Automatic cleaning system for high-precision printing machine

Abstract

The invention provides an automatic cleaning system for a high-precision printing machine, and relates to the technical field of cleaning regulation and control systems. According to the method, the optimal cleaning parameters can be accurately predicted by collecting and preprocessing the historical cleaning data and constructing the parameter prediction model, so that the process of multiple times of trial and adjustment in a traditional cleaning mode is avoided, the cleaning efficiency is greatly improved, and meanwhile, the parameter adjustment model can accurately adjust the cleaning parameters according to the residual amount of the printing ink monitored in real time. According to the method, cleaning parameters are dynamically adjusted, it is ensured that the cleaning effect is always kept in the optimal state, the problem of insufficient cleaning or excessive cleaning is avoided, and then the cleaning strategy is dynamically adjusted according to data monitored in real time to adapt to real-time changes of the working state of the printing machine, so that the flexibility and reliability of the system are enhanced.

Description

Technical Field

[0001] The invention relates to the technical field of cleaning control systems, and in particular to an automatic cleaning system for a high-precision printing press. Background Art

[0002] With the continuous development of printing technology, high-precision printing presses play an increasingly important role in the printing industry. However, during the use of printing presses, various parts of the printing presses often accumulate a large amount of ink residue, which not only affects the printing quality, but may also cause the printing press to malfunction. Traditional cleaning methods often rely on manual operation and require multiple attempts and adjustments to the cleaning parameters, which is not only inefficient, but also difficult to ensure the consistency and stability of the cleaning effect. In addition, traditional cleaning methods lack adaptability to different printing press models, working environments, and ink types. In actual applications, the working status of the printing press and the amount of ink residue will change in real time, resulting in poor cleaning effects or inefficiencies.

[0003] Therefore, it is necessary to provide an automatic cleaning system for a high-precision printing press to solve the above technical problems. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides an automatic cleaning system for a high-precision printing press to solve the problems that the traditional cleaning system requires multiple attempts and adjustments of cleaning parameters, resulting in difficulty in ensuring the cleaning effect, and the working state of the printing press and the amount of ink residue will change in real time, resulting in poor cleaning effect or low efficiency.

[0005] The present invention provides an automatic cleaning system for a high-precision printing press, the automatic cleaning system comprising: A data acquisition module is used to acquire historical cleaning data of the printing press and perform preprocessing to obtain the historical cleaning data after preprocessing; The first model training module is used to analyze the correlation between the cleaning parameters and the cleaning effect in the pre-processed historical cleaning data by using statistical methods, and to construct a parameter estimation model based on this; A parameter estimation module is used to receive the current cleaning instruction of the printing press, analyze and output the predicted cleaning parameters through the constructed parameter estimation model; The second model training module is used to obtain the correlation between the ink residue and the cleaning parameters under different historical working hours of the printing press by using statistical analysis methods, and to build a parameter adjustment model; A parameter adjustment module is used to monitor the current ink residue in the printing machine operation status data in real time, and determine whether the current ink residue meets the triggering condition of the preset parameter adjustment model. When the current ink residue meets the triggering condition of the preset parameter adjustment model, the predicted cleaning parameters are adjusted by the parameter adjustment model, and the final cleaning parameters are output; The instruction generation module is used to generate corresponding instructions according to the final cleaning parameters and transmit them to the central controller to control the execution of the cleaning work.

[0006] Preferably, the steps of acquiring the historical cleaning data of the printing press and preprocessing it to obtain the preprocessed historical cleaning data are as follows: Collect historical cleaning data of the printing press from a historical database, including but not limited to parameters of cleaning time, cleaning temperature, cleaning pressure and cleaning frequency; The historical cleaned data is cleaned, specifically including removing abnormal data and duplicate data, to obtain the pre-processed historical cleaned data.

[0007] Preferably, the statistical method is used to analyze the correlation between the cleaning parameters and the cleaning effect in the historical cleaning data after preprocessing, and a parameter estimation model is constructed based on this, and the specific steps are: Using statistical methods to identify the correlation between each cleaning parameter and the cleaning effect from the pre-processed historical cleaning data, and obtain the correlation analysis results; specifically including the concentration of the cleaning agent, cleaning time, cleaning temperature and cleaning pressure; Based on the correlation analysis results, the cleaning parameters related to the cleaning effect are screened and extracted, including cleaning time, cleaning temperature and cleaning pressure; A multivariate regression model is selected as the training model, and the cleaning parameters related to the cleaning effect are used as input and the cleaning effect is used as output for training to obtain a parameter estimation model.

