Cast steel smelting management control system

Abstract

The invention relates to a cast steel smelting management control system. The system comprises a prenatal inspection module used for configuring inspection content according to collected equipment data information; the ingredient calculation module is used for configuring an ingredient list according to the collected product data information; the data acquisition analysis optimization module is used for judging whether data in the smelting process are qualified or not and giving suggestions; the statistical analysis module is used for generating reports and reports; the AI assistant processes various data types through a multi-modal deep learning model, is integrated with the prenatal examination module, the ingredient calculation module, the data acquisition analysis optimization module and the statistical analysis module, is in butt joint with all the modules and existing infrastructures through service deployment and interface design, and provides real-time guidance and analysis reports through a human-computer interaction interface; the AI assistant is used for assisting in prenatal inspection, ingredient calculation, data acquisition analysis optimization and statistical analysis, intelligent management and optimization regulation and control are carried out on the smelting process in combination with the process requirements of the cast steel smelting process, and the quality and efficiency improvement problem is solved.

Description

Technical Field

[0001] The invention relates to the technical field of cast steel smelting, and in particular to a cast steel smelting management and control system. Background Art

[0002] The process flow of cast steel smelting is complex. In order to ensure the quality of the final product, process data needs to be continuously collected during the smelting process. In traditional cast steel smelting operations, the production process mainly relies on the experience of technicians for operation and judgment, lacks intelligent precision control, and product quality is easily affected by the technicians' experience level and working status fluctuations, resulting in the difficulty in ensuring the consistency and reliability of castings, and the production process has high energy consumption. Summary of the invention

[0003] Based on this, it is necessary to provide a cast steel smelting management and control system that can perform precise control, automatic optimization, and efficient operation in order to address the problem of lack of intelligent precise control of the cast steel smelting process.

[0004] A cast steel smelting management and control system provided by the present invention comprises:

[0005] Prenatal examination module: used to configure inspection content and fault analysis based on the collected equipment data information;

[0006] Ingredient calculation module: used to calculate ingredients based on the collected product data information and generate an ingredient list;

[0007] Data acquisition, analysis and optimization module: used to collect process data, determine whether the smelting process data is qualified and give suggestions;

[0008] Statistical analysis module: used to generate reports and statements;

[0009] AI assistant: The AI ​​assistant processes multiple data types through a multimodal deep learning model, and is integrated with the prenatal examination module, the batching calculation module, the data acquisition and analysis optimization module, and the statistical analysis module. It connects with each module and the existing infrastructure through service-oriented deployment and interface design, and provides real-time guidance and analysis reports through a human-computer interaction interface. The AI ​​assistant is used to assist in prenatal examinations, batching calculations, data acquisition and analysis optimization, and statistical analysis, and combines the process requirements of the cast steel smelting process to intelligently manage and optimize the smelting process.

[0010] In one embodiment, the prenatal examination module includes collecting data information related to equipment inspection through an AI assistant, using machine learning and deep learning models to analyze data information to find equipment anomalies and predict health conditions, configuring key inspection content based on analysis results and clarifying the inspection process through a flowchart, assisting inspection personnel in on-site inspections, diagnosing faults when they are found, and taking measures to resolve the faults.

[0011] In one embodiment, the ingredient calculation module includes obtaining data information of the current product of the system, preprocessing the collected product data information, obtaining product process parameter information, material information and line-side library information as model input, inputting the data of the smelting process into the model for real-time analysis and calculation and global optimization, and outputting the ingredient list.

[0012] In one embodiment, the data acquisition and analysis optimization module includes real-time acquisition of various data in the smelting process, preprocessing the collected raw data, extracting characteristic parameters that have a greater impact on the smelting process from the preprocessed data, and inputting the data of the current smelting process into a trained model for real-time analysis. The model evaluates whether the input data is qualified and outputs recommendations based on the input data.

