A risk management and control platform for digital twin technology of metallurgical furnaces
Through the risk control platform of metallurgical furnace kiln digital twin technology, real-time acquisition and analysis of furnace kiln data, risk classification and intelligent decision-making are solved, and the problem of traditional methods is difficult to cope with complex environments and potential risks is achieved, and the efficiency, safety and Sustainable operation.
Patent Information
- Application Number
- CN202410188838.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-02-20
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2044-02-20
AI Technical Summary
Metallurgical furnaces face various risks during operation, including safety hazards of man-machine objects, equipment failures, process deviations, material unevenness, pipeline pressure fluctuations, environmental pollution and energy consumption problems, resulting in production interruptions, cost increases and products. Quality declines, and traditional risk control methods are difficult to cope with complex and changing environments and potential risks.
The risk management and control platform adopts the metallurgical furnace and kiln digital twin technology, including data acquisition module, digital twin module, risk classification module, management and control decision-making module and execution module. By obtaining furnace operation data in real time, building a digital twin model, risk classification and intelligence Decision-making, generation of control instructions, and real-time risk control of furnaces.
It improves the safety and operating efficiency of the furnace, reduces the possibility of accidents, extends the service life of the equipment, reduces maintenance and production costs, improves product quality and production capacity, and significantly enhances the safety production capacity.
Smart Images

Figure CN117910808B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of metallurgical production safety technology, and in particular to a risk management and control platform for metallurgical furnace digital twin technology. Background Art
[0002] Furnaces are key equipment in the production process of the metallurgical industry. The main function of metallurgical furnaces is to heat treat materials to change their physical, chemical and mechanical properties. Furnaces are devices that change the physical, chemical and structural properties of raw materials through high-temperature treatment. The process has a direct impact on the quality and production capacity of the final product. Therefore, it is very important to ensure the safe, stable and efficient operation of the furnace.
[0003] Metallurgical furnaces face a variety of risks during operation, including safety hazards of "man, machine and object", equipment failure, process deviation, uneven materials, pressure fluctuations in pipe networks, environmental pollution and energy consumption. These risks may lead to production interruptions, increased costs, reduced product quality, and even serious accidents.
[0004] Digital twin technology is an emerging technology trend that simulates, analyzes and predicts the behavior of physical systems in a virtual environment by creating a virtual copy of the physical system (i.e., digital twin). This technology allows operators to test, optimize and troubleshoot furnaces without affecting actual production. With the development of sensor technology, data processing capabilities and simulation software, digital twin technology is becoming increasingly mature and has been applied in multiple industries.
[0005] With the advancement of industrial automation and the improvement of safety production requirements, accurate and real-time control of furnace risks has become an urgent need. Traditional risk control methods are often based on experience judgment or regular maintenance, which is difficult to cope with the complex and changing furnace environment and potential risks. Summary of the invention
[0006] 1. Purpose of the invention
[0007] The purpose of the present invention is to provide a risk management and control platform for metallurgical furnace digital twin technology that can improve the safety of metallurgical furnaces.
[0008] (II) Technical solution
[0009] In order to solve the above problems, the present invention provides a risk management and control platform for metallurgical furnace digital twin technology, including: a data acquisition module, a digital twin module, a risk classification module, a management and control decision module and an execution module;
[0010] The data acquisition module is used to obtain the operation data of the metallurgical furnace in real time, including temperature, pressure, speed, material status and equipment health status;
[0011] The digital twin module is connected to the data acquisition module, and is used to build a digital twin model of the kiln based on historical operation data, and receive the operation data collected by the data acquisition module to simulate the operation status of the kiln in real time;
[0012] The risk classification module is connected to the digital twin module and is used to perform real-time risk classification of the kiln according to the operating status of the digital twin model in combination with a preset risk classification model;
[0013] The control decision module is connected to the risk classification module and is used to generate control instructions based on the classified risks and in combination with the preset control strategies;
[0014] The execution module is connected to the management and control decision module, and is used to receive management and control instructions and control the kiln to execute corresponding risk management and control measures.
[0015] In another aspect of the present invention, preferably, the digital twin module includes a furnace layer, a digital twin model layer and a twin data layer;
[0016] The furnace layer includes a virtual entity model, and the virtual entity model includes a digital model of a physical entity of a metallurgical furnace;
[0017] The digital twin model layer includes digitizing the operation process of the kiln and integrating it into the virtual entity model to obtain a digital twin model;
[0018] The twin data layer processes and stores the collected operating data in the digital twin model to simulate the operating status of the furnace in real time.
