Printing efficiency optimization method based on intelligent adjustment of digital printing parameters

Abstract

The present invention discloses a printing efficiency optimization method for intelligently adjusting digital printing parameters, which belongs to the field of digital printing technology and includes the following steps: S1: collecting and processing real-time digital printing data to determine digital printing feature data; S2: training a printing efficiency prediction model, and analyzing the digital printing feature data to determine the printing efficiency prediction result of a digital printing machine; S3, printing efficiency optimization: automatically and intelligently adjusting digital printing parameters, and real-time tracking, predicting and optimizing the printing efficiency of the digital printing machine after the automatic and intelligent adjustment of the digital printing parameters, so that the printing efficiency of the digital printing machine is optimal. The present invention solves the existing problem that the digital printing parameters cannot be intelligently adjusted according to the actual situation of digital printing, resulting in low printing efficiency. The present invention can intelligently adjust the digital printing parameters according to the actual situation of digital printing, which can improve the printing efficiency and achieve a more efficient printing process.

Description

Technical Field

[0001] The present invention relates to the technical field of digital printing, and in particular to a printing efficiency optimization method for intelligently adjusting digital printing parameters. Background Art

[0002] In the actual production process, due to the influence of different digital printing parameters, the printing effect is often unsatisfactory. Therefore, how to improve printing efficiency has become an important topic in the field of digital printing.

[0003] The Chinese patent application with publication number CN119255914A discloses a method for printing paper by a digital printing device, wherein the digital printing device has a plurality of coating application tools for applying printing inks of different colors on the paper, the paper to be printed passes through the coating application tools along a feeding direction, the digital printing device has a device configured and adapted to prevent or reduce the formation of condensation on the coating application tools, and the formation of condensation on the coating application tools is prevented or reduced by the device; however, the patent has the following defects:

[0004] The existing digital printing parameters cannot be intelligently adjusted according to the actual digital printing situation, resulting in low printing efficiency and failure to achieve a more efficient printing process. Summary of the invention

[0005] The purpose of the present invention is to provide a printing efficiency optimization method for intelligently adjusting digital printing parameters, which can intelligently adjust digital printing parameters according to the actual digital printing situation, improve printing efficiency, and achieve a more efficient printing process, thereby solving the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The printing efficiency optimization method of intelligently adjusting digital printing parameters comprises the following steps:

[0008] S1. Data collection and processing: collecting and processing the real-time data of digital printing based on artificial intelligence, and processing the real-time data of digital printing based on artificial intelligence to determine the characteristic data of digital printing based on artificial intelligence;

[0009] S2. Model training and printing efficiency prediction: Train the printing efficiency prediction model based on deep learning, analyze the digital printing feature data based on artificial intelligence, predict the printing efficiency of the digital printing press, and determine the printing efficiency prediction results of the digital printing press;

[0010] S3. Printing efficiency optimization: Optimize the printing efficiency of the digital printing press according to the printing efficiency prediction results of the digital printing press, automatically and intelligently adjust the digital printing parameters, and conduct real-time tracking, prediction and optimization of the printing efficiency of the digital printing press after the automatic and intelligent adjustment of the digital printing parameters, so as to optimize the printing efficiency of the digital printing press.

[0011] Preferably, in S1, collecting real-time data of digital printing based on artificial intelligence includes:

[0012] Based on intelligent monitoring equipment, the printing speed of the digital printing machine during the printing process is monitored and collected in real time to obtain digital printing speed parameters;

[0013] Based on intelligent monitoring equipment, the printing pressure of the digital printing machine during the printing process is monitored and collected in real time to obtain digital printing pressure parameters;

[0014] Based on intelligent monitoring equipment, the number and size of the digital printing machine nozzles during the printing process are monitored and collected in real time to obtain the digital printing nozzle parameters;

[0015] Based on intelligent monitoring equipment, the amount of ink used by the digital printing press during the printing process is monitored and collected in real time to obtain the digital printing ink usage parameters;

[0016] Based on intelligent monitoring equipment, the temperature, humidity and air flow speed of the digital printing machine during the printing process are monitored and collected in real time to obtain digital printing environment parameters;

