Chromatography error control method and device, electronic equipment and storage medium

Abstract

The invention provides a color register error control method, electronic equipment and a storage medium. The color register error control method comprises the following steps: acquiring a control quantity and a color register error of a current gravure unit at a first moment; the control quantity of at least one preorder gravure unit at the first moment is obtained, and the preorder gravure unit is located in front of the current gravure unit according to the printing sequence; according to the control quantity and the color register error of the current gravure unit at the first moment and the control quantity of at least one preorder gravure unit at the first moment, predicting the color register error of the current gravure unit at the second moment through an error prediction model to obtain a predicted color register error of the current gravure unit at the second moment, the second moment is after the first moment; and determining the control quantity of the current gravure unit at the second moment according to the predicted color register error of the current gravure unit at the second moment. According to the method, the color register error in the gravure printing process can be reduced.

Description

Technical Field

[0001] The present application relates to the field of printing technology, and in particular to a color registration error control method, device, electronic device and storage medium. Background Art

[0002] Intaglio printing is an important printing method, which is widely used in printing of paper, film, aluminum foil and other materials and flexible electronic materials. The printed products by intaglio printing are usually a combination of multiple color patterns, which are sequentially printed on the printing material by different gravure units. Affected by many factors in the printing process, different color patterns may not be aligned, which is called color registration error. Color registration error is a key indicator to measure the quality of printed products. When printing, the color registration error needs to be controlled within the target range.

[0003] At present, the rotation speed of the gravure roller in the gravure printing unit is controlled by a proportional integral differential (PID) algorithm to control the color registration error.

[0004] However, due to the coupling of the upstream gravure printing unit, the paper tension disturbance between the gravure printing units, the transmission lag, the slip and other factors, it is difficult for the PID feedback control to obtain accurate and stable control effects, resulting in large color registration errors. Summary of the invention

[0005] In view of this, the color registration error control method, device, electronic device and storage medium provided in the present application can reduce the color registration error in the gravure printing process.

[0006] According to an embodiment of the present application, a method for controlling a color registration error is provided, including: obtaining a control amount and a color registration error of a current gravure unit at a first moment, the control amount being used to indicate a set value of an angular velocity of rotation when the gravure unit is operating; obtaining a control amount of at least one preceding gravure unit at the first moment, the preceding gravure unit being located before the current gravure unit in the printing order; predicting the color registration error of the current gravure unit at a second moment through an error prediction model based on the control amount and the color registration error of the current gravure unit at the first moment, and the control amount of the at least one preceding gravure unit at the first moment, to obtain a predicted color registration error of the current gravure unit at the second moment, the second moment being located after the first moment; determining the control amount of the current gravure unit at the second moment based on the predicted color registration error of the current gravure unit at the second moment.

[0007] According to an embodiment of the present application, a color registration error control device is provided, including: a first acquisition unit, used to acquire a control amount and a color registration error of a current gravure unit at a first moment, wherein the control amount is used to indicate a set value of a rotational angular velocity when controlling the gravure unit; a second acquisition unit, used to acquire a control amount of at least one preceding gravure unit at the first moment, wherein the preceding gravure unit is located before the current gravure unit in the printing order; a prediction unit, used to predict the color registration error of the current gravure unit at a second moment through an error prediction model according to the control amount and the color registration error of the current gravure unit at the first moment, and the control amount of the at least one preceding gravure unit at the first moment, so as to obtain a predicted color registration error of the current gravure unit at the second moment, wherein the second moment is located after the first moment; and a control unit, used to determine the control amount of the current gravure unit at the second moment according to the predicted color registration error of the current gravure unit at the second moment.

[0008] According to an embodiment of the present application, an electronic device is provided, comprising: a processor, a memory, a communication interface and a bus, wherein the processor, the memory and the communication interface communicate with each other through the bus; the memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the color error control method described in the first aspect above.

[0009] According to an embodiment of the present application, a computer-readable storage medium is provided, on which computer instructions are stored. When the computer instructions are executed by a processor, the processor executes the color registration error control method as described in the first aspect above.

[0010] According to an embodiment of the present application, a computer program product is provided, which is tangibly stored on a computer-readable medium and includes computer-executable instructions, which, when executed, enable at least one processor to perform the color registration error control method as described in the first aspect above.

[0011] It can be seen from the above technical solution that the error prediction model can obtain the predicted color registration error of the current gravure printing unit at the second moment according to the control amount and color registration error of the current gravure printing unit at the first moment, and the control amount of at least one preceding gravure printing unit of the current gravure printing unit at the first moment, and then determine the control amount of the current gravure printing unit at the second moment according to the predicted color registration error of the current gravure printing unit at the second moment, and control the rotation angular velocity of the current gravure printing unit at the second moment according to the determined control amount, so that the current gravure printing unit produces a smaller color registration error at the second moment. Since the error prediction model is constructed by a data-driven modeling method, the error prediction model can accurately characterize the various factors that produce the color registration error, ensure the accuracy of the obtained predicted color registration error, and then control the rotation angular velocity of the current gravure printing unit at the second moment after determining the control amount according to the predicted color registration error, so that the current gravure printing unit produces a smaller color registration error at the second moment, thereby improving the quality of printed products. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 is a flow chart of a method for controlling color registration errors according to an embodiment of the present application;

[0013] Figure 2 is a schematic diagram of a gravure printing system according to an embodiment of the present application;

[0014] Figure 3 is a flow chart of a method for constructing an error prediction model according to an embodiment of the present application;

[0015] Figure 4 is a schematic diagram of an error prediction model of an embodiment of the present application;

[0016] Figure 5 is a schematic diagram of an error prediction model of another embodiment of the present application;

[0017] Figure 6 is a schematic diagram of a color registration error control process according to an embodiment of the present application;

[0018] Figure 7 is a schematic diagram of a color registration error control device according to an embodiment of the present application;

[0019] Figure 8 It is a schematic diagram of an electronic device according to an embodiment of the present application.

[0020] List of reference numerals:

[0021] 100: Color error control method 200: Gravure printing system 300: Error prediction model construction method 400: Error prediction model 700: Color error control device 800: Electronic equipment

[0022] 201: Printing material U k : Current gravure unit U k-1 : First pre-gravure printing unit

[0023] U k-2 : Second preceding gravure printing unit 601: Color error controller 602: Current gravure printing unit

[0024] 701: first acquisition unit 702: second acquisition unit 703: prediction unit

[0025] 704: control unit 802: processor 804: communication interface

[0026] 806: memory 808: bus 810: program

[0027] 101-104: Method steps 301-305: Method steps DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the embodiments of the present application should fall within the scope of protection of the embodiments of the present application.

