Intelligent Management Method and System for Refining Furnace Smelting Based on Edge Computing

Abstract

The present invention discloses an intelligent management method and system for refining furnace smelting based on edge computing, which relates to the technical field of data processing. It includes analyzing the correlation relationship between smelting information in each smelting stage, providing a reliable basis for the establishment and early warning of the standard state of subsequent abnormal events. Multiple constituent elements of each abnormal event are determined through the correlation relationship between smelting information, and abnormal evaluation is carried out for each dimension to improve the reliability and accuracy of refining furnace smelting early warning. An early warning cycle for edge computing analysis in each smelting stage is set according to the fluctuation of smelting information. Combining with the real-time data processing and analysis ability of edge computing, an adapted early warning cycle is set for each smelting stage to ensure the timeliness and immediacy of early warning. The possible abnormal events are analyzed through the state transition probability between the real-time state of smelting and the standard state of abnormal events, realizing the management optimization of refining furnace smelting and ensuring the efficient and safe operation of the refining furnace smelting process.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to an intelligent management method and system for refining furnace smelting based on edge computing. Background Art

[0002] With the rapid development of the steel industry, the complexity and real-time requirements of the refining furnace smelting process are increasing day by day. Traditional management methods are difficult to meet the production needs of high efficiency and accuracy. As an emerging computing mode, edge computing realizes low latency, high bandwidth utilization, and enhanced privacy protection by placing computing resources and data storage on edge devices close to the data generation location. In the field of refining furnace smelting, edge computing technology can process and analyze massive data in the smelting process in real time, providing strong support for intelligent management. By real-time monitoring of equipment status, smelting process parameters, and output product quality, edge computing technology can detect abnormalities and give early warnings in a timely manner, ensuring the safe, stable, and efficient operation of the smelting process.

[0003] In the prior art, warnings are often made only based on single-type data. However, relying solely on single-type data without considering the correlation between multiple types of data results in poor reliability and low accuracy of the refining furnace smelting warning, which is not conducive to the intelligent management of subsequent warning measures.

[0004] Therefore, how to improve the reliability and accuracy of the refining furnace smelting warning is a technical problem to be solved at present. Summary of the Invention

[0005] The purpose of the present invention is to solve the problem of poor reliability and low accuracy of the refining furnace smelting warning in the prior art due to warning only based on single-type data, and to propose an intelligent management method for refining furnace smelting based on edge computing. The method includes:

[0006] Define each smelting stage of the refining furnace smelting process, and analyze the correlation between the smelting information in each smelting stage;

[0007] Collect the smelting information of all abnormal events in each smelting stage, determine multiple constituent elements of each abnormal event through the correlation between the smelting information, and integrate the multiple constituent elements to establish the standard state of each abnormal event in each stage;

[0008] Analyze the fluctuation of the smelting information in each smelting stage, and set the warning period of edge computing analysis for each smelting stage according to the fluctuation of the smelting information;

[0009] Monitor the smelting information in real time for each smelting stage, define the real-time smelting status, and regularly update the real-time smelting status based on the warning cycle. Generate warning information through the real-time smelting status and the standard status of abnormal events, and achieve management optimization for the refining furnace smelting in response to the warning information.

[0010] In some embodiments of the present application, analyze the correlation relationship between the smelting information in each smelting stage, including,

[0011] The smelting information includes equipment status data, smelting process data, and smelting output data;

[0012] Construct an equipment status data sequence, a smelting process data sequence, and a smelting output data sequence according to the equipment status data, smelting process data, and smelting output data, and perform pair processing on the equipment status data sequence, smelting process data sequence, and smelting output data sequence according to the time stamp;

[0013] Allocate the equipment status data sequence, smelting process data sequence, and smelting output data sequence to the corresponding smelting stage. For the same smelting stage, calculate the cross-correlation function among the equipment status data sequence, smelting process data sequence, and smelting output data sequence, and draw a cross-correlation graph. Obtain the correlation relationship among the equipment status data, smelting process data, and smelting output data in each smelting stage through the cross-correlation graph of the equipment status data, smelting process data, and smelting output data;

[0014] Among them, the abscissa of the cross-correlation graph represents the time lag amount of two-by-two data among the equipment status data, smelting process data, and smelting output data, and the ordinate represents the correlation coefficient of two-by-two data among the equipment status data, smelting process data, and smelting output data.

