Intelligent control method and device for paper product production line

Abstract

The invention relates to the technical field of production line intelligent control, and discloses an intelligent control method and device for a paper product production line, and the method comprises the steps: collecting the thickness data and humidity data of paper through a data collection module; calculating a thickness coefficient, a humidity coefficient and a production quality index of the paper according to the thickness data and the humidity data; calculating a quality parameter matrix value of the paper according to the thickness coefficient, the humidity coefficient and the production quality index; according to the quality parameter matrix value and an estimated value based on a pre-trained standard specification matching model, calculating to obtain a matching correction value of the production line; the current state of the production line is judged according to the matching correction value, and a regulation and control value is obtained through calculation according to the current regulation and control data; and regulating and controlling the operation state of the production line according to the regulation and control value. The method has the following effects that production equipment can be controlled and adjusted, and the production quality and the product yield of paper products are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control of production lines, and in particular to an intelligent control method and device for a paper product production line. Background Art

[0002] At present, in the field of printing and packaging, the production line of paper products needs to meet high requirements for product quality and stability. Various equipment on the production line, such as printing machines, cutting machines, packaging machines, etc., need to work together accurately to ensure that products that meet specifications and quality requirements are produced. In the process of paper product production, the production quality of paper products on the production line is closely related to the performance of paper and the performance of production equipment. The adjustment of equipment parameters and paper performance needs to be set according to the quality requirements of paper products in order to meet production requirements as much as possible. At present, the monitoring and control accuracy of the production line for paper products is not high, resulting in deviations between the produced paper products and the requirements, resulting in low product yield, or large fluctuations in the quality of paper products during production, which is not conducive to the stable production regulation.

[0003] In a prior art, a method, apparatus and computing equipment for automatic control of a production line include: collecting image information of the surfaces of multiple products in a first production line; wherein the first production line is a production line for producing the same kind of product; based on the image information, determining the quality characteristic value of each product, and determining the total quality value of the first production line; when the total quality value is less than a set quality threshold, adjusting the operating parameters of the first production line.

[0004] The existing technology does not collect data on the thickness and humidity of paper, which results in uneven quality and large quality fluctuations of products produced on the production line, resulting in a low product yield. Summary of the invention

[0005] The present invention provides an intelligent control method and device for a paper product production line to solve the problems of uneven quality and large quality fluctuations of products produced on the production line, and to improve the production quality and product yield of paper products. In a first aspect, in order to solve the above technical problems, the present invention provides an intelligent control method for a paper product production line, comprising: Collect paper thickness data and humidity data through the data acquisition module; Calculating the thickness coefficient, moisture coefficient and production quality index of the paper according to the thickness data and the moisture data; Calculating a quality parameter matrix value of paper according to the thickness coefficient, the moisture coefficient and the production quality index; Calculate the matching correction value of the production line according to the quality parameter matrix value and the estimated value based on the pre-trained standard specification matching model; Determining the current state of the production line according to the matching correction value; When it is determined that the current state of the production line is abnormal, current control data is obtained, and a control value is calculated based on the current control data; wherein the current control data includes a current judgment value and an initial judgment value; Regulating the operating state of the production line according to the regulation value; The training process of the standard specification matching model includes: Obtain historical thickness data, historical moisture data, historical length data and historical raw material absorption speed; Performing data preprocessing on the historical thickness data, the historical humidity data, the historical length data and the historical raw material absorption speed to obtain standardized data; An initial specification matching model is constructed based on the linear regression algorithm using the standardized data as input data, and the initial specification matching model is trained according to the label samples to obtain a standard specification matching model.

[0006] In an optional implementation, the calculating the thickness coefficient, the moisture coefficient and the production quality index of the paper according to the thickness data and the moisture data includes: The thickness factor is calculated by the following formula: ; The humidity coefficient is calculated by the following formula: ; The production quality index is calculated by the following formula: ; in, is the thickness coefficient, It is The thickness data of each paper, It is The humidity data of each paper, is the threshold of paper thickness data, is the threshold value of paper humidity data, is the total number of data points; is the humidity coefficient, is the conversion calculation coefficient, is the paper width data, is the paper absorption speed, is the speed at which paper absorbs raw materials, is the length data of the paper, is a production parameter; is the production quality index, is the humidity data of the finished paper product, It is the thickness data of the finished paper. is the humidity data of paper raw materials, is the thickness data of paper raw material, It is the ratio of humidity compensation of paper finished product to humidity data of paper raw material. It is the ratio of the thickness compensation of the finished paper to the thickness data of the paper raw material. is the production quality coefficient.

