Online coating data remote acquisition and analysis method and device for thermo-sensitive paper production line

Abstract

The invention relates to the technical field of production control, in particular to an online coating data remote acquisition and analysis method and device for a thermo-sensitive paper production line. According to the method, a thermo-sensitive paper image and various information during coating are analyzed in time sequence. The thickness change significance of each thickness area can be effectively quantified by analyzing the thickness change and the shape change between adjacent moments. The first coating inhomogeneity is quantified at each moment in time. The influence of the humidity in the current environment can be evaluated by analyzing the linear correlation between the first coating non-uniformity and the environment humidity, the second coating non-uniformity is obtained, the influence weight of each kind of parameter data on the scraper is obtained, and the real-time parameter data is adjusted based on the adjusting quantity. According to the method, characteristics such as thickness change in the thermal-sensitive paper coating process on the time sequence are analyzed in real time, the influence of environment humidity on the coating thickness is combined, the real non-uniformity generated by characterizing scraper abrasion is quantified, then scraper parameters are adjusted, and the scraper is prevented from being further abraded in time.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of production control, in particular to an online coating data remote acquisition and analysis method and device for a thermal paper production line. BACKGROUND

[0002] Thermal paper is a special coated paper that directly generates images through heat. Its core principle is to trigger the color reaction of chemicals in the coating layer by using heat energy, without the need for traditional ink or carbon powder to record information. In the production process, the raw materials are ground into fine powder and mixed into water-based paint. The paint is evenly applied to the base paper by rolling, spraying or scraping. Each layer is coated and dried to ensure adhesion. The final product is applied to receipts, labels, medical records and other fields after rewinding and cutting.

[0003] In the production process of thermal paper, the doctor blade is the core component of the coating process, and its wear will directly affect the uniformity of the coating and the thermal color development performance. The doctor blade height is usually fixed and designed, and cannot dynamically adapt to the working condition changes after wear, resulting in uneven print pressure distribution, coating thickness fluctuation and other problems, which further cause color development blur, coating leakage and other quality defects.

[0004] Therefore, the prior art determines whether there is uneven thickness on the thermal paper coating, and then determines whether the doctor blade is worn. The prior art only determines the uneven thickness according to the thickness at the preset detection time, without considering the real-time of the coating process, so it cannot effectively evaluate the doctor blade wear and timely adjust the parameters to avoid further wear. And after the thermal paper coating process is completed, it needs to be dried. At this time, it is difficult to accurately control the humidity of the environment. When the humidity is too high, the substrate will swell due to moisture absorption, affecting the adhesion of the coating. This uncontrollable factor will directly affect the thickness change of the final coating, resulting in misjudgment of the degree of doctor blade wear. SUMMARY

[0005] In order to solve the technical problems that the prior art only analyzes the surface thickness of the thermal paper at a fixed time, and ignores the influence of environmental humidity on the coating material of the thermal paper, resulting in inaccurate judgment of uneven thickness, and further unable to effectively adjust the parameters to avoid further wear of the doctor blade, the purpose of the present application is to provide an online coating data remote acquisition and analysis method and device for a thermal paper production line. The technical solution adopted is as follows: The present application provides an online coating data remote acquisition and analysis method for a thermal paper production line, which comprises: Real-time acquisition of parameter data, thermal paper image, surface thickness of each position of the thermal paper and environmental humidity during the use of the doctor blade at each time; dividing each thickness region on the thermal paper image according to the surface thickness of each position on the thermal paper; matching the thickness regions between adjacent time instants; obtaining a thickness change significance of each thickness region at each time instant according to a thickness difference and a shape difference between the thickness regions matched between adjacent time instants; and obtaining a first coating unevenness at each time instant according to a change in the thickness change significance and a thickness change of different thickness regions at each time instant. obtaining a linear correlation between the environmental humidity and the first coating unevenness in time sequence, and obtaining a second coating unevenness according to the linear correlation and the first coating unevenness; if the second coating unevenness satisfies a preset regulation condition, obtaining an influence weight of each parameter data on the doctor blade, obtaining a regulation amount according to the influence weight and a preset regulation step, and adjusting the real-time parameter data based on the regulation amount.

