Intelligent control method for transverse expansion and shrinkage registration error of paper gravure press and related equipment

Abstract

The invention discloses an intelligent control method for a transverse expansion and shrinkage registration error of a paper gravure press and related equipment, and belongs to the technical field of an electronic shaft control system of the paper gravure press. And assigning theoretical oven temperature and fan wind speed to corresponding oven set values for printing, collecting a transverse expansion and shrinkage registration error generated by printing, establishing an RBF neural network control model among the transverse expansion and shrinkage registration error, the oven temperature and the reverse fan wind speed, and outputting compensation amounts of the oven temperature and the reverse oven wind speed. The control compensation amount is accumulated to the theoretical oven temperature and the reverse oven air speed, intelligent control over the transverse expansion and shrinkage registration error is achieved, the problem that direct modeling control over the transverse expansion and shrinkage registration error is difficult is solved, and high-precision control over the transverse expansion and shrinkage registration error of the water-based ink paper gravure press is achieved.

Description

Technical Field

[0001] The invention belongs to the technical field of electronic axis control systems for paper gravure printing machines, and in particular relates to an intelligent control method for transverse expansion and contraction registration errors of paper gravure printing machines and related equipment. Background Art

[0002] The printing and packaging industry is developing rapidly. As the core equipment of packaging and printing equipment, water-based ink paper gravure printing machine has many advantages such as thick ink layer, realistic image, clear layer, bright color, stable process, high printing durability, etc. At the same time, compared with solvent-based ink, water-based ink has less organic solvent content, less pollution to the environment, and is more suitable for the green development of packaging and printing industry. However, paper absorbs water from ink after printing with water-based ink. During the drying process, if the absorbed water cannot be completely evaporated, lateral expansion and contraction registration error is likely to occur. Traditional lateral expansion and contraction registration error control relies entirely on the operator's experience to subjectively adjust the oven temperature and fan speed, which has poor control effect, low efficiency, and insufficient timeliness; at the same time, the coupling mechanism between the lateral expansion and contraction registration error and the oven temperature and fan speed is complex, and the direct mechanism model control is difficult, and the existing registration error control strategy cannot achieve precise control. Summary of the invention

[0003] The invention provides an intelligent control method for the transverse expansion and contraction registration error of a paper gravure printing machine and related equipment, which solves the problem of complex coupling between the transverse expansion and contraction registration error and oven parameters and difficulty in direct modeling control.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] An intelligent control method for transverse expansion and contraction registration error of a paper gravure printing machine, comprising:

[0006] Collect printing process parameters and ambient humidity temperature, and calculate theoretical oven temperature and fan speed parameters based on the printing process parameters and ambient humidity temperature;

[0007] Assign theoretical oven temperature and fan speed to the corresponding oven parameter printing, and collect the lateral expansion and contraction registration error during the printing process;

[0008] Establish the RBF neural network control model between the lateral expansion and contraction registration error and the printing parameters, and output the compensation of the oven temperature and the reverse oven wind speed based on the RBF neural network control model;

[0009] The oven temperature and the reverse oven wind speed compensation are added to the theoretical oven temperature and fan wind speed to obtain the final oven operation parameters, thus realizing the intelligent control of the lateral expansion and contraction registration error.

[0010] Preferably, the collected printing process parameters include: printing speed, printing plate area, paper format, ink application amount, water content in ink, paper water absorption rate and oven nozzle diameter.

[0011] Preferably, the steps of calculating the theoretical oven temperature and fan speed parameters according to the printing process parameters and the ambient humidity temperature are specifically as follows:

[0012]

[0013] Among them, T L is the oven temperature, V1 is the front oven wind speed, V L2 is the wind speed of the reverse oven, h fg is the latent heat of vaporization of water, A s is the ink printing area, M s is the molar mass of water in the ink, P s is the saturated vapor pressure of the ink, R u is the universal gas constant, ρ A is the hot air density, c A is the specific heat capacity of hot air, T s is the ink temperature during constant drying, λ A is the thermal conductivity of hot air, c A is the specific heat capacity of hot air, D A is the diffusion coefficient of water vapor in hot air, L is the characteristic length, and μ is the temperature T L The dynamic viscosity of air under the condition of α, β and δ are empirical parameters, B is the nozzle diameter, is the convective heat transfer coefficient, K ct is the convection mass transfer coefficient of the reverse oven.

