A die-cutting machine operation control method and system

Abstract

The present invention relates to the field of data processing technology, and in particular to a die-cutting machine operation control method and system. The method comprises the following steps: collecting a plurality of tension data of each tension control roller; obtaining target tension data of each tension control roller; obtaining a characteristic vector of the target tension data of each tension control roller, obtaining the correlation degree of the target tension data of every two tension control rollers according to the characteristic vector, and obtaining the target tension control roller of each tension control roller according to the correlation degree; weighting the surrounding data of the target tension data of each tension control roller according to the fluctuation of the correlation degree between the surrounding data of the target tension data of each tension control roller and its target tension control roller, and obtaining the weighted moving average of the target tension data of each tension control roller; controlling the tension of each tension control roller on the die-cutting machine according to the weighted moving average, and the present invention improves the accuracy of tension control of the tension control roller.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a die-cutting machine operation control method and system. Background Art

[0002] In the production process of composite film, a die-cutting machine is required to stick multiple layers of raw film together, and the composite film is punched by a circular knife on the die-cutting machine. In this process, the tension at each tension control roller on the die-cutting machine needs to be controlled to ensure that the composite film remains flat and uniform. If the tension at the tension control roller is not properly controlled during the production process, the tension of the composite film at the tension control roller is also improperly controlled, which may cause insufficient tension on the composite film and cause positional displacement or breakage of the composite film, affecting the production quality of the composite film. Therefore, tension sensors at each tension control roller of the die-cutting machine are used to collect several tension data of each tension control roller, and compare whether the tension data of each tension control roller is within the set tension range of each tension control roller, so as to adjust each tension control roller on the die-cutting machine so that the tension on each tension control roller is maintained within its set tension range.

[0003] The patent application document with the publication number CN118625932A currently discloses a method and system for smoothing and stabilizing eye movement interaction data in a shaking environment. The eye movement data stream is filtered once by using a weighted moving average algorithm; the eye movement data stream after the primary filtering is filtered twice by using a Kalman filter algorithm; and the weighted moving average algorithm and the Kalman filter algorithm are adjusted according to the eye movement data stream after the secondary filtering by using a dynamic feedback adjustment algorithm.

[0004] Due to the large amount of electromagnetic interference in the composite film production environment and the mechanical vibration caused by the die-cutting machine itself, these factors will cause certain noise in the tension data collected by the tension sensor. The existence of noise data may cause abnormal tension adjustment of each tension control roller, and then cause the composite film to be subjected to insufficient tension and position displacement or composite film breakage. Therefore, when filtering the tension data of each tension control roller according to the weighted moving average algorithm, it is necessary to analyze the noise situation of the collected tension data, assign different weights to the tension data according to the noise situation, and then sum the weighted tension data and divide it by the total weight to complete the filtering. Summary of the invention

[0005] In order to solve the technical problem that there is a large amount of electromagnetic interference in the composite film production environment and the mechanical vibration caused by the die-cutting machine itself, which causes certain noise data in the tension data collected by the tension sensor, and may cause abnormal tension adjustment of each tension control roller, thereby affecting the production quality of the composite film, the present invention provides a die-cutting machine operation control method and system.

[0006] In a first aspect, the present invention provides a die-cutting machine operation control method, which adopts the following technical solution:

[0007] A die-cutting machine operation control method comprises the steps of:

[0008] Collect several tension data of each tension control roller; obtain target tension data of each tension control roller; obtain the correlation degree of target tension data of every two tension control rollers:

[0009] , Indicates the degree of correlation between the target tension data of the i-th tension control roller and the k-th tension control roller; represents the amplitude similarity between the i-th tension control roller and the k-th tension control roller; as well as represents the tension similarity factor of the target tension data of the i-th tension control roller and the k-th tension control roller; norm() represents the linear normalization function; || represents taking the absolute value; and the weighted moving average of the target tension data of each tension control roller is obtained:

[0010] , represents the weighted moving average of the target tension data of the i-th tension control roller; The number of surrounding data representing the target tension data of the i-th tension control roller; represents the value of the vth surrounding data of the target tension data of the i-th tension control roller; as well as They respectively represent the correlation between the vth surrounding data and the v-1th surrounding data of the target tension data of the i-th tension control roller and its target tension control roller; exp() represents an exponential function with a natural constant as the base;

[0011] The tension of each tension control roller on the die-cutting machine is controlled according to the weighted moving average value.