[0008] Preferably, the receiving of the current cleaning instruction of the printing machine, analyzing and outputting the predicted cleaning parameters through the constructed parameter estimation model, the specific steps are: After receiving the cleaning instruction, the constructed parameter estimation model is loaded; After obtaining the expected cleaning effect information in the cleaning instruction, it is input into the parameter estimation model as input data, and the parameter estimation model outputs the estimated cleaning parameters, wherein the estimated cleaning parameters specifically include cleaning time, cleaning temperature and cleaning pressure.

[0009] Preferably, the statistical analysis method is used to obtain the correlation between the ink residue and the cleaning parameters under different historical working hours of the printing press, and a parameter adjustment model is constructed, and the specific steps are: Collect the ink residue data and corresponding cleaning parameter data of the printing press at different historical working hours; Using the correlation coefficient to analyze the correlation between the ink residue data and the cleaning parameter data, and obtaining the cleaning parameter data associated with the ink residue data; A multivariate regression model is selected as a training model, and the ink residue data is used as input and the associated cleaning parameter data is used as output for training to obtain a parameter adjustment model.

[0010] Preferably, the real-time monitoring of the current ink residue in the printing machine operation status data determines whether the current ink residue meets the triggering condition of the preset parameter adjustment model, wherein when the current ink residue meets the triggering condition of the preset parameter adjustment model, the predicted cleaning parameters are adjusted by the parameter adjustment model, and the final cleaning parameters are output, and the specific steps are: Define a residual ink threshold, and use the residual ink threshold as a trigger condition for the parameter adjustment model; Real-time monitoring of the current ink residue in the printing machine operation status data, and comparison of the current ink residue with the ink residue threshold, judging whether the triggering condition of the parameter adjustment model is met according to the comparison result, wherein if it is judged that the current ink residue does not exceed the ink residue threshold, the predicted cleaning parameters are retained, and if it is judged that the current ink residue exceeds the ink residue threshold, the triggering condition of the parameter adjustment model is met, the current ink residue is input into the parameter adjustment model, and the adjustment parameters are output; Comparing the adjustment parameters with the predicted cleaning parameters to obtain deviation values ​​of each cleaning parameter in the predicted cleaning parameters; The cleaning parameters whose deviation values ​​exceed the preset deviation threshold are identified, and the cleaning parameters whose deviation values ​​exceed the preset deviation threshold are replaced by adjusting the parameters to generate final cleaning parameters.

[0011] Preferably, according to the automatic cleaning system for a high-precision printing machine according to claim 1, it is characterized in that the corresponding instructions are generated according to the final cleaning parameters and transmitted to the central controller to control the execution of the cleaning work, and the specific steps are: Convert the final cleaning parameters into an instruction format to obtain a cleaning instruction, and encode the cleaning instruction into a data packet of a fixed protocol recognized by the central controller; The data packet is transmitted to the central controller, and each component in the cleaning device performs the cleaning operation according to the instruction of the central controller, wherein the cleaning operation specifically includes controlling the switch of the water injection valve, the switch of the water spray valve and the temperature of the heating rod.

[0012] Compared with the related art, the automatic cleaning system for a high-precision printing press provided by the present invention has the following beneficial effects: The present invention can accurately predict the optimal cleaning parameters by collecting and preprocessing historical cleaning data and constructing a parameter prediction model, thereby avoiding the process of multiple attempts and adjustments required in traditional cleaning methods and greatly improving the cleaning efficiency. At the same time, the parameter adjustment model can dynamically adjust the cleaning parameters according to the real-time monitored ink residue to ensure that the cleaning effect always remains in the best state, avoiding the problem of insufficient or excessive cleaning. Secondly, the cleaning strategy is dynamically adjusted according to the real-time monitored data to adapt to the real-time changes in the working state of the printing press, thereby enhancing the flexibility and reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 The system block diagram of an automatic cleaning system for a high-precision printing press according to the present invention. DETAILED DESCRIPTION

[0014] The present invention will be further described below in conjunction with the accompanying drawings and implementation modes.