[0006] Further, the thickness region dividing method comprises: performing clustering on each position based on the surface thickness by using a DBSCAN clustering algorithm, and taking each region of the clustered clusters on the thermal paper as a thickness region.

[0007] Further, the shape difference obtaining method comprises: optionally taking one time instant as a target time instant, taking one thickness region at the target time instant as a target thickness region, taking a set of thickness regions matched with the target thickness region at adjacent time instants of the target time instant as a comparison region of the target thickness region, obtaining a width difference between the comparison region and the target thickness region in a scanning direction of the thickness detection sensor, and obtaining the shape difference according to the width difference and a number of regions in the set of thickness regions matched at adjacent time instants.

[0008] Further, the thickness change significance obtaining method comprises: after negatively correlating and normalizing the shape difference, multiplying the thickness difference to obtain the thickness change significance.

[0009] Further, the first coating unevenness obtaining method comprises: for each thickness region, multiplying the thickness change significance and a region average thickness to obtain a thickness coating feature, obtaining a thickness coating feature difference between all thickness regions at each time instant, and taking a cumulative sum of all thickness coating feature differences as the first coating unevenness at each time instant.

[0010] Further, the second coating unevenness obtaining method comprises: Taking the first coating unevenness as the longitudinal coordinate and the environmental humidity at the corresponding time as the horizontal coordinate, a coordinate system is constructed and curve fitting is performed to obtain the tangent slope on the fitting curve at each time; the tangent slope is negatively correlated and normalized to obtain a non-environmental influence weight; and the product of the non-environmental influence weight and the first coating unevenness is taken as the second coating unevenness.

[0011] Further, the method for obtaining the influence weight comprises: The second coating unevenness at each value of the variable is obtained by using the control variable method to obtain each parameter data as a variable, and the wear rate at each value is obtained according to the tangent slope on the curve; the parameter data sequence as a variable is aligned with the wear rate sequence, and the Pearson correlation coefficient is calculated, and the Pearson correlation coefficient is taken as the influence weight.

[0012] Further, the method for obtaining the adjustment amount comprises: The product of the influence weight and the preset adjustment step is taken as the regulation amount.

[0013] Further, the method for adjusting the real-time parameter data based on the adjustment amount comprises: The difference between the real-time parameter data and the regulation amount is taken as the regulated parameter data.

[0014] The application further provides an online coating data remote acquisition and analysis device for a thermal paper production line, which comprises a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor implements the steps of any one of the online coating data remote acquisition and analysis methods for the thermal paper production line when executing the computer program.

[0015] The application has the following beneficial effects: The present application analyzes the thermal paper image and various information during coating in time sequence. For the thermal paper image at each time, the thickness change significance of each thickness area can be effectively quantified by analyzing the thickness change and shape change between adjacent time. Further, the first coating unevenness is quantified at each time. Further, the influence of environmental humidity is analyzed, and the influence of the current environment can be evaluated by analyzing the linear correlation between the first coating unevenness and the environmental humidity, that is, the greater the current environmental influence, the more likely the thickness unevenness at this time is not caused by the scraper wear, so the second coating unevenness can be further obtained to represent the unevenness caused by the scraper wear. That is, the greater the second coating unevenness, the more obvious the scraper wear at this time, and the scraper parameters need to be adjusted in time to avoid further wear. Therefore, the influence weight of each parameter data on the scraper can be obtained, and the real-time parameter data is adjusted based on the adjustment amount. The present application quantifies the real unevenness caused by the scraper wear by analyzing the thickness change and other characteristics in the thermal paper coating process in time sequence, combining the influence of environmental humidity on the coating thickness, and adjusting the scraper parameters in time to avoid further wear of the scraper. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort.

[0017] Figure 1 A flow chart of online coating data remote acquisition and analysis of a thermal paper production line provided by an embodiment of the present application; Figure 2 A thermal paper scanning schematic diagram provided by an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined application purpose, the following specifically describes the specific implementation, structure, features and effects of a thermal paper production line online coating data remote acquisition and analysis method and device according to the present application, with reference to the drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0020] The application provides a method and device for collecting and analyzing online coating data of a thermal paper production line.