[0013] In one embodiment, the AI ​​assistant includes: data processing, model design, training implementation, evaluation and verification, and deployment integration; data processing is used to collect, integrate, and pre-process multimodal smelting data, including real-time monitoring images and videos of smelting equipment, equipment maintenance, record materials of fault handling processes, and historical smelting data, and multimodal fusion of data to form training samples suitable for model training; model design builds a network architecture that can simultaneously process multiple data types through a multimodal deep learning model, and combines feature extraction, joint training, and multi-task learning mechanisms to enable the model to extract complementary information from different modal data; training implementation divides the data and sets learning goals including equipment fault prediction, parameter optimization suggestions, and ingredient calculation, uses optimization algorithms and performs iterative training to verify model performance; evaluation and verification evaluates model performance by using comprehensive indicators, compares the differences between AI assistant assistance and traditional methods, and evaluates the actual effects in improving production efficiency and reducing costs; deployment integration ensures that each module of the system can call the AI ​​assistant by deploying the trained model to a cloud platform or a local server, and enables operators to obtain guidance suggestions, view analysis reports, and reports through a human-computer interaction interface.

[0014] The above-mentioned cast steel smelting management and control system constructs a cast steel smelting management and control system that integrates an AI assistant, a prenatal inspection module, a batching calculation module, a digital analysis and optimization module, and a statistical analysis module. Through the integration of the AI ​​assistant, it is possible to achieve precise control of the smelting process, realize prenatal inspection, batching calculation, and automatic analysis and optimization of smelting parameters, and efficiently guide actual production operations, thereby achieving the goal of improving production efficiency and casting quality. Among them, the AI ​​assistant is based on a multimodal deep learning model, which can process multiple data types such as text, images, and videos, and combined with the process requirements of the cast steel smelting process, through an intuitive human-computer interaction interface, the batching calculation results are displayed in the form of reports and statements, or the real-time analysis results are displayed in the form of text and charts, so that operators can easily understand and apply the information provided, enhance the ease of use and operating efficiency of the system, and realize the intelligent management and optimization of the smelting process. By combining artificial intelligence technology with smelting technology, the problems of low efficiency, high energy consumption, and difficult skill inheritance in the traditional smelting process are solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the overall process of the cast steel smelting management and control system in one embodiment;

[0016] Figure 2 It is a schematic diagram of a pre-production inspection module of a cast steel smelting management and control system in one embodiment;

[0017] Figure 3 Schematic diagram of a batching calculation module of a cast steel smelting management and control system in one embodiment;

[0018] Figure 4 Schematic diagram of the analysis and optimization module of the cast steel smelting management and control system in one embodiment. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present invention, so the present invention is not limited by the specific embodiments disclosed below.

[0020] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0021] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0022] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0023] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0024] It should be noted that when an element is referred to as being "fixed to" or "disposed on" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "upper", "lower", "left", "right" and similar expressions used herein are for illustrative purposes only and are not intended to be the only implementation method.

[0025] See also Figures 1 to 4 , a cast steel smelting management and control system provided by one embodiment of the present invention comprises:

[0026] Prenatal examination module: used to configure inspection content and fault analysis based on the collected equipment data information;

[0027] Ingredient calculation module: used to calculate ingredients based on the collected product data information and generate an ingredient list;

[0028] Data acquisition, analysis and optimization module: used to collect process data, determine whether the smelting process data is qualified and give suggestions;

[0029] Statistical analysis module: used to generate reports and statements;

[0030] AI assistant: The AI ​​assistant processes multiple data types through a multimodal deep learning model, and is integrated with the prenatal examination module, the batching calculation module, the data acquisition and analysis optimization module, and the statistical analysis module. It connects with each module and the existing infrastructure through service-oriented deployment and interface design, and provides real-time guidance and analysis reports through a human-computer interaction interface. The AI ​​assistant is used to assist in prenatal examinations, batching calculations, data acquisition and analysis optimization, and statistical analysis, and combines the process requirements of the cast steel smelting process to intelligently manage and optimize the smelting process.

