Steelmaking process quality monitoring and analysis system

Abstract

A steelmaking process quality monitoring and analysis system, comprising: an application layer, wherein the application layer comprises adaptive process quality monitoring and analysis modules for steelmaking procedures, and the process quality monitoring and analysis modules are used for implementing process quality monitoring and analysis during a steelmaking process; a control layer, wherein the control layer comprises control modules corresponding to the steelmaking procedures in the application layer; and an equipment layer, wherein the equipment layer comprises hardware equipment corresponding to the adaptive process quality monitoring and analysis modules for the steelmaking procedures in the application layer. The present invention is applicable to process quality monitoring and analysis for procedures in a steelmaking workshop; a process quality monitoring and analysis system for steelmaking procedures is constructed, and process equipment parameter data structures and analysis models are constructed, such that scaling factor algorithms, process quality monitoring and analysis models and adaptive process quality monitoring and analysis algorithms for steelmaking procedures are implemented, thereby providing feasible technical support for the improvement of the steelmaking process quality and the product quality, and realizing lean production in steelmaking workshops.

Description

A steelmaking process quality monitoring and analysis system Technical Field

[0001] The invention belongs to the field of steel production technology and information technology, and particularly relates to a steelmaking process quality monitoring and analysis system. Background Art

[0002] Currently, the long-process steelmaking process uses blast furnace molten iron as raw material. The molten iron undergoes desulfurization and slag removal in the desulfurization process. The treated molten iron then passes through the converter process for oxygen injection and decarburization. The treated molten steel then undergoes refining, where bottom blowing, stirring, heating, and alloy adjustment are used to improve its purity. Finally, the molten steel is continuously cast into billets for subsequent rolling. Each process in the long-process steelmaking process has its own unique production characteristics, which affect the quality of the steel products produced by the long-process steelmaking process.

[0003] Currently, the global industrial intelligentization movement is in full swing, and the steel industry is poised to embrace comprehensive innovation and reform in intelligent manufacturing. Furthermore, rising steel raw material prices and increasingly stringent market regulations are forcing domestic steel manufacturers to continuously improve product quality to maximize profits. However, a long-process steelmaking plant includes desulfurization, converters, refining (LF, RH), and continuous casting. Each process involves various process and equipment parameters, and different process equipment parameters utilize different process quality monitoring and analysis models. Managing these parameters across various processes and equipment is a pressing issue.

[0004] Secondly, some of the parameter range values ​​for each steelmaking process and each process equipment have only upper limits, some process equipment parameter range values ​​have only lower limits, and some have both upper and lower limits. In addition, due to different measurement units, there are large differences in the range values ​​of these parameters, which will cause the analysis results to be unable to be displayed within the same coordinate when using the conformity diagram algorithm for process quality monitoring and analysis.

[0005] Thirdly, each process has different process equipment parameters with different production characteristics. When conducting process quality monitoring and analysis for each steelmaking process, the analysis model is selected based on these characteristics. Some process equipment parameters are suitable for process quality monitoring and analysis using the SPC model, while others can only be analyzed using the conformance chart model, and some are suitable for other analysis models. Therefore, a reasonable solution is urgently needed for how to conduct adaptive process quality monitoring and analysis for each steelmaking process (desulfurization, converter, refining, and continuous casting).

[0006] Finally, how to provide process management and process operators with process operation improvement directions based on the process quality monitoring and analysis results of each steelmaking process is also an issue that needs to be solved urgently.

[0007] Summary of the Invention

[0008] The purpose of the present invention is to overcome the defects of the existing technology. In order to solve the above technical problems, the present invention provides a steelmaking process quality monitoring and analysis system. Based on the Six Sigma management concept, the present invention builds a process quality monitoring and analysis system and application methodology for each steelmaking process, performs process quality monitoring and analysis on the production process data of each process equipment in each process of long-process steelmaking, and displays abnormal quality data in red, thereby providing specific and feasible technical support for improving the quality of the steelmaking process and enhancing the quality of steelmaking products.

[0009] In order to achieve the expected effect, the present invention adopts the following technical solutions:

[0010] The present invention discloses a steelmaking process quality monitoring and analysis system, comprising:

[0011] An application layer, comprising an adaptive process quality monitoring and analysis module for each steelmaking process, wherein the process quality monitoring and analysis module is used to implement process quality monitoring and analysis during the steelmaking process;

[0012] A control layer, comprising control modules corresponding to various steelmaking processes in the application layer;

[0013] The equipment layer includes hardware devices corresponding to the adaptive process quality monitoring and analysis modules of each steelmaking process in the application layer.

[0014] Furthermore, the steelmaking processes include: a desulfurization process, a converter process, a refining process, and a continuous casting process.

[0015] Furthermore, the process quality monitoring and analysis module includes: a first module, a second module, a third module, a fourth module, a fifth module,

[0016] The first module is used to construct a basic data structure of configurable parameters of each process equipment in each steelmaking process;

[0017] The second module is used to collect the actual measured values ​​of each process equipment in each process based on the basic data structure of the parameters of each process equipment in each process;

[0018] The third module is used to adaptively select a process quality monitoring and analysis model for each process equipment parameter in each process based on the actual measured values ​​of the parameters of each process equipment in each process;

[0019] The fourth module is used to implement process quality monitoring and analysis of parameters of each process equipment in each step;

[0020] The fifth module is used to display the analysis results of the fourth module.