[0007] In an optional implementation, calculating the quality parameter matrix value of paper according to the thickness coefficient, the moisture coefficient and the production quality index includes: According to the production quality index ,like , the paper is determined to be qualified; if , the paper is determined as unqualified; Summing the production quality indexes of all the unqualified products to obtain the sum of the production quality indexes of the unqualified products; Based on the sum of the production quality indexes, the corrected value of the quality parameter is calculated by the following formula: ; According to the correction value, the quality parameter matrix value is calculated: ; in, is the threshold value of the production quality index, is the corrected value of the quality parameter, is the sum of the production quality index of all papers, is the sum of the production quality index of defective products, is the quality parameter matrix value, is the average value of the quality parameter, is the mean square error of the quality parameter.

[0008] In an optional implementation manner, the calculating of the matching correction value of the production line according to the quality parameter matrix value and the estimated value based on the pre-trained standard specification matching model includes: Constructing a matching correction function including an initial matching correction value according to the quality parameter matrix value and the estimated value of the standard specification matching model; Initializing parameters of the matching correction function and setting the initial matching correction value as the first matching correction feature; Iterate the matching correction function according to the gradient descent method to obtain the second matching correction feature, and record the number of iterations; Determine whether the second matching correction feature is better than the first matching correction feature, if so, update the second matching correction feature to the first matching correction feature; if not, discard the second matching correction feature; Continue to the next iteration, and when the number of iterations is greater than or equal to the preset number of iterations, output the current matching correction value as the optimal matching correction value.

[0009] The training process of the standard specification matching model includes: Obtain historical thickness data, historical moisture data, historical length data and historical raw material absorption speed; Performing data preprocessing on the historical thickness data, the historical humidity data, the historical length data and the historical raw material absorption speed to obtain standardized data; An initial specification matching model is constructed based on the linear regression algorithm using the standardized data as input data, and the initial specification matching model is trained according to the label samples to obtain a standard specification matching model.

[0010] In an optional implementation manner, judging the current state of the production line according to the matching correction value includes: if and , it is determined that the current status of the production line is normal; if or , it is determined that the current state of the production line is abnormal; in, is the matching correction value, is the lower threshold of the production line matching correction value, is the upper threshold of the production line matching correction value.

[0011] In an optional implementation, the calculating the control value according to the current control data includes: The control value is calculated by the following formula: ; in, For the the control value of the control step, For the The current judgment value of the control step, For the The initial judgment value of the control step, the current control data includes the current judgment value and the initial judgment value.

[0012] In an optional implementation, regulating the operating state of the production line according to the regulation value includes: According to the control value, the operation state of the production line is controlled: if , it is determined that the regulation continues; if , then the control is judged to be over; in, For the the control value of the control step, is the threshold of the control value.

[0013] In a second aspect, the present invention provides an intelligent control device for a paper product production line, comprising: A data acquisition module, used for collecting thickness data and humidity data of paper through a data acquisition module; A coefficient calculation module, used for calculating the thickness coefficient, moisture coefficient and production quality index of the paper according to the thickness data and the moisture data; A quality parameter matrix value calculation module, used for calculating the quality parameter matrix value of paper according to the thickness coefficient, the moisture coefficient and the production quality index; A matching correction value calculation module, used to calculate the matching correction value of the production line according to the quality parameter matrix value and the estimated value based on the pre-trained standard specification matching model; A current state judgment module, used to judge the current state of the production line according to the matching correction value; A control value calculation module, used to obtain current control data when it is determined that the current state of the production line is abnormal, and calculate the control value according to the current control data; An operation state control module, used to control the operation state of the production line according to the control value; The training process of the standard specification matching model includes: Obtain historical thickness data, historical moisture data, historical length data and historical raw material absorption speed; Performing data preprocessing on the historical thickness data, the historical humidity data, the historical length data and the historical raw material absorption speed to obtain standardized data; An initial specification matching model is constructed based on the linear regression algorithm using the standardized data as input data, and the initial specification matching model is trained according to the label samples to obtain a standard specification matching model.