[0015] In some embodiments of the present application, obtain the correlation relationship among the equipment status data, smelting process data, and smelting output data in each smelting stage through the cross-correlation graph of the equipment status data, smelting process data, and smelting output data, including,

[0016] Screen out the data category combinations with high correlation according to the correlation coefficient of the highest point in the cross-correlation graph. Divide the cross-correlation graph into multiple curve segments according to the abscissa range value in the cross-correlation graph of the data category combinations with high correlation. Calculate the average value of the slope change of each curve segment, and obtain the overall average value of the slope change after integration. Divide the data category combinations into two categories: stable relationship and unstable relationship through the overall average value of the slope change, and analyze the trend component in the cross-correlation graph;

[0017] For the data category combinations with a stable relationship, use the abscissa value of the highest point in their cross-correlation graph as the standard time lag amount;

[0018] For the combination of data categories with unstable relationships, determine the curve segment with the highest frequency of occurrence in the cross-correlation graph, and use the abscissa value of this curve segment and the highest point as the standard time lag amount;

[0019] Input the standard time lag amount, correlation coefficient, and trend component into a multiple regression model to determine the correlation relationship among the equipment status data, smelting process data, and smelting output data.

[0020] In some embodiments of the present application, multiple constituent elements of each abnormal event are determined through the correlation relationship among smelting information, including,

[0021] For the same abnormal event, screen out the range of abnormal data parameters in the three types of data: equipment status data, smelting process data, and smelting output data, confirm the change trend before and after the data anomaly, and determine the abnormal correlation through the correlation relationship among the equipment status data, smelting process data, and smelting output data and the abnormal data;

[0022] The constituent elements include key elements and evaluation elements. The range of abnormal data parameters, the change trend before and after the data anomaly, and the abnormal correlation are used as key elements. Each key element is evaluated, and after synthesis, an event anomaly degree level is generated, and the anomaly degree level is used as the evaluation element.

[0023] In some embodiments of the present application, each key element is evaluated, and after synthesis, an event anomaly degree level is generated, including,

[0024] Determine the evaluation characteristics corresponding to each key element, generate the evaluation index of each key element through the evaluation characteristics, and synthesize the evaluation indexes of each key element to generate the event anomaly degree level;

[0025] ;

[0026] Among them, is the event anomaly degree level of the th abnormal event, , , are the combination weights of the three key elements: the range of abnormal data parameters, the change trend before and after the data anomaly, and the abnormal correlation, respectively, , , are the evaluation indexes of the three key elements: the range of abnormal data parameters, the change trend before and after the data anomaly, and the abnormal correlation of the th abnormal event, respectively, is the maximum value among the three, , are preset constants, respectively, is the rounding symbol.

[0027] In some embodiments of the present application, the fluctuation of the smelting information in each smelting stage is analyzed, and the warning period of the edge computing analysis for each smelting stage is set according to the fluctuation of the smelting information, including,

[0028] Calculate the coefficient of variation of three types of data: equipment status data, smelting process data, and smelting output data, collect the event abnormal degree levels of all abnormal events in the smelting stage, and determine the warning period;

[0029] ;

[0030] Among them, is the warning period in the th smelting stage, represents the coefficient of variation of the th type of data in the th smelting stage, is the initial warning period in the th smelting stage, represents the initial warning period of the th type of data mapped from the coefficient of variation of the th type of data in the is the number of types of abnormal events in the th smelting stage, is the event abnormal degree level of the th abnormal event in the th smelting stage, is the abnormal conversion coefficient determined by the occurrence frequency of the th abnormal event in the th smelting stage, is a preset constant.

[0031] In some embodiments of the present application, both the standard state of the abnormal event and the real-time smelting state have key elements and evaluation elements corresponding to the abnormal data parameter range, the change trend before and after the data abnormality, and the abnormal association.

[0032] In some embodiments of the present application, warning information is generated by the real-time smelting state and the standard state of the abnormal event, including,

[0033] According to the event abnormal degree level in the real-time smelting state, the standard state of the abnormal event in the smelting stage is screened, the abnormal events with the same event abnormal degree level are screened out, and the real-time smelting state and the standard state are matched for the screened abnormal events to calculate the state transition probability, so as to generate warning information.