[0029] As mentioned above, in the process of gravure printing, in order to improve the quality of printed products, it is necessary to dynamically adjust the speed of the gravure roller in the gravure printing unit to control the color registration error. At present, the color registration error at the current moment is used as the input of the PID algorithm, and the speed of the gravure roller in the gravure printing unit at the next moment is determined by the PID algorithm, and then the gravure roller is controlled to rotate according to the speed output by the PID algorithm. However, under the influence of multiple factors such as the coupling of the upstream gravure printing unit, the paper tension disturbance between the gravure printing units, the transmission lag, and the slip, the speed control of the gravure roller by PID feedback has the problem of poor accuracy and stability, resulting in a large color registration error.

[0030] In the embodiment of the present application, a data-driven modeling method is used to construct an error prediction model, and the control amount and the color registration error of the current gravure printing unit at the current moment, as well as the control amount of the previous gravure printing unit at the current moment, are used as at least part of the input of the error prediction model, and the color registration error of the current gravure printing unit at the next moment is predicted by the error prediction model, and then the control amount of the current gravure printing unit at the next moment is determined based on the prediction result. The error prediction model constructed by the pure data-driven modeling method can accurately characterize the mapping relationship between the color registration error and the model input, and then accurately predict the color registration error, and determine the control amount of the gravure printing unit at the future moment according to the prediction result, so as to reduce or eliminate the color registration error, thereby improving the quality of printed products.

[0031] The color registration error control method, device, electronic device and storage medium provided in the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0032] Chromatic Error Control Method

[0033] Figure 1 FIG. 1 is a flow chart of a method for controlling color registration errors according to an embodiment of the present invention. Figure 1 As shown, the color registration error control method 100 includes the following steps:

[0034] Step 101: Obtain the control amount and color registration error of the current gravure printing unit at the first moment.

[0035] The gravure printing system includes a plurality of gravure printing units. When gravure printing is performed, the printing material passes through each gravure printing unit in sequence, and each gravure printing unit prints a color pattern on the printing material. In order to print the required pattern on the printing material, different gravure printing units need to print the pattern to the corresponding position on the printing material. If the printing position of the pattern is offset, it will cause color registration error. According to the order in which the printing material passes, the first gravure printing unit in the gravure printing system first prints the pattern on the printing material. The pattern printed by the first gravure printing unit does not have a positional offset, that is, the first gravure printing unit does not have a color registration error, so the current gravure printing unit can be any gravure printing unit in the gravure printing system except the first gravure printing unit.

[0036] It should be noted that in each embodiment of the present application, the color registration error refers to the longitudinal color registration error, that is, the color registration error in the moving direction of the printing material, and the transverse color registration error is no longer within the scope of the embodiments of the present application.

[0037] During the printing process of the gravure printing system, the color error of the gravure printing unit will change dynamically. Therefore, it is necessary to dynamically adjust the control amount of the gravure printing unit to control the gravure printing unit to have a smaller color error. Therefore, the control cycle can be set in advance, and the control amount of the gravure printing unit can be adjusted at the beginning of each control cycle. The first moment can be the starting moment of the current control cycle.

[0038] The control amount is used to indicate the set value of the rotational angular velocity of the gravure roller in the gravure printing unit. During the printing process of the gravure printing system, the gravure roller in a gravure printing unit is controlled to rotate at a corresponding rotational angular velocity according to the control amount of a gravure printing unit. It should be noted that the control amount is the set value of the rotational angular velocity, but the actual rotational angular velocity of the gravure roller may deviate from the control amount to a certain extent.

[0039] The control amount of the current gravure printing unit at the first moment is a known amount, and the color registration error of the current gravure printing unit at the first moment can be obtained by measurement.

[0040] Step 102: Obtain a control value of at least one preceding gravure printing unit at a first moment.

[0041] In the gravure printing system, each gravure printing unit prints patterns on the substrate in sequence, and the printing order of each gravure printing unit is the same as the order in which the substrate passes through each gravure printing unit. The gravure printing unit located before the current gravure printing unit in the printing order is the preceding gravure printing unit, and the preceding gravure printing unit of the current gravure printing unit may be a plurality of consecutive gravure printing units, and the current gravure printing unit is adjacent to the last gravure printing unit among the plurality of consecutive gravure printing units.

[0042] Figure 2 Schematic diagram of a gravure printing system according to an embodiment of the present application. Figure 2 As shown, the gravure printing system 200 includes a plurality of gravure printing units. The printing material 201 moves in the direction of the arrow in the figure. The current gravure printing unit is the gravure printing unit U. k When the gravure printing unit U k-1 And gravure unit U k-2 All of them are the preceding gravure printing units of the current gravure printing unit.

[0043] Since the first moment is the current moment, the control amount of the preceding gravure printing unit at the first moment is a known amount.

[0044] Step 103: predict the color registration error of the current gravure printing unit at the second moment through an error prediction model based on the control amount and color registration error of the current gravure printing unit at the first moment and the control amount of at least one preceding gravure printing unit at the first moment, and obtain the predicted color registration error of the current gravure printing unit at the second moment.

[0045] The error prediction model can be a pre-trained neural network model, for example, the error prediction model can be obtained based on recurrent neural network (RNN) training. The error prediction model can predict the color registration error of the gravure printing unit. The input of the error prediction model includes the control amount and color registration error of the current gravure printing unit at the first moment, and the control amount of at least one preceding gravure printing unit of the current gravure printing unit at the first moment. The output of the error prediction model includes the predicted color registration error of the current gravure printing unit at the second moment. When the first moment is the current moment, the second moment is a future moment after the first moment, so the error prediction model outputs the predicted value of the color registration error of the current gravure printing unit at the second moment.

[0046] Step 104: Determine the control amount of the current gravure printing unit at the second moment according to the predicted color registration error of the current gravure printing unit at the second moment.

[0047] According to the predicted color registration error of the current gravure printing unit at the second moment, the control amount of the current gravure printing unit at the second moment can be determined, so as to control the rotation angular velocity of the current gravure printing unit at the second moment according to the determined control amount, so that the current gravure printing unit has a smaller color registration error at the second moment.