[0014] In a third aspect, the present invention further provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements an intelligent control method for a paper product production line as described in any one of the above.

[0015] In a fourth aspect, the present invention further provides a computer-readable storage medium, the computer-readable storage medium comprising a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned intelligent control methods for a paper product production line.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention discloses an intelligent control method for a paper product production line, the method comprising collecting paper thickness data and humidity data through a data acquisition module; calculating the paper thickness coefficient, humidity coefficient and production quality index according to the thickness data and humidity data; calculating the paper quality parameter matrix value according to the thickness coefficient, humidity coefficient and production quality index; calculating the matching correction value of the production line according to the quality parameter matrix value and the estimated value based on the pre-trained standard specification matching model; judging the current state of the production line according to the matching correction value and calculating the control value according to the current control data; and controlling the operation state of the production line according to the control value. The method has the following effects: it can control and adjust the production equipment, and improve the production quality and product yield of paper products. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic flow chart of an intelligent control method for a paper product production line provided by the first embodiment of the present invention; Figure 2 It is a structural schematic diagram of an intelligent control device for a paper product production line provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] At present, in the field of printing and packaging, the production line of paper products needs to meet high requirements for product quality and stability. Various equipment on the production line, such as printing machines, cutting machines, packaging machines, etc., need to work together accurately to ensure that products that meet specifications and quality requirements are produced. In the process of paper product production, the production quality of paper products on the production line is closely related to the performance of paper and the performance of production equipment. The adjustment of equipment parameters and paper performance needs to be set according to the quality requirements of paper products in order to meet production requirements as much as possible. At present, the monitoring and control accuracy of the production line for paper products is not high, resulting in deviations between the produced paper products and the requirements, resulting in low product yield, or large fluctuations in the quality of paper products during production, which is not conducive to the stable production regulation.

[0020] In a prior art, a method, device and computing equipment for automatic control of a production line include: collecting image information of the surfaces of multiple products in a first production line; wherein the first production line is a production line for producing the same product; based on the image information, determining the quality characteristic value of each product, and determining the total quality value of the first production line; when the total quality value is less than a set quality threshold, adjusting the operating parameters of the first production line. However, the prior art does not collect data on the thickness and humidity of paper, resulting in uneven quality and large quality fluctuations of the products produced on the production line, resulting in a low product yield.

[0021] To solve the above problems, refer to Figure 1 The first embodiment of the present invention provides an intelligent control method for a paper product production line, comprising the following steps: S11, collecting thickness data and humidity data of paper through a data collection module; S12, calculating the thickness coefficient, humidity coefficient and production quality index of the paper according to the thickness data and the humidity data; S13, calculating a quality parameter matrix value of paper according to the thickness coefficient, the moisture coefficient and the production quality index; S14, calculating a matching correction value of the production line according to the quality parameter matrix value and an estimated value based on a pre-trained standard specification matching model; S15, judging the current state of the production line according to the matching correction value; S16, when it is determined that the current state of the production line is abnormal, obtaining current control data, and calculating a control value according to the current control data; S17, regulating the operation state of the production line according to the regulation value; The training process of the standard specification matching model includes: Obtain historical thickness data, historical moisture data, historical length data and historical raw material absorption speed; Performing data preprocessing on the historical thickness data, the historical humidity data, the historical length data and the historical raw material absorption speed to obtain standardized data; An initial specification matching model is constructed based on the linear regression algorithm using the standardized data as input data, and the initial specification matching model is trained according to the label samples to obtain a standard specification matching model.

[0022] The present invention discloses an intelligent control method for a paper product production line, the method comprising collecting paper thickness data and humidity data through a data acquisition module; calculating the paper thickness coefficient, humidity coefficient and production quality index according to the thickness data and humidity data; calculating the paper quality parameter matrix value according to the thickness coefficient, humidity coefficient and production quality index; calculating the matching correction value of the production line according to the quality parameter matrix value and the estimated value based on the pre-trained standard specification matching model; judging the current state of the production line according to the matching correction value and calculating the control value according to the current control data; and controlling the operation state of the production line according to the control value. The method has the following effects: it can control and adjust the production equipment, and improve the production quality and product yield of paper products.