[0034] Correspondingly, the present application also provides an intelligent management system for refining furnace smelting based on edge computing, including:

[0035] The first module is used to define each smelting stage of the refining furnace smelting process and analyze the correlation relationship between the smelting information under each smelting stage;

[0036] The second module is used to collect the smelting information of all abnormal events under each smelting stage, determine multiple constituent elements of each abnormal event through the correlation relationship between the smelting information, and integrate the multiple constituent elements to establish the standard state of each abnormal event under each stage;

[0037] The third module is used to analyze the fluctuation of the smelting information under each smelting stage and set the warning period for edge computing analysis of each smelting stage according to the fluctuation of the smelting information;

[0038] The fourth module is used to monitor the smelting information under each smelting stage in real time, define the real-time smelting state, and regularly update the real-time smelting state based on the warning period. Generate warning information through the real-time smelting state and the standard state of abnormal events, and realize the management optimization of refining furnace smelting for the warning information.

[0039] By applying the above technical solutions, each smelting stage of the refining furnace smelting process is defined, the correlation relationship between the smelting information under each smelting stage is analyzed, and the correlation between the equipment status data, smelting process data, and smelting output data is analyzed, providing a reliable basis for the establishment of the standard state of subsequent abnormal events and early warning. Determine multiple constituent elements of each abnormal event through the correlation relationship between the smelting information, describe the abnormal conditions of the abnormal events in multiple dimensions through the multiple constituent elements, and perform abnormal evaluation on each dimension to improve the reliability and accuracy of the refining furnace smelting early warning. Set the warning period for edge computing analysis of each smelting stage according to the fluctuation of the smelting information, and combine the real-time data processing and analysis capabilities of edge computing to set an appropriate warning period for each smelting stage to ensure the timeliness and promptness of the early warning. Monitor the smelting information under each smelting stage in real time, define the real-time smelting state, and regularly update the real-time smelting state based on the warning period. Analyze the possible abnormal events through the state transition probability between the real-time smelting state and the standard state of the abnormal events, thereby generating warning information, and realizing the management optimization of refining furnace smelting for the warning information, ensuring the efficient and safe operation of the refining furnace smelting process. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a schematic flow chart of the intelligent management method for refining furnace smelting based on edge computing proposed by the present invention;

[0041] Figure 2Schematic diagram of the intelligent management system for refining furnace smelting based on edge computing proposed by the present invention. Specific embodiments

[0042] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments.

[0043] Refer to Figure 1 , the intelligent management method for refining furnace smelting based on edge computing includes the following steps:

[0044] Step S101, define each smelting stage in the refining furnace smelting process, and analyze the correlation relationship between the smelting information in each smelting stage.

[0045] In this embodiment, the refining furnace smelting process can usually be divided into the following stages:

[0046] Preheating stage: Preheat the furnace charge to prepare for entering the melting stage.

[0047] Melting stage: The furnace charge melts at high temperature to form a metal molten pool.

[0048] Refining stage: Remove impurities in the molten pool by adding refining agents, adjusting temperature and stirring, etc.

[0049] Alloying stage: Add alloying elements as needed to adjust the metal composition.

[0050] Tapping stage: Pour out the refined molten metal to prepare for the next process.

[0051] In this embodiment, the smelting information includes equipment status data, including parameters such as the operating status, temperature, pressure, and flow rate of smelting equipment. These data are used to monitor the health status of the equipment and the stability of the smelting process. The smelting process data includes real-time oxygen content measurement information, real-time temperature measurement information, power consumption, argon consumption, soft blowing time, soft blowing argon consumption, wire feeding length, wire feeding real-time speed, etc. These data reflect the real-time status and process parameters during the smelting process, and the smelting output data includes flue gas emissions, sewage emissions, slag volume, output, etc. There are complex correlation relationships between these three types of data. For example, the change in furnace temperature in the equipment status data will affect the amount of refining agent used in the smelting process data, and further affect the flue gas emissions in the smelting output data, etc. Through data analysis and mining, these correlation relationships can be revealed, providing a basis for abnormal event detection.

[0052] In some embodiments of the present application, analyzing the correlation relationship between the smelting information in each smelting stage includes,

[0053] The smelting information includes equipment status data, smelting process data, and smelting output data;

[0054] Construct an equipment status data sequence, a smelting process data sequence, and a smelting output data sequence based on the equipment status data, smelting process data, and smelting output data, and process the equipment status data sequence, smelting process data sequence, and smelting output data sequence pairwise according to the timestamps;

[0055] Allocate the equipment status data sequence, smelting process data sequence, and smelting output data sequence to the corresponding smelting stages. For the same smelting stage, calculate the cross-correlation function among the equipment status data sequence, smelting process data sequence, and smelting output data sequence, and draw a cross-correlation graph. Obtain the correlation relationship among the equipment status data, smelting process data, and smelting output data under each smelting stage through the cross-correlation graph of the equipment status data, smelting process data, and smelting output data;

[0056] Among them, the abscissa of the cross-correlation graph represents the time lag amount of pairwise data among the equipment status data, smelting process data, and smelting output data, and the ordinate represents the correlation coefficient of pairwise data among the equipment status data, smelting process data, and smelting output data.

