An online pattern measuring instrument dynamic monitoring system

Abstract

The present invention discloses a dynamic monitoring system for an online pattern measuring instrument, which relates to the technical field of foil measurement. The system includes a data acquisition module, a central processor, an online interaction module, and a display and alarm module. The historical data of offline foil film parameters and online foil film parameters are collected through the data acquisition module, and mathematical modeling and regression analysis are performed based on the central processor to establish an offline-online hybrid model to obtain a regression equation and evaluate the effectiveness of the regression equation. Then, the real-time foil parameters are fed back to the central processor through the online interaction module and substituted into the regression equation to determine whether the foil is qualified, and an online alarm prompt signal is generated and transmitted to the display and alarm module, so as to perform corresponding parameter display and alarm prompt operations, improving the work efficiency of foil detection, ensuring the comprehensiveness and integrity of foil detection, and improving the accuracy of alarm prompts for the foil processing process.

Description

Technical Field

[0001] The present invention relates to the technical field of foil measurement, and in particular to a dynamic monitoring system for an online pattern measuring instrument. Background Art

[0002] The production of lithium batteries has strict requirements for the thickness, width, surface quality, etc. of foils. With the development of sensor, data processing, and automation technologies, it provides a technical basis for the realization of an online pattern measuring instrument, enabling it to monitor the quality of foils in real time and with high precision.

[0003] Since it is difficult to monitor foils during the production process of lithium batteries, the current production line usually adopts an offline on-machine sampling inspection mode, which is cumbersome, time-consuming, and laborious. The sampling acquisition area accounts for a low proportion of the entire foil area, and it is impossible to achieve large-area real-time dynamic monitoring. There are defects in low monitoring efficiency and insufficient accuracy of foils. Therefore, the traditional offline sampling inspection mode cannot meet the requirements of real-time monitoring, affecting production efficiency and product quality.

[0004] In view of the above technical defects, a solution is proposed now. Summary of the Invention

[0005] The purpose of the present invention is to solve the defects of low monitoring efficiency and insufficient accuracy of foils existing in the prior art, improve the working efficiency of foil detection, ensure the comprehensiveness and integrity of foil detection, and further improve the accuracy of alarm prompts for the foil processing process.

[0006] In order to achieve the above purpose, the present invention adopts the following technical solutions:

[0007] A dynamic monitoring system for an online pattern measuring instrument, including a data acquisition module, a central processor, an online interaction module, and a display and alarm module. Among them, the data acquisition module, the central processor, the online interaction module, and the display and alarm module are communicatively connected.

[0008] The data acquisition module is used to collect foil data: by using an offline pattern measuring instrument and an online pattern measuring instrument to respectively perform offline detection and online detection on the foil, obtaining historical data of offline foil parameters and online foil parameters, and integrating and marking the historical data of offline foil parameters and online foil parameters as foil data.

[0009] The central processor is used to construct an offline-online hybrid model: by preliminarily analyzing the foil data, evaluating the flatness of the offline foil and the flatness of the online foil, and integrating and obtaining pattern data through n sets of data values of foil flatness, building an offline-online hybrid model to obtain a regression equation through mathematical modeling and regression analysis of the pattern data, and evaluating the effectiveness of the regression equation.

[0010] The online interaction module is used to determine the qualification of the foil material online: through real-time detection by an online pattern measuring instrument, obtain real-time data of the online foil film parameters, and evaluate the flatness of the online foil film; set the qualification standard of the foil material by an offline pattern instrument and feedback it to the central processing unit to substitute into the regression equation, so as to obtain the online alarm threshold; then compare the online foil film flatness with the online alarm threshold to generate an online alarm prompt signal.

[0011] The display alarm module is used to receive the signal and perform display alarm: by receiving the online alarm prompt signal, edit the prompt text and perform corresponding parameter display and alarm prompt operations.

[0012] Furthermore, the specific process of obtaining the pattern data is as follows:

[0013] A1. The offline foil film parameters include the offline foil film thickness and the offline foil film range;

[0014] The offline pattern measuring instrument collects single-laser data by means of reciprocating stops, so as to collect the parameters of the produced foil material multiple times; extract Ny offline detection feature points through the movement trajectory of the single-laser rangefinder reciprocating stop, mark any one of the offline detection feature points as Dy, and mark the offline foil film thickness of the offline detection feature point Dy as Hy, so as to obtain the offline foil film thickness Hy of Ny offline detection feature points.