[0014] Preferably, when collecting the lateral expansion and contraction registration error during the printing process, when the lateral expansion and contraction registration error e>±0.1mm, adjust the oven temperature and the reverse oven wind speed to achieve lateral expansion and contraction registration error control

[0015] Preferably, establishing the RBF neural network control model between the lateral expansion and contraction registration error and the printing parameters also includes training a generative adversarial network to enhance the printing data set based on the collected historical printing process parameters, the lateral expansion and contraction registration error and the random noise, which is divided into the following steps:

[0016] The generator is fixed, and the real printing history data and the generated sample data are used as the input of the discriminator, and the discriminator is optimized to maximize its accuracy;

[0017] A fixed discriminator is used to input random noise into the generator to generate sample data, and the authenticity of the sample data is determined by the discriminator, and the weight of the generator is updated until the accuracy of the generator is maximized;

[0018] Repeat the above steps to complete the training of the generative adversarial network and expand the printing data set.

[0019] Preferably, an RBF neural network control model between the lateral expansion and contraction registration error and the printing parameters is established, and the specific establishment steps are:

[0020] Determine the input, output and network structure of the neural network. The input layer contains four nodes, namely, the lateral expansion and contraction registration error, printing speed, ink loading and paper water absorption; the output layer contains two nodes, namely, the oven temperature compensation and the reverse oven fan speed. The RBF neural network model structure is determined to be 4-10-2.

[0021] The activation function from the input layer to the hidden layer is the Gaussian radial basis function, which is expressed as:

[0022]

[0023] In the formula, X is the input vector of the neural network, C k is the center vector corresponding to the kth neuron in the hidden layer, D k is the width vector of the kth neuron in the hidden layer;

[0024] The linear output function is used from the hidden layer to the output layer, and its expression is:

[0025]

[0026] Where j is the total number of neurons in the hidden layer, w k is the neuron connection weight from the hidden layer to the output layer, and y is the output result of the neural network.

[0027] Preferably, collecting the lateral expansion and contraction registration error during the printing process also includes data denoising, abnormal data cleaning and data set division.

[0028] An intelligent control system for transverse expansion and contraction registration error of a paper gravure printing machine, comprising:

[0029] Data acquisition module: used to collect printing process parameters and ambient humidity temperature, and calculate theoretical oven temperature and fan speed parameters according to the printing process parameters and ambient humidity temperature;

[0030] Assignment module: used to assign theoretical oven temperature and fan speed to corresponding oven parameter printing, and collect lateral expansion and contraction registration errors during printing;

[0031] Model building module: used to establish the RBF neural network control model between the lateral expansion and contraction registration error and the printing parameters, and output the compensation amount of the oven temperature and the reverse oven wind speed based on the RBF neural network control model;

[0032] Parameter acquisition module: used to add the oven temperature and the reverse oven wind speed compensation to the theoretical oven temperature and fan wind speed to obtain the final oven operation parameters and realize the intelligent control of the lateral expansion and contraction registration error.

[0033] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of an intelligent control method for transverse expansion and contraction registration error of a paper gravure printing machine are implemented.

[0034] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of an intelligent control method for the transverse expansion and contraction registration error of a paper gravure printing machine.

[0035] Compared with the prior art, the present invention has the following beneficial effects: the present invention provides an intelligent control method for the lateral expansion and contraction registration error of a paper gravure printing machine, which collects printing process parameters and ambient humidity temperature, calculates theoretical oven temperature and fan speed, assigns the theoretical oven temperature and fan speed to corresponding oven setting values ​​for printing, collects the lateral expansion and contraction registration error generated by printing, establishes an RBF neural network control model between the lateral expansion and contraction registration error and the oven temperature and the back fan speed, outputs the compensation amount of the oven temperature and the back oven speed, accumulates the control compensation amount to the theoretical oven temperature and the back oven speed, realizes intelligent control of the lateral expansion and contraction registration error, solves the problem of difficulty in direct modeling and control of the lateral expansion and contraction registration error, and realizes high-precision control of the lateral expansion and contraction registration error of a water-based ink paper gravure printing machine. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a flow chart of an intelligent control method for lateral expansion and contraction registration error of a paper gravure printing machine according to the present invention;

[0037] Figure 2 A detailed flow chart of an intelligent control method for lateral expansion and contraction registration error of a paper gravure printing machine according to the present invention;

[0038] Figure 3 This is a block diagram of the lateral expansion and contraction registration error control based on the mechanism model and data-driven of the present invention;

[0039] Figure 4 RBF neural network structure diagram of the lateral expansion and contraction registration error of the present invention;