[0031] The above-mentioned cast steel smelting management and control system constructs a cast steel smelting management and control system that integrates an AI assistant, a prenatal inspection module, a batching calculation module, a digital analysis and optimization module, and a statistical analysis module. Through the integration of the AI ​​assistant, it is possible to achieve precise control of the smelting process, realize prenatal inspection, batching calculation, and automatic analysis and optimization of smelting parameters, and efficiently guide actual production operations, thereby achieving the goal of improving production efficiency and casting quality. Among them, the AI ​​assistant is based on a multimodal deep learning model, which can process multiple data types such as text, images, and videos, and combined with the process requirements of the cast steel smelting process, through an intuitive human-computer interaction interface, the batching calculation results are displayed in the form of reports and statements, or the real-time analysis results are displayed in the form of text and charts, so that operators can easily understand and apply the information provided, enhance the ease of use and operating efficiency of the system, and realize the intelligent management and optimization of the smelting process. By combining artificial intelligence technology with smelting technology, the problems of low efficiency, high energy consumption, and difficult skill inheritance in the traditional smelting process are solved.

[0032] In one embodiment, the functional modules of the AI ​​assistant include: data processing, model design, training implementation, evaluation verification, and deployment integration; data processing is used to collect, integrate, and pre-process multimodal smelting data, including real-time monitoring images and videos of smelting equipment, equipment maintenance, record materials of fault handling processes, and historical smelting data, and multimodally fuse the data to form training samples suitable for model training; the model design module builds a network architecture that can simultaneously process multiple data types through a multimodal deep learning model, combined with feature extraction, including extracting high-level semantic features through pre-trained feature extractors such as ResNet or Transformer, and designing a multimodal joint training mechanism, so that the model can learn complementary information from different modalities and improve the overall prediction and decision-making capabilities of the model; training implementation divides the data set into training set, verification set, and test set through data partitioning, and sets learning goals including equipment failure prediction, parameter optimization suggestions, and ingredient calculation. Use optimization algorithms and perform iterative training to verify model performance, including selecting optimizers (such as AdamW, Adaptive Moment Estimation with Weight Decay, optimization algorithms for deep learning) and learning rate strategies, applying regularization techniques (such as L1 / L2 regularization) to avoid overfitting, and performing multiple rounds of iterative training. Regularly verify model performance, and adjust hyperparameters such as learning rate and batch size based on the verification results. Evaluation and verification evaluates model performance by using comprehensive indicators, including accuracy, recall, and customized indicators for specific tasks, comparing the differences between AI assistant assistance and traditional methods, and evaluating the actual effects in improving production efficiency and reducing costs. Deployment and integration ensures that each module of the system can call the AI ​​assistant by deploying the trained model to the cloud platform or local server, and enables operators to obtain guidance and suggestions, view analysis reports, and statements through the human-computer interaction interface.

[0033] Optionally, the AI ​​assistant is based on the Qwen2-7B-Instruct multimodal model and designs a network structure, which can simultaneously process multimodal inputs such as text, images, and videos, and improve the system's understanding and response capabilities to complex smelting scenarios. It can be understood that the AI ​​assistant is an artificial intelligence assistant.

[0034] Optionally, deploy the trained model to a cloud platform or local server, and design a RESTful API (Representational State Transfer Application Programming Interface) to ensure that other system modules can easily call the AI ​​assistant's services.

[0035] like Figure 1 and Figure 2As shown, in one of the embodiments, the prenatal examination module includes collecting data information related to equipment inspection through an AI assistant, including equipment operation logs, sensor data, and information input by users; using machine learning and deep learning models to analyze data information to find equipment anomalies and predict equipment health status; configuring key inspection content based on data analysis results, including inspection items for key equipment and equipment in poor health, and clarifying the inspection process through a flowchart; assisting inspection personnel in on-site inspections, using existing knowledge bases and diagnostic algorithms to perform fault diagnosis, including system log analysis, error information interpretation, application of elimination methods, etc., and giving suggestions. Inspection personnel take measures to resolve the fault based on the suggestions of the AI ​​assistant and the on-site situation, including adjusting equipment parameters, replacing parts, etc.