[0048] In the embodiment of the present application, the error prediction model can obtain the predicted color registration error of the current gravure printing unit at the second moment according to the control amount and color registration error of the current gravure printing unit at the first moment, and the control amount of at least one preceding gravure printing unit of the current gravure printing unit at the first moment, and then determine the control amount of the current gravure printing unit at the second moment according to the predicted color registration error of the current gravure printing unit at the second moment, and control the rotation angular velocity of the current gravure printing unit at the second moment according to the determined control amount, so that the current gravure printing unit produces a smaller color registration error at the second moment. Since the error prediction model is constructed by a data-driven modeling method, the error prediction model can accurately characterize the various factors that produce the color registration error, ensure the accuracy of the obtained predicted color registration error, and then control the rotation angular velocity of the current gravure printing unit at the second moment after determining the control amount according to the predicted color registration error, so that the current gravure printing unit produces a smaller color registration error at the second moment, thereby improving the quality of printed products.

[0049] In a possible implementation, the intermediate model can be trained by the control values ​​of the current gravure printing unit and the preceding gravure printing unit at multiple historical moments and the color registration errors of the current gravure printing unit at multiple historical moments, and then the error prediction model can be obtained based on the intermediate model. Figure 3 is a flowchart of a method for constructing an error prediction model according to an embodiment of the present application. Figure 3 As shown, the error prediction model construction method 300 includes the following steps:

[0050] Step 301: Obtain a first control quantity sequence.

[0051] The first control amount sequence includes the control amount of the current gravure printing unit at multiple historical moments, where the historical moment is before the first moment. If the first moment is the start moment of the current control cycle, the historical moment is the start moment of the historical control cycle. The multiple historical moments may include the start moment of each control cycle in a plurality of consecutive control cycles, for example, Figure 2 As shown, the first control quantity sequence is ω t-L ,ω t-L+1 ,…,ω t-2 ,ω t-1 ,ω t ,ω t is the current gravure unit U k The control quantity at time t, ω t-1 is the current gravure unit U k The control quantity at time t-1, ω t-2 is the current gravure unit U k The control quantity at time t-2, ω t-L+1 is the current gravure unit U k The control quantity at time t-L+1, ω t-L is the current gravure unit U k The control amount at time tL.

[0052] Step 302: Obtain a second control quantity sequence.

[0053] The second control amount sequence includes the control amount of each preceding gravure printing unit at multiple historical moments. The second control amount sequence may include multiple subsequences, each preceding gravure printing unit corresponds to a subsequence, and the subsequence includes the control amount of the corresponding preceding gravure printing unit at multiple historical moments. It should be noted that the multiple historical moments corresponding to the control amounts included in the subsequence are the same as the multiple historical moments corresponding to the control amounts included in the first control amount sequence, that is, at any historical moment corresponding to the control amount in the first control amount sequence, each subsequence includes the control amount of the corresponding preceding gravure printing unit at that historical moment.

[0054] For example, Figure 2 As shown, the second control amount sequence includes subsequence 1 and subsequence 2, and subsequence 1 includes the preceding gravure printing unit U k-1 The control amount at multiple historical moments, subsequence 2 includes the preceding gravure unit U k-2 The amount of control at multiple historical moments.

[0055] Subsequence 1 is ω′ t-L ,ω′ t-L+1 ,...,ω′ t-2 ,ω′ t-1 ,ω′ t,ω′ t U is the preceding gravure printing unit k-1 The control quantity at time t, ω′ t-1 U is the preceding gravure printing unit k-1 The control quantity at time t-1, ω′ t-2 U is the preceding gravure printing unit k-1 The control quantity at time t-2, ω′ t-L+1 U is the preceding gravure printing unit k-1 The control quantity at time t-L+1, ω′ t-L U is the preceding gravure printing unit k-1 The control amount at time tL.

[0056] Subsequence 2 is ω″ t-L ,ω″ t-L+1 ,...,ω″ t-2 ,ω″ t-1 ,ω″ t ,ω″ t U is the preceding gravure printing unit k-2 The control quantity at time t, ω″ t-1 U is the preceding gravure printing unit k-2 The control quantity at time t-1, ω″ t-2 U is the preceding gravure printing unit k-2 The control quantity at time t-2, ω″ t-L+1 U is the preceding gravure printing unit k-2 The control quantity at time t-L+1, ω″ t-L U is the preceding gravure printing unit k-2 The control amount at time tL.

[0057] Step 303: Obtain a color registration error sequence.

[0058] The color error sequence includes the color errors of the current gravure printing unit at multiple historical moments. The multiple historical moments corresponding to the color errors included in the color error sequence are the same as the multiple historical moments corresponding to the control quantities included in the first control quantity sequence, that is, at any historical moment corresponding to the control quantity in the first control quantity sequence, the color error sequence includes the color error of the current gravure printing unit at the historical moment.

[0059] For example, in the first control quantity sequence ω t-L ,ω t-L+1 ,…,ω t-2 ,ω t-1 ,ω t When the color error sequence is E t-L ,E t-L+1 ...,E t-2 ,E t-1 ,E t , E t is the current gravure unit Uk The color error at time t, E t-1 is the current gravure unit U k The color error at time t-1, E t-2 is the current gravure unit U k The color error at time t-2, E t-L+1 is the current gravure unit U k The color error at time t-L+1, E t-L is the current gravure unit U k Chromatic error at time tL.

[0060] Step 304: Use the first control amount sequence, the second control amount sequence and the color error sequence as model inputs to train the intermediate model.

[0061] Based on the first control amount sequence, the second control amount sequence and the color error sequence, a training sample can be constructed. The training sample is characterized by the first control amount sequence, the second control amount sequence and the color error sequence, and the color error of the current gravure printing unit at the next moment of the most recent historical moment in multiple historical moments is used as a label. For example, the training sample is based on the first control amount sequence (ω t-L ,ω t-L+1 ,...,ω t-2 ,ω t-1 ,ω t ), subsequence 1(ω′ t-L ,ω′ t-L+1 ,…,ω′ t-2 ,ω′ t-1 ,ω′ t ), subsequence 2(ω″ t-L ,ω″ t-L+1 ,…,ω″ t-2 ,ω″ t-1 ,ω″ t ) and the color error sequence (E t-L ,E t-L+1 …,E t-2 ,E t-1 ,E t ) is characterized by the color registration error of the current gravure printing unit at time t+1.

[0062] By changing multiple historical moments relative to the first moment, multiple training samples can be constructed, and different training samples correspond to different historical moment spans. For example, one training sample corresponds to a historical moment span from moment tL to moment t, and another training sample corresponds to a historical moment span from moment tL-1 to moment t-1.

[0063] The intermediate model can be trained by constructing multiple training samples. The output of the intermediate model is the color error of the current gravure printing unit at a future time relative to the historical time span corresponding to the model input. The intermediate model can be an RNN model, and the embodiment of the present application does not limit the network type of the intermediate model.