[0017] Based on intelligent monitoring equipment, the color, clarity and glossiness of the digital printing press during the printing process are monitored and collected in real time to obtain digital printing quality parameters;

[0018] Based on intelligent monitoring equipment, the paper type, thickness, surface tension and ink absorption of the digital printing press during the printing process are monitored and collected in real time to obtain the digital printing paper type parameters;

[0019] Among them, the real-time digital printing data based on artificial intelligence is determined based on digital printing speed parameters, digital printing pressure parameters, digital printing nozzle parameters, digital printing ink usage parameters, digital printing environment parameters, digital printing quality parameters and digital printing paper type parameters.

[0020] Preferably, in S1, processing the real-time data of digital printing based on artificial intelligence includes:

[0021] Acquire and clean real-time data of digital printing based on artificial intelligence;

[0022] Among them, the real-time data of digital printing based on artificial intelligence is checked based on the data processing tool, duplicate values, missing values ​​and abnormal values ​​in the real-time data of digital printing based on artificial intelligence are found, and the duplicate values, missing values ​​and abnormal values ​​in the real-time data of digital printing based on artificial intelligence are processed;

[0023] For duplicate values ​​in the AI-based digital printing real-time data, the duplicate values ​​are deleted and the unique digital printing data record is retained;

[0024] For missing values ​​in the real-time data of digital printing based on artificial intelligence, deletion, filling or interpolation methods are used to process the missing values ​​so that the missing values ​​are removed or completed;

[0025] For outliers in the real-time data of digital printing based on artificial intelligence, deletion, replacement or correction methods are used to process the outliers so that the outliers are removed or normalized.

[0026] Preferably, in S1, processing the real-time data of digital printing based on artificial intelligence also includes:

[0027] Acquire the AI-based digital printing real-time data after cleaning, and convert the AI-based digital printing real-time data after cleaning;

[0028] Among them, the format and type of the cleaned artificial intelligence-based digital printing real-time data are converted to a standardized format, the dimensional difference between the artificial intelligence-based digital printing real-time data is reduced, and the standardized digital printing real-time data is determined;

[0029] Integrate the standardized digital printing real-time data into a unified view, and verify the integrated digital printing real-time data to determine whether the integrated digital printing real-time data conforms to the expected format and structure. After the verification is qualified, store the integrated digital printing real-time data in the database, and back up and store the integrated digital printing real-time data.

[0030] Preferably, in S1, processing the real-time data of digital printing based on artificial intelligence also includes:

[0031] Acquire the converted standardized digital printing real-time data, and perform feature selection and extraction on the converted standardized digital printing real-time data;

[0032] Among them, the information entropy of each feature in the real-time data of digital printing is calculated based on the information gain method, and then the feature with the largest information entropy is selected as the optimal feature to determine the most important feature vector for optimizing printing efficiency. The feature vector is extracted and reduced in dimension based on the principal component analysis method to reduce the data dimension and noise impact and determine the digital printing feature data based on artificial intelligence.

[0033] Preferably, in S2, training a printing efficiency prediction model based on deep learning includes:

[0034] According to the printing efficiency optimization requirements based on intelligent adjustment of digital printing parameters, digital printing historical data are collected, and the collected digital printing historical data are divided to determine a training set and a test set;

[0035] Based on deep learning technology, the deep learning model is trained with a training set so that the deep learning model can autonomously learn the printing efficiency prediction process, fit the relationship between digital printing parameters and printing efficiency, and predict the printing efficiency of the digital printing machine, and determine the printing efficiency prediction model based on deep learning;

[0036] Based on the test set, the performance of the printing efficiency prediction model based on deep learning is tested to determine whether the printing efficiency prediction model based on deep learning can achieve the expected effect.

[0037] Among them, when the printing efficiency prediction model based on deep learning cannot achieve the expected effect, the printing efficiency prediction model based on deep learning is optimized until the printing efficiency prediction model based on deep learning can achieve the expected effect.