[0019] In another aspect of the present invention, preferably, the real-time risk classification of the furnace according to the operating status of the digital twin model in combination with a preset risk classification model comprises:
[0020] Acquire data representing the operating status of the digital twin model;
[0021] Constructing a risk classification model, wherein the risk classification model includes a first classification model, a second classification model and a third classification model;
[0022] Using a preset first classification model, converting the data of the operating status into a table having rows and columns;
[0023] Using a preset second classification model, characteristic information of each row and each column of data in the table is obtained respectively;
[0024] The data of the operating status is classified by using a preset third classification model according to the acquired characteristic information and a plurality of preset risk categories.
[0025] In another aspect of the present invention, preferably, the converting the data of the operating status into a table having rows and columns by using a preset first classification model comprises:
[0026] Combining the data of the operating status by numbers;
[0027] Calculate the correlation coefficient between the data of the running status after the number combination;
[0028] According to the correlation, the data of the operating status are converted into a table having rows and columns.
[0029] In another aspect of the present invention, preferably, the calculating the correlation coefficient between the data of the operating status includes calculating the correlation coefficient using the following formula:
[0030] ;
[0031] Wherein, X represents the correlation coefficient, i and j represent the serial numbers of the data of the running status, and x i Indicates the running status data of number i, x j Indicates the running status data of number j, represents the average value of the running status data, n represents the total number, R (x i ) represents x i The rank, R(x j ) represents x j rank.
[0032] In another aspect of the present invention, preferably, the using a preset second classification model to obtain feature information of each row and each column of data in the table includes:
[0033] Performing maximum aggregation representation on each row and column of data in the table;
[0034] According to the maximum aggregate representation, using a preset activation function, obtaining feature information of each row and each column;
[0035] The feature information of each row and each column is fused using a preset fusion algorithm.
[0036] In another aspect of the present invention, preferably, performing maximum aggregate representation on each row and column of data in the table includes performing maximum aggregate representation using the following formula:
[0037] ;
[0038] Among them, h k represents the maximum aggregate representation of k rows, represents the maximum aggregation function, x k Represents all the data in k rows; ls represents the maximum aggregate representation of column s, y s Represents all the data in column s.
[0039] In another aspect of the present invention, preferably, according to the maximum aggregate representation, using a preset activation function, obtaining feature information of each row and each column includes obtaining feature information of each row and each column using the following formula;
[0040] ;
[0041] in, Represents the characteristic information of each row, Represents the characteristic information of each column, f relu represents the activation function, Q and is the model parameter.
[0042] In another aspect of the present invention, preferably, using a preset fusion algorithm to fuse the feature information of each row and each column includes fusing using the following formula:
[0043] ;
[0044] Among them, V conv represents the fused vector; represents the fusion operation, Represents the characteristic information of each row, Represents the characteristic information of each column.
[0045] In another aspect of the present invention, preferably, using a preset third classification model, classifying the data of the operating status according to the acquired characteristic information and a plurality of preset risk categories comprises:
[0046] ;
[0047] in, is the predicted probability, is the trainable weight matrix, t is the bias term, and Softmax represents the conv +t results are classified, and the softmax includes multiple preset risk categories.
[0048] (III) Beneficial effects
[0049] The above technical solution of the present invention has the following beneficial technical effects:
[0050] The data acquisition module of the present invention can obtain the key operating data of the kiln in real time, such as temperature, pressure, speed, etc., to ensure the immediate grasp of the kiln status, which is helpful to timely discover potential problems. The risk classification module uses the real-time simulation data of the digital twin model, combined with the preset risk classification model, to accurately classify the risks in the operation of the kiln; this classification helps to distinguish the severity and urgency of different risks, and provide strong support for subsequent management and control decisions. The management and control decision module can quickly generate targeted management and control instructions based on the risk classification results and the preset management and control strategies. This intelligent decision-making process reduces the delays and errors of human intervention and improves the efficiency and accuracy of risk management. After receiving the management and control instructions, the execution module can quickly control the kiln to execute the corresponding risk management and control measures. This ensures that risks are handled in a timely and effective manner and reduces the possibility of accidents.