[0064] It should be noted that the time t in the embodiment of the present application is a historical time relative to the first time, and the time t and the first time may not be adjacent.

[0065] Step 305: Obtain an error prediction model according to the intermediate model.

[0066] According to the training process of the intermediate model, the intermediate model can be used to predict the color error of the current gravure printing unit at a future moment, so the error prediction model can be determined based on the intermediate model. For example, the intermediate model can be directly determined as the error prediction model, or the error prediction model can be obtained by transforming the intermediate model.

[0067] In the embodiment of the present application, an intermediate model that can predict the color registration error of the current gravure printing unit is trained through the control amount and color registration error of the current gravure printing unit at multiple historical moments, and the control amount of the previous gravure printing unit of the current gravure printing unit at multiple historical moments, and then an error prediction model for predicting the color registration error of the current gravure printing unit is obtained according to the intermediate model. Since the intermediate model is constructed using a pure data-driven modeling method, it is not necessary to understand the mechanism of the gravure printing system, no professional mechanism indication is required, and no ideal assumptions are required, which makes the model construction process simpler and can ensure that the error prediction model obtained can accurately predict the color registration error of the current gravure printing unit.

[0068] In a possible implementation manner, an intermediate model obtained through training is determined as an error prediction model.

[0069] When the intermediate model is determined as the error prediction model, the input of the error prediction model includes the control amount and the color registration error of the current gravure printing unit at the first moment and multiple moments before the first moment, and the control amount of at least one preceding gravure printing unit of the current gravure printing unit at the first moment and multiple moments before the first moment, and the output of the error prediction model is the predicted color registration error of the current gravure printing unit at the second moment.

[0070] Figure 4 FIG. 1 is a schematic diagram of an error prediction model of an embodiment of the present application. Figure 4 As shown, the input of the error prediction model 400 includes the current gravure unit U k The control quantity sequence (ω t-L ,ω t-L+1 ,…,ω t-2 ,ω t-1 ,ωt ), Pre-order gravure printing unit U k-1 The control quantity sequence (ω′ t-L ,ω′ t-L+1 ,…,ω′ t-2 ,ω′ t-1 ,ω′ t ), Pre-order gravure printing unit U k-2 The control quantity sequence (ω″ t-L ,ω″ t-L+1 ,…,ω″ t-2 ,ω″ t-1 ,ω″ t ), and the current gravure printing unit U k The error sequence (E t-L ,E t-L+1 …,E t-2 ,E t-1 ,E t ), the output of the error prediction model 400 is the current gravure unit U k Predicted color error at the second moment

[0071] It should be noted that in the embodiment of the present application and the subsequent embodiments, time t is the first time, and time t+1 is the second time, so ω t is the current gravure unit U k The control quantity at the first moment, ω′ t U is the preceding gravure printing unit k-1 The control quantity at the first moment, ω″ t U is the preceding gravure printing unit k-2 The control quantity at the first moment, E t is the current gravure unit U k Chromatic error at the first moment.

[0072] In an embodiment of the present application, the intermediate model is determined as an error prediction model for predicting the color error of the current gravure printing unit at the second moment. There is no need to transform the intermediate model, which can shorten the time for obtaining the error prediction model and improve the efficiency of obtaining the error prediction model.

[0073] In a possible implementation, when the intermediate model is determined as the error prediction model, the recursive formula of the error prediction model may be the following formula (1) and formula (2):

[0074]

[0075] Used to characterize the predicted color registration error of the current gravure printing unit at time t+1, Used to characterize the activation function, X tIt is used to represent the input vector composed of the control value and color registration error of the current gravure printing unit at time t, and the control value of at least one preceding gravure printing unit of the current gravure printing unit at time t, H t Used to characterize the hidden variables of the error prediction model at time t, H t-1 Used to characterize the hidden variables of the error prediction model at time t-1, W xh The weight matrix used to represent the hidden variables connecting the input vector, W hh The weight matrix representing the hidden variable connection itself, W ho The weight matrix used to represent the hidden variables of the predicted color error connection, b h and b o are all constants.

[0076] like Figure 4 As shown, the input of the error prediction model 400 includes the current gravure unit U k The control quantity sequence (ω t-L ,ω t-L+1 ,…,ω t-2 ,ω t-1 ,ω t ), Pre-order gravure printing unit U k-1 The control quantity sequence (ω′ t-L ,ω′ t-L+1 ,…,ω′ t-2 ,ω′ t-1 ,ω′ t ), Pre-order gravure printing unit U k-2 The control quantity sequence (ω″ t-L ,ω″ t-L+1 ,…,ω″ t-2 ,ω″ t-1 ,ω″ t ), and the current gravure printing unit U k The error sequence (E t-L ,E t-L+1 …,E t-2 ,E t-1 ,E t ). will include ω t-L ,ω′ t-L ,ω″ t-L and E t-L X t-L Substituting into the above formula (1) we can obtain H t-L , H t-L and including ω t-L+1 ,ω′ t-L+1 ,ω″ t-L+1 and E t-L+91 X t-L+1 Substituting into the above formula (1) we can obtain H t-L+1 , and so on, H t-1and including ω t ,ω′ t ,ω″ t and E t X t Substituting into the above formula (1) we can obtain H t , and then H t Substituting into the above formula (2) we can obtain

[0077] When predicting the color registration error of the current gravure printing unit at the second moment, the moment t+1 is the second moment, and the moment t is the first moment.

[0078] W xh , W hh , W ho , b h and b o are the parameters of the intermediate model, W xh , W hh and W ho It can be determined by model training, b h and b o It can be determined through model training or it can be a preset threshold.

[0079] H t-1 Characterize the hidden variables of the error prediction model at time t-1, namely H t-1 Obtained when determining the predicted color registration error of the current gravure printing unit at time t. t Characterize the hidden variables of the error prediction model at time t, that is, H t When determining the predicted color error of the current gravure printing unit at time t+1, H t It can be used to determine the predicted color registration error of the current gravure printing unit at time t+2.

[0080] In the embodiment of the present application, in the mathematical expression of the error prediction model, W xh The weight matrix that represents the hidden variables connecting the input vector, W hh The weight matrix representing the hidden variable connection itself, W ho The weight matrix representing the predicted color registration error connection hidden variables, the error prediction model calculates the predicted color registration error of the current gravure printing unit at the current moment based on the input vector, the hidden variables at the previous moment and the hidden variables at the current moment, and ensures the accuracy of the determined predicted color registration error.