[0021] Furthermore, the construction of the basic data structure of each process equipment parameter of each configurable steelmaking process specifically includes: determining each process equipment parameter according to the process, unit, section, and steel type, and setting a baseline value, upper limit value and lower limit value for each process equipment parameter.

[0022] Furthermore, the process quality monitoring and analysis model for adaptively selecting the parameters of each process equipment in each process based on the actual measured values ​​of each process equipment in each process specifically includes: configuring a single value range chart analysis model and a compliance chart analysis model for the parameters of each process equipment in the desulfurization process, the converter process and the refining process; and configuring a single value range chart analysis model, a P chart analysis model, a trend chart analysis model, a compliance chart analysis model and a statistical analysis report for the parameters of each process equipment in the continuous casting process.

[0023] Furthermore, a sixth module is included, which is used to set a scaling factor for each process equipment parameter of the configuration compliance diagram analysis model to implement a scaling factor algorithm.

[0024] Furthermore, the scaling factor algorithm sets coordinate scale ranges for different range values ​​of the process equipment parameters, and then combines the linear transformation method to map different range values ​​to the same coordinate, so as to realize the same coordinate display of analysis results of different range intervals.

[0025] Furthermore, the scaling factor algorithm sets coordinate scale ranges for different range values ​​of the process equipment parameters, and then combines the linear transformation method to map different range values ​​to the same coordinate, so as to realize the same coordinate display of analysis results of different range intervals. Specifically, the method includes:

[0026] Query and obtain the parameters of each process equipment, and determine whether the parameters of each process equipment are empty. If so, add the process equipment parameters. Otherwise, determine whether the parameters of each process equipment are configured as a compliance diagram analysis model.

[0027] If the parameters of each process equipment are configured as a compliance diagram analysis model, it is determined whether the parameters of each process equipment have an upper limit value, otherwise the scaling factor algorithm calculation is not performed;

[0028] If each process equipment parameter has no upper limit value, determine whether each process equipment parameter has a lower limit value; if there is a lower limit value, use the preset qualified upper and lower limits as the coordinate scale range and perform linear transformation calculation to obtain the calculation result of the scaling factor algorithm, otherwise the scaling factor algorithm calculation is not performed;

[0029] If each process equipment parameter has an upper limit value, determine whether each process equipment parameter has a lower limit value; if there is a lower limit value, use the upper limit value and the lower limit value as the coordinate scale range and perform linear transformation calculation to obtain the calculation result of the scaling factor algorithm; otherwise, use the upper limit value and the preset qualified lower limit value as the coordinate scale range and perform scaling factor algorithm calculation.

[0030] Furthermore, the single value range chart analysis model and the P chart analysis model perform process quality monitoring and analysis on the measured values ​​of process equipment parameters with shifts or days as the measurement unit, the compliance chart analysis model performs process quality monitoring and analysis on the measured values ​​of process equipment parameters with furnaces as the analysis unit, and the trend chart analysis model and statistical analysis report perform process quality monitoring and analysis on the measured values ​​of process equipment parameters with a selected analysis time period.

[0031] Furthermore, collecting the measured values ​​of the parameters of each process equipment in each process based on the basic data structure of the parameters of each process equipment in each process specifically includes: collecting the measured values ​​of the parameters of each process equipment in each process at preset time intervals and performing data cleaning.

[0032] Compared with the prior art, the present invention has the following advantages: It provides a steelmaking process quality monitoring and analysis system that adaptively selects relevant algorithms to monitor and analyze process quality of various process equipment parameters in the desulfurization, converter, refining (LF, RH), and continuous casting processes of a long-process steelmaking workshop. The analysis results are then displayed in the form of charts, thereby providing process management and process operators with guidance for process operation improvements. The present invention can improve the operational skills of technicians in the steelmaking process, avoid and reduce the impact of various adverse factors, and control product quality fluctuations within an acceptable range, thereby providing technical support for lean production in enterprises and effectively improving the quality of steel products. The present invention is applicable to process quality monitoring and analysis of various processes in a steelmaking workshop. By constructing a process quality monitoring and analysis system for each steelmaking process, building a process equipment parameter data structure and analysis model, and implementing a scaling factor algorithm, a process quality monitoring and analysis model, and an adaptive process quality monitoring and analysis algorithm for each steelmaking process, the present invention provides feasible technical support for improving steelmaking process and product quality, thereby achieving lean production in steelmaking workshops. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0034] FIG1 is a flow chart of a scaling factor algorithm provided by an embodiment of the present invention.

[0035] FIG2 is an architecture diagram of a steelmaking process quality monitoring and analysis system provided by an embodiment of the present invention.

