neuron network, which solves the problems of complexity and error of yield strength prediction in the existing technology, and achieves high-accuracy prediction and intelligent control, reducing the R&D cycle.

CN118942591APending Publication Date: 2024-11-12SHOUGANG JINGTANG IRON & STEEL CO LTD
View PDF 0 Cites 4 Cited by

Patent Information

Application Number
CN202411035961.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-31
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The existing technology is difficult to effectively predict the yield strength of cold-rolled metal sheets, which leads to material engineers facing the problems of professional complexity and long cycles in calculation and process design, and the initial experiment has a large deviation and lacks appropriate prediction methods.

Method used

The yield intensity prediction model of cold-rolled metal sheets is constructed using deep neuron network structure. By obtaining multi-source data for preprocessing and feature extraction, using FCNN neuron network for training, the yield intensity prediction model is obtained, and the model parameters are adjusted through optimization algorithm. Until the preset accuracy is reached.

Benefits of technology

It improves the accuracy of yield strength prediction, reduces errors caused by human limitations, shortens the R&D cycle, and realizes accurate prediction of yield strength and intelligent control of the impact factors throughout the process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118942591A_ABST
    Figure CN118942591A_ABST
Patent Text Reader

Abstract

The invention discloses a cold-rolled sheet metal yield strength prediction model construction method and related equipment, and relates to the technical field of full-process processing and product development of cold-rolled sheet metal, and the method comprises the following steps: obtaining a data source file and cold-rolled sheet metal yield strength characteristics, the data source file comprises laboratory measurement data and full-process measurement data, and the full-process measurement data comprises chemical components, temperature and ductility; constructing a deep neural network structure according to the yield strength characteristic of the cold-rolled metal plate, wherein the neural network structure is an FCNN neural network structure; training a neural network model according to the deep neural network structure to obtain a yield strength prediction model; and obtaining a prediction result according to the data source file and the yield strength prediction model.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of full-process processing and product development of cold-rolled metal sheets, and in particular to a method for constructing a yield strength prediction model for cold-rolled metal sheets and related equipment. Background Art

[0002] At present, the yield strength of cold-rolled metal sheets refers to the strength value corresponding to when the non-proportional extension (mainly the plastic deformation part) of the metal material reaches 0.2% during the stretching process, that is, the yield limit when the metal material yields. Its specific value will vary depending on factors such as the composition of the material, processing method, and processing technology. Therefore, building a model to predict it involves the influence of the chemical composition of metal materials on the mechanical properties, as well as the influence of processes such as hot rolling, cold rolling, and annealing on the performance of metal sheets.

[0003] However, this part of the work is done by professional material engineers to perform calculations and process design, and arrange experiments according to the estimated range, and adjust the composition and process according to the experimental results. But this process is extremely professional and complicated, limited by the professional ability of material engineers, the cycle is too long, and generally the initial experimental deviation is large. At present, there is no appropriate method to solve the above problems. Therefore, it is necessary to propose a method for constructing a yield strength prediction model for cold-rolled metal sheets to at least solve some of the above problems. Summary of the invention

[0004] A series of simplified concepts are introduced in the Summary of the Invention section, which will be further described in detail in the Detailed Description of the Invention section. The Summary of the Invention section of this application does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0005] In a first aspect, an embodiment of the present application provides a method for constructing a yield strength prediction model for a cold-rolled metal sheet, the method comprising: obtaining a data source file and a yield strength characteristic of the cold-rolled metal sheet, the data source file comprising laboratory measurement data and full-process measurement data, the full-process measurement data comprising chemical composition, temperature and elongation;

[0006] Constructing a deep neural network structure according to the yield strength characteristics of the cold-rolled metal sheet, wherein the neural network structure is a FCNN neural network structure;

[0007] Training the neural network model according to the deep neural network structure to obtain a yield strength prediction model;

[0008] A prediction result is obtained according to the data source file and the yield strength prediction model.