[0038] Preferably, in S2, predicting the printing efficiency of the digital printing press includes:

[0039] Obtain a printing efficiency prediction model based on deep learning, and deploy the printing efficiency prediction model based on deep learning in an actual printing efficiency optimization environment;

[0040] The artificial intelligence-based digital printing feature data is input into the printing efficiency prediction model based on deep learning. The artificial intelligence-based digital printing feature data is analyzed according to the printing efficiency prediction model based on deep learning, and the printing efficiency of the digital printing press is predicted to determine the printing efficiency prediction result of the digital printing press.

[0041] Preferably, in S3, the printing efficiency of the digital printing press is optimized, including:

[0042] Obtain the printing efficiency prediction results of digital printing presses;

[0043] When it is predicted that the printing efficiency of a digital printing press is lower than a preset standard efficiency, the digital printing parameters are automatically and intelligently adjusted according to the prediction result of the printing efficiency of the digital printing press, and the printing efficiency of the digital printing press after the automatic and intelligent adjustment of the digital printing parameters is tracked, predicted and optimized in real time to determine whether the printing efficiency of the digital printing press after the automatic and intelligent adjustment of the digital printing parameters can reach the preset standard efficiency, so as to optimize the printing efficiency of the digital printing press.

[0044] Preferably, the printing efficiency optimization method of intelligently adjusting digital printing parameters further includes:

[0045] Save the digital printing real-time data after standardization and normalization; collect and save the digital printing fault data, and mark the digital printing real-time data according to the digital printing fault data;

[0046] Based on big data analysis technology, a printing fault prediction model is constructed. The printing fault prediction model uses a neural network machine learning algorithm to perform prediction training on real-time digital printing data, and compares the training results with the marked content. If the training results do not match the marked content, the parameters of the printing fault prediction model are optimized and adjusted until the training results match the marked content.

[0047] By using the trained printing fault training model, the real-time data of the currently printed digital printing is used as input data to predict printing faults and obtain fault prediction results;

[0048] If the fault prediction result indicates that there is a fault risk, that is, it is predicted that a fault may occur, a fault cause diagnosis and analysis is performed to obtain the predicted fault cause;

[0049] Further analyze the cause of the fault, use fault diagnosis analysis, combined with the equipment's operating data and maintenance records to accurately locate the fault;

[0050] Based on the cause of the fault and the precise location of the fault in the predictive analysis results, preventive measures and maintenance treatment plans are generated, and sent to and reminded maintenance personnel to perform equipment maintenance and eliminate potential faults, thereby ensuring printing efficiency.

[0051] Preferably, the printing efficiency optimization method of intelligently adjusting digital printing parameters further includes:

[0052] Through the diffusion experiment of different ink materials on different paper materials, the test data in the diffusion experiment is analyzed by using the normal distribution theory to obtain the normal distribution variance of the diffusion range of each ink material on different paper materials, establish a comparison table of ink materials, paper materials and diffusion normal distribution variance, and import the comparison table into the printing control system;

[0053] When printing, obtain the ink material parameters and paper quality data used for printing, query the comparison table based on the ink material parameters and paper quality data, and determine the normal distribution variance of the ink diffusion range on the paper;

[0054] At the current printing speed, the diffusion data of the ink used for printing on the paper plane is detected. The diffusion data includes the lateral diffusion data and the longitudinal diffusion data. The ink diffusion coefficient is calculated using the following formula:

[0055]

[0056] In the above formula, Indicates the ink diffusion coefficient at the current printing speed; It represents the normal distribution variance of the spread of the ink used in printing on the paper; represents a natural constant; Indicates the lateral diffusion data of ink on the paper plane; Indicates the longitudinal diffusion data of ink on the paper plane;

[0057] The ink diffusion coefficient at the current printing speed is compared with the set diffusion threshold. If it exceeds the set deviation range, the printing speed is optimized and adjusted; if the ink diffusion coefficient is greater than the diffusion threshold, the printing speed is increased, otherwise the printing speed is reduced.

