Method and device for analyzing correlation between steelmaking process parameters and user objection

Abstract

The invention discloses a correlation analysis method and device for steelmaking process parameters and user objection, and relates to the technical field of intelligent manufacturing. The relation between each value and the value grade of the steelmaking process parameters is described by constructing the membership relation of single steelmaking process parameters and utilizing the fuzzy membership relation; the fuzzy membership relations of all the steelmaking process parameters are combined to obtain the membership relation matrix of the single steel coil, the comprehensive evaluation can consider the influence of the multiple steelmaking process parameters on the quality of the steel coil, and then the characterization quantity of the single steel coil belonging to different value grades is obtained through weighted aggregation; according to the method, the interaction among the steelmaking process parameters is integrated into the correlation evaluation, so that the state judgment of all the steelmaking process parameters of the steel coil is realized, the one-sidedness of representing the quality of the steel coil by a single process parameter is overcome, and the comprehensive analysis of the correlation between the steelmaking process parameters and user objection is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent manufacturing, and particularly relates to a method, device, equipment and medium for analyzing the correlation between steelmaking process parameters and user objections. Background Art

[0002] The correlation analysis between the steelmaking process and user objections is an important link in improving steelmaking quality. User objections usually manifest as the classification of the quality of products put forward by users; user objections usually reflect potential problems in the performance, quality or cost of the final product, and these problems can often be traced back to the control and optimization of specific process parameters; by systematically analyzing the relationship between the steelmaking process and user objections, the key process factors affecting product quality can be more accurately identified, so as to make targeted improvements, and finally significantly improve steelmaking quality and enhance customer satisfaction.

[0003] At present, the analysis of user objections is usually based on the fuzzy production experience of a single process parameter, which mainly includes several processes such as clarifying the analysis target, collecting fuzzy production experience, analyzing user objections, establishing a correlation model, and optimizing process parameters; clarifying the analysis target means analyzing user objections based on which specific single process parameter; collecting fuzzy production experience is to collect the fuzzy production experience related to this process parameter, and this experience may come from multiple aspects such as actual observations in the production process, historical data, employee feedback, and expert opinions; analyzing user objections, user objections may come from multiple aspects such as product quality, production efficiency, and delivery time, but here mainly focus on the objections related to a single process parameter; establishing a correlation model is to establish a correlation model between the process parameter and user objections, and this model can be methods such as regression analysis and correlation analysis based on statistical data, or judgment based on expert knowledge and experience; finally, optimize the process parameter. According to the analysis results of the correlation model, the process parameter can be optimized, and the purpose of optimization is usually to improve product quality, reduce production costs, and improve production efficiency, etc.

[0004] However, when analyzing user objections based on the fuzzy production experience of a single process parameter, this analysis process is likely to ignore the interaction between process parameters and the comprehensive impact on the final quality, so that the correlation between the analyzed steelmaking process parameters and user objections usually represents the correlation between a single process parameter and user objections, resulting in the judgment result being difficult to comprehensively represent the correlation between steelmaking process parameters and user objections, and it is difficult to meet the actual application requirements of high-quality steelmaking process optimization. Summary of the Invention

[0005] An embodiment of the present invention provides a method and device for analyzing the correlation between steelmaking process parameters and user objections, which can solve the problem in the prior art that the existing methods at the present stage are prone to ignoring the interaction between process parameters and the comprehensive impact on the final quality, so that the correlation between the analyzed steelmaking process parameters and user objections usually represents the correlation between a single process parameter and user objections, resulting in the judgment result being difficult to comprehensively represent the correlation between steelmaking process parameters and user objections.