[0009] In one embodiment of the present invention, the step of training a neural network model according to the deep neural network structure to obtain a yield strength prediction model includes:

[0010] Acquire multi-source data, wherein the multi-source data includes full-process process data;

[0011] Preprocessing the multi-source data to obtain data features;

[0012] The data features are input into the deep neural network structure, and the neural network model is trained to obtain a yield strength prediction model.

[0013] In one embodiment of the present invention, the step of preprocessing the multi-source data to obtain data features includes:

[0014] Aggregating and analyzing the multi-source data to obtain aggregated data;

[0015] Optimizing the aggregated data according to an optimization algorithm to obtain optimized model parameters; the optimization algorithm includes a back propagation algorithm, a machine gradient descent algorithm, and Adam;

[0016] Feature extraction is performed on the optimization model parameters to obtain data features.

[0017] In one embodiment of the present invention, the steps after obtaining the prediction result according to the data source file and the yield strength prediction model include:

[0018] Evaluating the yield strength prediction model to obtain an evaluation result;

[0019] The yield strength prediction model is optimized according to the evaluation results.

[0020] In one embodiment of the present invention, the step of evaluating the yield strength prediction model to obtain an evaluation result includes:

[0021] Obtain actual rolling force value;

[0022] Calculating the predicted result and the actual rolling force value to obtain a deviation value;

[0023] If the deviation value is within the preset range, the evaluation result is that the model is accurate;

[0024] If the deviation value is outside the preset range, the evaluation result is that there is an error in the model.

[0025] In one embodiment of the present invention, the step of optimizing the yield strength prediction model according to the evaluation result includes:

[0026] When the evaluation result shows that the model is accurate, outputting the yield strength prediction model;

[0027] When the evaluation result is that the model has errors, a category with low precision is obtained, and the latest source data of the category is acquired, and the neural network model is trained according to the latest source data until the evaluation result is that the model is accurate.

[0028] In one embodiment of the present invention, the prediction result is stored in a database.

[0029] In a second aspect, the present application proposes a system for constructing a yield strength prediction model for cold-rolled metal sheets, the system comprising: a data acquisition module, a model construction module and a model training module;

[0030] The data acquisition module is configured to: acquire a data source file and yield strength characteristics of a cold-rolled metal sheet;

[0031] The model building module is configured to: construct a deep neural network structure according to the yield strength characteristics of the cold-rolled metal sheet;

[0032] The model training module is configured to: train the neural network model according to the deep neural network structure to obtain a yield strength prediction model; and obtain a prediction result according to the data source file and the yield strength prediction model.

[0033] In a third aspect, an electronic device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is used to implement the steps of a method for constructing a yield strength prediction model for cold-rolled metal sheets as described in any one of the first aspects above when executing the computer program stored in the memory.

[0034] In a fourth aspect, the present application further proposes a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for constructing a yield strength prediction model for cold-rolled metal sheets according to any one of the first aspects.

[0035] In summary, a method for constructing a yield strength prediction model for low cold-rolled metal sheets in an embodiment of the present application includes: obtaining a data source file and yield strength characteristics of cold-rolled metal sheets, the data source file includes laboratory measurement data and full-process measurement data, the full-process measurement data includes chemical composition, temperature and elongation; constructing a deep neural network structure according to the yield strength characteristics of cold-rolled metal sheets, the neural network structure is a CNN neural network structure; training the neural network model according to the deep neural network structure to obtain a yield strength prediction model; and obtaining a prediction result according to the data source file and the yield strength prediction model. Through data processing technology, the multi-source data of the entire process is integrated, cleaned and feature engineering is extracted, and the neural network structure is selected to conduct comprehensive analysis and modeling of the feature quantities, which can greatly improve the accuracy of the prediction, reduce errors caused by human limitations, and reduce the research and development cycle.