[0012] The innovation of the present invention lies in obtaining the correlation degree of the target tension data of two tension control rollers according to the characteristic vector of the target tension data of each tension control roller, making full use of the integrity of the composite film and the correlation of the tension at each tension control roller, and providing a more reasonable reference for obtaining the weighted moving average weight; then, according to the fluctuation of the correlation degree between the surrounding data of the target tension data of each tension control roller and its target tension control roller, the surrounding data of the target tension data of each tension control roller is weighted to obtain the weighted moving average of the target tension data of each tension control roller, and finally the tension control roller of the die-cutting machine is controlled by the tension data after the weighted moving average, which reduces the influence of the noise data in the tension data, can make the tension data of each tension control roller closer to the actual tension size, and also reduces to a certain extent the problem of reduced production quality of the composite film caused by improper tension control at the tension control roller.

[0013] Preferably, obtaining the amplitude similarity between the i-th tension control roller and the k-th tension control roller includes:

[0014] Obtain a feature vector of the target tension data of each tension control roller; and record the cosine similarity between the feature vector of the target tension data of the i-th tension control roller and the feature vector of the target tension data of the k-th tension control roller as the amplitude similarity between the i-th tension control roller and the k-th tension control roller.

[0015] Preferably, the step of obtaining a characteristic vector of target tension data of each tension control roller includes:

[0016] Obtain surrounding data and comparison data of the target tension data of each tension control roller; take the average value of all surrounding data of the target tension data of each tension control roller and the average value of all comparison data of the target tension data of each tension control roller as the feature vector of the target tension data of each tension control roller.

[0017] This facilitates the subsequent acquisition of the correlation degree of the target tension data of the two tension control rollers according to the characteristic vector of the target tension data of each tension control roller.

[0018] Preferably, the step of obtaining the surrounding data and comparison data of the target tension data of each tension control roller includes:

[0019] The number of data is preset to N, and the target tension data of each tension control roller and the previous N tension data are recorded as the surrounding data of the target tension data of each tension control roller; for the kth surrounding data of the target tension data of the ith tension control roller, the mean of the absolute values ​​of the differences between the kth surrounding data and its adjacent surrounding data is recorded as the absolute difference of the kth surrounding data, and the mean of the absolute differences of all surrounding data of the target tension data of the ith tension control roller is recorded as the first mean; if the absolute difference of any surrounding data of the target tension data of the ith tension control roller is less than the first mean, the surrounding data is recorded as the comparison data of the target tension data of the ith tension control roller.

[0020] Preferably, obtaining the tension similarity factor of the target tension data of the tension control roller includes:

[0021] The cosine similarity between the feature vector of the target tension data of each tension control roller and the feature vector of the previous tension data of the target tension data of each tension control roller is recorded as the tension similarity factor of the target tension data of each tension control roller.

[0022] Preferably, the acquisition of the target tension control roller data includes:

[0023] According to the method for obtaining the correlation degree of the target tension data of the two tension control rollers, the correlation degree of each surrounding data of the target tension data of the i-th tension control roller and the k-th tension control roller is obtained, and the average of the correlation degrees of all the surrounding data is recorded as the final correlation degree of the target tension data of the i-th tension control roller and the k-th tension control roller;

[0024] The final correlation degree between the i-th tension control roller and the target tension data of each tension control roller except the i-th tension control roller is obtained, and the tension control roller corresponding to the maximum value in the final correlation degree is recorded as the target tension control roller of the i-th tension control roller.

[0025] It is convenient for subsequent comparison of the fluctuation of the correlation degree between the surrounding data of the tension control roller and the target tension data of its target tension control roller, and can better reflect the noise situation of the surrounding data.

[0026] Preferably, controlling the tension of each tension control roller on the die-cutting machine according to the weighted moving average value comprises:

[0027] If the mean of the weighted moving average of all tension data of any tension control roller on the die-cutting machine is not within the set tension range of the tension control roller, the tension control roller on the die-cutting machine is adjusted so that the tension at the tension control roller is maintained at the set tension, thereby completing the operation control of the die-cutting machine.

[0028] The tension data at the tension control roller is controlled according to the filtered tension data, which reduces the influence of noise to a certain extent, makes the tension control at the tension control roller more accurate, and improves the production quality of the composite film.