[0015] Example

[0016] like Figure 1 As shown, an automatic cleaning system for a high-precision printing press comprises: A data acquisition module is used to acquire historical cleaning data of the printing press and perform preprocessing to obtain the historical cleaning data after preprocessing; In the specific implementation process, the data acquisition module is used to: Collect historical cleaning data of the printing press from the historical database, including but not limited to parameters such as cleaning time, cleaning temperature, cleaning pressure, and cleaning frequency; Specifically, historical data related to parameters such as cleaning time, cleaning temperature, cleaning pressure, and cleaning frequency are screened out from the cloud database. After the required historical data is determined, these data are extracted using methods such as SQL query, data crawling tools, or API interfaces; Exemplarily, in this embodiment, the cleaning time, cleaning temperature, cleaning pressure and cleaning frequency of each cleaning of each printing press are extracted from a database containing cleaning records of all printing presses in the past year, and the required historical data are extracted from this table through existing SQL query statements; Clean the historical cleansing data, including removing abnormal data and duplicate data; Specifically, a special data cleaning tool is used to detect the historical cleaned data, and a variety of processing methods are adopted to process the detected abnormal data, including deletion, replacement or correction, and the pre-processed historical cleaned data is obtained after cleaning.

[0017] The first model training module is used to analyze the correlation between the cleaning parameters and the cleaning effect in the pre-processed historical cleaning data by using statistical methods, and to construct a parameter estimation model based on this; In the specific implementation process, the first model training module is used to: Using statistical methods to identify the correlation between each cleaning parameter and the cleaning effect from the pre-processed historical cleaning data, and obtain the correlation analysis results; specifically including the concentration of the cleaning agent, cleaning time, cleaning temperature and cleaning pressure; Specifically, a statistical method is used to identify the correlation between each cleaning parameter and the cleaning effect from the historical cleaning data after preprocessing. In this embodiment, the correlation coefficient is used to quantify the linear relationship between the cleaning parameter and the cleaning effect; variance analysis is used to test whether the influence of different cleaning parameters on the cleaning effect is significant, specifically, the correlation coefficient between the concentration of the cleaning agent, cleaning time, cleaning temperature and cleaning pressure and the ink residue after cleaning is calculated, and the correlation coefficient threshold is set to 0.65. When it is judged that the correlation coefficient between a certain parameter and the cleaning effect is high, it indicates that there is a significant correlation between the parameter and the cleaning effect.

[0018] Based on the correlation analysis results, the cleaning parameters related to the cleaning effect are screened and extracted, including cleaning time, cleaning temperature and cleaning pressure; Specifically, according to the results of the correlation analysis, a screening threshold is set to screen the cleaning parameters related to the cleaning effect, and the cleaning parameters greater than or equal to the screening threshold in the correlation analysis results are screened out as the cleaning parameters related to the cleaning effect. In this embodiment, the screening threshold is set to 0.7, and the cleaning parameters greater than or equal to 0.7 in the correlation analysis results are screened out. For example, in the correlation analysis, the correlation coefficients of the cleaning time, cleaning temperature and cleaning pressure are 0.8, 0.75 and 0.9 respectively, and the correlation coefficient of the concentration of the cleaning agent is 0.6, then the cleaning time, cleaning temperature and cleaning pressure are screened out as cleaning parameters related to the cleaning effect.

[0019] Select a multivariate regression model as a training model, and use cleaning parameters related to cleaning effects as input and cleaning effects as output for training to obtain a parameter estimation model; Specifically, according to the characteristics of the data and the analysis objectives, a multivariate regression model is selected as the training model, the screened cleaning parameters are used as input variables, the cleaning effect is used as the output variable, the training data is prepared, ensuring that the format and type of the data meet the requirements of the model, and the multivariate regression model is trained using the training data to obtain a parameter estimation model; in this embodiment, the LinearRegression class in the scikit-learn library is selected to train the multivariate regression model, the screened cleaning parameters (cleaning time, cleaning temperature and cleaning pressure) are used as the input variable X, and the cleaning effect (ink residue after cleaning) is used as the output variable y, then, the model's fit method is used to train the model, and the predict method is used to predict the new cleaning effect, and the parameter estimation model is obtained after verification.