[0015] Sort the offline foil film thickness Hy of Ny offline detection feature points to obtain the maximum value of the offline foil film thickness Hy and the minimum value , so as to calculate the offline foil film range Ry, evaluate the offline foil film flatness Y through the offline foil film range Ry, and construct an offline pattern number set Qy through n offline foil film flatnesses Y;

[0016] A2. The online foil film parameters include the online foil film thickness and the online foil film range;

[0017] The online pattern measuring instrument performs real-time multi-laser ranging during the production and transmission of the foil material, so as to collect the parameters of the foil material during production; extract Nx online detection feature points through the relative movement trajectory of the foil film dynamically transmitted on the multi-laser rangefinder, mark any one of the online detection feature points as Dx, and mark the online foil film thickness of the online detection feature point Dx as Hx, so as to obtain the online foil film thickness Hx of Nx online detection feature points.

[0018] Sort the online foil film thickness Hx of Nx online detection feature points to obtain the maximum value of the online foil film thickness Hx and the minimum value , thereby calculating the online foil film range Rx, evaluating the online foil film flatness X through the online foil film range Rx, and constructing an online pattern number set Qx based on n online foil film flatness values X;

[0019] A3. Integrate and label the offline pattern number set Qy and the online pattern number set Qx as pattern data.

[0020] Furthermore, the specific process of building an offline-online hybrid model is as follows:

[0021] B1. Identify and prioritize pattern data through a Pareto chart of the standardization effect, and determine the correlation between the offline pattern number set Qy and the online pattern number set Qx;

[0022] B2. Obtain the overall Pearson correlation coefficient γxy through Pearson modeling to evaluate the degree of correlation between the online pattern number set Qx and the offline pattern number set Qy;

[0023] B3. Conduct a regression analysis on the pattern data to evaluate the estimation accuracy of the model coefficients, the fitting effect and significance of the regression model, thereby comprehensively evaluating the effectiveness of the regression equation.

[0024] Furthermore, the specific process of conducting a regression analysis on the pattern data is as follows:

[0025] B3-1. Build a mathematical function model through the offline pattern number set Qy and the online pattern number set Qx to construct a regression equation: Offline pattern data Y = + * Online pattern data X;

[0026] B3-2. Build a scatter plot of the pattern data through the pattern data and conduct a regression analysis by constructing a matrix through the scatter plot, thereby obtaining the regression analysis data of the pattern data and generating a regression model: ; Furthermore, obtain the estimation accuracy evaluation index Xjd of the model coefficients to evaluate the estimation accuracy of the model coefficients;

[0027] B3-3. Evaluate the fitting effect of the regression model to obtain the model fitting effect evaluation parameters, and then comprehensively obtain the fitting effect evaluation index Xnh through the model fitting effect evaluation parameters to evaluate the fitting effect of the regression model;

[0028] B3-4. Conduct an analysis of variance on the regression equation to obtain the model significant factor evaluation parameters, and comprehensively obtain the significance evaluation index Xxz through the model significant factor evaluation parameters to evaluate the significance of the regression model;

[0029] B3-5, and then by combining the estimation accuracy evaluation index Xjd of the model coefficients, the fitting effect evaluation index Xnh of the regression model, and the significance evaluation index Xxz, the effective index Eff of the regression equation is obtained to comprehensively evaluate the effectiveness of the regression equation.

[0030] Further, the specific process of obtaining the overall Pearson correlation coefficient γxy through Pearson modeling is as follows:

[0031] B2-1, the online pattern number set Qx contains n data values of the online foil film flatness X, and the overall mean and the standard deviation Sx are obtained through the online pattern number set Qx;

[0032] B2-2, the offline pattern number set Qy contains n data values of the offline foil film flatness Y, and the overall mean and the standard deviation Sy are obtained through the offline pattern number set Qy;

[0033] B2-3, and then the overall covariance and the overall Pearson correlation coefficient γxy are obtained;

[0034] B2-4, set the evaluation interval of the overall Pearson correlation coefficient γxy, and evaluate the correlation degree between the online pattern number set Qx and the offline pattern number set Qy through interval comparison.

[0035] Further, the specific parameters for the regression analysis of the pattern data are:

[0036] The regression analysis data includes the coefficients of the regression equation, the standard error of the coefficients, the T value, the P value, and the variance inflation factor. Among them, the coefficient of the marked independent variable is , and the coefficient of the marked constant term is ; the standard error of the coefficient of the marked independent variable is , and the standard error of the coefficient of the marked constant term is ; T value = coefficient / standard error of the coefficient; a regression model is generated through the regression analysis data: ;

[0037] The model fitting effect evaluation parameters include the coefficient of determination Rsq, the adjusted coefficient of determination Radj, and the predicted coefficient of determination Rpred;

[0038] The model significant factor evaluation parameters include degrees of freedom (DF), adjusted sum of squares (AdjSS), adjusted mean square (AdjMS), F value (F-statistic), and P value (P-value).