[0036] FIG3 is a flow chart of a steelmaking process quality monitoring and analysis method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0038] 1 to 3 , the present invention discloses a steelmaking process quality monitoring and analysis system, comprising:

[0039] An application layer, comprising an adaptive process quality monitoring and analysis module for each steelmaking process, wherein the process quality monitoring and analysis module is used to implement process quality monitoring and analysis during the steelmaking process;

[0040] Preferably, the steelmaking processes include: a desulfurization process, a converter process, a refining process, and a continuous casting process.

[0041] Preferably, the process quality monitoring and analysis module includes: a first module, a second module, a third module, a fourth module, a fifth module,

[0042] The first module is used to construct a basic data structure of parameters of each process equipment in each configurable steelmaking process and an analysis model of parameters of each process equipment; this solves the problem of parameter management of each process equipment in each process.

[0043] Specifically, first, a process quality monitoring and analysis system for each process of long-process steelmaking and an application methodology for process quality monitoring and analysis are constructed; then, a basic data structure for the process equipment parameters of each steelmaking process is constructed; then, based on the process equipment parameter data structure, combined with the process characteristics of each process equipment parameter, an analysis model and an analysis model display mode are set for the process equipment parameters of each process, thereby realizing the management of the process equipment parameters and analysis models of each process of the entire steelmaking process.

[0044] The present invention proposes a configurable process equipment parameter data structure and analysis model, which facilitates users to maintain and manage the huge process equipment parameters of long-process steelmaking, and also provides a guarantee for subsequent adaptive process quality monitoring and analysis of various steelmaking processes.

[0045] In a preferred embodiment, the construction of the basic data structure of each process equipment parameter of each configurable steelmaking process specifically includes: determining each process equipment parameter according to the process, unit, section, and steel type, and setting a baseline value, upper limit value and lower limit value for each process equipment parameter.

[0046] The second module is used to collect the actual measured values ​​of each process equipment in each process based on the basic data structure of the parameters of each process equipment in each process;

[0047] Furthermore, collecting the measured values ​​of the parameters of each process equipment in each process based on the basic data structure of the parameters of each process equipment in each process specifically includes: collecting the measured values ​​of the parameters of each process equipment in each process at preset time intervals and performing data cleaning.

[0048] The third module is used to adaptively select a process quality monitoring and analysis model for each process equipment parameter in each process based on the actual measured values ​​of the parameters of each process equipment in each process;

[0049] Preferably, the process quality monitoring and analysis model for adaptively selecting the parameters of each process equipment in each process based on the actual measured values ​​of each process equipment in each process specifically includes: configuring a single value range chart analysis model and a compliance chart analysis model for the parameters of each process equipment in the desulfurization process, the converter process and the refining process; and configuring a single value range chart analysis model, a P chart analysis model, a trend chart analysis model, a compliance chart analysis model and a statistical analysis report for the parameters of each process equipment in the continuous casting process.

[0050] The present invention realizes the unified maintenance and management of all process equipment parameters in the entire long-process steelmaking process, and prepares for the subsequent adaptive process quality monitoring and analysis of each steelmaking process.

[0051] Furthermore, the single value range chart analysis model and the P chart analysis model perform process quality monitoring and analysis on the measured values ​​of process equipment parameters with shifts or days as the measurement unit, the compliance chart analysis model performs process quality monitoring and analysis on the measured values ​​of process equipment parameters with furnaces as the analysis unit, and the trend chart analysis model and statistical analysis report perform process quality monitoring and analysis on the measured values ​​of process equipment parameters with a selected analysis time period.

[0052] Exemplarily, the SPC algorithm includes the single value range chart analysis model and the P chart analysis model.

[0053] Step 1: Adaptively obtain the configured basic data of process equipment parameters and display mode according to the analysis model, process, unit, section and steel grade;

[0054] Step 2: Based on the process equipment parameter data obtained in step 1, the actual measured values ​​of the process equipment parameters for the shift or the day are automatically collected and data preprocessing is performed, that is, the obtained data is judged to be null value. If it is a null value, the data is obtained again.

[0055] Step 3: Obtain the configured SPC subgroup constant values. If analyzing only one shift's production data, obtain a constant value for the subgroup capacity of 20; if analyzing one day's production data, obtain a constant value for the subgroup capacity of 40; if analyzing two days' production data, obtain a constant value for the subgroup capacity of 80. Performing process quality monitoring and analysis on a daily basis can monitor steelmaking quality data during a shift change, while performing process quality monitoring and analysis on a two-day basis can monitor steelmaking quality data during a shift change. Individual value range charts and P charts can collect and analyze actual performance data for a specific shift or day. Performing process quality monitoring and analysis on a shift basis can monitor steelmaking quality during that shift, while performing process quality monitoring and analysis on a daily basis can monitor steelmaking quality during that day.

[0056] Step 4: Calculate the drawing data based on the measured values ​​of the process equipment parameters and the constant values, and mark the measured values ​​on the graph for subsequent graphical display.

[0057] Step 5: Determine whether there is any quality abnormality data based on the point distribution, and mark the quality abnormality data for subsequent red display.