[0081] In one possible implementation, an error prediction model is obtained by performing an equivalent differential transformation on the intermediate model. When the predicted color registration error of the current gravure printing unit at the second moment is determined by the error prediction model, the input of the error prediction model includes historical hidden variables, the control amount and color registration error of the current gravure printing unit at the first moment, and the control amount of at least one preceding gravure printing unit of the current gravure printing unit at the first moment. The output of the error prediction model is the predicted color registration error of the current gravure printing unit at the second moment, and the hidden variables corresponding to the second moment.

[0082] The historical hidden variables are output by the error prediction model when predicting the color error of the current gravure printing unit at the first moment. That is, when the predicted color error of the current gravure printing unit at the first moment is determined by the error prediction model, the error prediction model will output the predicted color error of the current gravure printing unit at the first moment and the hidden variables corresponding to the first moment. When determining the predicted color error of the current gravure printing unit at the second moment, the hidden variables corresponding to the first moment are historical hidden variables relative to the second moment.

[0083] When determining the predicted color error of the current gravure printing unit at the second moment, the error prediction model will output the predicted color error of the current gravure printing unit at the second moment and the hidden variables corresponding to the second moment. The hidden variables corresponding to the second moment can be used to determine the predicted color error of the current gravure printing unit at the next moment after the second moment.

[0084] In an embodiment of the present application, an error prediction model is obtained by performing an equivalent differential transformation on the intermediate model, so that the input of the error prediction model includes historical hidden variables, the control amount and the color registration error of the current gravure unit at the first moment, and the control amount of at least one preceding gravure unit of the current gravure unit at the first moment, without the need to input relevant data of the current gravure unit and the preceding gravure unit at multiple historical moments, that is, only the latest state features need to be input, and no feature sequence needs to be input, thereby improving the efficiency of color registration error prediction and reducing memory consumption in the process of color registration error prediction.

[0085] In one possible implementation, the preceding gravure unit of the current gravure unit includes a first preceding gravure unit and a second preceding gravure unit. In printing order, the first preceding gravure unit, the second preceding gravure unit and the current gravure unit are adjacent to each other in sequence, and the first preceding gravure unit is located between the second preceding gravure unit and the current gravure unit.

[0086] like Figure 2 As shown, the current gravure printing unit is gravure printing unit U k When the first preceding gravure printing unit is gravure printing unit U k-1 The second preceding gravure printing unit is gravure printing unit U k-2 .

[0087] On the premise that the error prediction model is obtained by performing equivalent differential transformation on the intermediate model, when the predicted color registration error of the current gravure unit at the second moment is determined by the error prediction model, the input of the error prediction model includes the control amount and color registration error of the current gravure unit at the first moment, the control amount of the first preceding gravure unit at the first moment, the control amount of the second preceding gravure unit at the first moment, and historical hidden variables.

[0088] In an embodiment of the present application, the preceding gravure unit of the current gravure unit includes a first preceding gravure unit adjacent to the current gravure unit, and a second preceding gravure unit adjacent to the first preceding gravure unit. When the predicted color registration error of the current gravure unit at the second moment is determined through the error prediction model, the control amounts of the first preceding gravure unit and the second preceding gravure unit at the first moment are used as partial inputs of the model. While ensuring the accuracy of the prediction results, the calculation amount of the error prediction model is reduced, thereby improving the efficiency of color registration error prediction and reducing memory consumption in the color registration error prediction process.

[0089] In a possible implementation, when the error prediction model is obtained by performing an equivalent differential transformation on the intermediate model, the mathematical representation of the error prediction model may be the following formula (3), formula (4) and formula (5):

[0090]

[0091]

[0092] Used to characterize the predicted color registration error of the current gravure printing unit at time t+1, Used to characterize the activation function, E t Used to characterize the color registration error of the current gravure printing unit at time t, H t Used to characterize the error prediction model in predicting The hidden variable H is output when t-1 The hidden variable used to characterize the error prediction model’s output when predicting the color error of the current gravure unit at time t, ω t Used to characterize the control quantity of the current gravure unit at time t, ω′ t Used to characterize the control quantity of the first preceding gravure printing unit at time t, ω″ t Used to characterize the control amount of the second preceding gravure printing unit at time t, The weight matrix of the hidden variables connecting the input vector used to represent the error prediction model, b h and b o are all constants.

[0093] When the predicted color registration error of the current gravure printing unit at the second moment is determined by the error prediction model shown in formulas (3) to (5), is the predicted color error of the current gravure printing unit at the second moment, E t is the color registration error of the current gravure printing unit at the first moment, H t-1 H is the hidden variable output by the error prediction model when predicting the predicted color error of the current gravure printing unit at the first moment. t is the hidden variable output by the error prediction model when predicting the predicted color error of the current gravure printing unit at the second moment, ω t is the control value of the current gravure unit at the first moment, ω′ t is the control amount of the first preceding gravure printing unit at the first moment, ω″ t is the control amount of the second preceding gravure printing unit at the first moment.

[0094] Weight Matrix W vh , W xh and W ωh By changing W in formula (1) xh Disassemble and assemble to obtain.

[0095] Figure 5 FIG. 1 is a schematic diagram of an error prediction model of another embodiment of the present application. Figure 5 As shown, from the error prediction model shown in formula (3) to formula (5), it can be seen that the input of the error prediction model 400 includes V t , H t-1 and ω t , the output of the error prediction model 400 includes and H t .H t The method can be used to determine the predicted color registration error of the current gravure printing unit at the next moment after the second moment.

[0096] In the embodiment of the present application, the error prediction model is obtained by performing an equivalent differential transformation on the intermediate model, and a mature nonlinear solution algorithm can be used to solve the error prediction model, thereby ensuring the accuracy of the obtained predicted color error and improving the efficiency of model solution. The input of the error prediction model only requires the feature vector at the current moment, and does not require feature sequences corresponding to multiple historical moments, thereby improving the computational efficiency and reducing memory consumption.

[0097] In one possible implementation, when determining the control amount of the current gravure printing unit at the second moment based on the predicted color registration error of the current gravure printing unit at the second moment, the color registration error of the current gravure printing unit at at least one third moment after the second moment can be predicted by an error prediction model to obtain the predicted color registration error of the current gravure printing unit at each third moment, and then the control amount of the current gravure printing unit at the second moment is determined based on the predicted color registration error of the current gravure printing unit at the second moment and the predicted color registration error of the current gravure printing unit at each third moment.