[0039] Further, the generation process of the online alarm prompt signal is:

[0040] Set the qualified standard for the foil material of the preset offline pattern instrument, and mark the offline alarm threshold Gy for the flatness Y of the offline foil film in the offline pattern number set Qy;

[0041] Substitute the qualified condition that the offline foil film flatness Y ≤ the offline alarm threshold Gy into the regression equation , so as to set the online alarm threshold Gx. When the online foil film flatness X of the online pattern number set Qx is lower than the online alarm threshold Gx, an online alarm prompt signal is generated.

[0042] In summary, due to the adoption of the above technical solutions, the beneficial effects of the present invention are as follows:

[0043] The present invention collects the historical data of the offline foil film parameters and the online foil film parameters through the data acquisition module, and conducts mathematical modeling and regression analysis based on the central processing unit, builds an offline-online hybrid model to obtain the regression equation, evaluates the effectiveness of the regression equation, and then feeds the real-time foil material parameters back to the central processing unit through the online interaction module, and substitutes them into the regression equation to determine whether the foil material is qualified, generates an online alarm prompt signal and transmits it to the display alarm module for corresponding parameter display and alarm prompt operations;

[0044] Among them, the online pattern measuring instrument based on this system is separately installed in the foil material processing production lines such as slitting machines and carbon coating machines, and real-time multi-laser ranging is carried out during the production and transmission of the foil material. The intelligent monitoring improves the working efficiency of foil material detection; through the dynamic transmission in the foil material production process, the comprehensive real-time monitoring of the foil material processing standards is realized, ensuring the comprehensiveness and integrity of foil material detection; through the effectiveness evaluation of the regression equation of the offline-online hybrid model, the accuracy of alarm prompts for the foil material processing process is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 Shows the connection schematic diagram of the system modules of the present invention;

[0046] Figure 2 Shows the step schematic diagram of the solution flow of the present invention;

[0047] Figure 3 Shows the scatter plot of the pattern data of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0048] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0049] Example 1:

[0050] As Figures 1 - 3 shown, an online pattern measuring instrument dynamic monitoring system includes a data acquisition module, a central processor, an online interaction module, and a display and alarm module. Among them, the data acquisition module, the central processor, the online interaction module, and the display and alarm module are communicatively connected;

[0051] Since at present, in the industry, off-line pattern testers are generally used to monitor the foils that have been produced by sampling, and small-area data acquisition and monitoring are carried out for the entire roll of foils; and in the premise that the dynamic transfer process of lithium batteries in the production line cannot be monitored in real time, in this case, an online pattern tester is designed and developed, and real-time detection of foils is realized based on an online pattern measuring instrument dynamic monitoring system;

[0052] The specific working steps of the online pattern measuring instrument dynamic monitoring system are as follows:

[0053] S1. The data acquisition module acquires foil data: By setting an off-line pattern measuring instrument and an online pattern measuring instrument, offline detection and online detection are respectively carried out on the foil, historical data of offline foil parameters and online foil parameters are obtained, and the historical data of offline foil parameters and online foil parameters are integrated and marked as foil data;

[0054] S1-1. The off-line pattern measuring instrument performs data acquisition by means of reciprocating stop and laser ranging, and collects once every certain distance, and repeatedly collects the parameters of the produced foil multiple times;

[0055] The offline foil parameters include the offline foil thickness and the offline foil range;

[0056] Ny offline detection feature points are extracted through the movement trajectory of the single laser rangefinder with reciprocating stop. Any one of the offline detection feature points is marked as Dy, and the offline foil thickness of the offline detection feature point Dy is marked as Hy, so as to obtain the offline foil thickness Hy of Ny offline detection feature points;

[0057] Sort the offline foil thickness Hy of Ny offline detection feature points to obtain the highest value and the lowest value , so as to calculate the offline foil range Ry: ;

[0058] Evaluate the flatness Y of the offline foil through the offline foil range Ry: ; Among them, is a conversion coefficient and is greater than 0, the conversion coefficient It refers to the preset constant for converting the offline foil film range Ry into the offline foil film flatness Y. When the offline foil film range Ry is higher, the offline foil film flatness Y is evaluated to be lower.