[0058] The present invention optimizes the SPC algorithm and expands the subgroup capacity from 25 to 100 through relevant calculations, thereby increasing the SPC algorithm analysis sample space and meeting the needs of large sample spaces for process quality monitoring and analysis. Empirical calculations show that one shift can produce 20 furnaces of molten steel, and 40 furnaces of molten steel can be smelted in a day. Therefore, the sample space with an atomic group capacity of 25 is not sufficient for daily process quality monitoring and analysis. By expanding the sample space to 100 through calculation, it can meet the quality analysis of 40 furnaces (one day) and 80 furnaces (two days) of molten steel, realizing the monitoring of molten steel quality fluctuations during shift production, thereby intervening and controlling related quality factors and improving the quality of molten steel produced during shift production.

[0059] Specifically, the SPC subgroup capacity is expanded from 25 to 100 to meet the requirements of process quality monitoring and analysis on a daily basis and to monitor the fluctuation of molten steel process quality during shift changes on the same day. The calculated SPC constants for the 25-100 subgroup capacity are shown in Table 1.

[0060] Table 1

[0061] Conformity Graph Algorithm:

[0062] Step 1: Adaptively obtain the standard values ​​and display modes of configured process equipment parameters based on the analysis model, process, unit, and section;

[0063] Step 2: Then adaptively collect the actual measured values ​​of the furnace process equipment parameters and perform data preprocessing, that is, perform null value judgment on the acquired data. If it is a null value, re-acquire the data.

[0064] Step 3: Then compare the measured values ​​of the process equipment parameters with the standard values ​​to determine whether each process equipment parameter is qualified, exceeds the upper limit, or exceeds the lower limit, and mark them accordingly;

[0065] Step 4: Finally, the scaling factor algorithm is introduced to map the parameter range values ​​of each process equipment to the same range through the scaling factor algorithm. The compliance diagram is analyzed based on the actual performance data of each furnace.

[0066] Trend chart algorithm:

[0067] Step 1: Adaptively obtain the standard values ​​and display modes of configured process equipment parameters based on the analysis model, process, unit, and section;

[0068] Step 2: Obtain the actual measured values ​​of the process equipment parameters during the period and perform data preprocessing, that is, perform null value judgment on the acquired data. If it is a null value, re-acquire the data.

[0069] Step 3: Compare the measured value with the standard value and mark the qualified, exceeded upper limit, and exceeded lower limit marks respectively for subsequent graphical display. Trend charts analyze the performance data over a period of time.

[0070] Statistical report algorithm:

[0071] Step 1: Adaptively obtain the basic data and display mode of the configured process equipment parameters based on the analysis model, process, unit, and section;

[0072] Step 2: Obtain the measured values ​​of process equipment parameters during this period and perform data preprocessing;

[0073] Step 3: Calculate the measured values: calculate the cumulative value, maximum value, minimum value, average value, and standard deviation. Statistical reports analyze the performance data over a period of time.

[0074] The fourth module is used to implement process quality monitoring and analysis of parameters of each process equipment in each step;

[0075] Specifically, the specific steps of realizing the adaptive process quality monitoring and analysis algorithm of the desulfurization process, converter process, refining process (LF refining, RH refining) and continuous casting process in the long-process steelmaking workshop include: first, obtaining the actual measured values ​​of the process equipment parameters of the analysis process and performing data preprocessing on the actual measured values, that is, performing a null value judgment on the obtained data, and if it is a null value, re-acquiring the data; then, according to the processing results of the obtained actual measured values ​​of the process equipment parameters, obtaining the analysis model and display model required for the process quality monitoring and analysis; then, according to the process equipment parameter analysis model and display model, performing process quality monitoring and analysis on the relevant process equipment parameters in the analysis process.

[0076] The analysis model and display model required for the process quality monitoring analysis obtained based on the obtained measured values ​​of the process equipment parameters specifically include:

[0077] All process parameter data for the steelmaking plant, known as basic data, is configured based on the process, unit, section number, and steel grade. This basic data includes standard values, analysis models, scaling factors, and display modes for these parameters. This data structure enables adaptive process quality monitoring and analysis for each process.

[0078] The specific steps are as follows:

[0079] Step 1: Get the measured values ​​of each process parameter. According to the measured values, the process, unit, section number and steel grade of the process parameter can be obtained.

[0080] Step 2: According to the measured values ​​of the process, unit, section number and steel type, the corresponding analysis model and display mode can be obtained in the configuration information.

[0081] Exemplarily, the specific steps include:

[0082] Step 1: Select the analysis model and analysis process, and then automatically obtain the process equipment parameters and display mode applicable to the model through the configured process equipment parameter basic data structure and analysis model;

[0083] Step 2: Automatically obtain corresponding performance data based on the acquired process equipment parameters and perform data cleaning;

[0084] Step 3: Since the converter process includes the front furnace area, back furnace area, and ladle area, and each area has corresponding process equipment parameters, the analysis model, analysis process, and analysis section must be determined before conducting converter process quality monitoring and analysis. The refining process includes LF refining and RH refining, each of which has corresponding process equipment parameters. Therefore, the analysis model, LF refining, and RH refining must be determined before conducting refining process quality monitoring and analysis.

[0085] Step 4: Based on the analysis model obtained in step 1, use the corresponding analysis model algorithm to perform quality monitoring analysis of the corresponding process.

[0086] The fifth module is used to display the analysis results of the fourth module.