[0040] Figure 5 The present invention is a block diagram of an intelligent control system for the lateral expansion and contraction registration error of a paper gravure printing machine. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0042] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0044] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0045] like Figure 1 As shown, the present invention provides an intelligent control method for the transverse expansion and contraction registration error of a paper gravure printing machine, comprising:

[0046] S101 collects printing process parameters and ambient humidity temperature, and calculates theoretical oven temperature and fan speed parameters based on the printing process parameters and ambient humidity temperature;

[0047] S102 assigns theoretical oven temperature and fan speed to corresponding oven parameter printing, and collects lateral expansion and contraction registration errors during the printing process;

[0048] S103 establishes an RBF neural network control model between the lateral expansion and contraction registration error and the printing parameters, and outputs the compensation amount of the oven temperature and the reverse oven wind speed based on the RBF neural network control model;

[0049] S104 adds the oven temperature and the reverse oven wind speed compensation to the theoretical oven temperature and the fan wind speed to obtain the final oven operation parameters, thereby realizing the intelligent control of the lateral expansion and contraction registration error.

[0050] Detailed steps are as follows Figure 2 As shown, specifically:

[0051] Step 1: Collect printing process parameters and ambient humidity temperature, and calculate theoretical oven temperature and fan speed parameters;

[0052] After the water-based ink is printed and transferred to the paper surface, part of the water is absorbed by the paper, and the other part remains on the surface of the paper. Assuming that the front and back ovens are separated by the paper and do not affect each other, the front oven dries the water in the ink, and the back oven dries the water in the paper. The theoretical oven temperature and fan speed required for the evaporation of water in the paper and ink are calculated as the initial values ​​of the oven parameter settings.

[0053] The collected printing process parameters specifically include: printing speed, printing plate area, paper format, ink application amount, water content in ink, paper water absorption rate, and oven nozzle diameter.

[0054] Furthermore, the oven temperature T L , front oven wind speed V1, back oven wind speed V L2 The specific calculation expression is:

[0055]

[0056] In the formula, h fg is the latent heat of vaporization of water, A s is the ink printing area, M s is the molar mass of water in the ink, P s is the saturated vapor pressure of the ink, R u is the universal gas constant, ρ A is the hot air density, c A is the specific heat capacity of hot air, T s is the ink temperature during constant drying, λ A is the thermal conductivity of hot air, c A is the specific heat capacity of hot air, D A is the diffusion coefficient of water vapor in hot air, L is the characteristic length, and μ is the temperature T L The dynamic viscosity of air under the condition of α, β and δ are empirical parameters, and their value ranges are [0.20, 0.40], [0.50, 0.60] and [0.20, 0.30] respectively. B is the nozzle diameter. is the convective heat transfer coefficient, K ct is the convection mass transfer coefficient of the reverse oven, and the specific expression is:

[0057]

[0058] Where A is the paper area, M is w is the molar mass of water, ΔH v is the enthalpy of water vapor evaporating from the paper, ΔH s is the adsorption heat of water in paper, P p is the saturated vapor pressure in paper, P tot is the saturated vapor pressure in the environment.

[0059] Step 2: Calculate the theoretical oven temperature T L , the oven wind speed V1, V2 is assigned to the corresponding parameters of the oven pre-registration for printing, and the lateral expansion and contraction registration error during the printing process is collected;

[0060] Step 3: Establish the RBF neural network control model between the lateral expansion and contraction registration error and the printing parameters, and output the compensation amount of the oven temperature and the reverse oven wind speed;

[0061] The paper passes through the middle of the oven and is dried by hot air from the front and back ovens. The lateral expansion and shrinkage registration control system controls the lateral expansion and shrinkage registration error by adjusting the oven temperature and the back air inlet speed. The coupling mechanism between the lateral expansion and shrinkage registration error and the oven parameters is complex and cannot be directly controlled by the mechanism model. It is proposed to integrate RBF neural network data drive to achieve precise control of the lateral expansion and shrinkage registration error. The control process is as follows Figure 3 shown.

[0062] At present, the equipment in the printing industry is not intelligent enough, and the historical operation data is not fully recorded. In order to solve the problem of small sample size of lateral expansion and contraction registration error and poor training effect of neural network prediction model, adversarial generative network is selected to expand the printing historical data. The adversarial generative network training process is as follows:

[0063] The generator G is fixed, and the real printing history data and the generated sample data are used as the input of the discriminator D, and the discriminator D is optimized to maximize its accuracy;

[0064] Fixed discriminator D, input random noise to the generator G to generate sample data G(z), determine its authenticity through discriminator D, and update the generator weight until the accuracy of generator G is maximized;

[0065] Repeat the above steps to complete the training of the generative adversarial network and obtain the trained adversarial network.