[0059] Construct an offline pattern data set Qy through n offline foil flatness Y;

[0060] S1-2, the online pattern measuring instrument is separately set up in the foil processing production line such as the slitting machine and the carbon coating machine, and performs real-time multi-laser ranging during the foil production and transmission process, so as to collect the parameters of the foil in production;

[0061] Online foil parameters include online foil thickness and online foil range;

[0062] Through the relative motion trajectory of the foil film dynamically transmitted on the multi-laser rangefinder, Nx online detection feature points are extracted, any online detection feature point is marked as Dx, and the online foil film thickness of the online detection feature point Dx is marked as Hx, so as to obtain the online foil film thickness Hx of the Nx online detection feature points;

[0063] Sort the online foil thickness Hx of Nx online detection feature points to obtain the highest value of the online foil thickness Hx and the minimum value , and then calculate the online foil range Rx: ;

[0064] Evaluation of online foil flatness X by online foil extreme difference Rx: ;in, is the conversion coefficient and Greater than 0, conversion coefficient It refers to the preset constant that converts the online foil film range Rx into the online foil film flatness X. When the online foil film range Rx is higher, the online foil film flatness is evaluated to be lower;

[0065] Construct an online pattern set Qx through n online foil flatness X;

[0066] S1-3, integrate and mark the offline pattern data set Qy and the online pattern data set Qx as pattern data.

[0067] S2, the central processing unit builds an offline-online hybrid model: by performing preliminary analysis on the foil data, evaluating the offline foil flatness and the online foil flatness, and integrating n groups of foil flatness data values ​​to obtain the pattern data, and by performing Pearson modeling and regression analysis on the pattern data, building an offline-online hybrid model to obtain the regression equation, and evaluating the effectiveness of the regression equation.

[0068] The specific process of building an offline-online hybrid model is as follows:

[0069] S2-1. Identify and prioritize the pattern data through the Pareto chart of the standardization effect. The response is the offline pattern data, and the standardization effect value α = 0.05, indicating that the factor with the greatest impact on the result is the offline pattern data, thus indicating the correlation between the offline pattern data set Qy and the online pattern data set Qx;

[0070] Then, through Pearson modeling, obtain the overall Pearson correlation coefficient γxy. The specific process is as follows:

[0071] S2-101. The online pattern data set Qx contains n data values of the online foil film flatness X;

[0072] Then the online pattern data set Qx: {X1, X2, X3... Xn};

[0073] The overall mean of the online pattern data set Qx is: ; The standard deviation Sx of the online pattern data set Qx is: ; i is the element serial number of the index set;

[0074] S2-102. The offline pattern data set Qy contains n data values of the offline foil film flatness Y;

[0075] Then the offline pattern data set Qy: {Y1, Y2, Y3... Yn};

[0076] The overall mean of the offline pattern data set Qy is: ; The standard deviation Sy of the offline pattern data set Qy is: ;

[0077] S2-103. The overall covariance is: ;

[0078] Thus, obtain the overall Pearson correlation coefficient γxy: ;

[0079] Set the evaluation interval of the overall Pearson correlation coefficient γxy, and evaluate the correlation between the online pattern data set Qx and the offline pattern data set Qy through interval comparison, so as to determine and conduct regression analysis;

[0080] Through experimental data calculation, obtain the overall Pearson correlation coefficient γxy = 0.906;

[0081] It is preset that when γxy ∈ (0.5, 1.0), it indicates that there is a strong positive correlation between the two, and thus further conduct regression analysis on the offline pattern data set Qy and the online pattern data set Qx.

[0082] S2-2. The specific process of performing regression analysis on the pattern data is as follows:

[0083] Some experimental values of the pattern data are shown in Table 1:

[0084] Table 1 Record Table of Experimental Data of Pattern Data

[0085]

[0086] By performing mathematical function modeling on the offline pattern data set Qy and the online pattern data set Qx, a regression equation is established: Offline pattern data Y = 1.455 + 1.7664 * Online pattern data X.