[0057] In this embodiment, there is a time lag in the influence among the equipment status data, smelting process data, and smelting output data. Therefore, they are converted into the form of data sequences for correlation calculation. Calculate the cross-correlation function among the equipment status data, smelting process data, and smelting output data, and analyze the dynamic correlation relationship among different data sequences. Through the cross-correlation graph, observe the time lag effect and mutual dependence relationship among the data sequences. The cross-correlation function is a statistic that measures the correlation degree between two time series at different time lags. By calculating the cross-correlation function, we can obtain the correlation coefficients at different time lags, so as to understand how the change of one data sequence affects another data sequence. To more intuitively observe the time lag effect and mutual dependence relationship, we can draw the results of the cross-correlation function into a cross-correlation graph. In the cross-correlation graph, the horizontal axis represents the time lag amount, and the vertical axis represents the correlation coefficient. By observing the cross-correlation graph, we can find the time lag point with the largest correlation coefficient, and this point is the time lag amount of the strongest correlation between the two data sequences (for the cross-correlation graph with relatively small changes).

[0058] In some embodiments of the present application, the correlation relationship among the equipment status data, smelting process data, and smelting output data under each smelting stage is obtained through the cross-correlation graph of the equipment status data, smelting process data, and smelting output data, including,

[0059] Select data category combinations with high correlation based on the correlation coefficient at the highest point in the cross-correlation graph. Divide the cross-correlation graph into multiple curve segments according to the abscissa range value in the cross-correlation graph of the data category combinations with high correlation. Calculate the average slope change of each curve segment, and obtain the overall average slope change after integration. Classify the data category combinations into stable relationships and unstable relationships based on the overall average slope change, and analyze the trend component in the cross-correlation graph;

[0060] For the data category combinations with stable relationships, use the abscissa value at the highest point in their cross-correlation graph as the standard time lag;

[0061] For the data category combinations with unstable relationships, determine the curve segment with the highest frequency of occurrence in the cross-correlation graph, and use the abscissa values of this curve segment and the highest point as the standard time lag;

[0062] Input the standard time lag, correlation coefficient, and trend component into a multiple regression model to determine the correlation relationship among the equipment status data, smelting process data, and smelting output data.

[0063] In this embodiment, time lag effect: Observe which data sequence changes lag behind those of another data sequence and the length of the lag. The lag effect may be caused by various factors such as equipment response speed, material transfer time, chemical reaction rate, etc. This helps to understand the time delay and interaction between different links in the smelting process. Interdependence relationship: Analyze the magnitude and sign of the correlation coefficients among the equipment status data, smelting process data, and smelting output data. The magnitude of the correlation coefficient reflects the degree of association between two data sequences, while the sign indicates the positive or negative correlation relationship between them. Dynamic change: Observe the change of the cross-correlation function over time to understand whether the dynamic correlation relationship is stable and whether there are periodic or trend changes. This helps to identify potential problems and optimization points in the smelting process.

[0064] In this embodiment, for data category combinations with relatively small changes, i.e., stable ones, the closest connection between two time series is sought, that is, the strongest correlation between them. By finding the point with the largest correlation coefficient, we can determine when (i.e., which time lag) the two time series reach the strongest association, which is crucial for understanding their interaction and causal relationship. For data category combinations with relatively large changes, i.e., unstable ones, in addition to the point with the largest correlation coefficient, we can also consider the points within the mode range of the correlation coefficient. The mode range refers to the range of values that appear most frequently or are relatively concentrated in a set of data. Selecting the points within the mode range as the time lag can take into account the strong association relationships under multiple time lags and increase the robustness of the results. Based on the point with the largest correlation coefficient and the points within the mode range of the correlation coefficient, we can comprehensively obtain a standard time lag. The standard time lag, correlation coefficient, and trend component are used as input variables. A multiple regression model (time lag terms can be added) is constructed using these input variables to determine the specific association relationship (functional relationship) between each pair of data category combinations with high correlation.