[0020] A parameter estimation module is used to receive the current cleaning instruction of the printing press, analyze and output the predicted cleaning parameters through the constructed parameter estimation model; In the specific implementation process, the parameter estimation module is used to: After receiving the cleaning instruction, the constructed parameter estimation model is loaded; Specifically, a cleaning instruction is received from an external device or an operation interface through a communication interface (such as a network interface, a serial port, etc.), wherein the cleaning instruction usually includes information about the cleaning effect that the user wants to achieve. Then, after receiving the cleaning instruction, a previously constructed parameter estimation model is loaded from a storage medium (a hard disk, a memory, etc.) according to a preset path or configuration information; After obtaining the expected cleaning effect information in the cleaning instruction, the expected cleaning effect information is input as input data into the parameter estimation model, and the parameter estimation model outputs the estimated cleaning parameters, wherein the estimated cleaning parameters specifically include cleaning time, cleaning temperature and cleaning pressure; Specifically, the cleaning effect information expected by the user is extracted from the received cleaning instruction, where the information is expressed in the form of numerical values ​​or text, such as "the ink residue after cleaning does not exceed 0.1 mg / cm²". Then, the extracted expected cleaning effect information is converted into a format that the model understands and input into the parameter estimation model as input data. After receiving the input data, the parameter estimation model makes predictions based on the previously learned rules and outputs the estimated cleaning parameters. For example, after receiving the cleaning instruction, the previously constructed parameter estimation model is automatically loaded, and then the expected cleaning effect information "ink residue does not exceed 0.1 mg / cm²" is extracted from the cleaning instruction and converted into a format that the model can understand, such as 0.1. Then, this input data is input into the parameter estimation model. The parameter estimation model makes predictions based on the previously learned rules and outputs the estimated cleaning parameters, with the cleaning time being 10 minutes, the cleaning temperature being 60°C, and the cleaning pressure being 0.5 MPa.

[0021] The second model training module is used to obtain the correlation between the ink residue and the cleaning parameters under different historical working hours of the printing press by using statistical analysis methods, and to build a parameter adjustment model; In the specific implementation process, the second model training module is used to: Collect the ink residue data and corresponding cleaning parameter data of the printing press at different historical working hours; Specifically, determine the scope and accuracy of data collection, including which printing presses to select for data collection (e.g., printing presses of different models and different service years), as well as determine the time interval and number of sampling points for data collection. During the operation of the printing press, regularly record its working hours, ink residue, and corresponding cleaning parameters; Using the correlation coefficient to analyze the correlation between the ink residue data and the cleaning parameter data, and obtaining the cleaning parameter data associated with the ink residue data; Specifically, the collected data is preprocessed, including data cleaning, and then correlation analysis is performed using professional statistical analysis software (such as SPSS, R language, etc.) to analyze the correlation between the ink residue data and the cleaning parameter data, obtain the correlation coefficient of each cleaning parameter, and according to the preset correlation coefficient threshold of 0.7, it is determined that the cleaning parameters with a correlation coefficient exceeding 0.7 are associated with the ink residue data; A multivariate regression model is selected as a training model, and the ink residue data is used as input and the associated cleaning parameter data is used as output for training to obtain a parameter adjustment model.

[0022] A parameter adjustment module is used to monitor the current ink residue in the printing machine operation status data in real time, and determine whether the current ink residue meets the triggering condition of the preset parameter adjustment model. When the current ink residue meets the triggering condition of the preset parameter adjustment model, the predicted cleaning parameters are adjusted by the parameter adjustment model, and the final cleaning parameters are output; In the specific implementation process, the parameter adjustment module is used to: Define a residual ink threshold, and use the residual ink threshold as a trigger condition for the parameter adjustment model; Specifically, a threshold value of ink residue is set. In this embodiment, the threshold value of ink residue is specifically set to 0.15 mg / cm². At the same time, the ink residue exceeding the threshold value of ink residue is set as a trigger condition of the parameter adjustment model. Specifically, when the ink residue monitored in real time exceeds this threshold, the parameter adjustment model will be automatically triggered to adjust the cleaning parameters. Real-time monitoring of the current ink residue in the printing machine operation status data, and comparison of the current ink residue with the ink residue threshold, judging whether the triggering condition of the parameter adjustment model is met according to the comparison result, wherein if it is judged that the current ink residue does not exceed the ink residue threshold, the predicted cleaning parameters are retained, and if it is judged that the current ink residue exceeds the ink residue threshold, the triggering condition of the parameter adjustment model is met, the current ink residue is input into the parameter adjustment model, and the adjustment parameters are output; Specifically, the operating status data of the printing press, including the current ink residue, is monitored in real time through a sensor or a monitoring system, and the current ink residue monitored in real time is compared with a set ink residue threshold, and a determination is made based on the comparison result whether the triggering condition of the parameter adjustment model is met; if the current ink residue does not exceed the threshold, the previously predicted cleaning parameters are retained; if the current ink residue exceeds the threshold, the triggering condition is met and the next step is entered.