[0051] Through simulation analysis of digital twin technology, the platform can not only manage current risks, but also predict possible problems in the future, thereby achieving preventive maintenance. This helps to extend the service life of equipment and improve the overall operating efficiency of the kiln. Effective risk management reduces the number of unexpected shutdowns and production interruptions, thereby reducing maintenance costs and production costs. At the same time, optimized kiln operation helps to improve production capacity and product quality. The platform significantly enhances the safe production capacity of the kiln through real-time monitoring and intelligent management and control. It ensures the efficient, safe and sustainable operation of the kiln. BRIEF DESCRIPTION OF THE DRAWINGS
[0052] Figure 1 It is a schematic diagram of the overall structure of an embodiment of the present invention. DETAILED DESCRIPTION
[0053] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, the description of well-known structures and technologies is omitted to avoid unnecessary confusion of the concept of the present invention.
[0054] Obviously, the described embodiments are only some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0055] In the description of the present invention, it should be noted that the terms “first”, “second” and “third” are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.
[0056] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.
[0057] Embodiment 1
[0058] A risk management and control platform for digital twin technology of metallurgical furnaces, characterized by comprising: a data acquisition module, a digital twin module, a risk classification module, a management and control decision module and an execution module;
[0059] The specific content of the data acquisition module is not limited here. Optionally, in this embodiment, the data acquisition module is used to obtain the operation data of the metallurgical furnace in real time, including temperature, pressure, speed, material status and equipment health status; the data acquisition module can obtain the key operation data of the furnace in real time, such as temperature, pressure, speed, etc., to ensure the real-time grasp of the furnace status, which is helpful to timely discover potential problems;
[0060] The specific content of the digital twin module is not limited here. Optionally, in this embodiment, the digital twin module is connected to the data acquisition module to build a digital twin model of the furnace according to historical operation data, and receive the operation data collected by the data acquisition module to simulate the operation status of the furnace in real time;
[0061] Further, in this embodiment, the digital twin module includes a furnace layer, a digital twin model layer and a twin data layer;
[0062] The furnace layer includes a virtual entity model, and the virtual entity model includes a digital model of a physical entity of a metallurgical furnace;
[0063] The digital twin model layer includes digitizing the operation process of the kiln and integrating it into the virtual entity model to obtain a digital twin model;
[0064] The twin data layer processes and stores the collected operation data into the digital twin model to simulate the operation status of the furnace in real time;
[0065] The risk classification module is connected to the digital twin module and is used to perform real-time risk classification of the kiln according to the operating status of the digital twin model in combination with a preset risk classification model;
[0066] The specific content of the risk classification module is not limited here. Optionally, in this embodiment, the real-time risk classification of the kiln according to the operating status of the digital twin model and the preset risk classification model includes:
[0067] Acquire data representing the operating status of the digital twin model;
[0068] Constructing a risk classification model, wherein the risk classification model includes a first classification model, a second classification model and a third classification model;
[0069] Using a preset first classification model, converting the data of the operating status into a table having rows and columns;
[0070] Using a preset second classification model, characteristic information of each row and each column of data in the table is obtained respectively;
[0071] The data of the operating status is classified by using a preset third classification model according to the acquired characteristic information and a plurality of preset risk categories.
[0072] The risk classification module uses the real-time simulation data of the digital twin model, combined with the preset risk classification model, to accurately classify the risks in furnace operation; this classification helps to distinguish the severity and urgency of different risks, providing strong support for subsequent management and control decisions.
[0073] Further, in this embodiment, the using of the preset first classification model to convert the data of the operating status into a table having rows and columns includes:
[0074] Combining the data of the operating status by numbers;
[0075] Calculate the correlation coefficient between the data of the running status after the number combination;
[0076] According to the correlation, the data of the operating status are converted into a table having rows and columns.
[0077] Further, in this embodiment, the calculating the correlation coefficient between the data of the operating status includes calculating the correlation coefficient using the following formula:
[0078] ;
[0079] Wherein, X represents the correlation coefficient, i and j represent the serial numbers of the data of the running status, and x i Indicates the running status data of number i, x j Indicates the running status data of number j, represents the average value of the running status data, n represents the total number, R (x i ) represents x i The rank, R(x j ) represents x j rank.
[0080] Through the above correlation calculation, correlation is used to identify associations in data, and this embodiment uses multiple correlation formulas for calculation, taking into account the distribution differences between different categories of data to avoid information loss.