[0087] Specifically, the analysis results are finally displayed using the E-CHART method and abnormal quality data are marked in red.

[0088] The present invention adaptively obtains the basic data and display mode of the corresponding process equipment parameters based on the analysis model; then adaptively collects the actual measured values ​​of the corresponding process equipment parameters; then uses the actual measured values ​​of the process equipment parameters and the basic data to perform relevant calculations, that is, adopts the corresponding analysis model to perform process quality analysis; finally, based on the calculation results, the process quality monitoring analysis is performed to obtain abnormal quality data and normal data for subsequent graphical display.

[0089] Specifically, the determination of abnormal data varies depending on the analysis model used:

[0090] 1. SPC model (single value range chart model and P chart model): Its abnormal data is the measured value exceeding the configured standard value range of the working parameter, or the measured value dot results on the chart have several consecutive points (such as 7 points) on one side, or several consecutive points (such as 7 points) have an upward or downward trend, or several points (two-thirds of the points) are concentrated in a narrow band.

[0091] 2. Conformity diagram model: Its abnormal data is the measured value that exceeds the configured standard value range of the working parameters.

[0092] 3. Trend chart analysis model: Its abnormal data is the measured value exceeding the configured standard value range of the working parameters.

[0093] Preferably, a sixth module is further included, and the sixth module is used to set a scaling factor for each process equipment parameter of the configuration compliance diagram analysis model to implement a scaling factor algorithm.

[0094] In one embodiment, the scaling factor algorithm sets coordinate scale ranges for different range values ​​of the process equipment parameters, and then combines the linear transformation method to map different range values ​​to the same coordinate, so as to realize the same coordinate display of analysis results of different range intervals.

[0095] Specifically, the scaling factor algorithm of the present invention maps the range values ​​of various process equipment parameters that vary significantly across different sections to the same coordinate interval through linear transformation for display and comparative analysis. This invention can be used not only in the field of process quality analysis and process quality monitoring, but also in other fields where comparative analysis of widely varying range values ​​is required.

[0096] In another embodiment, the scaling factor algorithm sets coordinate scale ranges for different range values ​​of the process equipment parameter, and then combines the linear transformation method to map the different range values ​​to the same coordinate, so as to realize the same coordinate display of the analysis results of different range intervals. Specifically, the method includes:

[0097] Query and obtain the parameters of each process equipment, and determine whether the parameters of each process equipment are empty. If so, add the process equipment parameters. Otherwise, determine whether the parameters of each process equipment are configured as a compliance diagram analysis model.

[0098] If the parameters of each process equipment are configured as a compliance diagram analysis model, it is determined whether the parameters of each process equipment have an upper limit value, otherwise the scaling factor algorithm calculation is not performed;

[0099] If each process equipment parameter has no upper limit value, determine whether each process equipment parameter has a lower limit value; if there is a lower limit value, use the preset qualified upper and lower limits as the coordinate scale range and perform linear transformation calculation to obtain the calculation result of the scaling factor algorithm, otherwise the scaling factor algorithm calculation is not performed;

[0100] If each process equipment parameter has an upper limit value, determine whether each process equipment parameter has a lower limit value; if there is a lower limit value, use the upper limit value and the lower limit value as the coordinate scale range and perform linear transformation calculation to obtain the calculation result of the scaling factor algorithm; otherwise, use the upper limit value and the preset qualified lower limit value as the coordinate scale range and perform scaling factor algorithm calculation.

[0101] For example, the preset upper limit of the qualified value is 22, the preset lower limit of the qualified value is 75, and the qualified coordinate scale range is [25,75], which can better display the compliance analysis results.

[0102] The scaling factor algorithm is divided into three cases for study based on the range of process equipment parameters:

[0103] The range value of the process equipment parameter has a lower limit and an upper limit: obtain the qualified coordinate scale range [25,75], then obtain the actual upper limit Max and lower limit Min of the process equipment parameter, and finally obtain the conversion result according to the linear transformation;

[0104] The range value of the process equipment parameter has a lower limit but no upper limit: obtain the qualified coordinate scale [25,100], then obtain the actual lower limit value Min of the process equipment parameter, and finally obtain the conversion result according to the linear transformation;

[0105] The range value of the process equipment parameter has an upper limit but no lower limit: obtain the qualified coordinate scale [0,75], then obtain the actual upper limit Max of the process equipment parameter, and finally obtain the conversion result based on linear transformation.

[0106] The present invention first collects the measured values ​​of the corresponding working parameters, and then uses the compliance diagram algorithm to perform process quality analysis based on the measured values, the configured standard values ​​and the scaling factors.