[0029] Preferably, the step of obtaining target tension data of each tension control roller includes:

[0030] Any sampling moment is recorded as a target moment; and the tension data of each tension control roller at the target moment is recorded as the target tension data of each tension control roller.

[0031] In a second aspect, the present invention provides a die-cutting machine operation control system, which adopts the following technical solution:

[0032] A die-cutting machine operation control system comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned die-cutting machine operation control method is implemented.

[0033] By adopting the above technical solution, the above-mentioned die-cutting machine operation control method is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a terminal device based on the memory and the processor for easy use.

[0034] The present invention has the following technical effects: the purpose of the present invention is to first obtain the degree of correlation of the target tension data of two tension control rollers according to the characteristic vector of the target tension data of each tension control roller, make full use of the integrity of the composite film and the correlation of the tension at each tension control roller, and provide a more reasonable reference for obtaining the weighted moving average weight; then, according to the fluctuation of the degree of correlation between the surrounding data of the target tension data of each tension control roller and its target tension control roller, weight the surrounding data of the target tension data of each tension control roller to obtain the weighted moving average of the target tension data of each tension control roller, and finally control the tension control roller of the die-cutting machine by the tension data after the weighted moving average, so that the tension data of each tension control roller can be closer to the actual tension size, and to a certain extent reduce the problem of reduced production quality of the composite film caused by improper tension control at the tension control roller. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0036] Figure 1 The present invention is a flowchart of a method for controlling the operation of a die-cutting machine according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] 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 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0038] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0039] The embodiment of the present invention discloses a die-cutting machine operation control method, referring to Figure 1 , comprising steps S1 to S4:

[0040] S1: Collect several tension data of each tension control roller.

[0041] In the implementation of the present invention, the sampling time is preset to 2 seconds / time, and the data is collected for a total of one hour. A tension sensor is installed on each tension control roller in the die-cutting machine. During the stable production of the composite film, the tension data of each tension control roller on the die-cutting machine is collected to obtain a plurality of tension data of each tension control roller. It should be noted that the tension data of each tension control roller correspond to each other in time sequence.

[0042] S2: Record any sampling moment as the target moment; record the tension data of each tension control roller at the target moment as the target tension data of each tension control roller, and obtain the characteristic vector of the target tension data of each tension control roller.

[0043] It should be noted that, through the tension sensors at each tension control roller of the die-cutting machine, several tension data of each tension control roller are collected, and the tension data of each tension control roller are compared to see whether they are within the set tension range of each tension control roller, so as to adjust each tension control roller on the die-cutting machine, so that the tension on each tension control roller is maintained within its set tension range, thereby completing the adjustment of the tension on the composite film and the control of the die-cutting machine. However, in the composite film production environment, there are a large amount of electromagnetic interference and mechanical vibration caused by the die-cutting machine itself. These factors will cause certain noise in the tension data collected by the tension sensor. The presence of noise data may cause abnormal tension adjustment of each tension control roller, and then cause the tension of the generated composite film to be insufficient, resulting in positional displacement or fracture of the composite film. Therefore, the present invention uses a weighted moving average algorithm to filter several tension data of each tension control roller, and needs to analyze the noise condition of the collected tension data, assign different weights to the tension data according to the noise condition, and then sum the weighted tension data and divide it by the sum of the weights to complete the filtering.

[0044] It should be noted that when the die-cutting machine is operating normally, the tension of each tension control roller should change smoothly, and the composite film of each tension control roller is in different stages of the production process. Some composite films of tension control rollers are in a single-layer state, and some composite films of tension control rollers are in a multi-layer state. Therefore, there will be certain differences in the tension of each tension control roller. Therefore, any sampling moment is recorded as the target moment, and the surrounding data of any tension data of each tension control roller is first obtained. Subsequently, the average value of all tension data in the surrounding data of any tension data of each tension control roller can be used as one of the characteristic vectors of any tension data of each tension control roller.

[0045] Due to the large amount of electromagnetic interference in the composite film production environment and the mechanical vibration caused by the die-cutting machine itself, these factors will cause noise data to exist in the tension data collected by the tension sensor. It is known that the difference between the noise data and its adjacent data is large. Therefore, based on the difference between the tension data and its adjacent data, the absolute difference of each tension data in the surrounding data of any tension data of each tension control roller is obtained, and then the tension data with a large absolute difference is deleted to obtain the comparison data in the surrounding data of any tension data of each tension control roller, eliminating the influence of the noise data, and taking the average value of all comparison data in the surrounding data of any tension data of each tension control roller as one of the characteristic vectors of the target tension data of each tension control roller.