[0058] Compared with the prior art, the present invention has the following beneficial effects:

[0059] The present invention collects real-time digital printing data based on artificial intelligence, processes the real-time digital printing data based on artificial intelligence, determines digital printing feature data based on artificial intelligence, predicts the printing efficiency of a digital printing press by training a printing efficiency prediction model based on deep learning, and analyzes the digital printing feature data based on artificial intelligence, determines the printing efficiency prediction result of the digital printing press, optimizes the printing efficiency of the digital printing press according to the printing efficiency prediction result of the digital printing press, automatically and intelligently adjusts digital printing parameters, and performs real-time tracking, prediction and optimization of the printing efficiency of the digital printing press after the digital printing parameters are automatically and intelligently adjusted, so that the printing efficiency of the digital printing press is optimized, and the digital printing parameters can be intelligently adjusted according to the actual digital printing situation, so as to improve the printing efficiency and achieve a more efficient printing process. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 The present invention is a flow chart of the printing efficiency optimization method for intelligently adjusting digital printing parameters. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] In order to solve the existing problem that the digital printing parameters cannot be intelligently adjusted according to the actual situation of digital printing, resulting in low printing efficiency and failure to achieve a more efficient printing process, please refer to Figure 1 , this embodiment provides the following technical solutions:

[0063] The printing efficiency optimization method of intelligently adjusting digital printing parameters comprises the following steps:

[0064] S1. Data collection and processing: collecting and processing the real-time data of digital printing based on artificial intelligence, and processing the real-time data of digital printing based on artificial intelligence to determine the characteristic data of digital printing based on artificial intelligence;

[0065] In this embodiment, the real-time data of digital printing based on artificial intelligence is collected, including:

[0066] Based on intelligent monitoring equipment, the printing speed of the digital printing machine during the printing process is monitored and collected in real time to obtain digital printing speed parameters;

[0067] Among them, printing speed refers to how many prints a digital printing machine can complete in a unit of time, which is one of the important factors affecting printing quality and production efficiency;

[0068] Based on intelligent monitoring equipment, the printing pressure of the digital printing machine during the printing process is monitored and collected in real time to obtain digital printing pressure parameters;

[0069] Among them, printing pressure refers to the pressure that the digital printing machine applies to the substrate during printing. Too much pressure will lead to a decrease in printing quality, while too little pressure may cause unclear printing.

[0070] Based on intelligent monitoring equipment, the number and size of the digital printing machine nozzles during the printing process are monitored and collected in real time to obtain the digital printing nozzle parameters;

[0071] Among them, the increase in the number of nozzles can improve the printing resolution, but it will also lead to an increase in cost. The change in nozzle size will also affect the printing quality and resolution.

[0072] Based on intelligent monitoring equipment, the amount of ink used by the digital printing press during the printing process is monitored and collected in real time to obtain the digital printing ink usage parameters;

[0073] Among them, ink usage refers to the amount of ink used by a digital printing press during the printing process. The setting of ink usage will affect the printing quality, cost and environmental protection;

[0074] Based on intelligent monitoring equipment, the temperature, humidity and air flow speed of the digital printing machine during the printing process are monitored and collected in real time to obtain digital printing environment parameters;

[0075] Among them, environmental parameters refer to the temperature, humidity and air flow speed of the digital printing machine during the printing process. Changes in these environmental factors will also have a certain impact on the printing process and affect the operating status and printing quality of the digital printing machine;

[0076] Based on intelligent monitoring equipment, the color, clarity and glossiness of the digital printing press during the printing process are monitored and collected in real time to obtain digital printing quality parameters;

[0077] Among them, printing quality refers to the overall quality of printed products printed by digital printing presses, including color, clarity, glossiness and other aspects;

[0078] Based on intelligent monitoring equipment, the paper type, thickness, surface tension and ink absorption of the digital printing press during the printing process are monitored and collected in real time to obtain the digital printing paper type parameters;

[0079] Among them, paper type, thickness, surface tension and changes in ink absorption will affect printing quality, speed and cost;

[0080] Among them, the real-time digital printing data based on artificial intelligence is determined based on digital printing speed parameters, digital printing pressure parameters, digital printing nozzle parameters, digital printing ink usage parameters, digital printing environment parameters, digital printing quality parameters and digital printing paper type parameters.