[0036] The method for constructing a yield strength prediction model for cold-rolled metal sheets proposed in this application, and other advantages, objectives and features of this application will be partially reflected through the following description, and will also be partially understood by technical personnel in this field through research and practice of this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0038] Figure 1 A schematic diagram of a process for constructing a cold-rolled metal sheet yield strength prediction model provided in an embodiment of the present application;

[0039] Figure 2 A deep neural network structure diagram in a method for constructing a cold-rolled metal sheet yield strength prediction model is proposed for this application;

[0040] Figure 3 A schematic diagram of a cold-rolled metal sheet yield strength prediction model construction system provided in an embodiment of the present application;

[0041] Figure 4 A schematic diagram of the electronic device structure of a method for constructing a cold-rolled metal sheet yield strength prediction model provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] 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.

[0043] In this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or equipment. In the absence of more restrictions, the elements limited by the statement "comprise one..." do not exclude the existence of other identical elements in the process, method, article or equipment including the elements. The term "more than two" includes two or more than two situations.

[0044] See also Figure 1 , is a schematic diagram of a process of constructing a cold-rolled metal sheet yield strength prediction model provided in an embodiment of the present application, which may specifically include:

[0045] S110, obtaining a data source file and yield strength characteristics of a cold-rolled metal sheet, wherein the data source file includes laboratory measurement data and full-process measurement data, wherein the full-process measurement data includes chemical composition, temperature, and elongation;

[0046] Exemplarily, the yield strength characteristics of cold-rolled metal sheets are obtained, which are the physical characteristics and data features of the metal sheet to be tested, including tensile strength and yield strength. At the same time, the data source file is obtained, which includes laboratory measurement data and full-process measurement data, and the full-process measurement data specifically includes chemical composition, temperature and elongation. The chemical composition specifically includes carbon C, silicon Si, manganese Mn, phosphorus P, sulfur S, copper Cu, nickel Ni, chromium Cr, arsenic As, and tin Sn.

[0047] S120, constructing a deep neural network structure according to the yield strength characteristics of the cold-rolled metal sheet, wherein the neural network structure is a FCNN neural network structure;

[0048] For example, Figure 2As shown, this is a deep neural network structure diagram in a method for constructing a cold-rolled metal sheet yield strength prediction model proposed in this application. The obtained yield strength characteristics of the cold-rolled metal sheet are substituted into the neural network, and the intrinsic laws and characteristics of the data are learned to obtain a deep neural network structure, wherein the deep neural network structure is an FCNN neural network structure, and a fully connected neural network (Fully Connected Neural Network, FCNN) can provide better fitting capabilities.

[0049] S130, training a neural network model according to the deep neural network structure to obtain a yield strength prediction model;

[0050] Exemplarily, the FCNN neural network structure trains the neural network model to obtain a yield strength prediction model, and the obtained yield strength prediction model can adapt to changes in different process conditions and product requirements, thereby maintaining its good prediction performance.

[0051] S140. Obtain a prediction result according to the data source file and the yield strength prediction model.

[0052] Exemplarily, the feature set in the data source file is extracted to obtain source data feature quantities, and the source data feature quantities are introduced into the yield strength prediction model to obtain prediction results, wherein the prediction results include the yield strength of the product corresponding to the component and process, and the results of analyzing the influence of each feature.

[0053] In summary, the method for constructing a yield strength prediction model for cold-rolled metal plates proposed in the embodiment of the present application integrates, cleans and extracts feature engineering from multi-source data throughout the entire process through data processing technology, and selects a neural network structure to conduct comprehensive analysis and modeling of feature quantities, which can greatly improve the accuracy of predictions, reduce errors caused by human limitations, and shorten the R&D cycle.

[0054] In some examples, the step of training the neural network model according to the deep neural network structure to obtain the yield strength prediction model includes:

[0055] Acquire multi-source data, wherein the multi-source data includes full-process process data;

[0056] Preprocessing the multi-source data to obtain data features;

[0057] The data features are input into the deep neural network structure, and the neural network model is trained to obtain a yield strength prediction model.