[0023] In step S11, the thickness data and humidity data of the paper are collected by a data collection module.

[0024] It should be noted that in a specific application scenario, the paper thickness data can use the STM32 series microcontroller as the main controller, and the capacitance value between the two metal plates of the parallel plate capacitor can be collected in real time through the FC method to detect the corresponding paper thickness, or the capacitance value change of the capacitive sensor FDC2214 based on the LC resonant circuit principle can be used to collect the paper thickness data. The paper humidity data can be collected using the USR-SENS-WSD temperature and humidity data acquisition module, which supports the MODBUS protocol and can read humidity data through the command frame. In a specific application scenario, the command frame for reading humidity data is 0x11 0x04 0x00 0x00 0x00 0x01 0x33 0x5A, and the response frame is 0x11 0x04 0x02 0x010xC3 0x39 0x32, where the returned humidity data is 0x01C3, which is converted to decimal 451, indicating that the current relative humidity is 45.1%.

[0025] In step S12, the thickness coefficient, moisture coefficient and production quality index of the paper are calculated according to the thickness data and the moisture data.

[0026] The thickness factor is calculated by the following formula: ; The humidity coefficient is calculated by the following formula: ; The production quality index is calculated by the following formula: ; in, is the thickness coefficient, It is The thickness data of each paper, It is The humidity data of each paper, is the threshold of paper thickness data, is the threshold value of paper humidity data, is the total number of data points; is the humidity coefficient, is the conversion calculation coefficient, is the paper width data, is the paper absorption speed, is the speed at which paper absorbs raw materials, is the length data of the paper, is a production parameter; is the production quality index, is the humidity data of the finished paper product, It is the thickness data of the finished paper. is the humidity data of paper raw materials, is the thickness data of paper raw material, It is the ratio of humidity compensation of paper finished product to humidity data of paper raw material. It is the ratio of the thickness compensation of the finished paper to the thickness data of the paper raw material. is the production quality coefficient.

[0027] It should be noted that the threshold of paper thickness data It refers to the upper and lower limits of the allowable thickness range set during paper production and quality control to ensure that the paper meets certain quality standards. The threshold of paper thickness data is an important indicator for measuring paper uniformity and consistency. By setting the threshold, it can ensure that the paper thickness is within the specified range, thereby meeting the quality requirements of printing, packaging and other applications. The uniformity of paper thickness is crucial to printing performance. Paper with inconsistent thickness may cause uneven printing pressure and uneven ink color, affecting the quality of printed products.

[0028] Threshold value for paper moisture data It refers to the upper and lower limits of the humidity range set to ensure the quality and performance of paper during paper production, processing and use. The moisture content of paper has an important impact on its physical properties and printability. Too high or too low humidity will lead to a decrease in paper performance.

[0029] Paper absorption speed It refers to the time required for a certain amount of water or other solution to be absorbed by the paper after it drops onto the surface of the paper. The absorption speed of the paper affects the absorption of the ink during the printing process. If the paper absorbs too quickly, too much of the binder in the ink will be absorbed into the paper, resulting in a decrease in the number of pigment particles deposited on the surface of the paper, and the ink film will lack luster after drying. In severe cases, the print will fall off as soon as it is wiped off, which is the so-called ink powdering phenomenon. On the contrary, if the paper absorbs too slowly, the ink will dry slowly, and it is easy to cause the back to stick and dirty.

[0030] Paper absorbs raw materials quickly It refers to the ability of paper to absorb ink or liquid during the production or printing process, especially the absorption speed. This involves factors such as the pore structure, fiber properties, beating degree and paper structure of the paper. The ink absorption of paper is an important printability index for evaluating the performance of printing paper and affecting the quality of printed products. Inappropriate paper ink absorption will have an adverse effect on the quality of printed products. For example, if the ink absorption of paper is too high, it will lead to excessive absorption of ink binders, dull and matte prints, and even show-through or powdering; if the ink absorption is too low, the ink drying speed will be slowed down, which will easily cause the back of the printed product to be stained.

[0031] Production Quality Index It is a comprehensive index that reflects the average degree of change in product quality over a certain period of time. The production quality index can help companies monitor and evaluate the quality level of their products. By analyzing the changing trend of the index, companies can adjust production processes and quality control measures in a timely manner to improve product quality.