[0087] S2-3. Through the experimental values of the pattern data, a scatter plot of the pattern data is constructed, as Figure 3 shown. By constructing a matrix through the scatter plot for regression analysis, the regression analysis data of the pattern data is obtained. The regression analysis data of the pattern data includes coefficients, standard error of coefficients, T-statistic, P-value, and variance inflation factor (VIF), as shown in Table 2:

[0088] Table 2 Record Table of Regression Analysis Data of Pattern Data

[0089]

[0090] S2-301. The independent variable refers to the online pattern data, and the coefficient of the independent variable refers to the influence degree of the online pattern data on the offline pattern data. Mark the coefficient of the independent variable as : ;

[0091] S2-302. The constant term refers to the intercept term of the regression model, indicating the predicted value of the dependent variable when the independent variable takes a value of 0. Mark the coefficient of the constant term as : ;

[0092] S2-303. The standard error of the coefficient is used to measure the accuracy of the coefficient estimation. When the standard error of the coefficient is smaller, it indicates that the estimation is more accurate;

[0093] Mark the standard error of the coefficient of the independent variable as The formula is: ; where is the estimated value of the error variance. Let ; RSS is the residual sum of squares. Let ;

[0094] Then the coefficient of the constant term The standard error of The formula is: .

[0095] S2-304, The T value is used to test whether the coefficient is significant. T value = coefficient / standard error of the coefficient. The larger the T value, the more significant the coefficient is;

[0096] S2-305, Generate a regression model through the regression analysis data of the pattern data: ;

[0097] S2-306, By combining the standard error of the independent variable coefficient with the standard error of the constant term coefficient obtain the estimation accuracy evaluation index Xjd of the model coefficient: The standard error of ; Among them, , , are the standard errors of the independent variable coefficient and the constant term coefficient respectively, and The standard error of is the weight factor coefficient, and , The preset values of are both greater than 0; Set the evaluation interval of the estimation accuracy evaluation index Xjd. When the estimation accuracy evaluation index Xjd is higher, the estimation accuracy of the evaluation model coefficient is better.

[0098] S2-4, Then evaluate the fitting effect of the regression model to obtain the model fitting effect evaluation parameters. The model fitting effect evaluation parameters include the coefficient of determination Rsq, the adjusted coefficient of determination Radj, and the predicted coefficient of determination Rpred;

[0099] S2-401, Coefficient of determination Rsq: , Among them, is the i-th observed value, is the i-th predicted value, is the mean of the observed values;

[0100] The coefficient of determination Rsq is between the intervals (0,1). When the coefficient of determination Rsq is closer to 1, it indicates that the model has a higher fitting degree to the data; when the coefficient of determination Rsq is closer to 0, it indicates that the model has a lower fitting degree to the data;

[0101] S2-402, Adjusted coefficient of determination Radj: ;

[0102] The adjusted coefficient of determination Radj is used to reflect the true fitting degree of the model. When the number of independent variables is adjusted, it can be used to compare the differences in the fitting effects of models with different numbers of independent variables. When the adjusted coefficient of determination Radj increases, it indicates that the newly added independent variables have a significant impact on the model and explanatory power.

[0103] S2-403, the predicted coefficient of determination Rpred: , where, is the predicted value of the i-th sample after building a model using all data except the i-th sample; when the predicted coefficient of determination Rpred is higher, it indicates that the prediction ability of the regression model is better and the predicted value is more accurate.

[0104] The numerical values of the model fitting effect evaluation parameters are shown in Table 3:

[0105] Table 3 Record Table of Model Fitting Effect Evaluation Parameters

[0106]

[0107] S2-404, obtain the fitting effect evaluation index Xnh through the comprehensive model fitting effect evaluation parameters:

[0108] ; where, 、 、 are the weight factor coefficients of the coefficient of determination Rsq, the adjusted coefficient of determination Radj, and the predicted coefficient of determination Rpred respectively, and 、 、 The preset values of are all greater than 0; set the evaluation interval of the fitting effect evaluation index Xnh. When the fitting effect evaluation index Xnh is higher, the fitting effect of the evaluation regression model is better.

[0109] S2-5, then perform an analysis of variance on the regression equation to obtain the model significant factor evaluation parameters. The model significant factor evaluation parameters include degrees of freedom (DF), adjusted sum of squares (AdjSS), adjusted mean square (AdjMS), F value (F-statistic), and P value (P-value), as shown in Table 4:

[0110] Table 4 Record Table of Model Significant Factor Evaluation Parameters

[0111]

[0112] S2-501, the degrees of freedom (DF) refers to the number of samples of independent information; there are 85 preset data samples. Among them, the lack-of-fit error is used to evaluate the systematic deviation between the model and the data; the pure error refers to the random variation of the data itself;

[0113] S2-502, AdjSS refers to the contribution of each factor to the total variation;

[0114] Label the AdjSS of the regression model as ModelSS: ;

[0115] Label the AdjSS of the error as ErrorSS: ;