[0058] Exemplarily, multi-source data is obtained, wherein the multi-source data is full-process process data, the multi-source data is preprocessed to extract data features of the multi-source data, and the data features are input into a deep neural network structure to train the neural network model, thereby obtaining a yield strength prediction model.

[0059] In some examples, the step of preprocessing the multi-source data to obtain data features includes:

[0060] Aggregating and analyzing the multi-source data to obtain aggregated data;

[0061] Optimizing the aggregated data according to an optimization algorithm to obtain optimized model parameters; the optimization algorithm includes a back propagation algorithm, a machine gradient descent algorithm, and Adam;

[0062] Feature extraction is performed on the optimization model parameters to obtain data features.

[0063] Exemplarily, when preprocessing multi-source data, it is necessary to aggregate the multi-source data, analyze the results of the multi-source data aggregation to obtain aggregated data, and then use an optimization algorithm to optimize the aggregated data to obtain optimized model parameters, wherein the optimization algorithm includes a back propagation algorithm, a machine gradient descent (SGD) algorithm, and an Adam optimization algorithm (Adaptive Moment Estimation), etc., and adjust according to actual conditions. Feature extraction is performed on the obtained optimized model parameters to obtain the required data features.

[0064] In some examples, the steps after obtaining the prediction result according to the data source file and the yield strength prediction model include:

[0065] Evaluating the yield strength prediction model to obtain an evaluation result;

[0066] The yield strength prediction model is optimized according to the evaluation results.

[0067] Exemplarily, after the training is completed, the yield strength prediction model needs to be evaluated to obtain the evaluation results. The evaluation process specifically evaluates the loss function value, prediction accuracy, stability and other indicators of the yield strength prediction model training process. In order to prevent overfitting and improve the generalization ability of the yield strength prediction model, some regularization techniques such as L1 regularization and L2 regularization can be used, and the yield strength prediction model can be optimized according to the evaluation results. The specific optimization steps include adjusting the network structure and increasing the training data.

[0068] In some examples, the step of evaluating the yield strength prediction model to obtain an evaluation result includes:

[0069] Obtain actual rolling force value;

[0070] Calculating the predicted result and the actual rolling force value to obtain a deviation value;

[0071] If the deviation value is within the preset range, the evaluation result is that the model is accurate;

[0072] If the deviation value is outside the preset range, the evaluation result is that there is an error in the model.

[0073] Exemplarily, the actual rolling force value is obtained. The actual rolling force value can be directly obtained through the corresponding measuring equipment during the metal rolling process. The predicted result and the actual rolling force value are calculated to obtain the deviation value, which is used to evaluate the prediction accuracy and stability of the yield strength prediction model. If the deviation value is within the preset range, it proves that the yield strength prediction model is relatively accurate, so the evaluation result at this time is that the model is accurate, wherein the range of the deviation value is between plus and minus 3. If the deviation value is outside the preset range, it proves that the yield strength prediction model has errors, so the evaluation result at this time is that the model has errors.

[0074] In some examples, the step of optimizing the yield strength prediction model according to the evaluation result includes:

[0075] When the evaluation result shows that the model is accurate, outputting the yield strength prediction model;

[0076] When the evaluation result is that the model has errors, a category with low precision is obtained, and the latest source data of the category is acquired, and the neural network model is trained according to the latest source data until the evaluation result is that the model is accurate.

[0077] For example, if the evaluation result at this time is that the model is accurate, then the yield strength prediction model will be output and put into use. If the evaluation result at this time is that the model has errors, then the directional acquisition data enters incremental self-learning to improve the adaptability and accuracy of the model. Specifically, analyze the category that causes low accuracy, apply for the latest source data of the category, and retrain the neural network model based on the latest source data until the evaluation result is that the model is accurate.

[0078] In some examples, the prediction results are stored in a database.