[0065] Step S102: Collect the smelting information of all abnormal events in each smelting stage, and determine multiple constituent elements of each abnormal event through the association relationship between the smelting information, and integrate the multiple constituent elements to establish the standard state of each abnormal event in each stage.

[0066] In this embodiment, historical data is reviewed, and the equipment status data, smelting process data, and smelting output data of the abnormal events occurring in each stage are collected. For each abnormal event, its parameters (such as abnormal values, durations), change trends (such as sudden increase, gradual decrease), and the correlation situation between the three types of data are analyzed as constituent elements. The standard state of each abnormal event in each stage is established.

[0067] In some embodiments of the present application, multiple constituent elements of each abnormal event are determined through the association relationship between the smelting information, including

[0068] For the same abnormal event, screen out the abnormal data parameter ranges in the three types of data of equipment status data, smelting process data, and smelting output data, confirm the change trend before and after the data anomaly, and determine the abnormal association through the association relationship between the equipment status data, smelting process data, and smelting output data and the abnormal data;

[0069] The constituent elements include key elements and evaluation elements. The abnormal data parameter range, the change trend before and after the data anomaly, and the abnormal association are used as key elements, each key element is evaluated, and the event anomaly degree level is generated after synthesis, and the anomaly degree level is used as the evaluation element.

[0070] In this embodiment, for each abnormal event, its parameters are first analyzed, such as the range of abnormal values, the length of the duration, etc. These parameters are the basis for describing the characteristics of the abnormal event. Analyze the change trend of the abnormal event data, such as the sudden increase or gradual decrease of the device status data, the fluctuation of the smelting process data, etc. These trends help to understand the development process of the abnormal event. Abnormal association is the matching situation of three types of data association relationships. For example, an abnormality in one type of data causes abnormalities in the other two types of data: this is an abnormal association situation that conforms to the three types of data association relationships. For example, an abnormal increase in the temperature in the device status data causes an increase in the reaction rate in the smelting process data, and further causes a decrease in the product quality-related parameters in the smelting output data. This abnormal situation indicates that the abnormality of the device status directly affects the smelting process and the output result. For example, an abnormality in one type of data, while the other two associated types of data are normal: this situation is relatively rare but equally important. For example, the pressure in the device status data abnormally increases, but the smelting process data and the smelting output data remain normal. This may mean that there are potential faults or hidden dangers inside the device, but they have not directly affected the smelting process and the output result. Since this does not conform to the association relationship of the three types of data, it will make the abnormality more complex or unpredictable, etc.

[0071] In some embodiments of the present application, each key element is evaluated, and after synthesis, an event abnormality degree level is generated, including

[0072] Determine the evaluation characteristics corresponding to each key element, generate the evaluation index of each key element through the evaluation characteristics, and generate the event abnormality degree level by synthesizing the evaluation indexes of each key element;

[0073] ;

[0074] Among them, is the event abnormality degree level of the th abnormal event, , , are the combination weights of the three key elements of the abnormal data parameter range, the change trend before and after the data abnormality, and the abnormal association respectively, , , are the evaluation indexes of the three key elements of the abnormal data parameter range, the change trend before and after the data abnormality, and the abnormal association of the th abnormal event respectively, is the maximum value among the three, , are preset constants respectively, is the rounding symbol.

[0075] In this embodiment, evaluation features corresponding to each key element are determined. For example, for the abnormal data parameter range, evaluation features such as the range of abnormal values, the amplitude beyond the normal range, the frequency of abnormal values, and the duration are used to determine. The change trend before and after data abnormality (considering the speed of data change, the amplitude of change, and the direction of change, etc.). For example, a sudden large change may be regarded as highly abnormal, while a slow small change may be regarded as normal or mildly abnormal. Abnormal association, statistically check whether the abnormal data conditions of the three types of data match the association relationship. A match indicates that the abnormal situation is relatively controllable and traceable. If there is no match, it means that the abnormality is more complex or more serious, which is not conducive to abnormal positioning. Integrate all evaluation features and all parameters to determine the evaluation index for each type of data among the three types of data, and jointly illustrate the abnormal situation from three dimensions (parameter range, change trend, and abnormal association).

[0076] In this embodiment, It represents the correction of the average value of the three dimensions by the maximum evaluation index among the three types of data. The evaluation index is an index describing the degree of abnormality, and different abnormal events may correspond to different serious situations or abnormal situations.