[0021] Please refer to Figure 1 which shows a flow chart of a method for collecting and analyzing online coating data of a thermal paper production line according to an embodiment of the application, the method comprises: Step S1: Real-time acquisition of parameter data in the process of using the doctor blade at each moment, thermal paper images, surface thicknesses of each position of the thermal paper, and environmental humidity.

[0022] In the process of coating the thermal paper, different degrees of doctor blade wear will have different degrees of influence. In the initial wear stage, the blade edge is slightly blunted, and the coating thickness is slightly increased. If the thickness at a fixed detection moment is directly detected, it is not easy to determine that wear has occurred. In the intermediate wear stage, the blade edge is uneven, and the coating layer has stripes or uneven thickness, which affects the uniformity of thermal paper color development. The unevenness of the coating thickness in this stage is significantly higher and is relatively easy to detect, but significant wear of the blade edge has already occurred, and the doctor blade should be replaced. In the final wear stage, the blade edge is severely damaged, the coating layer is missing, and even the doctor blade is broken to cause a stop. Therefore, in order to ensure the effective progress of the coating process and prolong the service life of the doctor blade, the unevenness of the coating thickness caused by the coating in the initial wear stage needs to be effectively identified, and the doctor blade parameters need to be adjusted in time to avoid further wear. Therefore, in the embodiment of the application, the parameter data in the process of using the doctor blade at each moment, the thermal paper images, the surface thicknesses of each position of the thermal paper, and the environmental humidity are acquired in real time, and the data is analyzed and processed in the subsequent process.

[0023] In the embodiment of the application, a laser sensor can be used to identify the thickness of each position in the thermal paper image. As shown in Figure 2 which shows a scanning schematic diagram of the thermal paper according to an embodiment of the application. Because the width D of the thermal paper is fixed, the scanning width d of the sensor is also fixed. Therefore, the scanning direction of the sensor is set to be perpendicular to the moving direction of the thermal paper, and longitudinal scanning is performed. The surface thickness at each scanning position can be obtained by continuously traversing the scanning.

[0024] In the embodiment of the application, the parameter data of the doctor blade at least includes the coating speed and the doctor blade pressure. These parameter data are directly related to the service life of the doctor blade. Therefore, these parameters can be adjusted to avoid further wear of the doctor blade.

[0025] In the embodiment of the application, the environmental humidity can be obtained by a humidity sensor installed in the production line environment. The thermal paper image can be obtained by a camera perpendicular to the thermal paper.

[0026] In the embodiment of the present application, each kind of data is collected at a fixed sampling frequency, and the data is collected once every time the doctor blade performs a flat coating operation. Moreover, since the embodiment of the present application quantitatively evaluates the features based on the changes and correlations of various data, the obtained data can be normalized and standardized to eliminate the dimension effect during data processing. The specific technical means is well known to those skilled in the art, and thus will not be described here.

[0027] In the embodiment of the present application, after the data of each dimension is collected, the data is saved in the memory of the device and transmitted to the control terminal through the Internet of Things for data processing. The control terminal feeds back the control command to the coating device after data processing.

[0028] Step S2: dividing each thickness region on the thermal paper image according to the surface thickness of each position of the thermal paper; matching the thickness regions between adjacent time instants; obtaining the thickness change significance of each thickness region at each time instant according to the thickness difference and shape difference between the thickness regions matched between adjacent time instants; and obtaining the first coating unevenness at each time instant according to the change of the thickness change significance and the thickness change of different thickness regions at each time instant.

[0029] Since the surface thickness of each position of the thermal paper has been obtained in the above step S1, the surface thickness of the corresponding position can be mapped in the thermal paper image, so as to divide each thickness region in the thermal paper image, wherein one thickness region is a region composed of similar surface thickness and continuous positions. Since the coating is performed in time sequence, the changes of each thickness region between adjacent time instants can be analyzed, and then the features generated by the coating at each time instant can be quantified.