[0081] Further, in this embodiment, the using of the preset second classification model to obtain the characteristic information of each row and each column of data in the table includes:
[0082] Performing maximum aggregation representation on each row and column of data in the table;
[0083] According to the maximum aggregate representation, using a preset activation function, obtaining feature information of each row and each column;
[0084] Using a preset fusion algorithm, the feature information of each row and each column is fused;
[0085] Further, in this embodiment, performing maximum aggregate representation on each row and each column of data in the table includes performing maximum aggregate representation using the following formula:
[0086] ;
[0087] Among them, h k represents the maximum aggregate representation of k rows, represents the maximum aggregation function, x k Represents all the data in k rows; l s represents the maximum aggregate representation of column s, y s Represents all the data in column s.
[0088] Further, in this embodiment, according to the maximum aggregation representation, using a preset activation function, obtaining feature information of each row and each column includes obtaining feature information of each row and each column using the following formula;
[0089] ;
[0090] in, Represents the characteristic information of each row, Represents the characteristic information of each column, f relu represents the activation function, Q and is the model parameter.
[0091] Furthermore, in this embodiment, using a preset fusion algorithm to fuse the feature information of each row and each column includes fusing using the following formula:
[0092] ;
[0093] Among them, V conv represents the fused vector; represents the fusion operation, Represents the characteristic information of each row, Represents the characteristic information of each column.
[0094] Furthermore, in this embodiment, using a preset third classification model, classifying the data of the operating status according to the acquired characteristic information and the preset multiple risk categories includes:
[0095] ;
[0096] in, is the predicted probability, is the trainable weight matrix, t is the bias term, and Softmax represents the conv +t results are classified, and the softmax includes multiple preset risk categories.
[0097] The risk classification model of this embodiment can improve the classification accuracy. The risk classification module uses the real-time simulation data of the digital twin model and combines it with the preset risk classification model to accurately classify the risks in the operation of the furnace. This classification helps to distinguish the severity and urgency of different risks and provide strong support for subsequent management and control decisions.
[0098] The management and control decision module is connected to the risk classification module, and is used to generate management and control instructions based on the classified risks in combination with the preset management and control strategies; the specific content of the preset management and control strategies is not limited here. Optionally, in this embodiment, the preset management and control strategies include defining different risk level classification standards according to different components, such as low risk, medium risk and high risk; setting corresponding response mechanisms for different risk levels, including warnings, automatic adjustment of process parameters, starting backup equipment, emergency shutdown, etc.; adjusting furnace process parameters according to real-time collected material status, temperature, pressure and other data to ensure product quality and energy efficiency; when process deviations are detected, automatically or manually adjusting furnace settings to reduce waste and energy waste, etc.
[0099] The execution module is connected to the management and control decision module, and is used to receive management and control instructions and control the kiln to execute corresponding risk management and control measures.
[0100] The data acquisition module of the present invention can obtain the key operating data of the kiln in real time, such as temperature, pressure, speed, etc., to ensure the immediate grasp of the kiln status, which is helpful to timely discover potential problems. The risk classification module uses the real-time simulation data of the digital twin model, combined with the preset risk classification model, to accurately classify the risks in the operation of the kiln; this classification helps to distinguish the severity and urgency of different risks, and provide strong support for subsequent management and control decisions. The management and control decision module can quickly generate targeted management and control instructions based on the risk classification results and the preset management and control strategies. This intelligent decision-making process reduces the delays and errors of human intervention and improves the efficiency and accuracy of risk management. After receiving the management and control instructions, the execution module can quickly control the kiln to execute the corresponding risk management and control measures. This ensures that risks are handled in a timely and effective manner and reduces the possibility of accidents.
[0101] Through simulation analysis of digital twin technology, the platform can not only manage current risks, but also predict possible problems in the future, thereby achieving preventive maintenance. This helps to extend the service life of equipment and improve the overall operating efficiency of the kiln. Effective risk management reduces the number of unexpected shutdowns and production interruptions, thereby reducing maintenance costs and production costs. At the same time, optimized kiln operation helps to improve production capacity and product quality. The platform significantly enhances the safe production capacity of the kiln through real-time monitoring and intelligent management and control. It ensures the efficient, safe and sustainable operation of the kiln.
[0102] It should be understood that the above specific embodiments of the present invention are only used to illustrate or explain the principles of the present invention, and do not constitute a limitation of the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. In addition, the appended claims of the present invention are intended to cover all changes and modifications that fall within the scope and boundaries of the appended claims, or the equivalent forms of such scope and boundaries.
[0103] The present invention has been described above with reference to the embodiments of the present invention. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present invention. The scope of the present invention is defined by the appended claims and their equivalents. Without departing from the scope of the present invention, a person skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.
[0104] Although the embodiments of the present invention have been described in detail, it should be understood that the various changes, substitutions, and alterations could be made hereto without departing from the spirit and scope of the invention.