[0046] In an embodiment of the present invention, any sampling moment is recorded as a target moment; the tension data of each tension control roller at the target moment is recorded as the target tension data of each tension control roller; the target tension data of each tension control roller and the N tension data before it are all recorded as the surrounding data of the target tension data of each tension control roller; in an embodiment of the present invention, the preset number of data N=5, in other embodiments, the implementer can preset the value of the number of data N according to the specific implementation method.

[0047] For the kth surrounding data of the target tension data of the i-th tension control roller, the mean of the absolute values ​​of the differences between the kth surrounding data and its adjacent surrounding data is recorded as the absolute difference of the kth surrounding data, and the mean of the absolute differences of all surrounding data of the target tension data of the i-th tension control roller is recorded as the first mean; if the absolute difference of any surrounding data of the target tension data of the i-th tension control roller is less than the first mean, the surrounding data is recorded as the comparison data of the target tension data of the i-th tension control roller.

[0048] The average value of all surrounding data of the target tension data of the i-th tension control roller and the average value of all comparison data of the target tension data of the i-th tension control roller are used as the feature vector of the target tension data of the i-th tension control roller.

[0049] S3: According to the feature vector of the target tension data of each tension control roller, the correlation degree of the target tension data of every two tension control rollers is obtained.

[0050] It should be noted that during the production process of composite film, multiple single-layer films need to be bonded and punched. During this process, composite films at different positions on the die-cutting machine will be in different production states. Composite films at some positions are single-layered, and composite films at some positions are multi-layered. Therefore, the tension data collected under the tension control rollers at different positions have different characteristics. However, since the composite film is a whole, the tension data collected by each tension control roller on the die-cutting machine also have a certain correlation. However, due to the large amount of electromagnetic interference in the composite film production environment and the mechanical vibration caused by the die-cutting machine itself, there are certain noise data in the tension data collected by the tension sensor, and the noise data has a certain randomness. Therefore, the existence of noise data will cause the correlation between the tension data collected by a certain tension control roller and the tension data collected by other tension control rollers to change significantly.

[0051] When the cosine similarity between the characteristic vectors of the target tension data of any two tension control rollers is larger, it means that the amplitudes of the target tension data of the two tension control rollers are more similar, and the correlation degree of the target tension data of the two tension control rollers is higher at this time; however, the similarity in the amplitude of the tension data collected by the two tension control rollers cannot fully represent the correlation between the two tension control rollers. If the target tension data of the two tension control rollers have similar change trends, the target tension data of the two tension control rollers are also correlated to a certain extent. If the target tension data of the tension control roller is more similar to the previous tension data, it means that the change of the target tension data of the tension control roller is smaller. Therefore, if the change of the target tension data of the two tension control rollers is closer, the correlation degree of the target tension data of the two tension control rollers is greater.

[0052] Therefore, according to the amplitude similarity of the target tension data of the two tension control rollers and the proximity of the change of the target tension data of the two tension control rollers, the correlation degree of the target tension data of the two tension control rollers is obtained.

[0053] In the embodiment of the present invention, the cosine similarity between the feature vector of the target tension data of each tension control roller and the feature vector of the previous tension data of the target tension data of each tension control roller is recorded as the tension similarity factor of the target tension data of each tension control roller;

[0054] The cosine similarity between the feature vector of the target tension data of the i-th tension control roller and the feature vector of the target tension data of the k-th tension control roller is recorded as the amplitude similarity between the i-th tension control roller and the k-th tension control roller;

[0055] The calculation formula for obtaining the correlation degree between the target tension data of the i-th tension control roller and the k-th tension control roller is:

[0056] ;

[0057] In the formula, Indicates the degree of correlation between the target tension data of the i-th tension control roller and the k-th tension control roller; represents the amplitude similarity between the i-th tension control roller and the k-th tension control roller; A tension similarity factor representing the target tension data of the i-th tension control roller; represents the tension similarity factor of the target tension data of the kth tension control roller; norm() represents the linear normalization function; || represents taking the absolute value; The larger the value is, the more similar the amplitudes of the target tension data of the two tension control rollers are. At this time, the correlation degree of the target tension data of the two tension control rollers is greater. The smaller the value of , the smaller the change in the target tension data of the i-th tension control roller; The smaller the value is, the closer the changes in the target tension data of the two tension control rollers are, and the greater the correlation between the target tension data of the two tension control rollers is.