[0030] In the embodiment of the present application, the thickness regions between adjacent time instants are matched. For the thickness regions matched with each other, if the thickness difference is greater, it indicates that effective coating is performed at one time instant, and the coating thickness changes obviously. If the shape difference between the matched regions is generated, it indicates that the coating effect at one time instant is poor, and the doctor blade cannot effectively uniformly coat the paint. Therefore, the thickness change significance of each thickness region at each time instant is obtained according to the thickness difference and shape difference between the thickness regions matched between adjacent time instants. That is, the thickness change significance can represent the coating effect of the doctor blade at the corresponding time instant for each thickness region, so that the first coating unevenness at each time instant can be obtained by analyzing the change of the thickness change significance and the thickness change between different regions in the same frame of thermal paper image. That is, the greater the change of the thickness change significance and the greater the thickness change, the poorer the coating effect of the thermal paper at the current time instant, and the greater the first coating unevenness.

[0031] Preferably, in the embodiment of the present application, the thickness region division method comprises: The surface thicknesses of each position are clustered by a DBSCAN clustering algorithm, and each area of the thermal paper in the clustered cluster is a thickness area. The DBSCAN clustering algorithm is a technical means known to those skilled in the art, and will not be described here. The clustering measure in the clustering process can directly use the surface thickness difference.

[0032] In an embodiment of the present application, the previous time of each time is selected as the adjacent time, that is, for each time, the thermal paper image of the previous time is selected to match the thickness area. If the thickness area of the previous time is in the target thickness area of the current time in the same coordinate system, the thickness area of the previous time is the matching area of the target thickness area. After matching, the target thickness area can have multiple matching areas, thereby forming a matching area set of the target thickness area. Each thickness area at each time corresponds to a matching area set. It should be noted that because the embodiment of the present application selects the previous time to match each time, the corresponding thickness difference should be the average thickness of the target thickness area, and the difference between the average thickness in the matching area set, that is, the difference value retains the sign, and the obtained thickness difference is positive and larger, which indicates that more effective coating is produced at the current time.

[0033] Preferably, in the embodiment of the present application, the shape difference acquisition method comprises: Optionally, one time is selected as a target time, and one thickness area at the target time is selected as a target thickness area. The thickness area set matched with the target thickness area at the adjacent time of the target time constitutes the contrast area of the target thickness area.

[0034] It should be noted that if the thickness area set is split when merging into the contrast area, it can be filled by interpolation. Because the matching in the embodiment of the present application is in the same position in the same coordinate system, the matching areas in the thickness area set will not differ too much.

[0035] In the scanning direction of the thickness detection sensor, a width difference between the contrast region and the target thickness region is obtained; and the shape difference is obtained according to the width difference and the number of regions in the set of thickness regions matched at the adjacent time. That is, in the embodiment of the present application, the width in the scanning direction is selected as the reference data, and the shape difference between the two regions is evaluated by using the reference data. The greater the width difference, the more obvious the shape change after coating at the target time, which indicates that the coating effect at the target time is not uniform compared with the previous time. The greater the number of regions in the set of thickness regions, the more obvious the region inconsistency caused by the non-uniform coating of the doctor blade compared with the adjacent time. Therefore, the greater the width difference and the greater the number of regions in the set of thickness regions, the greater the shape difference. The greater the shape difference, the poorer the coating effect at the target time, and the smaller the thickness change significance.

[0036] In the embodiment of the present application, the Euclidean norm obtained according to the width difference and the number of regions in the set of thickness regions matched at the adjacent time is taken as the shape difference. That is, the two data are squared, summed and square rooted.

[0037] Preferably, in the embodiment of the present application, because the thickness change significance is used to represent the coating effectiveness at each time, the shape difference should be negatively correlated with the thickness change significance, and the thickness difference should be positively correlated. Therefore, the shape difference is negatively mapped and normalized, and then multiplied by the thickness difference to obtain the thickness change significance.

[0038] In the embodiment of the present application, the inverse of the shape difference is taken as the power of the exponential function with the natural constant as the base number, and the output data of the exponential function is the result of the negative correlation mapping and normalization.

[0039] Preferably, in the embodiment of the present application, the first coating non-uniformity obtaining method comprises: For each thickness region, the thickness change significance and the average thickness of the region are multiplied to obtain a thickness coating feature; at each time, the thickness coating feature difference between all the thickness regions is obtained, and the cumulative sum of all the thickness coating feature differences is taken as the first coating non-uniformity at each time. That is, in the embodiment of the present application, the thickness change significance and the average thickness of the region are integrated and quantified by using the multiplication method, and then the first coating non-uniformity can be obtained by the difference between the thickness coating features, that is, the greater the difference between the coating features of the regions, the more uneven the coating effect in the current thermal paper image.