[0023] Comparing the adjustment parameters with the predicted cleaning parameters to obtain deviation values ​​of each cleaning parameter in the predicted cleaning parameters; Specifically, the adjusted cleaning parameters are obtained from the parameter adjustment model, the adjusted cleaning parameters are compared with the previously predicted cleaning parameters, and the deviation value of each cleaning parameter, that is, the difference between the adjusted parameter value and the predicted parameter value, is calculated.

[0024] Identify cleaning parameters whose deviation values ​​exceed a preset deviation threshold, and replace the cleaning parameters whose deviation values ​​exceed the preset deviation threshold by adjusting the parameters to generate final cleaning parameters; Specifically, in this embodiment, the preset deviation threshold is ±5%. For example, a high-precision printing machine monitors in real time during operation that the current ink residue is 0.2 mg / cm², while the set ink residue threshold is 0.15 mg / cm². Since the current ink residue exceeds the threshold, the parameter adjustment model is triggered. The parameter adjustment model outputs a set of adjusted cleaning parameters, including cleaning time, cleaning temperature and cleaning pressure, based on the current ink residue and other operating status data of the printing machine. Then, the adjusted parameters are compared with the previously predicted parameters, and it is found that the deviation value of the cleaning time exceeds the preset deviation threshold of ±5%. Therefore, the predicted cleaning time is replaced with the adjusted cleaning time, and other parameters remain unchanged. Finally, a set of final cleaning parameters including the adjusted cleaning time is generated.

[0025] An instruction generation module is used to generate corresponding instructions according to the final cleaning parameters and transmit them to the central controller to control the execution of the cleaning work; In the specific implementation process, the instruction generation module is used to: Convert the final cleaning parameters into an instruction format to obtain a cleaning instruction, and encode the cleaning instruction into a data packet of a fixed protocol recognized by the central controller; Specifically, after obtaining the final cleaning parameters, these parameters are converted into cleaning instructions, and then after the cleaning instructions are generated, they are encoded into a data packet of a fixed protocol recognized by the central controller, the data packet contains all the information of the cleaning instructions and follows the communication protocol that the central controller can understand; The data packet is transmitted to the central controller, and each component in the cleaning device performs a cleaning operation according to the instruction of the central controller, wherein the cleaning operation specifically includes controlling the switch of the water injection valve, the switch of the water spray valve, and the temperature of the heating rod; Specifically, after the data packet is generated and verified to be correct, it is transmitted to the central controller through wired or wireless communication methods, such as Ethernet, CAN bus, Wi-Fi, etc. After receiving the data packet, the central controller will parse it and extract the key information in the cleaning instruction. According to the information in the cleaning instruction, the central controller will control each component in the cleaning equipment to perform the cleaning operation, specifically including controlling the switch of the water injection valve, the switch of the water spray valve, and the temperature of the heating rod, etc. It should be noted that the specific implementation of the valve and the heating rod is the existing technology, and its specific principle will not be described in detail here; For example, according to the information in the cleaning instruction, the central controller controls the water injection valve in the cleaning equipment to open, and the water spray valve starts to spray water at a certain pressure and flow rate, and the heating rod also starts to heat up. After a period of cleaning, the water injection valve and the water spray valve are closed, and the heating of the heating rod is stopped. At this time, the cleaning operation is completed and the printing press is ready for the next round of printing tasks.

[0026] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0027] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0028] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

Claims

1. An automatic cleaning system for a high-precision printing press, characterized in that: The automatic cleaning system comprises: A data acquisition module is used to acquire historical cleaning data of the printing press and perform preprocessing to obtain the historical cleaning data after preprocessing; The first model training module is used to analyze the correlation between the cleaning parameters and the cleaning effect in the pre-processed historical cleaning data by using statistical methods, and to construct a parameter estimation model based on this; A parameter estimation module is used to receive the current cleaning instruction of the printing press, analyze and output the predicted cleaning parameters through the constructed parameter estimation model; The second model training module is used to obtain the correlation between the ink residue and the cleaning parameters under different historical working hours of the printing press by using statistical analysis methods, and to build a parameter adjustment model; A parameter adjustment module is used to monitor the current ink residue in the printing machine operation status data in real time, and determine whether the current ink residue meets the triggering condition of the preset parameter adjustment model. When the current ink residue meets the triggering condition of the preset parameter adjustment model, the predicted cleaning parameters are adjusted by the parameter adjustment model, and the final cleaning parameters are output; The instruction generation module is used to generate corresponding instructions according to the final cleaning parameters and transmit them to the central controller to control the execution of the cleaning work.