[0006] An embodiment of the present invention provides a method for analyzing the correlation between steelmaking process parameters and user objections, including the following steps: Obtain various steelmaking process parameters of the steel coil. Each steelmaking process parameter has multiple values, and preliminarily divide the multiple values corresponding to each steelmaking process parameter into each value level; Calculate the multiple values of each steelmaking process parameter as the independent variable of the cosine function, and use the calculated result as the membership value of the multiple values of the corresponding steelmaking process parameter belonging to each value level. Set the membership value of the multiple values of each steelmaking process parameter belonging to each value level as the fuzzy membership relationship of each steelmaking process parameter; wherein, the value levels of the steelmaking process parameter include excellent, good, and poor; Merge the fuzzy membership relationships of all steelmaking process parameters to obtain the membership relationship matrix of a single steel coil; wherein, each row of the membership relationship matrix represents a steelmaking process parameter, each column represents a value level, and the elements in the membership relationship matrix represent the probability that the value of the steelmaking process parameter belongs to the corresponding value level; Weight and aggregate the elements in each column of the membership relationship matrix to obtain the fuzzy characterization quantity of a single steel coil belonging to different value levels, and analyze the correlation between the steelmaking process parameters and user objections according to the fuzzy characterization quantity.

[0007] Preferably, the step of preliminarily dividing the multiple values corresponding to each steelmaking process parameter into each value level includes: Obtain all steelmaking process parameters of the steel coil , and count the distribution relationship between each steelmaking process parameter and the unqualified rate feedback by users, as well as the production experience of experts in steelmaking, and preliminarily divide the multiple values corresponding to each steelmaking process parameter into three levels of excellent, good, and poor.

[0008] Preferably, the construction of the fuzzy membership relationship of each steelmaking process parameter includes: Calculate the multiple values of each steelmaking process parameter as the independent variable of the cosine function, and use the calculated result as the membership value of the multiple values of the corresponding steelmaking process parameter belonging to each value level, that is, represent each steelmaking process parameter distribution to construct each steelmaking process parameter The fuzzy membership relationship is expressed as: ; Where: Represents the steelmaking process parameter Value Of the membership relationship; Represents The value belonging to the poor; Represents The value belonging to the good; Represents The value belonging to the excellent; The larger the value, the greater the probability of belonging to this level.

[0009] Preferably, obtaining the fuzzy characterization quantity of a single steel coil belonging to different value levels includes: Summarize the membership relationships of all steelmaking process parameters corresponding to a single steel coil to obtain the membership relationship matrix of the single steel coil, expressed as: ; Where: Represents the number of steelmaking process parameters; the Row of , And Respectively represent the membership values of the th parameter, corresponding to , And ; Based on the membership relationship matrix of the single steel coil, construct the fuzzy rule of the single steel coil, expressed as: ; Where: , And Respectively represent the values of the steel coil belonging to the three levels of poor, good and excellent; the larger the value, the greater the probability of belonging to this level; Where the value belonging to each level is expressed as: ; Where: Represents the number of steelmaking process parameters of the steel coil; Represents the th process parameter of the steel coil belonging to the rd level of membership value; Represents the value of the steel coil belonging to the th level.

[0010] Preferably, the analysis of the correlation between steelmaking process parameters and user objections includes: Regarding the correlation between the subordination of steel coils to poor quality and user objections, the value of the subordination of steel coils with user objections to poor quality is large; Regarding the correlation between the subordination of steel coils to excellent quality and user objections, the value of the subordination of steel coils with user objections to excellent quality is small; Regarding the correlation between the subordination of steel coils to excellent or poor quality and user objections, the value of the subordination of steel coils with user objections to excellent quality is small, and the value of the subordination to poor quality is large; for steel coils without user objections, the value of the subordination to excellent quality is large, and the value of the subordination to poor quality is small.

[0011] The embodiment of the present invention also provides an analysis device for the correlation between steelmaking process parameters and user objections, including: A parameter acquisition module, configured to acquire various steelmaking process parameters of steel coils. Each steelmaking process parameter has multiple values, and the multiple values corresponding to each steelmaking process parameter are initially divided into each value level; A membership relationship construction module, configured to calculate the multiple values of each steelmaking process parameter as the independent variable of a cosine function, and use the calculated result as the membership value of the multiple values of the corresponding steelmaking process parameter belonging to each value level. Set the membership value of the multiple values of each steelmaking process parameter belonging to each value level as the fuzzy membership relationship of each steelmaking process parameter; wherein, the value levels of the steelmaking process parameters include excellent, good, and poor; A parameter characterization module, configured to merge the fuzzy membership relationships of all steelmaking process parameters to obtain a membership relationship matrix of a single steel coil; wherein, each row of the membership relationship matrix represents a steelmaking process parameter, each column represents a value level, and the elements in the membership relationship matrix represent the probability that the value of the steelmaking process parameter belongs to the corresponding value level; An analysis module, configured to perform weighted aggregation on the elements in each column of the membership relationship matrix to obtain a fuzzy characterization quantity of a single steel coil belonging to different value levels, and analyze the correlation between the steelmaking process parameters and user objections according to the fuzzy characterization quantity.