[0079] Exemplarily, the prediction results are stored in the database by storing the chemical composition and process parameter information issued by the previous process, and checking whether the yield strength of the product has been stored. If the yield strength of the product has not been stored, the corresponding source data feature quantity is retrieved, the yield strength predicted by the yield strength prediction model is called, and stored. If the yield strength of the product has been stored, the stored yield strength is directly read.

[0080] In summary, this application achieves accurate estimation of yield strength and intelligent control of factors affecting the entire process by constructing a yield strength prediction model for cold-rolled metal sheets. The yield strength prediction model has powerful learning and analysis capabilities, and can adaptively adapt to changes in product characteristics and process requirements. At the same time, the yield strength prediction model also has the ability of incremental self-learning, and can continuously optimize and improve itself to adapt to more complex and diverse production needs in the future. It provides a comprehensive solution for the prediction of yield strength of cold-rolled metal sheets.

[0081] Improve the intelligent prediction and monitoring analysis capabilities of the impact of the entire process of metal sheet processing on the yield strength of the finished product. Provide strong support for engineers to accurately select components suitable for specific application requirements to avoid insufficient or excessive strength of the finished product, thereby optimizing product performance and cost. Optimize the manufacturing process - by predicting the impact of different processes, optimize the process, reduce scrap rate, reduce R&D costs, and shorten product time to market. Help enterprises achieve refined and intelligent production management and improve their core competitiveness.

[0082] like Figure 3 As shown, a control system for zinc piling of low-melting-point coating resistance spot welding welds is proposed in this application, and the system includes: a data acquisition module 21, a model building module 22 and a model training module 23;

[0083] The data acquisition module 21 is configured to: acquire a data source file and yield strength characteristics of a cold-rolled metal sheet;

[0084] The model building module 22 is configured to: construct a deep neural network structure according to the yield strength characteristics of the cold-rolled metal sheet;

[0085] The model training module 23 is configured to: train the neural network model according to the deep neural network structure to obtain a yield strength prediction model; and obtain a prediction result according to the data source file and the yield strength prediction model.

[0086] The effects of the above-mentioned system when applying the above-mentioned method can be found in the description of the above-mentioned method embodiment, which will not be repeated here.

[0087] like Figure 4As shown, an embodiment of the present application also provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, the steps of any of the above-mentioned tire position self-learning methods are implemented.

[0088] Since the electronic device introduced in this embodiment is a device used to implement a degradation trend prediction device for a weighing sensor of a weighing instrument in the embodiment of the present application, based on the method introduced in the embodiment of the present application, technical personnel in this field can understand the specific implementation mode of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the equipment used by technical personnel in this field to implement the method in the embodiment of the present application is within the scope of protection of this application.

[0089] In the specific implementation process, when the computer program 311 is executed by the processor, it can achieve Figure 1 Any implementation manner in the corresponding embodiments.

[0090] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0091] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-readable program code.

[0092] 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 generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0093] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0094] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0095] An embodiment of the present application also 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 LDPC decoding method of the solid-state hard disk controller.

[0096] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the 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 devices. 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 a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. 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 a data center that includes one or more available media integration. 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)), etc.

[0097] Those skilled in the art can 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.

[0098] In the several embodiments provided in the present 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 only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, 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 interfaces, devices or units, which can be electrical, mechanical or other forms.

[0099] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0100] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0101] 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 to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0102] 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.

[0103] 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 concept. 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.

[0104] Obviously, those skilled in the art can make various changes and modifications to this specification without departing from the spirit and scope of this specification. Thus, if these modifications and variations of this specification fall within the scope of the claims of this specification and their equivalents, this specification is also intended to include these modifications and variations.