[0077] Step S103, analyze the fluctuation of the smelting information in each smelting stage, and set the warning period for edge computing analysis for each smelting stage according to the fluctuation of the smelting information.

[0078] In this embodiment, relying on the advantage that edge computing can perform data analysis and processing at the device end, different warning periods are set for different smelting stages. After the time period is met, the real-time smelting status is updated in real time, and the state transition probability is calculated.

[0079] In some embodiments of the present application, analyze the fluctuation of the smelting information in each smelting stage, and set the warning period for edge computing analysis for each smelting stage, including,

[0080] Calculate the coefficient of variation of three types of data: equipment status data, smelting process data, and smelting output data, collect the event abnormal degree levels of all abnormal events in the smelting stage, and determine the warning period;

[0081] ;

[0082] Wherein, is the warning period for the th smelting stage, represents the coefficient of variation of the th type of data in the th smelting stage, is the initial warning period for the th smelting stage, represents the The initial warning period of the category of data obtained by mapping the coefficient of variation of the category of data under the nth smelting stage, where is the number of types of abnormal events under the nth smelting stage, and is the event abnormal degree level of the mth abnormal event under the nth smelting stage. The abnormal conversion coefficient determined by the occurrence frequency of the mth abnormal event under the

[0083] In this embodiment, the coefficient of variation can describe the fluctuation of each parameter under three categories of data. By combining all parameters, the coefficient of variation of the three categories of data is generated. The 3 in the summation formula represents three categories of data: equipment status data, smelting process data, and smelting output data. represents that all abnormal severities of abnormal events under the smelting stage correct the average value of the initial warning period. The higher the abnormal degree, the shorter this period, and vice versa.

[0084] Step S104: Monitor the smelting information in real time for each smelting stage, define the real-time smelting status, and regularly update the real-time smelting status based on the warning period. Generate warning information through the real-time smelting status and the standard status of abnormal events, and realize the management optimization of the refining furnace smelting for the warning information.

[0085] In some embodiments of the present application, both the standard status of abnormal events and the real-time smelting status have key elements and evaluation elements corresponding to the abnormal data parameter range, the change trend before and after data abnormality, and abnormal association.

[0086] In this embodiment, if a certain key element is not abnormal in the real-time smelting status, the corresponding part is 0.

[0087] In some embodiments of the present application, generating warning information through the real-time smelting status and the standard status of abnormal events includes:

[0088] Screen the standard status of abnormal events in the smelting stage according to the event abnormal degree level in the real-time smelting status, screen out the abnormal events with the same event abnormal degree level, and perform the matching of the real-time smelting status and the standard status on the screened abnormal events, calculate the state transition probability, and generate warning information accordingly.

[0089] In this embodiment, three key elements are integrated into one state, and the state transition probability between the real-time smelting state and the standard state is calculated. Using probability models such as Markov chains, the probability of transitioning from the current state to the standard state of an abnormal event is calculated. When the state transition probability of a certain abnormal event is detected to exceed the warning threshold, corresponding warning information is generated according to the nature, influence range, and possible risk consequences of the abnormal event. The warning information should include the description of the abnormal event, the level of abnormality, possible risk consequences, and recommended countermeasures, etc., so as to assist in the subsequent management of the smelting process.

[0090] Correspondingly, the present application also provides an intelligent management system for refining furnace smelting based on edge computing, as Figure 2 shown, including,

[0091] The first module is used to define each smelting stage of the refining furnace smelting process and analyze the correlation between the smelting information in each smelting stage;

[0092] The second module is used to collect the smelting information of all abnormal events in each smelting stage, determine multiple constituent elements of each abnormal event through the correlation between the smelting information, and integrate the multiple constituent elements to establish the standard state of each abnormal event in each stage;

[0093] The third module is used to analyze the fluctuation of the smelting information in each smelting stage and set the warning period for edge computing analysis in each smelting stage according to the fluctuation of the smelting information;

[0094] The fourth module is used to monitor the smelting information in each smelting stage in real time, define the real-time smelting state, and regularly update the real-time smelting state based on the warning period. Warning information is generated through the real-time smelting state and the standard state of the abnormal event, and the management optimization of the refining furnace smelting is realized for the warning information.