[0012] The embodiment of the present invention also provides an electronic device, including a memory and a processor; The memory is used to store a computer program; The processor, when executing the computer program stored in the memory, implements the steps of the above-mentioned method for analyzing the correlation between steelmaking process parameters and user objections.

[0013] The embodiment of the present invention also provides a computer-readable storage medium, used to store a computer program, and when the computer program is executed by a processor, it implements the steps of the above-mentioned method for analyzing the correlation between steelmaking process parameters and user objections.

[0014] An embodiment of the present invention provides a method and device for analyzing the correlation between steelmaking process parameters and user objections. Compared with the prior art, the beneficial effects are as follows: In the present invention, the distribution of the cosine function is used for the distribution of each steelmaking process parameter, and the probability that multiple values of each steelmaking process parameter belong to each value level is set as the fuzzy membership relationship of each steelmaking process parameter; by using the fuzzy membership relationships of all steelmaking process parameters, fuzzy rules are constructed, and a quantitative standard representing all parameters of the steel coil is established to construct a characterization quantity of the steelmaking process parameters, so as to analyze the correlation between the steelmaking process parameters and user objections; in this process, by constructing the membership relationship of a single steelmaking process parameter, the fuzzy membership relationship is used to describe the relationship between each value of the steelmaking process parameter and the value level, and by combining the fuzzy membership relationships of all steelmaking process parameters, a membership relationship matrix of a single steel coil is obtained. This comprehensive evaluation can consider the influence of multiple steelmaking process parameters on the quality of the steel coil, and then through weighted aggregation, a characterization quantity of a single steel coil belonging to different value levels is obtained to incorporate the interaction between the steelmaking process parameters into the evaluation of the correlation, so as to realize the state determination of all steelmaking process parameters of the steel coil, overcome the one-sidedness of using a single process parameter to characterize the quality of the steel coil, and thus realize a comprehensive analysis of the correlation between the steelmaking process parameters and user objections. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a schematic overall flow chart of a method for analyzing the correlation between steelmaking process parameters and user objections provided by an embodiment of the present invention; Figure 2 is a schematic diagram for establishing the membership relationship of a single process parameter based on fuzzy for a method for analyzing the correlation between steelmaking process parameters and user objections provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] In order to make the above objects, features and advantages of the present invention more obvious and understandable, the following detailed description of the specific embodiments of the present invention will be given with reference to the accompanying drawings. Many specific details are set forth in the following description in order to fully understand the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0017] See Figure 1, an embodiment of the present invention provides a method for analyzing the correlation between steelmaking process parameters and user objections. First, the steelmaking process parameters are classified according to expert experience or statistical results of numbers; then, a membership function for a single process parameter is established, and a quantitative evaluation criterion for the quality of the entire steel coil is established based on fuzzy rules; finally, based on the characterization quantity of the steel coil quality, the correlation between the process parameters and user objections is analyzed; it can overcome the one-sidedness of a single process parameter in characterizing the quality of the steel coil and realize a comprehensive analysis of the correlation between the steelmaking process and user objections; specifically, it includes the following steps: Step S1: Establish a grading rule for a single steelmaking process parameter and construct a fuzzy membership relationship for a single steelmaking process parameter. As Figure 2 shown, it specifically includes:

[0018] Step S11: Statistically analyze the distribution relationship between each steelmaking process parameter and the unqualified rate of user feedback, as well as the production experience of experts in steelmaking.

[0019] Step S12: Whether the value of the steelmaking process parameter is excellent can be judged according to the unqualified rate, and it can be specifically expressed as: .

[0020] Where: and respectively represent the unqualified rates of the two values of the steelmaking process parameter and ; in the first case, it is determined that the value is better than the value ; in the second case, it is determined that the value is better than the value .