[0058] S4: According to the correlation degree between the target tension data of the two tension control rollers, the target tension control roller of each tension control roller is obtained; according to the fluctuation of the correlation degree between each tension control roller and the surrounding data of the target tension data of its target tension control roller, the surrounding data of the target tension data of each tension control roller is weighted to obtain the weighted moving average of the target tension data of each tension control roller; according to the weighted moving average of each tension data of each tension control roller, the tension of each tension control roller on the die-cutting machine is controlled.

[0059] It should be noted that the correlation degree of the target tension data of the two tension control rollers represents the correlation between the target tension data of the two tension control rollers. The larger the correlation degree is, the more correlated the target tension data of the two tension control rollers are. Therefore, the present invention first obtains the target tension control roller of each tension control roller according to the correlation degree of the target tension data of the two tension control rollers, that is, the most correlated tension control roller of each tension control roller.

[0060] The weighted sum of the surrounding data of the target tension data of the tension control roller is used as the weighted moving average of the target tension data of the tension control roller to complete the filtering. Therefore, it is necessary to obtain the weight of the surrounding data of the target tension data of the tension control roller. If the degree of correlation between the surrounding data of the tension control roller and its target tension data of the target tension control roller fluctuates, it means that the surrounding data of the target tension data of the tension control roller is noise data, and the weight of the surrounding data of the target tension data of the tension control roller is smaller.

[0061] In the embodiment of the present invention, according to the method for obtaining the correlation degree of the target tension data of two tension control rollers, the correlation degree of each surrounding data of the target tension data of the i-th tension control roller and the k-th tension control roller is obtained, and the average of the correlation degrees of all the surrounding data is recorded as the final correlation degree of the target tension data of the i-th tension control roller and the k-th tension control roller;

[0062] Similarly, the final correlation degree between the i-th tension control roller and the target tension data of each tension control roller except the i-th tension control roller is obtained, and the tension control roller corresponding to the maximum value in the final correlation degree is recorded as the target tension control roller of the i-th tension control roller.

[0063] Get the weighted moving average of the target tension data of the i-th tension control roller:

[0064] ;

[0065] In the formula, represents the weighted moving average of the target tension data of the i-th tension control roller; The number of surrounding data representing the target tension data of the i-th tension control roller; represents the value of the vth surrounding data of the target tension data of the i-th tension control roller; represents the correlation degree between the i-th tension control roller and the v-th surrounding data of the target tension data of its target tension control roller; represents the correlation degree between the i-th tension control roller and the v-1-th surrounding data of the target tension data of its target tension control roller; exp() represents an exponential function with a natural constant as the base; represents the weight of the vth surrounding data of the target tension data of the i-th tension control roller; The larger the value is, the more it indicates that the correlation between the surrounding data of the target tension data of the two most relevant tension control rollers has fluctuated, and the fluctuation may be caused by noise data. At this time, the surrounding data of the target tension data of the two most relevant tension control rollers is more likely to be noise data, and the smaller the weight of the vth surrounding data of the target tension data of the i-th tension control roller is.

[0066] According to the method for obtaining the weighted moving average of the target tension data of the i-th tension control roller, the weighted moving average of each tension data of each tension control roller is obtained.

[0067] If the mean of the weighted moving average of all tension data of any tension control roller on the die-cutting machine is not within the set tension range of the tension control roller, the tension control roller on the die-cutting machine is adjusted so that the tension at the tension control roller is maintained at the set tension, thereby completing the operation control of the die-cutting machine and, to a certain extent, avoiding the impact of improper tension maintenance at the tension control roller on the production quality of the composite film.

[0068] The embodiment of the present invention further discloses a die-cutting machine operation control system, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a die-cutting machine operation control method according to the present invention is implemented.

[0069] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0070] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory, a dynamic random access memory, a static random access memory, an enhanced dynamic random access memory, a high bandwidth memory, a hybrid storage cube, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device.