[0095] By applying the above technical solutions, each smelting stage of the refining furnace smelting process is defined, the correlation relationships between the smelting information in each smelting stage are analyzed, and the correlations among the equipment status data, smelting process data, and smelting output data are analyzed, providing a reliable basis for the establishment and early warning of the standard status of subsequent abnormal events. Multiple constituent elements of each abnormal event are determined through the correlation relationships between the smelting information, the abnormal conditions of the abnormal events in multiple dimensions are described through the multiple constituent elements, and abnormal evaluations are carried out for each dimension, improving the reliability and accuracy of the refining furnace smelting early warning. An early warning period for edge computing analysis is set for each smelting stage according to the fluctuation conditions of the smelting information. Combining the real-time data processing and analysis capabilities of edge computing, an appropriate early warning period is set for each smelting stage to ensure the timeliness and immediacy of the early warning. The smelting information in each smelting stage is monitored in real time, the real-time smelting status is defined, and the real-time smelting status is updated regularly based on the early warning period. The possible abnormal events are analyzed through the state transition probability between the real-time smelting status and the standard status of the abnormal events, thereby generating early warning information, and the management optimization of the refining furnace smelting is realized for the early warning information, ensuring the efficient and safe operation of the refining furnace smelting process.

[0096] Through the description of the above embodiments, those skilled in the art can clearly understand that the present invention can be implemented by hardware or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various implementation scenarios of the present invention.

[0097] Those skilled in the art can understand that the drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the drawings are not necessarily essential for implementing the present invention.

[0098] Those skilled in the art can understand that the modules in the system in the implementation scenario can be distributed in the system of the implementation scenario according to the description of the implementation scenario, or can be correspondingly changed and located in one or more systems different from this implementation scenario. The modules in the above implementation scenario can be combined into one module, or can be further split into multiple sub-modules.

[0099] The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution of the present invention and its inventive concept, makes equivalent substitutions or changes, and should be covered by the protection scope of the present invention.

Claims

1. The intelligent management method of refining furnace smelting based on edge computing is characterized by: include: Define the various smelting stages of the refining furnace smelting process and analyze the correlation between the smelting information in each smelting stage; Collect the smelting information of all abnormal events in each smelting stage, determine the multiple components of each abnormal event through the correlation between the smelting information, and integrate the multiple components to establish the standard state of each abnormal event in each smelting stage; Analyze the fluctuation of smelting information at each smelting stage, and set the early warning cycle of edge computing analysis at each smelting stage according to the fluctuation of smelting information; Real-time monitoring of smelting information at each smelting stage, definition of real-time smelting status, and regular update of real-time smelting status based on the early warning cycle. Early warning information is generated through the real-time smelting status and the standard status of abnormal events, and management optimization of refining furnace smelting is achieved based on the early warning information; Among them, smelting information includes equipment status data, smelting process data and smelting output data; The multiple components of each abnormal event are determined through the correlation between smelting information, including: For the same abnormal event, the abnormal data parameter ranges in the three types of data, namely, equipment status data, smelting process data and smelting output data, are screened out to confirm the changing trend before and after the data abnormality. The abnormal correlation is determined through the correlation between the equipment status data, smelting process data and smelting output data and the abnormal data; The components include key factors and evaluation factors. The abnormal data parameter range, the change trend before and after the data abnormality and the abnormal correlation are taken as key factors. Each key factor is evaluated, and the event abnormality degree level is generated after integration. The event abnormality degree level is used as the evaluation factor. Analyze the fluctuation of smelting information at each smelting stage, and set the early warning cycle of edge computing analysis at each smelting stage according to the fluctuation of smelting information, including: Calculate the coefficient of variation of three types of data: equipment status data, smelting process data, and smelting output data, collect the abnormality levels of all abnormal events in the smelting stage, and determine the early warning cycle; ； in, For the The early warning cycle in each smelting stage, Indicates The next smelting stage The coefficient of variation of the class data, Indicated by The next smelting stage The coefficient of variation of the class data is mapped to the The initial warning cycle of class data, For the The number of types of abnormal events in each smelting stage, For the The next smelting stage The abnormality level of each abnormal event, For the The next smelting stage The abnormal conversion coefficient is determined by the frequency of occurrence of abnormal events. is a preset constant.