[0081] In this embodiment, the real-time data of digital printing based on artificial intelligence is processed, including:

[0082] Acquire and clean real-time data of digital printing based on artificial intelligence;

[0083] Among them, the real-time data of digital printing based on artificial intelligence is checked based on the data processing tool, duplicate values, missing values ​​and abnormal values ​​in the real-time data of digital printing based on artificial intelligence are found, and the duplicate values, missing values ​​and abnormal values ​​in the real-time data of digital printing based on artificial intelligence are processed;

[0084] For duplicate values ​​in the AI-based digital printing real-time data, the duplicate values ​​are deleted and the unique digital printing data record is retained;

[0085] For missing values ​​in the real-time data of digital printing based on artificial intelligence, deletion, filling or interpolation methods are used to process the missing values ​​so that the missing values ​​are removed or completed;

[0086] For outliers in the real-time data of digital printing based on artificial intelligence, the outliers are processed by deletion, replacement or correction methods to remove or normalize the outliers;

[0087] Acquire the AI-based digital printing real-time data after cleaning, and convert the AI-based digital printing real-time data after cleaning;

[0088] Among them, the format and type of the cleaned artificial intelligence-based digital printing real-time data are converted to a standardized format, the dimensional difference between the artificial intelligence-based digital printing real-time data is reduced, and the standardized digital printing real-time data is determined;

[0089] Integrate the standardized real-time digital printing data into a unified view, verify the integrated real-time digital printing data, and determine whether the integrated real-time digital printing data conforms to the expected format and structure. After verification, store the integrated real-time digital printing data in the database, and perform backup and storage management on the integrated real-time digital printing data.

[0090] Acquire the converted standardized digital printing real-time data, and perform feature selection and extraction on the converted standardized digital printing real-time data;

[0091] Among them, the information entropy of each feature in the real-time data of digital printing is calculated based on the information gain method, and then the feature with the largest information entropy is selected as the optimal feature to determine the most important feature vector for optimizing printing efficiency. The feature vector is extracted and reduced in dimension based on the principal component analysis method to reduce the data dimension and noise impact and determine the digital printing feature data based on artificial intelligence.

[0092] S2. Model training and printing efficiency prediction: Train the printing efficiency prediction model based on deep learning, analyze the digital printing feature data based on artificial intelligence, predict the printing efficiency of the digital printing press, and determine the printing efficiency prediction results of the digital printing press;

[0093] In this embodiment, training a printing efficiency prediction model based on deep learning includes:

[0094] According to the printing efficiency optimization requirements based on intelligent adjustment of digital printing parameters, digital printing historical data are collected, and the collected digital printing historical data are divided to determine a training set and a test set;

[0095] Based on deep learning technology, the deep learning model is trained with a training set so that the deep learning model can autonomously learn the printing efficiency prediction process, fit the relationship between digital printing parameters and printing efficiency, and predict the printing efficiency of the digital printing machine, and determine the printing efficiency prediction model based on deep learning;

[0096] Based on the test set, the performance of the printing efficiency prediction model based on deep learning is tested to determine whether the printing efficiency prediction model based on deep learning can achieve the expected effect.

[0097] Among them, when the printing efficiency prediction model based on deep learning cannot achieve the expected effect, the printing efficiency prediction model based on deep learning is optimized until the printing efficiency prediction model based on deep learning can achieve the expected effect.

[0098] In this embodiment, predicting the printing efficiency of a digital printing press includes:

[0099] Obtain a printing efficiency prediction model based on deep learning, and deploy the printing efficiency prediction model based on deep learning in an actual printing efficiency optimization environment;

[0100] The artificial intelligence-based digital printing feature data is input into the printing efficiency prediction model based on deep learning. The artificial intelligence-based digital printing feature data is analyzed according to the printing efficiency prediction model based on deep learning, and the printing efficiency of the digital printing press is predicted to determine the printing efficiency prediction result of the digital printing press.