[0021] Step S13: According to the distribution of each steelmaking process parameter and user feedback, divide the values of the steelmaking process into three grades, namely excellent, good, and poor.

[0022] Step S14: Apply the distribution of the cosine function to the distribution of each process parameter to construct the membership relationship of the value of each steelmaking process parameter. The specific process can be expressed as: .

[0023] Where: represents the membership relationship of the value of the steelmaking process parameter ; represents the value belonging to poor; represents the value belonging to good; represents The membership value belonging to "good" has a larger value, indicating a greater probability of belonging to this level.

[0024] Step S2: Construct fuzzy rules for a single coil based on the membership relationships of all steelmaking process parameters. Specifically, it includes:

[0025] Step S21: Summarize the membership relationships of all steelmaking process parameters of a single coil to obtain a membership relationship matrix describing the coil, which can be expressed as: .

[0026] Where: represents the number of steelmaking process parameters; the th row of , and respectively represent the membership values of the th parameter, corresponding to , and in the above formula respectively.

[0027] Step S22: Based on the membership relationship matrix, construct fuzzy rules for a single coil, which can be specifically expressed as: .

[0028] Where: , and respectively represent the values of the coil belonging to the three levels of "poor", "good" and "excellent". The larger the value, the greater the probability of belonging to this level.

[0029] Among them, the value belonging to each level can be specifically expressed as: .

[0030] Where: represents the number of steelmaking process parameters of this coil; represents the membership value of the th process parameter of this coil belonging to the th level; represents the value of this coil belonging to the th level.

[0031] Step S3: A method for analyzing the correlation between steelmaking process parameters and user objections based on unified indicators. Specifically, it includes:

[0032] Step S31: Construct a correlation analysis of the coil belonging to "poor" and user objections. For coils with user objections, the values of their belonging to "poor" are generally larger.

[0033] Step S32: Construct the correlation analysis of the steel coil belonging to excellent and user objections. For the steel coils with user objections, the values of their belonging to excellent are generally small.

[0034] Step S33: Construct the correlation analysis of the steel coil belonging to poor, excellent and user objections. For the steel coils with user objections, the values of their belonging to excellent are generally small and the values of their belonging to poor are generally large. For the steel coils without user objections, the values of their belonging to excellent are generally large and the values of their belonging to poor are generally small.

[0035] The present invention establishes a characterization method for a single steelmaking process parameter by integrating expert experience and data statistical results, and then constructs a unified index system for comprehensively characterizing multiple process parameters, classifying the conditions of all process parameters into characterization quantities; through the correlation analysis between the characterization quantities and user objections, it effectively makes up for the one-sidedness of single-parameter analysis, improves the credibility and applicability of the analysis results, and thus provides a scientific basis for the optimization of the steelmaking process in steel coil production.

[0036] The present invention statistically analyzes the change trend of the steelmaking process parameters of steel coils and divides them into multiple levels according to production experience; constructs a fuzzy membership function to assign scores to each process parameter belonging to each level; constructs fuzzy rules, comprehensively combines the level scores of all process parameters of each steel coil, and establishes a quantitative standard for characterizing all parameters of the steel coil; based on the quantitative characterization of the steel coil parameters, analyzes the correlation between the steelmaking process parameters and user objections; compared with the prior art, the present invention overcomes the one-sidedness of using a single process parameter to characterize the quality of steel coils, constructs a characterization quantity that can describe all process parameters, and realizes a method for comprehensively analyzing the correlation between steelmaking process parameters and user objections.

[0037] The method for analyzing the correlation between steelmaking process parameters and user objections based on fuzzy in the present invention constructs a unified index system for comprehensively characterizing multiple process parameters, classifies the conditions of all process parameters into characterization quantities, and through the correlation analysis between the characterization quantities and user objections, can effectively make up for the deficiencies of single-parameter analysis, improve the credibility and applicability of the analysis results, and thus provide a scientific basis for the optimization of the steelmaking process.