Claims

1. A method for constructing a yield strength prediction model for cold-rolled metal sheets, characterized in that: The method comprises: Obtaining a data source file and yield strength characteristics of a cold-rolled metal sheet, wherein the data source file includes laboratory measurement data and full-process measurement data, wherein the full-process measurement data includes chemical composition, temperature, and elongation; Constructing a deep neural network structure according to the yield strength characteristics of the cold-rolled metal sheet, wherein the neural network structure is a FCNN neural network structure; Training the neural network model according to the deep neural network structure to obtain a yield strength prediction model; A prediction result is obtained according to the data source file and the yield strength prediction model.

2. The method for constructing a yield strength prediction model for cold-rolled metal sheets according to claim 1, characterized in that: The steps of training the neural network model according to the deep neural network structure to obtain the yield strength prediction model include: Acquire multi-source data, wherein the multi-source data includes full-process process data; Preprocessing the multi-source data to obtain data features; The data features are input into the deep neural network structure, and the neural network model is trained to obtain a yield strength prediction model.

3. The method for constructing a yield strength prediction model for cold-rolled metal sheets according to claim 2, characterized in that: The step of preprocessing the multi-source data to obtain data features includes: Aggregating and analyzing the multi-source data to obtain aggregated data; Optimizing the aggregated data according to an optimization algorithm to obtain optimized model parameters; the optimization algorithm includes a back propagation algorithm, a machine gradient descent algorithm, and Adam; Feature extraction is performed on the optimization model parameters to obtain data features.

4. The method for constructing a yield strength prediction model for cold-rolled metal sheets according to claim 1, characterized in that: The steps after obtaining the prediction result according to the data source file and the yield strength prediction model include: Evaluating the yield strength prediction model to obtain an evaluation result; The yield strength prediction model is optimized according to the evaluation results.

5. The method for constructing a yield strength prediction model for cold-rolled metal sheets according to claim 4, characterized in that: The step of evaluating the yield strength prediction model to obtain an evaluation result includes: Obtain actual rolling force value; Calculating the predicted result and the actual rolling force value to obtain a deviation value; If the deviation value is within the preset range, the evaluation result is that the model is accurate; If the deviation value is outside the preset range, the evaluation result is that there is an error in the model.

6. The method for constructing a yield strength prediction model for cold-rolled metal sheets according to claim 4, characterized in that: The step of optimizing the yield strength prediction model according to the evaluation result comprises: When the evaluation result shows that the model is accurate, outputting the yield strength prediction model; When the evaluation result is that the model has errors, a category with low precision is obtained, and the latest source data of the category is acquired, and the neural network model is trained according to the latest source data until the evaluation result is that the model is accurate.

7. The method for constructing a yield strength prediction model for cold-rolled metal sheets according to claim 1, characterized in that: The prediction results are stored in a database.

8. A system for constructing a yield strength prediction model for cold-rolled metal sheets, characterized in that: The system comprises: a data acquisition module, a model building module and a model training module; The data acquisition module is configured to: acquire a data source file and yield strength characteristics of a cold-rolled metal sheet; The model building module is configured to: construct a deep neural network structure according to the yield strength characteristics of the cold-rolled metal sheet; The model training module is configured to: train the neural network model according to the deep neural network structure to obtain a yield strength prediction model; and obtain a prediction result according to the data source file and the yield strength prediction model.

9. An electronic device, comprising: A memory and a processor, wherein the processor is used to implement the steps of a method for constructing a yield strength prediction model for cold-rolled metal sheets as described in any one of claims 1 to 7 when executing a computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for constructing a yield strength prediction model for cold-rolled metal sheets as described in any one of claims 1 to 7 are implemented.

Citation Information

Cited By

  • Cold-rolled dual-phase steel automobile sheet mechanical property prediction method and related equipment

    CN119763682A

  • Aircraft landing gear outer cylinder yield strength prediction method based on physical information deep neural network

    CN120217850A

  • Method for predicting yield strength of aircraft landing gear outer tube based on physical information deep neural network

    CN120217850B

  • Modeling method for yield strength of super martensitic stainless steel

    CN122528395A