[0036] Optionally, when performing inspections, inspectors can perform on-site inspections, take photos, and record videos of equipment according to the guidance of the AI ​​assistant, and improve inspection efficiency and accuracy through real-time data monitoring and intelligent recognition by the AI ​​assistant. At the same time, the AI ​​assistant will send warning information to relevant equipment administrators for equipment with potential risks.

[0037] like Figure 1 and Figure 3 As shown, in one of the embodiments, the ingredient calculation module includes obtaining data information of the current product of the system by extraction or manual push, including key information such as the product code and material brand of the current product; preprocessing the collected product data information, obtaining product process parameter information, material information and line-side library information as input of the AI ​​model, and inputting the data of the current smelting process into the trained AI model for real-time analysis and calculation. The model will use a trained optimization algorithm, such as a genetic algorithm, to perform global optimization based on the input data, calculate and output the ingredient list; the AI ​​assistant will display the analysis results in the form of a table to display the ingredient list. The operator can retain the calculation results of this time, or call up the historical calculation results of the same material through instructions for comparison, so as to obtain the optimal solution.

[0038] Furthermore, if Figure 1 and Figure 4As shown, in one of the embodiments, the data acquisition and analysis optimization module includes real-time collection of various data in the smelting process, including real-time collection of various data in the smelting process, such as temperature, pressure, oxygen content, component content, etc., through sensors, spectrometers, thermal analyzers, etc., and passing them into the AI ​​model through the API interface; preprocessing the collected raw data, including removing abnormal data and duplicate data through data cleaning, data transformation and data dimension reduction, etc., for subsequent analysis and processing; extracting characteristic parameters that have a greater impact on the smelting process from the preprocessed data, including temperature change trends, component content ratios, etc., and these characteristic parameters will be used as inputs to the AI ​​model; inputting the data of the current smelting process into the trained model for real-time analysis, and the model will quickly evaluate whether it is qualified based on the input data and output rationalization suggestions; displaying the analysis results in text or in the form of charts through the AI ​​assistant to guide the operator to perform the next step.

[0039] Furthermore, if Figure 1 and Figure 4 As shown, after the pre-production inspection module is the EAF (Electric Arc Furnace) smelting process, the AI ​​assistant is used to assist in the batching calculation, and assists in the optimization and adjustment of the process data of the subsequent melting period, oxidation period, reduction period and steel-out steps, so as to achieve precise control and intelligent management, so as to improve the quality and production efficiency of the final product; optionally, when the EAF smelting is completed and it needs to be switched to LF (Ladle Furnace) smelting, the AI ​​assistant is used to assist in the optimization and adjustment of the process data of slag adjustment, composition adjustment, argon blowing and steel-out steps, so as to achieve precise control and intelligent management, so as to improve the quality and production efficiency of the final product; optionally, when the LF smelting is completed and it needs to be switched to VOD (Vacuum Oxygen Decarburization) smelting, the AI ​​assistant is used to assist in the optimization and adjustment of the process data of oxygen blowing, carbon deoxidation, reduction and steel-out steps, so as to achieve precise control and intelligent management, so as to improve the quality and production efficiency of the final product; after the smelting process is completed, the subsequent casting process is entered.