[0071] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0072] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A die-cutting machine operation control method, characterized in that: Includes steps: Collect several tension data of each tension control roller; obtain target tension data of each tension control roller; obtain the correlation degree of target tension data of every two tension control rollers: , Indicates the degree of correlation between the target tension data of the i-th tension control roller and the k-th tension control roller; represents the amplitude similarity between the i-th tension control roller and the k-th tension control roller; as well as represents the tension similarity factor of the target tension data of the i-th tension control roller and the k-th tension control roller; norm() represents the linear normalization function; || represents taking the absolute value; and the weighted moving average of the target tension data of each tension control roller is obtained: , represents the weighted moving average of the target tension data of the i-th tension control roller; The number of surrounding data representing the target tension data of the i-th tension control roller; represents the value of the vth surrounding data of the target tension data of the i-th tension control roller; as well as They respectively represent the correlation between the vth surrounding data and the v-1th surrounding data of the target tension data of the i-th tension control roller and its target tension control roller; exp() represents an exponential function with a natural constant as the base; The tension of each tension control roller on the die-cutting machine is controlled according to the weighted moving average value.

2. A die-cutting machine operation control method according to claim 1, characterized in that: The acquisition of the amplitude similarity between the i-th tension control roller and the k-th tension control roller includes: Obtain a feature vector of the target tension data of each tension control roller; and record the cosine similarity between the feature vector of the target tension data of the i-th tension control roller and the feature vector of the target tension data of the k-th tension control roller as the amplitude similarity between the i-th tension control roller and the k-th tension control roller.

3. A die-cutting machine operation control method according to claim 2, characterized in that: The step of obtaining the characteristic vector of the target tension data of each tension control roller includes: Obtain surrounding data and comparison data of the target tension data of each tension control roller; take the average value of all surrounding data of the target tension data of each tension control roller and the average value of all comparison data of the target tension data of each tension control roller as the feature vector of the target tension data of each tension control roller.

4. A die-cutting machine operation control method according to claim 3, characterized in that: The step of obtaining surrounding data and comparison data of target tension data of each tension control roller includes: The number of data is preset to N, and the target tension data of each tension control roller and the previous N tension data are recorded as the surrounding data of the target tension data of each tension control roller; for the kth surrounding data of the target tension data of the ith tension control roller, the mean of the absolute values ​​of the differences between the kth surrounding data and its adjacent surrounding data is recorded as the absolute difference of the kth surrounding data, and the mean of the absolute differences of all surrounding data of the target tension data of the ith tension control roller is recorded as the first mean; if the absolute difference of any surrounding data of the target tension data of the ith tension control roller is less than the first mean, the surrounding data is recorded as the comparison data of the target tension data of the ith tension control roller.

5. A die-cutting machine operation control method according to claim 1, characterized in that: The acquisition of the tension similarity factor of the target tension data of the tension control roller includes: The cosine similarity between the feature vector of the target tension data of each tension control roller and the feature vector of the previous tension data of the target tension data of each tension control roller is recorded as the tension similarity factor of the target tension data of each tension control roller.

6. A die-cutting machine operation control method according to claim 1, characterized in that: The acquisition of the target tension control roller data includes: According to the method for obtaining the correlation degree of the target tension data of the two tension control rollers, the correlation degree of each surrounding data of the target tension data of the i-th tension control roller and the k-th tension control roller is obtained, and the average of the correlation degrees of all the surrounding data is recorded as the final correlation degree of the target tension data of the i-th tension control roller and the k-th tension control roller; The final correlation degree between the i-th tension control roller and the target tension data of each tension control roller except the i-th tension control roller is obtained, and the tension control roller corresponding to the maximum value in the final correlation degree is recorded as the target tension control roller of the i-th tension control roller.

7. A die-cutting machine operation control method according to claim 1, characterized in that: The controlling the tension of each tension control roller on the die-cutting machine according to the weighted moving average comprises: If the mean of the weighted moving average of all tension data of any tension control roller on the die-cutting machine is not within the set tension range of the tension control roller, the tension control roller on the die-cutting machine is adjusted so that the tension at the tension control roller is maintained at the set tension, thereby completing the operation control of the die-cutting machine.

8. A die-cutting machine operation control method according to claim 1, characterized in that: The step of obtaining target tension data of each tension control roller comprises: Any sampling moment is recorded as a target moment; and the tension data of each tension control roller at the target moment is recorded as the target tension data of each tension control roller.

9. A die-cutting machine operation control system, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a die-cutting machine operation control method according to any one of claims 1-8 is implemented.

Images