2. The intelligent management method for refining furnace smelting based on edge computing according to claim 1 is characterized in that: Analyze the correlation between smelting information at each smelting stage, including: Constructing an equipment status data sequence, a smelting process data sequence and a smelting output data sequence according to the equipment status data, the smelting process data and the smelting output data, and aligning the equipment status data sequence, the smelting process data sequence and the smelting output data sequence according to the timestamp; The equipment status data sequence, the smelting process data sequence and the smelting output data sequence are assigned to the corresponding smelting stages. For the same smelting stage, the cross-correlation function among the equipment status data sequence, the smelting process data sequence and the smelting output data sequence is calculated, and a cross-correlation diagram is drawn. The correlation relationship among the equipment status data, the smelting process data and the smelting output data in each smelting stage is obtained through the cross-correlation diagram among the equipment status data, the smelting process data and the smelting output data. Among them, the horizontal axis of the cross-correlation diagram represents the time lag between any two of the equipment status data, the smelting process data and the smelting output data, and the vertical axis represents the correlation coefficient between any two of the equipment status data, the smelting process data and the smelting output data.

3. The intelligent management method for refining furnace smelting based on edge computing according to claim 2 is characterized in that: The correlation between the equipment status data, smelting process data and smelting output data in each smelting stage is obtained through the cross-correlation diagram between the equipment status data, smelting process data and smelting output data, including: According to the correlation coefficient of the highest point in the cross-correlation diagram, the data category combination with higher correlation is screened out. In the cross-correlation diagram under the data category combination with higher correlation, the cross-correlation diagram is divided into multiple curve segments according to the horizontal axis range value, and the average value of the slope change of each curve segment is calculated. After integration, the overall slope change average value is obtained. The data category combination is divided into two categories: stable relationship and unstable relationship through the overall slope change average value, and the trend component in the cross-correlation diagram is analyzed; For the data category combination with stable relationship, the horizontal coordinate value of the highest point in its cross-correlation diagram is taken as the standard time lag; For the data category combination of non-stable relationship, determine the curve segment with the highest frequency of correlation coefficient in the cross-correlation diagram, and obtain the standard time lag from the curve segment and the horizontal coordinate value of the highest point in the cross-correlation diagram; The standard time lag, correlation coefficient and trend component were input into the multiple regression model to determine the relationship between equipment status data, smelting process data and smelting output data.

4. The intelligent management method for refining furnace smelting based on edge computing according to claim 1 is characterized in that: Both the standard state of abnormal events and the real-time state of smelting have key elements and evaluation elements corresponding to the abnormal data parameter range, the change trend before and after the data abnormality, and the abnormal correlation.

5. The intelligent management method for refining furnace smelting based on edge computing according to claim 1 is characterized in that: Each key factor is evaluated and the abnormality level of the event is generated after comprehensive analysis, including: Determine the evaluation features corresponding to each key factor, generate the evaluation index of each key factor through the evaluation features, and generate the abnormality level of the event by combining the evaluation index of each key factor; ； in, For the The abnormality level of each abnormal event, , , They are the combined weights of the three key factors: abnormal data parameter range, change trend before and after data anomaly, and abnormal correlation. , , Respectively The evaluation indicators of the three key factors of abnormal data parameter range, data change trend before and after abnormality, and abnormal correlation are as follows: for The maximum of the three, , are preset constants respectively, and [] is the rounding symbol.

6. The intelligent management method for refining furnace smelting based on edge computing according to claim 4 is characterized in that: Generate early warning information based on the real-time status of smelting and the standard status of abnormal events, including: According to the abnormality level of events under the real-time smelting state, the standard state of abnormal events under the smelting stage is screened, and abnormal events with the same abnormality level are screened out. The real-time smelting state and the standard state are matched for the screened abnormal events, and the state transition probability is calculated to generate early warning information.

7. The intelligent management system for refining furnace smelting based on edge computing is characterized by: For implementing the intelligent management method for refining furnace smelting based on edge computing as described in any one of claims 1 to 6, the system comprises: The first module is used to define the various smelting stages of the refining furnace smelting process and analyze the correlation between the smelting information in each smelting stage; The second module is used to collect the smelting information of all abnormal events in each smelting stage, determine the multiple components of each abnormal event through the correlation between the smelting information, and integrate the multiple components to establish the standard state of each abnormal event in each smelting stage; The third module is used to analyze the fluctuation of smelting information at each smelting stage, and set the early warning cycle of edge computing analysis at each smelting stage according to the fluctuation of smelting information; The fourth module is used to monitor the smelting information in each smelting stage in real time, define the real-time status of smelting, and regularly update the real-time status of smelting based on the early warning cycle. Early warning information is generated through the real-time status of smelting and the standard status of abnormal events, and the management optimization of refining furnace smelting is realized based on the early warning information.

Images