[0038] The present invention constructs the membership relationship of a single steelmaking process parameter, characterizes the fuzzy expert experience with a clear membership relationship; constructs a quantitative standard from a single steelmaking process parameter to the entire steel coil, realizes the determination of the states of all process parameters of the steel coil, and overcomes the one-sidedness of using a single process parameter to characterize the quality of steel coils; constructs a quality characterization quantity of process parameters based on the quantitative standard, and realizes the analysis of comprehensively analyzing the correlation between steelmaking process parameters and user objections.

[0039] The embodiment of the present invention also provides an apparatus for analyzing the correlation between steelmaking process parameters and user objections, including: A parameter acquisition module, configured to acquire various steelmaking process parameters of a steel coil. Each steelmaking process parameter has multiple values, and the multiple values corresponding to each steelmaking process parameter are initially classified into respective value levels.

[0040] A membership relationship construction module, configured to calculate the multiple values of each steelmaking process parameter as the independent variables of a cosine function, and use the obtained calculation results as the membership values of the multiple values of the corresponding steelmaking process parameter belonging to each value level. Set the membership values of the multiple values of each steelmaking process parameter belonging to each value level as the fuzzy membership relationship of each steelmaking process parameter; wherein, the value levels of the steelmaking process parameters include excellent, good, and poor.

[0041] A parameter characterization module, configured to merge the fuzzy membership relationships of all steelmaking process parameters to obtain a membership relationship matrix of a single steel coil; wherein, each row of the membership relationship matrix represents a steelmaking process parameter, each column represents a value level, and the elements in the membership relationship matrix represent the probability that the value of the steelmaking process parameter belongs to the corresponding value level.

[0042] An analysis module, configured to perform weighted aggregation on the elements in each column of the membership relationship matrix to obtain fuzzy characterization quantities of a single steel coil belonging to different value levels, and analyze the correlation between the steelmaking process parameters and user objections based on the fuzzy characterization quantities.

[0043] An embodiment of the present invention further provides an electronic device, including a memory and a processor.

[0044] The memory is used to store a computer program.

[0045] When the processor is used to execute the computer program stored in the memory, it implements the steps of a method for analyzing the correlation between steelmaking process parameters and user objections as described above.

[0046] An embodiment of the present invention further provides a computer-readable storage medium, configured to store a computer program, and when the computer program is executed by a processor, it implements the steps of a method for analyzing the correlation between steelmaking process parameters and user objections as described above.

[0047] The above embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several deformations and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the appended claims.

Claims

1. A method for analyzing the correlation between steelmaking process parameters and user objections, characterized in that: The following steps are involved: Acquire multiple steelmaking process parameters of the steel coil, each steelmaking process parameter has multiple values, and preliminarily classify the multiple values ​​corresponding to each steelmaking process parameter into various value levels; The multiple values ​​of each steelmaking process parameter are calculated as independent variables of the cosine function, and the calculated results are used as the membership values ​​of the multiple values ​​of the corresponding steelmaking process parameter belonging to each value level, and the membership values ​​of the multiple values ​​of each steelmaking process parameter belonging to each value level are set as the fuzzy membership relationship of each steelmaking process parameter; wherein the value levels of the steelmaking process parameter include excellent, good and poor; The fuzzy membership relationships of all steelmaking process parameters are merged to obtain a membership matrix of a single steel coil; wherein each row of the membership matrix represents a steelmaking process parameter, each column represents a value level, and the elements in the membership matrix represent the probability that the steelmaking process parameter value belongs to the corresponding value level; The elements of each column in the membership matrix are weighted and aggregated to obtain the fuzzy characterization of a single steel coil belonging to different value levels. The correlation between steelmaking process parameters and user objections is analyzed based on the fuzzy characterization.

2. The method for analyzing the correlation between steelmaking process parameters and user objections according to claim 1, characterized in that: The multiple values ​​corresponding to each steelmaking process parameter are initially divided into various value levels, including: Get all steelmaking process parameters of steel coils , statistics of each steelmaking process parameter The distribution relationship between the unqualified rate reported by users and the production experience of experts in steelmaking is used to calculate the distribution relationship between each steelmaking process parameter. The corresponding multiple values ​​are initially divided into three levels: good, excellent and poor.