[0116] S2-503, AdjMS is the adjusted mean square, which is calculated by dividing AdjSS by its degrees of freedom;

[0117] S2-504, The F value is used for model significance testing, ; The larger the F value, the greater the proportion of the variance that the regression model can explain in the total variance, that is, the better the fitting effect of the model to the data and the higher the significance;

[0118] Label the F value of the regression model as ModelF and the F value of the lack-of-fit error as ErrorF;

[0119] S2-505, The P value is used to judge model significance, which refers to the probability of the current F value or a larger F value in the state where the model is not significant. Therefore, when the model is significant, the P value of the regression model is 0; the P value of the lack-of-fit error is ; When the P value is smaller, there is more sufficient evidence that the model is significant;

[0120] Label the P value of the regression model as ModelP and the P value of the lack-of-fit error as ErrorP.

[0121] S2-506, Obtain the significance evaluation index Xxz by comprehensively evaluating the parameters of the significant model factors:

[0122] ; Among them, 、 、 、 are the weight factor coefficients of the F value ModelF of the regression model, the F value ErrorF of the lack-of-fit error, the P value ModelP of the regression model, and the P value ErrorP of the lack-of-fit error respectively, and 、 、 、 The preset values of are all greater than 0; Set the evaluation interval of the significance evaluation index Xxz. When the significance evaluation index Xxz is higher, the significance of the regression model is better evaluated.

[0123] S2-6, and then by combining the estimation accuracy evaluation index Xjd of the model coefficients, the fitting effect evaluation index Xnh of the regression model, and the significance evaluation index Xxz, the effective index Eff of the regression equation is obtained:

[0124] ;

[0125] Among them, 、 、 are the weight indexes of the estimation accuracy evaluation index Xjd of the model coefficients, the fitting effect evaluation index Xnh of the regression model, and the significance evaluation index Xxz respectively, and 、 、 The preset values of are all greater than 0; when the estimation accuracy evaluation index Xjd of the model coefficients, the fitting effect evaluation index Xnh of the regression model, and the significance evaluation index Xxz are higher, the effective index Eff of the regression equation is higher, and the effectiveness of the regression equation is evaluated higher; set the effective interval of the effective index Eff of the regression equation. When the effective index Eff of the regression equation is within the effective interval, it means that the regression equation =1.455 + 1.7664 * is effective, so as to conduct qualified monitoring of real-time online foil production based on the regression equation.

[0126] S3, the online interaction module determines the qualification of the foil through online interaction: through real-time detection by an online pattern measuring instrument, obtain the real-time data of the online foil film parameters, and evaluate the flatness of the online foil film; by setting the qualification standard of the foil for the offline pattern instrument and feeding it back to the central processing unit and substituting it into the regression equation, the online alarm threshold is obtained; then compare the flatness of the online foil film with the online alarm threshold to generate an online alarm prompt signal;

[0127] The preset qualification standard for the foil of the offline pattern instrument is: let the offline alarm threshold Gy of the offline foil film flatness Y of the offline pattern set Qy = 7mm;

[0128] Substitute Y ≤ 7mm into the regression equation Y = 1.455 + 1.7664 * X, and it can be deduced that X ≤ 3.13mm;

[0129] Then set the online alarm threshold Gx = 3. When the online foil film flatness X of the online pattern set Qx is lower than the online alarm threshold Gx, an online alarm prompt signal is generated;

[0130] Feed back the online foil film parameters detected in real time in the foil production line and substitute them into the regression equation:

[0131] =1.455 + 1.7664 * , and calculate the real-time offline foil film parameters.

[0132] S4. The display and alarm module receives the signal and conducts display and alarm: by receiving the online alarm prompt signal, it edits the prompt text, conducts corresponding parameter display, and performs the alarm prompt operation of the sound signal, so as to prompt the management personnel of the foil production line to conduct corresponding foil processing;

[0133] Among them, the prompt text includes the online foil film parameters and the deduced offline foil film parameters, so as to visually monitor the deviation degree of the flatness of the foil, and increase the data sample size of the subsequent regression equation, continuously improving the fitting degree of the regression equation.