[0066] Among them, the loss function of the adversarial generation network is as follows:

[0067]

[0068] In the formula, Loos G represents the loss function of the generator, Loos D represents the loss function of the discriminator, x represents each group of printing process parameters and lateral expansion and contraction registration error, z represents random noise, P x is the distribution of historical printing data x, P z is the distribution of random noise z, Represents all noise z according to its probability distribution P z Calculate the expectation, Represents all real printing data according to their probability distribution Px The expected value is calculated, G(z) represents the data generated by the generator, D(x) represents the authenticity score of the discriminator for the input sample x, and D(G(z)) represents the authenticity score of the discriminator for the generated data G(z).

[0069] The objective function of the adversarial generation network is as follows:

[0070]

[0071] Where V(G,D) is the value function of GAN.

[0072] Determine the specific structure of the RBF neural network model:

[0073] Determine the input, output and network structure of the neural network. The input layer contains four nodes, namely, the horizontal expansion and contraction registration error, printing speed, ink application amount, and paper water absorption; the output layer contains two nodes, namely, the oven temperature compensation ΔT and the reverse oven fan speed ΔV. Determine the RBF neural network model structure as 4-10-2, such as Figure 4 shown.

[0074] The activation function from the input layer to the hidden layer is the Gaussian radial basis function, which is expressed as:

[0075]

[0076] In the formula, X is the input vector of the neural network, C k is the center vector corresponding to the kth neuron in the hidden layer, D k is the width vector of the kth neuron in the hidden layer.

[0077] The linear output function is used from the hidden layer to the output layer, and its expression is:

[0078]

[0079] Where j is the total number of neurons in the hidden layer, w k is the neuron connection weight from the hidden layer to the output layer, and y is the output result of the neural network.

[0080] Step 4: Add the compensation output by the network model to the theoretical oven temperature and fan speed calculation values ​​to obtain the final oven operation parameters and realize intelligent control of lateral expansion and contraction registration errors.

[0081] Oven temperature T:

[0082] T=T L +ΔT (7)

[0083] Rear oven wind speed V2:

[0084] V2=V L2 +ΔV (8)

[0085] like Figure 5 As shown, the present invention provides an intelligent control system for transverse expansion and contraction registration error of a paper gravure printing machine, comprising:

[0086] Data acquisition module: used to collect printing process parameters and ambient humidity temperature, and calculate theoretical oven temperature and fan speed parameters according to the printing process parameters and ambient humidity temperature;

[0087] Assignment module: used to assign theoretical oven temperature and fan speed to corresponding oven parameter printing, and collect lateral expansion and contraction registration errors during printing;

[0088] Model building module: used to establish the RBF neural network control model between the lateral expansion and contraction registration error and the printing parameters, and output the compensation amount of the oven temperature and the reverse oven wind speed based on the RBF neural network control model;

[0089] Parameter acquisition module: used to add the oven temperature and the reverse oven wind speed compensation to the theoretical oven temperature and fan wind speed to obtain the final oven operation parameters and realize the intelligent control of the lateral expansion and contraction registration error.

[0090] A terminal device is provided in one embodiment of the present invention. The terminal device of this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0091] The computer program may be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to accomplish the present invention.

[0092] The terminal device may be a computing device such as a desktop computer, a notebook, a palmtop computer, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0093] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0094] The memory may be used to store the computer programs and / or modules, and the processor implements various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory.

[0095] If the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

Claims

1. An intelligent control method for transverse expansion and contraction registration error of a paper gravure printing machine, characterized in that: include: Collect printing process parameters and ambient humidity temperature, and calculate theoretical oven temperature and fan speed parameters based on the printing process parameters and ambient humidity temperature; Assign theoretical oven temperature and fan speed to the corresponding oven parameter printing, and collect the lateral expansion and contraction registration error during the printing process; Establish the RBF neural network control model between the lateral expansion and contraction registration error and the printing parameters, and output the compensation of the oven temperature and the reverse oven wind speed based on the RBF neural network control model; The oven temperature and the reverse oven wind speed compensation are added to the theoretical oven temperature and fan wind speed to obtain the final oven operation parameters, thus realizing the intelligent control of the lateral expansion and contraction registration error.

2. The method for intelligently controlling the transverse expansion and contraction registration error of a paper gravure printing machine according to claim 1, characterized in that: The collected printing process parameters include: printing speed, printing plate area, paper format, ink amount, water content in ink, paper water absorption rate and oven nozzle diameter.