[0040] It should be noted that in other embodiments of the present application, the variance of the thickness coating feature can also be used as the first coating non-uniformity to represent the fluctuation and non-uniformity of the data.

[0041] Step S3: obtaining a linear correlation between the time-series ambient humidity and the first coating unevenness, and obtaining a second coating unevenness according to the linear correlation and the first coating unevenness.

[0042] If the ambient humidity is too high, the base material on the paper surface will absorb moisture and swell, affecting the adhesion of the coating, and further affecting the thickness change of the thermal paper, leading to misjudgment of the degree of doctor blade wear. That is, if the ambient humidity at this time can affect the thickness, it means that the first coating unevenness currently judged is not simply caused by the doctor blade wear, and the influence of humidity needs to be eliminated before judging whether the doctor blade wear is currently generated. Therefore, the embodiment of the present application obtains the linear correlation between the time-series ambient humidity and the first coating unevenness, that is, the more related the two dimensions of data are, the more the thickness unevenness at this time is affected by humidity, and then the first coating unevenness is adjusted based on the linear correlation to obtain the second coating unevenness.

[0043] Preferably, in the embodiment of the present application, the method for obtaining the second coating unevenness comprises: A coordinate system is constructed and curve fitting is performed with the first coating unevenness as the ordinate and the ambient humidity at the corresponding time as the abscissa to obtain the tangent slope on the fitting curve at each time.

[0044] It should be noted that the least square method is used to fit the curve in the embodiment of the present application, and the fitting curve here is the same as the curve of the following parameter data, which is realized by the least square method. The specific content is a conventional means used by those skilled in the art, which is not described here.

[0045] The greater the tangent slope is, the stronger the linear correlation between the two dimensions is, so the tangent slope is negatively correlated and normalized to obtain the non-environmental impact weight. That is, the greater the non-environmental impact weight is, the smaller the influence of the ambient humidity on the thickness unevenness at this time is, and the first coating unevenness at this time is mainly caused by the doctor blade wear. Because the value range of the non-environmental impact weight is between 0 and 1, the product of the non-environmental impact weight and the first coating unevenness is taken as the second coating unevenness.

[0046] In the embodiment of the present application, the reciprocal of the tangent slope is taken as the power of the exponential function with the natural constant as the base number, and the output value of the exponential function is the value after negative correlation mapping and normalization. Those skilled in the art can also choose other negative correlation mapping and normalization methods, such as directly taking the reciprocal of the tangent slope as the negative correlation mapping result, and then using range standardization for normalization. The specific is not limited and described here.

[0047] Step S4: if the second coating unevenness meets the preset regulation condition, the influence weight of each parameter data on the doctor blade is obtained, the adjustment amount is obtained according to the influence weight and the preset adjustment step, and the real-time parameter data is adjusted based on the adjustment amount.

[0048] Because the data processing in the embodiment of the application is real-time operation, the second coating unevenness can be obtained at each time, and therefore the threshold value judgment condition can be set for the regulation and adjustment. In the embodiment of the application, the unevenness threshold value is set to 0.3, and if the normalized value of the second coating unevenness is greater than the unevenness threshold value, it is indicated that the thermal paper thickness unevenness at this time is caused by the doctor blade wear, and the doctor blade parameters need to be regulated in time. After the regulation, the real-time detection can be continuously performed, the automatic optimization of the parameter data is realized, and the closed-loop control is formed. It should be noted that when there is a time, after the doctor blade parameters are adjusted by operation, each doctor blade parameter has been adjusted to the rated upper limit or lower limit, and the second unevenness is still greater than the set unevenness threshold value, it is indicated that the current doctor blade wear period cannot be prolonged by process parameter adjustment, and the machine should be automatically stopped to reduce material loss, and the stop information and related collected data are transmitted to the remote control terminal through the Internet of Things, to remind the worker to replace the doctor blade.