[0105] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the invention.
Claims
1. A risk management and control platform for digital twin technology of metallurgical furnaces, characterized in that: include: Data collection module, digital twin module, risk classification module, management and control decision module and execution module; The data acquisition module is used to obtain the operation data of the metallurgical furnace in real time, including temperature, pressure, speed, material status and equipment health status; The digital twin module is connected to the data acquisition module, and is used to build a digital twin model of the kiln based on historical operation data, and receive the operation data collected by the data acquisition module to simulate the operation status of the kiln in real time; The risk classification module is connected to the digital twin module and is used to perform real-time risk classification of the kiln according to the operating status of the digital twin model in combination with a preset risk classification model; The control decision module is connected to the risk classification module and is used to generate control instructions based on the classified risks and in combination with the preset control strategies; The preset control strategy includes defining different risk levels according to different components: low risk, medium risk and high risk; setting corresponding response mechanisms for different risk levels, including warnings, automatic adjustment of process parameters, startup of backup equipment and emergency shutdown; The execution module is connected to the management and control decision module to receive management and control instructions and control the kiln to execute corresponding risk management and control measures; The real-time risk classification of the furnace according to the operating status of the digital twin model and the preset risk classification model includes: Acquiring data representing the operating status of the digital twin model; Constructing a risk classification model, wherein the risk classification model includes a first classification model, a second classification model and a third classification model; Using a preset first classification model, converting the data of the operating status into a table having rows and columns; Using a preset second classification model, characteristic information of each row and each column of data in the table is obtained respectively; Using a preset third classification model, classifying the data of the operating status according to the acquired characteristic information and a plurality of preset risk categories; The using a preset first classification model to convert the data of the operating status into a table having rows and columns includes: Combining the data of the operating status by numbers; Calculate the correlation coefficient between the data of the running status after the number combination; According to the correlation, converting the data of the operating status into a table having rows and columns; Calculating the correlation coefficient between the data of the running status includes calculating the correlation coefficient using the following formula: ; Wherein, X represents the correlation coefficient, i and j represent the serial numbers of the data of the running status, and x i Indicates the running status data of number i, x j Indicates the running status data of number j, represents the average value of the running status data, n represents the total number, R (x i ) represents x i The rank, R(x j ) represents x j rank.
2. The risk management and control platform according to claim 1, characterized in that: The digital twin module includes a furnace layer, a digital twin model layer and a twin data layer; The furnace layer includes a virtual entity model, and the virtual entity model includes a digital model of a physical entity of a metallurgical furnace; The digital twin model layer includes digitizing the operation process of the kiln and integrating it into the virtual entity model to obtain a digital twin model; The twin data layer processes and stores the collected operating data in the digital twin model to simulate the operating status of the furnace in real time.
3. The risk management and control platform according to claim 1 is characterized in that: The method of using the preset second classification model to obtain the characteristic information of each row and each column of data in the table includes: Performing maximum aggregation representation on each row and column of data in the table; According to the maximum aggregate representation, using a preset activation function, obtaining feature information of each row and each column; The feature information of each row and each column is fused using a preset fusion algorithm.
4. The risk management and control platform according to claim 3 is characterized in that: The performing the maximum aggregation expression on each row and each column of the table includes performing the maximum aggregation expression using the following formula: ; Among them, h k represents the maximum aggregate representation of k rows, represents the maximum aggregation function, x k Represents all the data in k rows; l s represents the maximum aggregate representation of column s, y s Represents all the data in column s.
5. The risk management and control platform according to claim 4 is characterized in that: According to the maximum aggregate representation, using a preset activation function, obtaining feature information of each row and each column includes obtaining feature information of each row and each column using the following formula; ; in, Represents the characteristic information of each row, Represents the characteristic information of each column, f relu represents the activation function, Q and is the model parameter.
6. The risk management and control platform according to claim 5, characterized in that: Using a preset fusion algorithm, fusing the feature information of each row and each column includes fusing using the following formula: ; Among them, V conv represents the fused vector; represents the fusion operation, Represents the characteristic information of each row, Represents the characteristic information of each column.
7. The risk management and control platform according to claim 1, characterized in that: Using a preset third classification model, classifying the data of the operating status according to the acquired characteristic information and a plurality of preset risk categories includes: ; in, is the predicted probability, is the trainable weight matrix, t is the bias term, and Softmax represents the conv +t results are classified, and the softmax includes multiple preset risk categories.