3. The intelligent control method for transverse expansion and contraction registration error of a paper gravure printing machine according to claim 1, characterized in that: The specific steps for calculating the theoretical oven temperature and fan speed parameters according to the printing process parameters and the ambient humidity temperature are as follows: Among them, T L is the oven temperature, V1 is the front oven wind speed, V L2 is the wind speed of the reverse oven, h fg is the latent heat of vaporization of water, A s is the ink printing area, M s is the molar mass of water in the ink, P s is the saturated vapor pressure of the ink, R u is the universal gas constant, ρ A is the hot air density, c A is the specific heat capacity of hot air, T s is the ink temperature during constant drying, λ A is the thermal conductivity of hot air, c A is the specific heat capacity of hot air, D A is the diffusion coefficient of water vapor in hot air, L is the characteristic length, and μ is the temperature T L The dynamic viscosity of air under the condition of α, β and δ are empirical parameters, B is the nozzle diameter, is the convective heat transfer coefficient, K ct is the convection mass transfer coefficient of the reverse oven.

4. The method for intelligently controlling the transverse expansion and contraction registration error of a paper gravure printing machine according to claim 1, characterized in that: When collecting the lateral expansion and contraction registration error during the printing process, when the lateral expansion and contraction registration error e>±0.1mm, adjust the oven temperature and the reverse oven wind speed to achieve lateral expansion and contraction registration error control.

5. The method for intelligently controlling the transverse expansion and contraction registration error of a paper gravure printing machine according to claim 1, characterized in that: Establishing the RBF neural network control model between the lateral expansion and contraction registration error and the printing parameters also includes training the adversarial generative network to enhance the printing data set based on the collected historical printing process parameters, lateral expansion and contraction registration error and random noise, which is divided into the following steps: The generator is fixed, and the real printing history data and the generated sample data are used as the input of the discriminator, and the discriminator is optimized to maximize its accuracy; A fixed discriminator is used to input random noise into the generator to generate sample data, and the authenticity of the sample data is determined by the discriminator, and the weight of the generator is updated until the accuracy of the generator is maximized; Repeat the above steps to complete the training of the generative adversarial network and expand the printing data set.

6. The method for intelligently controlling the transverse expansion and contraction registration error of a paper gravure printing machine according to claim 5, characterized in that: The RBF neural network control model between the lateral expansion and contraction registration error and the printing parameters is established. The specific steps are as follows: Determine the input, output and network structure of the neural network. The input layer contains four nodes, namely, the lateral expansion and contraction registration error, printing speed, ink loading and paper water absorption; the output layer contains two nodes, namely, the oven temperature compensation and the reverse oven fan speed. The RBF neural network model structure is determined to be 4-10-2. The activation function from the input layer to the hidden layer is the Gaussian radial basis function, which is expressed as: In the formula, X is the input vector of the neural network, C k is the center vector corresponding to the kth neuron in the hidden layer, D k is the width vector of the kth neuron in the hidden layer; The linear output function is used from the hidden layer to the output layer, and its expression is: Where j is the total number of neurons in the hidden layer, w k is the neuron connection weight from the hidden layer to the output layer, and y is the output result of the neural network.

7. The method for intelligently controlling the transverse expansion and contraction registration error of a paper gravure printing machine according to claim 1, characterized in that: The acquisition of lateral expansion and contraction registration errors during the printing process also includes data denoising, abnormal data cleaning and data set division.

8. An intelligent control system for transverse expansion and contraction registration error of a paper gravure printing machine, characterized in that: include: Data acquisition module: used to collect printing process parameters and ambient humidity temperature, and calculate theoretical oven temperature and fan speed parameters according to the printing process parameters and ambient humidity temperature; Assignment module: used to assign theoretical oven temperature and fan speed to corresponding oven parameter printing, and collect lateral expansion and contraction registration errors during printing; Model building module: used to establish the RBF neural network control model between the lateral expansion and contraction registration error and the printing parameters, and output the compensation amount of the oven temperature and the reverse oven wind speed based on the RBF neural network control model; Parameter acquisition module: used to add the oven temperature and the reverse oven wind speed compensation to the theoretical oven temperature and fan wind speed to obtain the final oven operation parameters and realize the intelligent control of the lateral expansion and contraction registration error.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the intelligent control method for the lateral expansion and contraction registration error of a paper gravure printing machine as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the intelligent control method for the lateral expansion and contraction registration error of a paper gravure printing machine as claimed in any one of claims 1 to 7 are implemented.

Images