[0134] To sum up, the present invention collects the historical data of the offline foil film parameters and the online foil film parameters through the data acquisition module, conducts mathematical modeling and regression analysis based on the central processing unit, builds an offline-online hybrid model to obtain a regression equation, evaluates the effectiveness of the regression equation, then feeds back the real-time foil parameters to the central processing unit through the online interaction module, substitutes them into the regression equation to determine whether the foil is qualified, generates an online alarm prompt signal and transmits it to the display and alarm module, and conducts corresponding parameter display and alarm prompt operations;

[0135] Among them, the online pattern measuring instrument based on this system is separately installed in the foil processing production lines such as the slitter and carbon coating machine, conducts real-time multi-laser ranging during the foil production and transmission process, and the intelligent monitoring improves the working efficiency of the foil detection; through the dynamic transmission in the foil production process, the full real-time monitoring of the foil processing standard is realized, ensuring the comprehensiveness and integrity of the foil detection; by evaluating the effectiveness of the regression equation, the accuracy of the alarm prompt during the foil processing process is improved.

[0136] The setting of the size of the interval and threshold is for the convenience of comparison. Regarding the size of the threshold, it depends on the amount of sample data and the base quantity set by those skilled in the art for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantified value.

[0137] The above formulas are all dimensionless and take their numerical calculations. The formula is obtained by collecting a large amount of data and conducting software simulation to get a formula closest to the real situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation;

[0138] The above is only the preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and should be covered by the protection scope of the present invention.

Claims

1. An online pattern measuring instrument dynamic monitoring system, characterized in that: It includes a data acquisition module, a central processor, an online interaction module and a display alarm module. Among them, the data acquisition module, the central processor, the online interaction module and the display alarm module are communicatively connected; The data acquisition module is used to collect foil film data: the offline foil film parameters and the historical data of the online foil film parameters are obtained by respectively performing offline detection and online detection on the foil film through an offline pattern measuring instrument and an online pattern measuring instrument, and the historical data of the offline foil film parameters and the online foil film parameters are integrated and marked as foil film data; The central processor is used to construct an offline-online hybrid model: by performing a preliminary analysis on the foil film data, evaluating the flatness of the offline foil film and the flatness of the online foil film, and integrating and obtaining the pattern data through n sets of data values of the foil film flatness, a mathematical model and a regression analysis are performed on the pattern data to build an offline-online hybrid model to obtain a regression equation, and the effectiveness of the regression equation is evaluated; The online interaction module is used to determine the qualification of the foil material online: the real-time data of the online foil film parameters are obtained through real-time detection by the online pattern measuring instrument, and the flatness of the online foil film is evaluated; by setting the qualification standard of the foil material of the offline pattern instrument and feeding it back to the central processor and substituting it into the regression equation, the online alarm threshold is obtained; then the flatness of the online foil film is compared with the online alarm threshold to generate an online alarm prompt signal; The display alarm module is used to receive the signal and perform display and alarm: by receiving the online alarm prompt signal, the prompt text is edited and the corresponding parameter display and alarm prompt operations are performed.

2. The dynamic monitoring system of an online pattern measuring instrument according to claim 1, wherein: The specific process of obtaining the pattern data is as follows: A1. The offline foil film parameters include the offline foil film thickness and the offline foil film range; The offline pattern measuring instrument performs single-laser data acquisition in a reciprocating stop manner, so as to repeatedly collect the parameters of the produced foil material; Ny offline detection feature points are extracted from the movement trajectory of the reciprocating stop in the single-laser ranging mode, any one of the offline detection feature points is marked as Dy, and the offline foil film thickness of the offline detection feature point Dy is marked as Hy, so as to obtain the offline foil film thickness Hy of Ny offline detection feature points; Sort by the offline foil film thickness Hy of Ny offline detection feature points to obtain the highest value of the offline foil film thickness Hy and the lowest value , so as to calculate the offline foil film range Ry, evaluate the flatness Y of the offline foil film through the offline foil film range Ry, and construct the offline pattern number set Qy through n offline foil film flatness Y; A2. The online foil film parameters include the online foil film thickness and the online foil film range; The online pattern measuring instrument performs real-time multi-laser ranging during the production and transmission of the foil material, so as to collect the parameters of the foil material in production; Nx online detection feature points are extracted from the relative movement trajectory of the foil film dynamically transmitted on the multi-laser rangefinder, any one of the online detection feature points is marked as Dx, and the online foil film thickness of the online detection feature point Dx is marked as Hx, so as to obtain the online foil film thickness Hx of Nx online detection feature points; Sort by the online foil thickness Hx of Nx online detection feature points to obtain the highest value of the online foil thickness Hx and the lowest value , thereby calculating the online foil range Rx, evaluating the online foil flatness X through the online foil range Rx, and constructing an online pattern number set Qx through n online foil flatnesses X; A3. The offline pattern data set Qy and the online pattern data set Qx are integrated and marked as pattern data.