[0107] Step 1: Get the measured values, configured standard values ​​and scaling factors of the analysis parameters;

[0108] Step 2: Since the qualified scale is [25,75], the measured value collected needs to be mapped to the qualified scale of [25,75] according to the configured standard value and scaling factor of the industrial parameter, and the measured value is analyzed in the following three cases. Where A is the measured value of the industrial parameter and B is the scaling factor of the industrial parameter:

[0109] Case 1: According to the industrial parameter configuration information, it is found that the industrial parameters have upper and lower limits:

[0110] If the measured value of the industrial parameter is greater than the upper limit of the configuration information, the calculated value of the industrial parameter scale = (A-upper limit)*B+75, that is, the measured value of the industrial parameter exceeds the upper limit;

[0111] If the lower limit value of the configuration information ≤ the actual measured value of the industrial parameter ≤ the upper limit value of the configuration information, then the calculated value of the industrial parameter scale = (A-lower limit value)*B+25, that is, the actual measured value of the industrial parameter is qualified;

[0112] If the actual measured value of the industrial parameter is less than the lower limit value of the configuration information, the calculated value of the industrial parameter scale = (A-lower limit value)*B+25, that is, the actual measured value of the industrial parameter is qualified and exceeds the lower limit value.

[0113] Case 2: According to the industrial parameter configuration information, it is found that the industrial parameter has an upper limit but no lower limit:

[0114] If the measured value of the industrial parameter is greater than the upper limit of the configuration information, the calculated value of the industrial parameter scale = (A-upper limit)*B+75, that is, the measured value of the industrial parameter exceeds the upper limit;

[0115] If the actual measured value of the industrial parameter is less than or equal to the upper limit of the configuration information, then the scale calculation value = A*B, that is, the actual measured value of the industrial parameter is qualified.

[0116] Case 3: According to the industrial parameter configuration information, it is found that the industrial parameter has a lower limit but no upper limit:

[0117] If the measured value of the working parameter is greater than or equal to the lower limit of the configuration information, the scale calculation value = (A-lower limit)*B+25, that is, the measured value of the working parameter is qualified;

[0118] If the actual measured value of the industrial parameter is less than the lower limit value of the configuration information, the scale calculation value = (A-lower limit value)*B+25, that is, the actual measured value of the industrial parameter is qualified and exceeds the lower limit value.

[0119] Preferably, the application layer also includes an edge cloud platform, which includes a physical machine, a virtual machine, a container, a storage module, a load balancing module, a relational database module, a real-time database module, an AI reasoning module, and the like.

[0120] The control layer includes control modules corresponding to the steelmaking processes in the application layer; for example, such as the desulfurization intelligent control module, the converter intelligent control module, the refining intelligent control module, the continuous casting intelligent control module, the steelmaking lot platform and the edge module cube, the edge module includes an industrial gateway module, a stream computing module, a real-time database module, and a message middleware module.

[0121] The equipment layer includes hardware devices corresponding to the adaptive process quality monitoring and analysis modules of each steelmaking process in the application layer, such as RFID radio frequency identification equipment, handheld terminals, cameras, sensors, basic automation equipment, database server equipment, workstation-related equipment, two-dimensional barcode equipment, production line equipment, production material equipment, logistics equipment, inspection and testing equipment, robots, public auxiliary equipment, etc.

[0122] The present invention realizes process quality monitoring and analysis of the desulfurization process, converter process, refining process (LF refining, RH refining) and continuous casting process in the long-process steelmaking workshop, provides direction for process operation improvement for process management and process operators, and provides technical support for the company's lean production, thereby effectively improving the quality of steelmaking products.

[0123] The core content of the present invention lies in: production process data integration management, analysis model optimization and process quality monitoring analysis and judgment.

[0124] In terms of realizing the integrated management of production process data, the present invention designs the basic data structure of the process equipment parameters of each steelmaking process and the process equipment parameter analysis model based on the principle of configurability, so as to realize the efficient management of the process equipment parameters of each process and its analysis model, and prepare for the subsequent adaptive process quality monitoring and analysis of each process.

[0125] In terms of the analysis model, the SPC algorithm has a maximum subgroup capacity of 25. Therefore, when performing process quality monitoring and analysis, only molten steel produced from 25 furnaces can be monitored and analyzed. This present invention optimizes the SPC algorithm and expands its subgroup capacity to 100, enabling daily process quality monitoring and analysis, and enabling quality monitoring and analysis of molten steel during shift changes. Furthermore, because the ranges of values ​​for different process equipment parameters in different processes can vary significantly, the analysis results of the compliance diagram algorithm are difficult to display within the same coordinate system. This present invention proposes a scaling factor algorithm to display process equipment parameter values ​​from different ranges within the same coordinate system.

[0126] SPC (Statistical Process Control) is a process control tool that utilizes mathematical statistics. It analyzes and evaluates production processes, promptly identifying signs of systemic factors based on feedback, and taking measures to eliminate their impact, thereby maintaining the process in a controlled state, influenced only by random factors, to achieve quality control.

[0127] In terms of implementing the process quality monitoring, analysis and judgment algorithm, the present invention breaks through the data barriers between L1, L2 and L3, integrates the production data of process equipment parameters of each process collected by the three, combines with the optimized analysis model, and adaptively performs process quality monitoring and analysis of each process.