[0049] In the embodiment of the application, the normalization method of the second unevenness adopts the range standardization, and the normalization of each data is realized by counting the maximum and minimum values of the second unevenness, and the specific method is a routine technical means for those skilled in the art and will not be described here.

[0050] In order to realize the effective regulation of the doctor blade parameters, the influence weight of each parameter data on the doctor blade needs to be obtained first, that is, the greater the influence weight, the more the parameter data in this dimension needs larger regulation, because the influence on the doctor blade wear is greater. The adjustment amount can be obtained in combination with the preset adjustment step. That is, the adjustment amount is a fixed amount, and the real-time parameter data can be adjusted based on the adjustment amount to realize the automatic optimization of the parameter data.

[0051] Preferably, in the embodiment of the present application, the influence weight of each parameter data on the blade wear can be determined by experimental means through the control variable method. That is, one parameter data is selected as a variable, while other parameter data remains unchanged, the variable value is gradually increased from small to large in the embodiment of the present application, and the curve of the second coating unevenness in time sequence under each value is counted. The slope of the tangent on the curve can represent the wear rate under the current value. By counting, a parameter data sequence composed of each value of the variable can be obtained, and at the same time, a wear rate sequence is obtained. After aligning the two sequences, the Pearson correlation coefficient can be obtained. The value range of the Pearson correlation coefficient is between -1 and 1. The greater the absolute value of the correlation coefficient, the higher the correlation between the parameter data and the blade wear. The positive and negative of the correlation coefficient shows the trend of the increase or decrease of the current process parameter on the blade wear. In the embodiment of the present application, the parameter data sequence is arranged in ascending order of value. Therefore, if the Pearson correlation coefficient is positive and large, it means that the blade wear is faster as the parameter data increases. If the Pearson correlation coefficient is negative and small, it means that the wear rate is slower as the parameter data increases. Therefore, the Pearson correlation coefficient can be used as the influence weight.

[0052] Further, the preset adjustment step can be obtained by the maximum adjustment amount specified in the process guide or the maximum adjustment amount preset in the process. That is, the preset adjustment step is the maximum amount that can be adjusted at one time.

[0053] Because the influence weight value range is between -1 and 1, the preset adjustment step can be weighted by multiplication. The product of the influence weight and the preset adjustment step is used as the adjustment amount. The positive and negative of the adjustment amount represents the adjustment direction. If it is positive, it means that the larger the parameter data, the more likely it is to cause further wear, so the current parameter data needs to be adjusted in the negative direction. If it is negative, it means that the smaller the parameter, the more likely it is to cause further wear, so the current parameter data needs to be adjusted in the positive direction. Therefore, in the embodiment of the present application, the difference between the real-time parameter data and the control amount can be used as the adjusted parameter data.

[0054] It should be noted that only one parameter data is used as an example in the above description. The same method can be used to analyze and process each parameter data. After obtaining the adjusted parameter data of each parameter data, the control terminal can send a control instruction to the coating equipment to adjust the parameters of the blade.

[0055] To sum up, the embodiment of the present application analyzes the thermal paper image and various information in the coating process in time sequence. The thickness change significance of each thickness area can be effectively quantified by analyzing the thickness change and shape change between adjacent time points. Then the first coating unevenness is quantified at each time point. By analyzing the linear correlation between the first coating unevenness and the environmental humidity, the influence of the current humidity can be evaluated, the second coating unevenness is obtained, the influence weight of each parameter data on the doctor blade is obtained, and the real-time parameter data is adjusted based on the adjustment amount. The present application quantifies the real unevenness caused by the doctor blade wear by analyzing the thickness change and other characteristics of the thermal paper coating process in time sequence, combines the influence of the environmental humidity on the coating thickness, quantifies the real unevenness caused by the doctor blade wear, and then adjusts the doctor blade parameters to avoid further wear of the doctor blade in time.

[0056] Based on the same inventive concept, the present application further provides an online coating data remote acquisition and analysis device for a thermal paper production line, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of any one of the online coating data remote acquisition and analysis methods for the thermal paper production line when executing the computer program.

[0057] It should be noted that the above-mentioned embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or may be advantageous.

[0058] Each embodiment in the specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other. Each embodiment mainly describes the difference from other embodiments.