[0032] Production quality factor It is an indicator that reflects the degree to which a product or service meets the specified standards and requirements at each link and stage in the production process. It is expressed in relative numbers, i.e. proportions, ratios, percentages, such as overall indicators such as product qualification rate, scrap rate, and finished product repair rate.

[0033] In step S13, the quality parameter matrix value of the paper is calculated according to the thickness coefficient, the moisture coefficient and the production quality index.

[0034] According to the production quality index ,like , the paper is determined to be qualified; if , the paper is determined as unqualified; Summing the production quality indexes of all the unqualified products to obtain the sum of the production quality indexes of the unqualified products; Based on the sum of the production quality indexes, the corrected value of the quality parameter is calculated by the following formula: ; According to the correction value, the quality parameter matrix value is calculated: ; in, is the threshold value of the production quality index, is the corrected value of the quality parameter, is the sum of the production quality index of all papers, is the sum of the production quality index of defective products, is the quality parameter matrix value, is the average value of the quality parameter, is the mean square error of the quality parameter.

[0035] It should be noted that the threshold of the production quality index It refers to a critical value used to judge whether the product quality meets the established standards or requirements in quality management. The threshold of the production quality index can help enterprises set quality control goals and standards. By comparing with the threshold, it can be judged whether the production process is under control and whether the product meets the quality requirements.

[0036] Corrected values ​​of quality parameters It is a specific value used to compensate or reduce the influence of systematic errors in measurement results. Its size is equal to the indication error, but its sign is opposite. There are two ways to obtain the correction value: one is to directly obtain the correction value through the verification or calibration certificate; the other is to calculate or analyze the correction value and correction factor based on the results in the verification or calibration certificate. For measuring instruments with a single range or using only a single range, the correction value of the measuring instrument can be calculated based on the indication of the verification or calibration point in the verification or calibration certificate and the corresponding standard value. For measuring instruments using multiple ranges, if the results of each verification or calibration point in the verification or calibration certificate have a good linear relationship, the correction factor of the measuring instrument can be calculated by linear regression; if the linear relationship is not good, the correction value of each calibration point can be calculated first, and then the correction value curve can be drawn. When using it, the corresponding correction value can be found on the curve according to the measurement result. The correction value can help improve the accuracy of the measurement result, and make the measurement value closer to the true value by compensating for the systematic error.

[0037] Average value of quality parameters It is a quantity used to describe the trend of a set of quality parameter data. In quality management, the average value of quality parameters is an important indicator to measure the stability and consistency of the production process. By monitoring the changes in the average value, abnormalities in the production process can be discovered in a timely manner.

[0038] Mean square error of quality parameters Refers to the standard deviation of the quality parameter, and the mean square error of the quality parameter can be calculated by the following steps: S131. First, calculate the average value (mean) of all quality parameters; S132. For each data point, calculate the difference between it and the mean, then square the difference, and finally add up all the squared differences; S133. Divide the sum of squared deviations by the number of data points (for population variance) or the number minus one (for sample variance) to obtain the variance of the quality parameter; S134. Take the square root of the variance and the result is the mean square deviation of the quality parameter.

[0039] In step S14, the matching correction value of the production line is calculated according to the quality parameter matrix value and the estimated value based on the pre-trained standard specification matching model.

[0040] Constructing a matching correction function including an initial matching correction value according to the quality parameter matrix value and the estimated value of the standard specification matching model; Initializing parameters of the matching correction function and setting the initial matching correction value as the first matching correction feature; Iterate the matching correction function according to the gradient descent method to obtain the second matching correction feature, and record the number of iterations; Determine whether the second matching correction feature is better than the first matching correction feature, if so, update the second matching correction feature to the first matching correction feature; if not, discard the second matching correction feature; Continue to the next iteration, and when the number of iterations is greater than or equal to the preset number of iterations, output the current matching correction value as the optimal matching correction value.

[0041] The training process of the standard specification matching model includes: Obtain historical thickness data, historical moisture data, historical length data and historical raw material absorption speed; Performing data preprocessing on the historical thickness data, the historical humidity data, the historical length data and the historical raw material absorption speed to obtain standardized data; An initial specification matching model is constructed based on the linear regression algorithm using the standardized data as input data, and the initial specification matching model is trained according to the label samples to obtain a standard specification matching model.