2. The automatic cleaning system for a high-precision printing press according to claim 1, characterized in that: The specific steps of obtaining the historical cleaning data of the printing press and preprocessing it to obtain the historical cleaning data after preprocessing are as follows: Collect historical cleaning data of the printing press from a historical database, including but not limited to parameters of cleaning time, cleaning temperature, cleaning pressure and cleaning frequency; The historical cleaned data is cleaned, specifically including removing abnormal data and duplicate data, to obtain the pre-processed historical cleaned data.

3. The automatic cleaning system for a high-precision printing press according to claim 1, characterized in that: The statistical method is used to analyze the correlation between the cleaning parameters and the cleaning effect in the pre-processed historical cleaning data, and a parameter estimation model is constructed based on this, and the specific steps are as follows: Using statistical methods to identify the correlation between each cleaning parameter and the cleaning effect from the pre-processed historical cleaning data, and obtain the correlation analysis results; specifically including the concentration of the cleaning agent, cleaning time, cleaning temperature and cleaning pressure; Based on the correlation analysis results, the cleaning parameters related to the cleaning effect are screened and extracted, including cleaning time, cleaning temperature and cleaning pressure; A multivariate regression model is selected as the training model, and the cleaning parameters related to the cleaning effect are used as input and the cleaning effect is used as output for training to obtain a parameter estimation model.

4. The automatic cleaning system for a high-precision printing press according to claim 1, characterized in that: The specific steps of receiving the current cleaning instruction of the printing machine, analyzing and outputting the predicted cleaning parameters through the constructed parameter estimation model are as follows: After receiving the cleaning instruction, the constructed parameter estimation model is loaded; After obtaining the expected cleaning effect information in the cleaning instruction, it is input into the parameter estimation model as input data, and the parameter estimation model outputs the estimated cleaning parameters, wherein the estimated cleaning parameters specifically include cleaning time, cleaning temperature and cleaning pressure.

5. The automatic cleaning system for a high-precision printing press according to claim 1, characterized in that: The statistical analysis method is used to obtain the correlation between the ink residue and the cleaning parameters under different historical working hours of the printing press, and a parameter adjustment model is constructed. The specific steps are as follows: Collect the ink residue data and corresponding cleaning parameter data of the printing press at different historical working hours; Using the correlation coefficient to analyze the correlation between the ink residue data and the cleaning parameter data, and obtaining the cleaning parameter data associated with the ink residue data; A multivariate regression model is selected as a training model, and the ink residue data is used as input and the associated cleaning parameter data is used as output for training to obtain a parameter adjustment model.

6. The automatic cleaning system for a high-precision printing press according to claim 1, characterized in that: The real-time monitoring of the current ink residue in the printing machine operation status data determines whether the current ink residue meets the triggering condition of the preset parameter adjustment model, wherein when the current ink residue meets the triggering condition of the preset parameter adjustment model, the predicted cleaning parameters are adjusted by the parameter adjustment model, and the final cleaning parameters are output, and the specific steps are: Define a residual ink threshold, and use the residual ink threshold as a trigger condition for the parameter adjustment model; Real-time monitoring of the current ink residue in the printing machine operation status data, and comparison of the current ink residue with the ink residue threshold, judging whether the triggering condition of the parameter adjustment model is met according to the comparison result, wherein if it is judged that the current ink residue does not exceed the ink residue threshold, the predicted cleaning parameters are retained, and if it is judged that the current ink residue exceeds the ink residue threshold, the triggering condition of the parameter adjustment model is met, the current ink residue is input into the parameter adjustment model, and the adjustment parameters are output; Comparing the adjustment parameters with the predicted cleaning parameters to obtain deviation values ​​of each cleaning parameter in the predicted cleaning parameters; The cleaning parameters whose deviation values ​​exceed the preset deviation threshold are identified, and the cleaning parameters whose deviation values ​​exceed the preset deviation threshold are replaced by adjusting the parameters to generate final cleaning parameters.

7. The automatic cleaning system for a high-precision printing press according to claim 1, characterized in that: The corresponding instructions are generated according to the final cleaning parameters and transmitted to the central controller to control the execution of the cleaning work. The specific steps are: Convert the final cleaning parameters into an instruction format to obtain a cleaning instruction, and encode the cleaning instruction into a data packet of a fixed protocol recognized by the central controller; The data packet is transmitted to the central controller, and each component in the cleaning device performs the cleaning operation according to the instruction of the central controller, wherein the cleaning operation specifically includes controlling the switch of the water injection valve, the switch of the water spray valve and the temperature of the heating rod.

Images