[0128] Based on the Six Sigma management concept, this invention establishes a process quality monitoring and analysis system and application methodology for each steelmaking process. This system conducts process quality monitoring and analysis on production process data from each process and equipment in the long-process steelmaking process, and displays abnormal quality data in red, thereby providing concrete and feasible technical support for improving the quality of the steelmaking process and enhancing the quality of steelmaking products. The Six Sigma management concept is a quality management method based on data analysis, aiming to achieve quality stability and optimization by reducing process variability. The name Six Sigma comes from the Greek letter "σ", which represents standard deviation and is a metric for measuring process variability. The core concept of Six Sigma management is "customer-centric, data-based, pursuing zero defects, and continuous improvement." In this concept, customers are the center of the enterprise, and all corporate activities should be centered on customer needs. Data is the foundation of Six Sigma management, and enterprises should use data analysis to determine the nature of problems and their root causes in order to develop targeted improvement measures.

[0129] Based on the same inventive concept, the present invention also discloses a process quality monitoring and analysis method in a steelmaking process, comprising:

[0130] Construct the basic data structure of configurable parameters of each process equipment in each steelmaking process;

[0131] Collect the measured values ​​of each process equipment in each process based on the basic data structure of each process equipment parameter;

[0132] Adaptively select the process quality monitoring and analysis model for each process equipment parameter in each process based on the measured values ​​of each process equipment parameter;

[0133] Realize process quality monitoring and analysis of parameters of each process equipment in each procedure;

[0134] Present the analysis results.

[0135] The method embodiments can be implemented one-to-one with the aforementioned system embodiments, and will not be described in detail here.

[0136] The core content of this invention lies in the integrated management of production process data, optimization of analysis models, and process quality monitoring, analysis, and decision-making. To achieve this, the present invention, based on the principle of configurability, designs a basic data structure for process equipment parameters and an analysis model for process equipment parameters in each steelmaking process. This enables efficient management of process equipment parameters and their analysis models for each process, and paves the way for subsequent adaptive process quality monitoring and analysis for each process. The present invention proposes a scaling factor algorithm that uses linear transformation to map the range values ​​of process equipment parameters with significant differences within different segments to the same coordinate interval for display and comparative analysis. This algorithm is applicable not only in the field of process quality monitoring and analysis, but also in other fields requiring comparative analysis of values ​​with significantly different ranges. The present invention optimizes the SPC algorithm by expanding the subgroup capacity from 25 to 100 through correlation calculations, thereby increasing the SPC algorithm's analysis sample space and accommodating large sample spaces for process quality monitoring and analysis. Empirical calculations show that if a shift produces 20 heats of molten steel, then 40 heats can be produced per day. Therefore, a sample space with an atomic group capacity of 25 is insufficient for daily process quality monitoring and analysis. By expanding the sample space to 100 by calculation, it can meet the quality analysis of 40 furnaces (one day) and 80 furnaces (two days) of molten steel, and realize the monitoring of the fluctuation of molten steel quality during shift production, so as to intervene and control the relevant quality factors and improve the quality of molten steel during shift production. The present invention proposes a configurable process equipment parameter data structure and analysis model, which is convenient for users to maintain and manage the huge process equipment parameters of long-process steelmaking, and also provides a guarantee for the subsequent adaptive process quality monitoring and analysis of each steelmaking process. The present invention realizes the process quality monitoring and analysis of the desulfurization process, converter process, refining process (LF refining, RH refining) and continuous casting process of the long-process steelmaking workshop, provides direction for process operation improvement for process management and process operators, provides technical support for the lean production of enterprises, and effectively improves the quality of steelmaking products.

[0137] Based on the same inventive concept, the present invention also discloses an electronic device, which may include: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus. The processor can call logic instructions in the memory to implement a steelmaking process quality monitoring and analysis system, including:

[0138] An application layer, comprising an adaptive process quality monitoring and analysis module for each steelmaking process, wherein the process quality monitoring and analysis module is used to implement process quality monitoring and analysis during the steelmaking process;

[0139] A control layer, comprising control modules corresponding to various steelmaking processes in the application layer;

[0140] The equipment layer includes hardware devices corresponding to the adaptive process quality monitoring and analysis modules of each steelmaking process in the application layer.

[0141] In addition, the logical instructions in the above-mentioned memory can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0142] On the other hand, an embodiment of the present invention further provides a computer program product, comprising a computer program stored on a non-transitory computer-readable storage medium, wherein the computer program comprises program instructions. When the program instructions are executed by a computer, the computer can implement a steelmaking process quality monitoring and analysis system, comprising:

[0143] An application layer, comprising an adaptive process quality monitoring and analysis module for each steelmaking process, wherein the process quality monitoring and analysis module is used to implement process quality monitoring and analysis during the steelmaking process;

[0144] A control layer, comprising control modules corresponding to various steelmaking processes in the application layer;

[0145] The equipment layer includes hardware devices corresponding to the adaptive process quality monitoring and analysis modules of each steelmaking process in the application layer.

[0146] In another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, a steelmaking process quality monitoring and analysis system is implemented, including:

[0147] An application layer, comprising an adaptive process quality monitoring and analysis module for each steelmaking process, wherein the process quality monitoring and analysis module is used to implement process quality monitoring and analysis during the steelmaking process;

[0148] A control layer, comprising control modules corresponding to various steelmaking processes in the application layer;

[0149] The equipment layer includes hardware devices corresponding to the adaptive process quality monitoring and analysis modules of each steelmaking process in the application layer.