[0042] It should be noted that the standard specification matching model refers to a set of standards or rules used to evaluate and ensure the matching degree between parts. This model can be based on physics, such as actual measured dimensional data; or based on computer simulation, such as simulated assembly of CAD models. The standard specification matching model can reduce the adjustment and correction work in production and improve production efficiency.

[0043] The estimated value of the standard specification matching model refers to the specification matching result predicted based on existing data and algorithms before the model is actually applied. By collecting relevant production parameter data, including but not limited to parameters such as size, shape, and function, the data is cleaned and standardized, and the model is trained using a linear regression algorithm. The model's predictive ability is then evaluated through cross-validation or an independent test set to obtain an estimated value. The estimated value can be used to evaluate the accuracy and reliability of the model and help understand the performance of the model in actual applications.

[0044] Match correction is an adjustment or compensation value used to correct errors or deviations in measurement or calculation to make it closer to the true value or standard value. In the specification matching model, by introducing the matching correction, the original measurement data can be adjusted to reduce the impact of systematic errors, thereby improving the accuracy of the matching results.

[0045] In step S15, the current state of the production line is determined according to the matching correction value.

[0046] if and , it is determined that the current status of the production line is normal; if or , it is determined that the current state of the production line is abnormal; in, is the matching correction value, is the lower threshold of the production line matching correction value, is the upper threshold of the production line matching correction value.

[0047] It should be noted that the matching correction value It is an adjustment or compensation value used to correct the error or deviation in measurement or calculation to make it closer to the true value or standard value. In the specification matching model, by introducing the matching correction value, the original measurement data can be adjusted to reduce the impact of systematic errors, thereby improving the accuracy of the matching results.

[0048] In step S16, when it is determined that the current state of the production line is abnormal, the current control data is acquired, and the control value is calculated based on the current control data.

[0049] The control value is calculated by the following formula: ; in, For the the control value of the control step, For the The current judgment value of the control step, For the The initial judgment value of the control step, the current control data includes the current judgment value and the initial judgment value.

[0050] It should be noted that when and , then the current state of the production line is determined to be abnormal. Among them, is the matching correction value, is the lower threshold of the production line matching correction value, is the upper threshold of the production line matching correction value.

[0051] Control data is data used to guide and adjust system operation. This data can ensure that the system operates according to predetermined goals or standards. Current control data can be collected in real time through sensors and monitoring equipment, or by analyzing historical operation data and log files to obtain past control data to guide current control data.

[0052] In step S17, the operation state of the production line is regulated according to the regulation value.

[0053] According to the control value, the operation state of the production line is controlled: if , it is determined that the regulation continues; if , then the control is judged to be over; in, For the the control value of the control step, is the threshold of the control value.

[0054] It should be noted that the control value is used to optimize the production process, improve efficiency and quality, and ensure the stability of production during the operation of the production line. In specific application scenarios, the operation status of the production line is regulated according to the control value: genetic algorithms and simulated annealing algorithms are used to optimize task scheduling to minimize production time and resource waste; or control parameters are adjusted according to real-time data, and adaptive control algorithms are used to adapt to the requirements of different working conditions to improve the flexibility and adaptability of the production line. The control value can enhance the balance of the production line, improve production capacity, and realize the "one-flow" production mode.

[0055] The following describes the working process of the present invention using a common scenario as an example. Figure 1 Schematic diagram of the working scenario of the method.

[0056] In modern papermaking enterprises, the thickness data and humidity data of paper are collected through the data acquisition module; the thickness coefficient, humidity coefficient and production quality index of paper are calculated based on the thickness data and the humidity data; the quality parameter matrix value of paper is calculated based on the thickness coefficient, the humidity coefficient and the production quality index; the matching correction value of the production line is calculated based on the quality parameter matrix value and the estimated value based on the pre-trained standard specification matching model; the current state of the production line is judged based on the matching correction value and the control value is calculated based on the current control data; the operation state of the production line is controlled according to the control value.