Claims

1. A method for remote acquisition and analysis of online coating data in a thermal paper production line, characterized in that, The method includes: Real-time acquisition of parameter data, thermal paper images, surface thickness of thermal paper at various locations, and ambient humidity during the scraper's operation at each moment; The thermal paper image is divided into various thickness regions based on the surface thickness at various locations of the thermal paper; the thickness regions between adjacent time points are matched; the thickness difference and shape difference between the matched thickness regions at adjacent time points are used to obtain the thickness change significance of each thickness region at each time point; the first coating non-uniformity at each time point is obtained based on the change in the thickness change significance and thickness change of different thickness regions at each time point. A linear correlation between ambient humidity and first coating nonuniformity over time is obtained, and a second coating nonuniformity is obtained based on the linear correlation and the first coating nonuniformity. If the second coating non-uniformity meets the preset control conditions, the influence weight of each parameter data on the doctor blade is obtained, the adjustment amount is obtained according to the influence weight and the preset adjustment step size, and the real-time parameter data is adjusted based on the adjustment amount.

2. The method for remote acquisition and analysis of online coating data in a thermal paper production line according to claim 1, characterized in that, The thickness region division method includes: Based on the surface thickness at each location, the DBSCAN clustering algorithm is used to cluster the data, and the respective regions of the clusters on the thermal paper are taken as the thickness regions.

3. The method for remote acquisition and analysis of online coating data in a thermal paper production line according to claim 1, characterized in that, The method for obtaining the shape difference includes: Choose any time as the target time, and choose any thickness region at the target time as the target thickness region. The set of thickness regions that match the target thickness region at adjacent times constitutes the comparison region of the target thickness region. In the scanning direction of the thickness detection sensor, obtain the width difference between the comparison region and the target thickness region. Based on the width difference and the number of regions in the set of thickness regions that match at adjacent times, obtain the shape difference.

4. The method for remote acquisition and analysis of online coating data in a thermal paper production line according to claim 1, characterized in that, The method for obtaining the significance of the thickness change includes: After negatively correlated mapping and normalization of the shape difference, it is multiplied by the thickness difference to obtain the significance of the thickness change.

5. The method for remote acquisition and analysis of online coating data in a thermal paper production line according to claim 1, characterized in that, The method for obtaining the first coating non-uniformity includes: For each thickness region, the thickness variation significance is multiplied by the average thickness of the region to obtain the thickness coating characteristics; at each time step, the thickness coating characteristic differences between all thickness regions are obtained, and the sum of all thickness coating characteristic differences is taken as the first coating non-uniformity at each time step.

6. The method for remote acquisition and analysis of online coating data in a thermal paper production line according to claim 1, characterized in that, The method for obtaining the second coating non-uniformity includes: Using the first coating non-uniformity as the ordinate and the ambient humidity at the corresponding time as the abscissa, a coordinate system is constructed and curve fitting is performed to obtain the tangent slope on the fitted curve at each time. The tangent slope is negatively correlated and normalized to obtain the non-environmental influence weight. The product of the non-environmental influence weight and the first coating non-uniformity is used as the second coating non-uniformity.

7. The method for remote acquisition and analysis of online coating data in a thermal paper production line according to claim 1, characterized in that, The methods for obtaining the influence weights include: The second coating non-uniformity curve over time is obtained for each value when each parameter data is used as a variable using the controlled variable method. The wear rate for each value is obtained based on the slope of the tangent line on the curve. The parameter data sequence used as a variable is aligned with the wear rate sequence, and the Pearson correlation coefficient is calculated. The Pearson correlation coefficient is used as the influence weight.

8. The method for remote acquisition and analysis of online coating data in a thermal paper production line according to claim 7, characterized in that, The method for obtaining the adjustment amount includes: The product of the influence weight and the preset adjustment step size is used as the control quantity.

9. The method for remote acquisition and analysis of online coating data in a thermal paper production line according to claim 8, characterized in that, The adjustment of real-time parameter data based on the adjustment amount includes: The difference between the real-time parameter data and the controlled amount is used as the parameter data after control.

10. A remote acquisition and analysis device for online coating data of a thermal paper production line, the device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the online coating data remote acquisition and analysis method for a thermal paper production line as described in any one of claims 1 to 9.

Images