[0098] When determining the predicted color registration error of the current gravure printing unit at the third moment through the error prediction model, it is necessary to input the control amount and color registration error of the current gravure printing unit at the previous moment of the third moment. Since the moment is a future moment, the color registration error of the current gravure printing unit at this moment cannot be obtained by measurement, so the predicted color registration error of the gravure printing unit at this moment is used as the color registration error at this moment, and the control amount of the gravure printing unit at this moment is determined based on the predicted color registration error of the current gravure printing unit at the previous moment of the moment. It should be noted that the process of determining the predicted color registration error and control amount of the current gravure printing unit at the third moment is the same as the method of determining the predicted color registration error and control amount of the current gravure printing unit at the second moment, and will not be repeated here.

[0099] In the embodiment of the present application, since the control amount of the current gravure printing unit at the second moment will affect the color registration error at the subsequent moment, the predicted color registration error of the current gravure printing unit at the second moment is determined through the error prediction model, and the predicted color registration errors of the current gravure printing unit at multiple third moments after the second moment are determined, and then the control amount of the current gravure printing unit at the second moment and the predicted color registration errors of the current gravure printing unit at each third moment is determined. When determining the control amount of the current gravure printing unit at the second moment, the influence of the control amount at the second moment on the color registration error at the subsequent moment is taken into account, so that the color registration error of the current gravure printing unit is stabilized at a small level, ensuring that the printed product has a high quality.

[0100] In a possible implementation, the control amount of the current gravure printing unit at the second moment can be obtained by solving the performance objective function shown in the following formula (6).

[0101]

[0102] J is used to characterize the performance objective function of the current gravure printing unit at the second moment, t is used to characterize the first moment, t+1 is used to characterize the second moment, n-1 is used to characterize the number of the third moment, and n is a positive integer greater than or equal to 1. It is used to characterize the predicted color error of the current gravure printing unit at time t′+1, E * t′ω1It is used to characterize the setting value of the color registration error of the current gravure printing unit at time t′+1. It is used to characterize the predicted color error of the current gravure printing unit at time t+n+1, E * t′+n+1 Used to characterize the setting value of the color error of the current gravure printing unit at time t′+n+1, Δω t′+1 =ω t′+1 -ω t′ , Used to characterize the control amount of the current gravure unit at time t′+1, ω t′ Used to characterize the control quantity of the current gravure unit at time t′, ω′ t′ It is used to characterize the control amount of the preceding gravure printing unit adjacent to the current gravure printing unit at time t', R and Q are both penalty coefficients or matrices. The symbol T represents matrix transposition.

[0103] In the above formula (6), the target term Indicates the deviation between the predicted color error and the color error setting value, penalty term Indicates the increment of the control amount of the current gravure unit, the penalty term Indicates the increment of the control amount of the current gravure unit relative to the previous gravure unit, terminal item Indicates the deviation of the predicted color error at the end of the prediction period from the color error set value.

[0104] When solving the performance objective function shown in formula (6), the performance objective function is solved with the minimum J as the goal, and ω is obtained. t+1 To t+n These n control quantities, ω t+1 is the control value of the current gravure unit at time t+1, ω t+n is the control amount of the current gravure unit at time t+n. Since time t+1 is the second time, ω t+1 That is, the control amount of the current gravure printing unit at the second moment. It should be noted that the ω obtained by solving the problem can be simply t+1 Control the rotation angular velocity of the gravure cylinder in the current gravure printing unit at the second moment, or according to the ω obtained by solving t+1 and t+2 The multiple control variables are used to control the rotational angular velocity of the gravure cylinder in the current gravure printing unit at the second moment.

[0105] In the embodiment of the present application, according to the target item Penalty Penalty and terminal term The error reference value is calculated, and then the control amount of the current gravure printing unit at the second moment is determined according to the error reference value. While making the gravure printing system have a smaller color registration error, the incremental change of the control amount can be constrained to avoid the printing material being torn due to excessive increment of the control amount, thereby improving the robustness of the gravure printing system.

[0106] Figure 6 FIG. 1 is a schematic diagram of a color registration error control process according to an embodiment of the present application. Figure 6 As shown, the error prediction model 400 performs n color error predictions under the control of the color error controller 601. Combining the above formulas (3) to (6), in the process of color error prediction, the color error controller 601 sets V t′ and sent to the error prediction model 400, which can input With E * t′+1 The deviation is input into the color error controller 601. The color error controller 601 can obtain the V t ,ω t and E t , and the color error controller 601 can be based on V t ,ω t 、E t 、E * t and multiple With E * t′+1 The deviation determines the control amount ω of the current gravure printing unit 602 at the second moment * t+1 , and then ω * t+1 Send it to the current gravure printing unit 602, so that the current gravure printing unit 602 follows ω * t+1 Control the rotation of the gravure roller. For example, the color error controller 601 solves the performance objective function shown in the above formula (6) with the goal of minimizing J to obtain ω * t+1 .

[0107] After the second moment, the actual color registration error E of the current gravure printing unit at the second moment can be calculated. t+1 and predicted color error The error prediction model 400 is updated to continuously optimize the error prediction model 400 and improve the prediction accuracy of the error prediction model 400 .

[0108] It should be noted that the model structure of the error prediction model can be RNN, gated recurrent unit (GRU), long short-term memory network (LSTM), etc. The network structure of the error prediction model shown in the above formulas (3) to (5) is RNN.

[0109] Color error control device

[0110] Figure 7 Schematic diagram of a color error control device according to an embodiment of the present application. Figure 7 As shown, the color registration error control device 700 includes a first acquisition unit 701, a second acquisition unit 702, a prediction unit 703 and a control unit 704. The first acquisition unit 701 is used to acquire the control amount and color registration error of the current gravure printing unit at the first moment, and the control amount is used to indicate the set value of the rotation angular velocity when the gravure printing unit is operating. The second acquisition unit 702 is used to acquire the control amount of at least one preceding gravure printing unit at the first moment, and the preceding gravure printing unit is located before the current gravure printing unit according to the printing sequence. The prediction unit 703 is used to predict the color registration error of the current gravure printing unit at the second moment through an error prediction model based on the control amount and color registration error of the current gravure printing unit at the first moment and the control amount of at least one preceding gravure printing unit at the first moment, and obtain the predicted color registration error of the current gravure printing unit at the second moment, and the second moment is located after the first moment. The control unit 704 is used to determine the control amount of the current gravure printing unit at the second moment based on the predicted color registration error of the current gravure printing unit at the second moment.