[0057] In summary, the present invention discloses an intelligent control method for a paper product production line, the method comprising collecting paper thickness data and humidity data through a data acquisition module; calculating the paper thickness coefficient, humidity coefficient and production quality index according to the thickness data and the humidity data; calculating the paper quality parameter matrix value according to the thickness coefficient, the humidity coefficient and the production quality index; calculating the matching correction value of the production line according to the quality parameter matrix value and the estimated value based on the pre-trained standard specification matching model; judging the current state of the production line according to the matching correction value and calculating the control value according to the current control data; and controlling the operation state of the production line according to the control value. This method has the following effects: it can control and adjust the production equipment to improve the production quality and product yield of paper products.

[0058] Reference Figure 2 The second embodiment of the present invention provides an intelligent control device for a paper product production line, comprising: A data acquisition module, used for collecting thickness data and humidity data of paper through a data acquisition module; A coefficient calculation module, used for calculating the thickness coefficient, moisture coefficient and production quality index of the paper according to the thickness data and the moisture data; A quality parameter matrix value calculation module, used for calculating the quality parameter matrix value of paper according to the thickness coefficient, the moisture coefficient and the production quality index; A matching correction value calculation module, used to calculate the matching correction value of the production line according to the quality parameter matrix value and the estimated value based on the pre-trained standard specification matching model; A current state judgment module, used to judge the current state of the production line according to the matching correction value; A control value calculation module, used to obtain current control data when it is determined that the current state of the production line is abnormal, and calculate the control value according to the current control data; An operation state control module, used to control the operation state of the production line according to the control value; The training process of the standard specification matching model includes: Obtain historical thickness data, historical moisture data, historical length data and historical raw material absorption speed; Performing data preprocessing on the historical thickness data, the historical humidity data, the historical length data and the historical raw material absorption speed to obtain standardized data; An initial specification matching model is constructed based on the linear regression algorithm using the standardized data as input data, and the initial specification matching model is trained according to the label samples to obtain a standard specification matching model.

[0059] It should be noted that the intelligent control device for a paper product production line provided in an embodiment of the present invention is used to execute all process steps of the intelligent control method for a paper product production line in the above embodiment. The working principles and beneficial effects of the two correspond one to one, and thus will not be described in detail.

[0060] The embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a data processing terminal program. When the processor executes the computer program, the steps in the above-mentioned intelligent control method for a paper product production line are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are implemented, such as the quality parameter matrix value calculation module.

[0061] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0062] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0063] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0064] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0065] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0066] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0067] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent control method for a paper product production line, characterized in that: Executed by a computer, including: Collect paper thickness data and humidity data through the data acquisition module; Calculating the thickness coefficient, moisture coefficient and production quality index of the paper according to the thickness data and the moisture data; Calculating a quality parameter matrix value of paper according to the thickness coefficient, the moisture coefficient and the production quality index; Calculate the matching correction value of the production line according to the quality parameter matrix value and the estimated value based on the pre-trained standard specification matching model; Determining the current state of the production line according to the matching correction value; When it is determined that the current state of the production line is abnormal, current control data is obtained, and a control value is calculated based on the current control data; wherein the current control data includes a current judgment value and an initial judgment value; Regulating the operating state of the production line according to the regulation value; The training process of the standard specification matching model includes: Obtain historical thickness data, historical moisture data, historical length data and historical raw material absorption speed; Performing data preprocessing on the historical thickness data, the historical humidity data, the historical length data and the historical raw material absorption speed to obtain standardized data; An initial specification matching model is constructed based on the linear regression algorithm using the standardized data as input data, and the initial specification matching model is trained according to the label samples to obtain a standard specification matching model.

2. The intelligent control method for a paper product production line according to claim 1, characterized in that: The step of calculating the thickness coefficient, the moisture coefficient and the production quality index of the paper according to the thickness data and the moisture data comprises: The thickness factor is calculated by the following formula: ； The humidity coefficient is calculated by the following formula: ； The production quality index is calculated by the following formula: ； in, is the thickness coefficient, It is The thickness data of each paper, It is The humidity data of each paper, is the threshold value of paper thickness data, is the threshold value of paper humidity data, is the total number of data points; is the humidity coefficient, is the conversion calculation coefficient, is the paper width data, is the paper absorption speed, is the speed at which paper absorbs raw materials, is the length data of the paper, is a production parameter; is the production quality index, is the humidity data of the finished paper product, It is the thickness data of the finished paper. is the humidity data of paper raw materials, is the thickness data of paper raw material, It is the ratio of humidity compensation of finished paper to humidity data of paper raw material. It is the ratio of the thickness compensation of the finished paper to the thickness data of the paper raw material. is the production quality coefficient.