3. The method for analyzing the correlation between steelmaking process parameters and user objections according to claim 2, characterized in that: The construction of the fuzzy membership relationship of each steelmaking process parameter includes: The multiple values ​​of each steelmaking process parameter are calculated as the independent variables of the cosine function, and the calculated results are used as the membership values ​​of the multiple values ​​of the corresponding steelmaking process parameter belonging to each value level, that is, the multiple values ​​of each steelmaking process parameter are characterized by the following formula: to construct the distribution of each steelmaking process parameter The fuzzy membership relationship is expressed as: ； in: Indicates steelmaking process parameters Value affiliation; express The value belonging to the difference; express Belongs to the value of good; express Belongs to the optimal value; The larger the value, the greater the probability of belonging to that level.

4. The method for analyzing the correlation between steelmaking process parameters and user objections according to claim 3, characterized in that: The method of obtaining the fuzzy characterization quantity of a single steel coil belonging to different value levels includes: The membership relationships of all steelmaking process parameters corresponding to a single steel coil are summarized to obtain the membership relationship matrix of a single steel coil, which is expressed as: ； in: Indicates the number of steelmaking process parameters; OK , and Respectively represent The membership values ​​of the parameters correspond to , and ; Based on the membership matrix of a single steel coil, the fuzzy rules of a single steel coil are constructed, which can be expressed as: ； in: , and They represent the values ​​of the steel coil belonging to the three grades of poor, good and excellent. The larger the value, the greater the probability of belonging to that grade. The values ​​belonging to each level are expressed as: ； in: Indicates the number of steelmaking process parameters of the steel coil; Indicates that the steel coil The process parameters belong to The value of the level of membership; Indicates that the steel coil belongs to The value of the level.

5. The method for analyzing the correlation between steelmaking process parameters and user objections according to claim 4, characterized in that: The analysis of the correlation between steelmaking process parameters and user objections includes: Regarding the correlation between the steel coil belonging difference and user objection, the steel coil with user objection has a large value of belonging difference; Regarding the correlation between the steel coil belonging to the best and the user objection, the value of the steel coil belonging to the best with the user objection is small; Regarding the correlation between whether a steel coil is excellent or poor and user objections, the value of the steel coil belonging to the excellent is small, and the value of the steel coil belonging to the poor is large; the value of the steel coil belonging to the excellent is large, and the value of the steel coil belonging to the poor is small without user objections.

6. A device for analyzing the correlation between steelmaking process parameters and user objections, characterized in that: include: A parameter acquisition module is used to acquire a variety of steelmaking process parameters of the steel coil. Each steelmaking process parameter has multiple values. The multiple values ​​corresponding to each steelmaking process parameter are preliminarily divided into various value levels. A membership relationship building module is used to calculate multiple values ​​of each steelmaking process parameter as independent variables of the cosine function, and use the calculated results as membership values ​​of the multiple values ​​of the corresponding steelmaking process parameter belonging to each value level, and set the membership values ​​of the multiple values ​​of each steelmaking process parameter belonging to each value level as the fuzzy membership relationship of each steelmaking process parameter; wherein the value levels of the steelmaking process parameter include excellent, good and poor; A parameter characterization module is used to merge the fuzzy membership relationships of all steelmaking process parameters to obtain a membership matrix of a single steel coil; wherein each row of the membership matrix represents a steelmaking process parameter, each column represents a value level, and the elements in the membership matrix represent the probability that the steelmaking process parameter value belongs to the corresponding value level; The analysis module is used to weight and aggregate the elements of each column in the membership matrix to obtain the fuzzy characterization of a single steel coil belonging to different value levels, and analyze the correlation between steelmaking process parameters and user objections based on the fuzzy characterization.

7. An electronic device, characterized in that: include: Memory and processor; The memory is used to store computer programs; The processor is used to implement the steps of a method for analyzing the correlation between steelmaking process parameters and user objections as described in any one of claims 1 to 5 when executing the computer program stored in the memory.

8. A computer-readable storage medium, characterized in that: Used to store a computer program, which, when executed by a processor, implements the steps of a method for analyzing the correlation between steelmaking process parameters and user objections as described in any one of claims 1 to 5.

Images