[0111] In the embodiment of the present application, the first acquisition unit 701 acquires the control amount and the color registration error of the current gravure printing unit at the first moment, the second acquisition unit 702 acquires the control amount of at least one preceding gravure printing unit of the current gravure printing unit at the first moment, and the prediction unit 703 can obtain the predicted color registration error of the current gravure printing unit at the second moment through the error prediction model according to the data acquired by the first acquisition unit 701 and the second acquisition unit 702, and then the control unit 704 can determine the control amount of the current gravure printing unit at the second moment according to the predicted color registration error of the current gravure printing unit at the second moment, and control the rotation angular velocity of the current gravure printing unit at the second moment according to the determined control amount, so that the current gravure printing unit produces a smaller color registration error at the second moment. Since the error prediction model is constructed by a data-driven modeling method, the error prediction model can accurately characterize the various factors that produce the color registration error, ensure the accuracy of the obtained predicted color registration error, and then control the rotation angular velocity of the current gravure printing unit at the second moment after determining the control amount according to the predicted color registration error, so that the current gravure printing unit produces a smaller color registration error at the second moment, thereby improving the quality of printed products.

[0112] It should be noted that the interaction between the various parts in the above-mentioned color error control device and the above-mentioned color error control method embodiment are based on the same concept. The specific content and beneficial effects can be found in the description in the above-mentioned color error control method embodiment, and will not be repeated here.

[0113] Electronic devices

[0114] Figure 8 is a schematic diagram of an electronic device provided in an embodiment of the present application. The specific embodiment of the present application does not limit the specific implementation of the electronic device. Figure 8 The electronic device 800 provided in the embodiment of the present application includes: a processor 802, a communication interface 804, a memory 806, and a bus 808. The processor 802, the communication interface 804, and the memory 806 communicate with each other through the bus 808. The communication interface 804 is used to communicate with other electronic devices or servers. The processor 802 is used to execute a program 810, which can specifically execute the relevant steps in the above-mentioned color registration error control method embodiment. Specifically, the program 810 may include a program code, and the program code includes a computer operation instruction.

[0115] The processor 802 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0116] The memory 806 is used to store the program 810. The memory 806 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0117] The program 810 may be specifically used to enable the processor 802 to execute the color registration error control method in any of the aforementioned embodiments.

[0118] The specific implementation of each step in program 810 can refer to the corresponding description of the corresponding steps and units in the above-mentioned color error control method embodiment, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-mentioned devices and modules can refer to the corresponding process description in the above-mentioned method embodiment, which will not be repeated here.

[0119] Through the electronic device of this embodiment, an error prediction model that can predict the color registration error of the gravure printing unit is trained. The error prediction model can obtain the predicted color registration error of the current gravure printing unit at the second moment according to the control amount and color registration error of the current gravure printing unit at the first moment, and the control amount of at least one preceding gravure printing unit of the current gravure printing unit at the first moment, and then determine the control amount of the current gravure printing unit at the second moment according to the predicted color registration error of the current gravure printing unit at the second moment, and control the rotation angular velocity of the current gravure printing unit at the second moment according to the determined control amount, so that the current gravure printing unit produces a smaller color registration error at the second moment. Since the error prediction model is constructed by a data-driven modeling method, the error prediction model can accurately characterize the various factors that produce the color registration error, ensure the accuracy of the obtained predicted color registration error, and then control the rotation angular velocity of the current gravure printing unit at the second moment after determining the control amount according to the predicted color registration error, so that the current gravure printing unit produces a smaller color registration error at the second moment, thereby improving the quality of printed products.

[0120] Computer readable storage medium

[0121] The present application also provides a computer-readable storage medium storing instructions for causing a machine to execute the color registration error control method as described herein. Specifically, a system or device equipped with a storage medium can be provided, on which a software program code for implementing the functions of any of the above embodiments is stored, and a computer (or CPU or MPU) of the system or device reads and executes the program code stored in the storage medium.

[0122] In this case, the program code read from the storage medium itself can implement the function of any one of the above embodiments, so the program code and the storage medium storing the program code constitute part of the present application.

[0123] The storage medium embodiments for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a non-volatile memory card, and a ROM. Alternatively, the program code can be downloaded from a server computer by a communication network.

[0124] In addition, it should be clear that the functions of any of the above embodiments can be implemented not only by executing the program code read by the computer, but also by enabling an operating system operating on the computer to complete part or all of the actual operations based on instructions from the program code.

[0125] In addition, it can be understood that the program code read from the storage medium is written to a memory provided in an expansion board inserted into the computer or to a memory provided in an expansion module connected to the computer, and then based on the instructions of the program code, a CPU installed on the expansion board or expansion module is enabled to perform part or all of the actual operations, thereby realizing the functions of any of the above-mentioned embodiments.

[0126] Computer program product

[0127] The embodiment of the present application also provides a computer program product, which is tangibly stored on a computer-readable medium and includes computer executable instructions, which, when executed, cause at least one processor to execute the color registration error control method provided in the above embodiments. It should be understood that each solution in this embodiment has the corresponding technical effect in the above method embodiment, which will not be repeated here.

[0128] It should be noted that not all steps and modules in the above-mentioned processes and device structure diagrams are necessary, and some steps or modules can be ignored according to actual needs. The execution order of each step is not fixed and can be adjusted as needed. The system structure described in the above-mentioned embodiments can be a physical structure or a logical structure, that is, some modules may be implemented by the same physical entity, or some modules may be implemented by multiple physical entities, or some components in multiple independent devices may be implemented together.

[0129] Nouns and pronouns relating to persons in this patent application are not limited to a specific gender.

[0130] In the above embodiments, the hardware module can be implemented mechanically or electrically. For example, a hardware module can include permanent dedicated circuits or logic (such as special processors, FPGA or ASIC) to complete the corresponding operation. The hardware module can also include programmable logic or circuits (such as general-purpose processors or other programmable processors), which can be temporarily set by software to complete the corresponding operation. The specific implementation method (mechanical method, or dedicated permanent circuit, or temporarily set circuit) can be determined based on cost and time considerations.

[0131] The present application is presented and described in detail above through the accompanying drawings and preferred embodiments; however, the present application is not limited to these disclosed embodiments, and those skilled in the art may know based on the above-mentioned multiple embodiments that the code review methods in the above-mentioned different embodiments may be combined to obtain more embodiments of the present application, and these embodiments are also within the protection scope of the present application.

Claims

1. A color registration error control method, comprising: Acquire the control amount and the color registration error of the current gravure printing unit at the first moment, wherein the control amount is used to indicate the set value of the rotation angular velocity when controlling the gravure printing unit; Acquire a control amount of at least one preceding gravure printing unit at the first moment, wherein the preceding gravure printing unit is located before the current gravure printing unit in the printing sequence; According to the control amount and the color registration error of the current gravure printing unit at the first moment and the control amount of the at least one preceding gravure printing unit at the first moment, predicting the color registration error of the current gravure printing unit at a second moment through an error prediction model, to obtain a predicted color registration error of the current gravure printing unit at the second moment, the second moment being located after the first moment; The control amount of the current gravure printing unit at the second moment is determined according to the predicted color registration error of the current gravure printing unit at the second moment.