3. The intelligent control method for a paper product production line according to claim 2, characterized in that: The step of calculating the quality parameter matrix value of paper according to the thickness coefficient, the moisture coefficient and the production quality index comprises: According to the production quality index ,like , the paper is determined to be qualified; if , the paper is determined as unqualified; Summing the production quality indexes of all the unqualified products to obtain the sum of the production quality indexes of the unqualified products; Based on the sum of the production quality indexes, the corrected value of the quality parameter is calculated by the following formula: ； According to the correction value, the quality parameter matrix value is calculated: ； in, is the threshold value of the production quality index, is the corrected value of the quality parameter, is the sum of the production quality index of all papers, is the sum of the production quality indexes of defective products, is the quality parameter matrix value, is the average value of the quality parameter, is the mean square error of the quality parameter.

4. The intelligent control method for a paper product production line according to claim 3, characterized in that: The method of calculating the matching correction value of the production line according to the quality parameter matrix value and the estimated value based on the pre-trained standard specification matching model includes: Constructing a matching correction function including an initial matching correction value according to the quality parameter matrix value and the estimated value of the standard specification matching model; Initializing parameters of the matching correction function and setting the initial matching correction value as the first matching correction feature; Iterate the matching correction function according to the gradient descent method to obtain the second matching correction feature, and record the number of iterations; Determine whether the second matching correction feature is better than the first matching correction feature, if so, update the second matching correction feature to the first matching correction feature; if not, discard the second matching correction feature; Continue to the next iteration, and when the number of iterations is greater than or equal to the preset number of iterations, output the current matching correction value as the optimal matching correction value.

5. The intelligent control method for a paper product production line according to claim 4, characterized in that: The judging of the current state of the production line according to the matching correction value includes: if and , it is determined that the current status of the production line is normal; if or , it is determined that the current state of the production line is abnormal; in, is the matching correction value, is the lower threshold of the production line matching correction value, is the upper threshold of the production line matching correction value.

6. The intelligent control method for a paper product production line according to claim 5, characterized in that: The calculating the control value according to the current control data includes: The control value is calculated by the following formula: ； in, For the the control value of the control step, For the The current judgment value of the control step, For the The initial judgment value of the control step, the current control data includes the current judgment value and the initial judgment value.

7. The intelligent control method for a paper product production line according to claim 1, characterized in that: The regulating the operation state of the production line according to the regulating value includes: According to the control value, the operation state of the production line is controlled: if , it is determined that the regulation continues; if , then the control is judged to be over; in, For the the control value of the control step, is the threshold of the control value.

8. An intelligent control device for a paper product production line, characterized in that: include: A data acquisition module, used for collecting thickness data and humidity data of paper through a data acquisition module; A coefficient calculation module, used for calculating the thickness coefficient, moisture coefficient and production quality index of the paper according to the thickness data and the moisture data; A quality parameter matrix value calculation module, used for calculating the quality parameter matrix value of paper according to the thickness coefficient, the moisture coefficient and the production quality index; A matching correction value calculation module, used to calculate the matching correction value of the production line according to the quality parameter matrix value and the estimated value based on the pre-trained standard specification matching model; A current state judgment module, used to judge the current state of the production line according to the matching correction value; A control value calculation module, used to obtain current control data when it is determined that the current state of the production line is abnormal, and calculate the control value according to the current control data; An operation state control module, used to control the operation state of the production line according to the control value; The training process of the standard specification matching model includes: Obtain historical thickness data, historical moisture data, historical length data and historical raw material absorption speed; Performing data preprocessing on the historical thickness data, the historical humidity data, the historical length data and the historical raw material absorption speed to obtain standardized data; An initial specification matching model is constructed based on the linear regression algorithm using the standardized data as input data, and the initial specification matching model is trained according to the label samples to obtain a standard specification matching model.

9. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, an intelligent control method for a paper product production line as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the intelligent control method for a paper product production line according to any one of claims 1 to 7.

Images