[0150] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0151] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A steelmaking process quality monitoring and analysis system, characterized in that: include: An application layer, the application layer includes an adaptive process quality monitoring and analysis module for each steelmaking process, the process quality monitoring and analysis module is used to implement process quality monitoring and analysis in the steelmaking process; A control layer, the control layer comprising control modules corresponding to various steelmaking processes in the application layer; The equipment layer includes hardware devices corresponding to the adaptive process quality monitoring and analysis modules of each steelmaking process in the application layer.

2. A steelmaking process quality monitoring and analysis system as claimed in claim 1, characterized in that: The steelmaking processes include: a desulfurization process, a converter process, a refining process, and a continuous casting process.

3. A steelmaking process quality monitoring and analysis system as claimed in claim 2, characterized in that: The process quality monitoring and analysis module includes: a first module, a second module, a third module, a fourth module, and a fifth module. The first module is used to construct a basic data structure of parameters of each process equipment in each configurable steelmaking process; The second module is used to collect the actual measured values ​​of each process equipment in each process based on the basic data structure of each process equipment parameter in each process; The third module is used to adaptively select a process quality monitoring and analysis model for each process equipment parameter in each process step based on the actual measured values ​​of each process equipment parameter in each process step; The fourth module is used to implement process quality monitoring and analysis of process equipment parameters in each process step; The fifth module is used to display the analysis results of the fourth module.

4. A steelmaking process quality monitoring and analysis system as claimed in claim 3, characterized in that: The construction of the basic data structure of each process equipment parameter of each configurable steelmaking process specifically includes: determining each process equipment parameter according to the process, unit, section, and steel type, and setting a reference value, an upper limit value, and a lower limit value for each process equipment parameter.

5. A steelmaking process quality monitoring and analysis system as claimed in claim 3, characterized in that: The process quality monitoring and analysis model for adaptively selecting the parameters of each process equipment in each process based on the actual measured values ​​of each process equipment in each process step specifically includes: configuring a single value range chart analysis model and a compliance chart analysis model for the parameters of each process equipment in the desulfurization process, the converter process and the refining process; and configuring a single value range chart analysis model, a P chart analysis model, a trend chart analysis model, a compliance chart analysis model and a statistical analysis report for the parameters of each process equipment in the continuous casting process.

6. A steelmaking process quality monitoring and analysis system as claimed in claim 5, characterized in that: It also includes a sixth module, which is used to set a scaling factor for each process equipment parameter of the configuration compliance diagram analysis model to implement a scaling factor algorithm.

7. A steelmaking process quality monitoring and analysis system as claimed in claim 6, characterized in that: The scaling factor algorithm sets the coordinate scale range for different range values ​​of the process equipment parameters respectively, and then combines the linear transformation method to map the different range values ​​to the same coordinate, so as to realize the same coordinate display of the analysis results of different range intervals.

8. A steelmaking process quality monitoring and analysis system as claimed in claim 7, characterized in that: The scaling factor algorithm sets coordinate scale ranges for different range values ​​of the process equipment parameters, and then combines the linear transformation method to map different range values ​​to the same coordinate, so as to realize the same coordinate display of analysis results of different range intervals. Specifically, it includes: Query and obtain the parameters of each process equipment, and determine whether each process equipment parameter is empty. If so, add the process equipment parameter. Otherwise, determine whether each process equipment parameter is configured as a compliance diagram analysis model. If each process equipment parameter is configured as a compliance diagram analysis model, it is determined whether each process equipment parameter has an upper limit value, otherwise the scaling factor algorithm calculation is not performed; If the parameters of each process equipment have no upper limit value, determine whether the parameters of each process equipment have a lower limit value; if there is a lower limit value, use the preset qualified upper and lower limits as the coordinate scale range and perform linear transformation calculation. The calculation result of the scaling factor algorithm is obtained, otherwise the scaling factor algorithm calculation is not performed; If each process equipment parameter has an upper limit value, determine whether each process equipment parameter has a lower limit value; if there is a lower limit value, use the upper limit value and the lower limit value as the coordinate scale range and perform linear transformation calculation to obtain the calculation result of the scaling factor algorithm; otherwise, use the upper limit value and the preset qualified lower limit value as the coordinate scale range and perform scaling factor algorithm calculation.

9. A steelmaking process quality monitoring and analysis system as claimed in claim 3, characterized in that: The single value range chart analysis model and the P chart analysis model perform process quality monitoring and analysis on the measured values ​​of process equipment parameters with shifts or days as the measurement unit, the compliance chart analysis model performs process quality monitoring and analysis on the measured values ​​of process equipment parameters with furnaces as the analysis unit, and the trend chart analysis model and statistical analysis report perform process quality monitoring and analysis on the measured values ​​of process equipment parameters with a selected analysis time period.

10. A steelmaking process quality monitoring and analysis system as claimed in claim 3, characterized in that: The collecting the measured values ​​of the parameters of each process equipment in each process based on the basic data structure of the parameters of each process equipment in each process specifically includes: collecting the measured values ​​of the parameters of each process equipment in each process at preset intervals and performing data cleaning.

Images