[0040] The above-mentioned cast steel smelting management and control system constructs a cast steel smelting management and control system that integrates an AI assistant, a prenatal inspection module, a batching calculation module, a digital analysis and optimization module, and a statistical analysis module. Through the integration of the AI ​​assistant, it is possible to achieve precise control of the smelting process, realize prenatal inspection, batching calculation, and automatic analysis and optimization of smelting parameters, and efficiently guide actual production operations, thereby achieving the goal of improving production efficiency and casting quality. Among them, the AI ​​assistant is based on a multimodal deep learning model, which can process multiple data types such as text, images, and videos, and combined with the process requirements of the cast steel smelting process, through an intuitive human-computer interaction interface, the batching calculation results are displayed in the form of reports and statements, or the real-time analysis results are displayed in the form of text and charts, so that operators can easily understand and apply the information provided, enhance the ease of use and operating efficiency of the system, and realize the intelligent management and optimization of the smelting process. By combining artificial intelligence technology with smelting technology, the problems of low efficiency, high energy consumption, and difficult skill inheritance in the traditional smelting process are solved.

[0041] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0042] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A cast steel smelting management and control system, characterized in that: The cast steel smelting management and control system comprises: Prenatal examination module: used to configure inspection content and fault analysis based on the collected equipment data information; Ingredient calculation module: used to calculate ingredients based on the collected product data information and generate an ingredient list; Data acquisition, analysis and optimization module: used to collect process data, determine whether the smelting process data is qualified and give suggestions; Statistical analysis module: used to generate reports and statements; AI assistant: The AI ​​assistant processes multiple data types through a multimodal deep learning model, and is integrated with the prenatal examination module, the batching calculation module, the data acquisition and analysis optimization module, and the statistical analysis module. It connects with each module and the existing infrastructure through service-oriented deployment and interface design, and provides real-time guidance and analysis reports through a human-computer interaction interface. The AI ​​assistant is used to assist in prenatal examinations, batching calculations, data acquisition and analysis optimization, and statistical analysis, and combines the process requirements of the cast steel smelting process to intelligently manage and optimize the smelting process.

2. The cast steel smelting management and control system according to claim 1, characterized in that: The prenatal examination module includes collecting data information related to equipment inspections through an AI assistant, using machine learning and deep learning models to analyze data information to find equipment anomalies and predict health conditions, configuring key inspection content based on analysis results and clarifying the inspection process through a flowchart, assisting inspection personnel in on-site inspections, diagnosing faults when they are found, and taking measures to resolve the faults.

3. The cast steel smelting management and control system according to claim 1, characterized in that: The ingredient calculation module includes obtaining data information of the current product of the system, preprocessing the collected product data information, obtaining product process parameter information, material information and line-side warehouse information as model input, inputting the data of the smelting process into the model for real-time analysis and calculation and global optimization, and outputting the ingredient list.

4. The cast steel smelting management and control system according to claim 1, characterized in that: The data acquisition and analysis optimization module includes real-time acquisition of various data in the smelting process, preprocessing of the collected raw data, extraction of characteristic parameters that have a greater impact on the smelting process from the preprocessed data, and input of the data of the current smelting process into a trained model for real-time analysis. The model evaluates whether the input data is qualified and outputs recommendations.

5. The cast steel smelting management and control system according to claim 1, characterized in that: The AI ​​assistant includes: data processing, model design, training implementation, evaluation and verification, and deployment integration; data processing is used to collect, integrate, and pre-process multimodal smelting data, including real-time monitoring images and videos of smelting equipment, equipment maintenance, record materials of fault handling processes, and historical smelting data, and multimodal fusion of data to form training samples suitable for model training; model design builds a network architecture that can simultaneously process multiple data types through a multimodal deep learning model, and combines feature extraction, joint training, and multi-task learning mechanisms to enable the model to extract complementary information from different modal data; training implementation divides data and sets learning goals including equipment fault prediction, parameter optimization suggestions, and ingredient calculation, uses optimization algorithms and performs iterative training to verify model performance; evaluation and verification evaluates model performance by using comprehensive indicators, compares the differences between AI assistant assistance and traditional methods, and evaluates the actual effects in improving production efficiency and reducing costs; deployment integration ensures that each module of the system can call the AI ​​assistant by deploying the trained model to a cloud platform or a local server, and enables operators to obtain guidance suggestions and view analysis reports and reports through a human-computer interaction interface.

Images