2. The method according to claim 1, further comprising: Acquire a first control amount sequence, where the first control amount sequence includes control amounts of the current gravure printing unit at a plurality of historical moments, where the historical moments are before the first moment; Acquire a second control amount sequence, wherein the second control amount sequence includes the control amount of each of the preceding gravure printing units at the plurality of historical moments; Acquire a color registration error sequence, wherein the color registration error sequence includes the color registration errors of the current gravure printing unit at the multiple historical moments; The first control amount sequence, the second control amount sequence and the color registration error sequence are used as model inputs to train an intermediate model, wherein the intermediate model takes the color registration error of the current gravure printing unit at a future moment as output; The error prediction model is obtained according to the intermediate model.

3. The method according to claim 2, wherein: The step of obtaining the error prediction model according to the intermediate model comprises: The intermediate model is determined as the error prediction model.

4. The method according to claim 3, wherein: The recursive formula of the error prediction model includes: used to characterize the predicted color registration error of the current gravure printing unit at time t+1, Used to characterize the activation function, X t is used to represent the input vector composed of the control amount and the color registration error of the current gravure printing unit at time t, and the control amount of at least one preceding gravure printing unit at time t, H t It is used to characterize the hidden variables of the error prediction model at time t, H t-1 It is used to characterize the hidden variables of the error prediction model at time t-1, W xh The weight matrix used to represent the hidden variables connecting the input vector, W hh The weight matrix used to represent the hidden variable connection itself, W ho The weight matrix used to represent the hidden variables of the predicted color error connection, b h and b o are all constants.

5. The method according to claim 2, wherein: The step of obtaining the error prediction model according to the intermediate model comprises: performing an equivalent differential transformation on the intermediate model to obtain the error prediction model; The method predicts the color registration error of the current gravure printing unit at the second moment through an error prediction model according to the control amount and the color registration error of the current gravure printing unit at the first moment and the control amount of at least one preceding gravure printing unit at the first moment, so as to obtain the predicted color registration error of the current gravure printing unit at the second moment, including: Acquire a historical hidden variable output by the error prediction model, wherein the historical hidden variable is output by the error prediction model when predicting the color registration error of the current gravure printing unit at the first moment; The control amount and the color error of the current gravure printing unit at the first moment, the control amount of at least one preceding gravure printing unit at the first moment, and the historical hidden variables are input into the error prediction model to obtain the predicted color error and hidden variables of the current gravure printing unit at the second moment output by the error prediction model.

6. The method according to claim 5, wherein: The at least one preceding gravure printing unit includes a first preceding gravure printing unit and a second preceding gravure printing unit. The first preceding gravure printing unit, the second preceding gravure printing unit and the current gravure printing unit are adjacent to each other in the printing order, and the first preceding gravure printing unit is located between the second preceding gravure printing unit and the current gravure printing unit.

7. The method according to claim 6, wherein: The error prediction model includes: used to characterize the predicted color registration error of the current gravure printing unit at time t+1, Used to characterize the activation function, E t It is used to characterize the color registration error of the current gravure printing unit at time t, H t Used to characterize the error prediction model in predicting The hidden variable H is output when t-1 The hidden variable used to characterize the output of the error prediction model when predicting the predicted color error of the current gravure printing unit at time t, ω t It is used to characterize the control amount of the current gravure printing unit at time t, ω′ t It is used to characterize the control amount of the first preceding gravure printing unit at time t, ω′ t ' is used to characterize the control amount of the second preceding gravure printing unit at time t, The weight matrix of the hidden variables connecting the input vector used to represent the error prediction model, b h and b o are all constants.

8. The method according to claim 1, wherein: The step of determining the control amount of the current gravure printing unit at the second moment according to the predicted color registration error of the current gravure printing unit at the second moment includes: Predicting the color registration error of the current gravure printing unit at at least one third moment after the second moment by the error prediction model, obtaining the predicted color registration error of the current gravure printing unit at each third moment, when predicting the predicted color registration error of the current gravure printing unit at the third moment, the color registration error of the current gravure printing unit at the moment before the third moment is the predicted color registration error at the moment, and the control amount of the current gravure printing unit at the moment before the third moment is the control amount determined according to the predicted color registration error at the moment; The control amount of the current gravure printing unit at the second moment is determined according to the predicted color registration error of the current gravure printing unit at the second moment and the predicted color registration error of the current gravure printing unit at the at least one third moment.

9. The method according to claim 8, wherein: The determining the control amount of the current gravure printing unit at the second moment according to the predicted color registration error of the current gravure printing unit at the second moment and the predicted color registration error of the current gravure printing unit at at least one third moment comprises: The control amount of the current gravure printing unit at the second moment is obtained by solving the following performance objective function: J is used to characterize the performance objective function of the current gravure printing unit at the second moment, t is used to characterize the first moment, t+1 is used to characterize the second moment, n-1 is used to characterize the number of the third moment, and n is a positive integer greater than or equal to 1. It is used to characterize the predicted color error of the current gravure printing unit at time t′+1, E * t′+1 A setting value for characterizing the color registration error of the current gravure printing unit at time t′+1, It is used to characterize the predicted color error of the current gravure printing unit at time t+n+1, E * t′ωn+1 The setting value used to characterize the color registration error of the current gravure printing unit at time t′+n+1, Δω t′+1 =ω t′+1 -ω t′ , ω t′+1 It is used to characterize the control amount of the current gravure printing unit at time t′+1, ω t′ It is used to characterize the control amount of the current gravure printing unit at time t′, ω′ t′ It is used to characterize the control amount of the preceding gravure printing unit adjacent to the current gravure printing unit at time t′, and both R and Q are penalty coefficients or matrices.

10. An electronic device (800), comprising: A processor (802), a communication interface (804), a memory (806) and a bus (808), wherein the processor (802), the communication interface (804) and the memory (806) communicate with each other via the bus (808); The memory (806) is used to store at least one executable instruction, and the executable instruction enables the processor (802) to perform operations corresponding to the color error control method as described in any one of claims 1-9.

11. A computer-readable storage medium, wherein computer instructions are stored on the computer-readable storage medium, and when the computer instructions are executed by a processor, the processor is caused to execute the method according to any one of claims 1 to 9.

12. A computer program product tangibly stored on a computer readable medium and comprising computer executable instructions which, when executed, cause at least one processor to perform the method according to any one of claims 1-9.

Images