3. An online pattern measuring instrument dynamic monitoring system according to claim 2, characterized in that: The specific process of building an offline-online hybrid model is as follows: B1. Identify and prioritize the pattern data through the Pareto chart of the standardization effect, and determine the correlation between the offline pattern data set Qy and the online pattern data set Qx; B2. Obtain the overall Pearson correlation coefficient γxy through Pearson modeling to evaluate the correlation degree between the online pattern data set Qx and the offline pattern data set Qy. B3. Conduct a regression analysis on the pattern data to evaluate the estimation accuracy of the model coefficients, the fitting effect and significance of the regression model, so as to comprehensively evaluate the effectiveness of the regression equation.

4. An online pattern measuring instrument dynamic monitoring system according to claim 3, characterized in that: The specific process of conducting a regression analysis on the pattern data is as follows: B3-1, mathematical function modeling is carried out through the offline pattern number set Qy and the online pattern number set Qx, thereby establishing a regression equation: Offline pattern data Y = + * Online pattern data X, where is the coefficient of the constant term, is the coefficient of the independent variable; B3-2, construct a scatter plot of the pattern data based on the pattern data, and construct a matrix through the scatter plot for regression analysis, so as to obtain the regression analysis data of the pattern data and generate a regression model: ; furthermore, obtain the estimation accuracy evaluation index Xjd of the model coefficient to evaluate the estimation accuracy of the model coefficient; B3-3. Evaluate the fitting effect of the regression model, obtain the evaluation parameters of the model fitting effect, and then comprehensively obtain the fitting effect evaluation index Xnh through the evaluation parameters of the model fitting effect to evaluate the fitting effect of the regression model. B3-4. Conduct an analysis of variance on the regression equation, obtain the evaluation parameters of the model significant factors, and comprehensively obtain the significance evaluation index Xxz through the evaluation parameters of the model significant factors to evaluate the significance of the regression model. B3-5. Furthermore, combine the estimation accuracy evaluation index Xjd of the model coefficients, the fitting effect evaluation index Xnh of the regression model, and the significance evaluation index Xxz to obtain the effective index Eff of the regression equation, and comprehensively evaluate the effectiveness of the regression equation.

5. An online pattern measuring instrument dynamic monitoring system according to claim 4, characterized in that: The specific process of obtaining the overall Pearson correlation coefficient γxy through Pearson modeling is as follows: B2-1. The online pattern number set Qx contains n data values of the flatness X of the online foil film, and the overall mean and the standard deviation Sx are obtained through the online pattern number set Qx; B2-2. The offline pattern number set Qy contains n data values of the flatness Y of the offline foil film, and the overall mean value is obtained through the offline pattern number set Qy and the standard deviation Sy; B2-3. Furthermore, obtain the overall covariance and the overall Pearson correlation coefficient γxy. B2-4. Set the evaluation interval of the overall Pearson correlation coefficient γxy, and evaluate the correlation degree between the online pattern data set Qx and the offline pattern data set Qy through interval comparison.

6. An online pattern measuring instrument dynamic monitoring system according to claim 5, characterized in that: The specific parameters for the regression analysis of the pattern data are: The regression analysis data includes the coefficients of the regression equation, the standard errors of the coefficients, the T-values, the P-values, and the variance inflation factors. Among them, the coefficient of the marked independent variable is , and the coefficient of the marked constant term is ; the standard error of the coefficient of the marked independent variable is , and the standard error of the coefficient of the marked constant term is ; T-value = coefficient / standard error of the coefficient; a regression model is generated through the regression analysis data: ; The evaluation parameters of the model fitting effect include the coefficient of determination Rsq, the adjusted coefficient of determination Radj, and the predicted coefficient of determination Rpred. The evaluation parameters of the model significant factors include degrees of freedom DF, adjusted sum of squares AdjSS, adjusted mean square AdjMS, F value, and P value.

7. An online pattern measuring instrument dynamic monitoring system according to claim 6, characterized in that: The generation process of the online alarm prompt signal is: Preset the qualified standard for the foil material of the offline pattern instrument, and mark the offline alarm threshold Gy of the offline foil film flatness Y of the offline pattern data set Qy. From the qualified condition that the flatness Y of the offline foil film ≤ the offline alarm threshold Gy, substitute it into the regression equation , so as to set the online alarm threshold Gx. When the online flatness X of the online pattern number set Qx is lower than the online alarm threshold Gx, an online alarm prompt signal is generated.

Images