[0101] S3. Printing efficiency optimization: Optimize the printing efficiency of the digital printing press according to the printing efficiency prediction results of the digital printing press, automatically and intelligently adjust the digital printing parameters, and conduct real-time tracking, prediction and optimization of the printing efficiency of the digital printing press after the automatic and intelligent adjustment of the digital printing parameters, so as to optimize the printing efficiency of the digital printing press.

[0102] In this embodiment, the printing efficiency of the digital printing press is optimized, including:

[0103] Obtain the printing efficiency prediction results of digital printing presses;

[0104] When it is predicted that the printing efficiency of a digital printing press is lower than a preset standard efficiency, the digital printing parameters are automatically and intelligently adjusted according to the prediction result of the printing efficiency of the digital printing press, and the printing efficiency of the digital printing press after the automatic and intelligent adjustment of the digital printing parameters is tracked, predicted and optimized in real time to determine whether the printing efficiency of the digital printing press after the automatic and intelligent adjustment of the digital printing parameters can reach the preset standard efficiency, so as to optimize the printing efficiency of the digital printing press.

[0105] In summary, by collecting real-time data of digital printing based on artificial intelligence and processing the real-time data of digital printing based on artificial intelligence, the digital printing feature data based on artificial intelligence is determined, and the printing efficiency of the digital printing press is predicted by training a printing efficiency prediction model based on deep learning and analyzing the digital printing feature data based on artificial intelligence. The printing efficiency prediction result of the digital printing press is determined, and the printing efficiency of the digital printing press is optimized according to the printing efficiency prediction result of the digital printing press. The digital printing parameters are automatically and intelligently adjusted, and the printing efficiency of the digital printing press after the automatic and intelligent adjustment of the digital printing parameters is tracked, predicted and optimized in real time, so that the printing efficiency of the digital printing press is optimized, and the digital printing parameters can be intelligently adjusted according to the actual situation of digital printing, which can improve the printing efficiency and achieve a more efficient printing process.

[0106] Based on the above-mentioned embodiment, the printing efficiency optimization method of intelligently adjusting digital printing parameters further includes:

[0107] Save the digital printing real-time data after standardization and normalization; collect and save the digital printing fault data, and mark the digital printing real-time data according to the digital printing fault data;

[0108] Based on big data analysis technology, a printing fault prediction model is constructed. The printing fault prediction model uses a neural network machine learning algorithm to perform prediction training on real-time digital printing data, and compares the training results with the marked content. If the training results do not match the marked content, the parameters of the printing fault prediction model are optimized and adjusted until the training results match the marked content.

[0109] By using the trained printing fault training model, the real-time digital printing data currently being printed is used as input data to perform printing fault prediction and obtain fault prediction results;

[0110] If the fault prediction result indicates that there is a fault risk, that is, it is predicted that a fault may occur, a fault cause diagnosis and analysis is performed to obtain the predicted fault cause;

[0111] Further analyze the cause of the fault, use fault diagnosis analysis, combined with the equipment's operating data and maintenance records to accurately locate the fault;

[0112] Based on the cause of the fault and the precise location of the fault in the predictive analysis results, preventive measures and maintenance treatment plans are generated, and sent to and reminded maintenance personnel to perform equipment maintenance and eliminate potential faults, thereby ensuring printing efficiency.

[0113] Specifically, by constructing a printing fault prediction model, the digital printing real-time data that has been standardized and normalized is used for model learning and training after marking whether the historical data involves a fault. The trained model is used to process the current digital printing real-time data and implement fault prediction to obtain the current fault prediction result. The prediction result is used to determine whether there is a fault risk. If so, the fault cause diagnosis is implemented to determine the specific cause of the predicted fault, and the cause is located. Preventive measures and maintenance solutions are provided to prompt maintenance personnel to intervene before the fault occurs, eliminate hidden dangers, and eliminate the cause of the fault, thereby reducing the fault rate and maintenance costs, more effectively guaranteeing printing production, and achieving improved printing efficiency.

[0114] Based on the above-mentioned embodiment, the printing efficiency optimization method of intelligently adjusting digital printing parameters further includes:

[0115] Through the diffusion experiment of different ink materials on different paper materials, the test data in the diffusion experiment is analyzed by using the normal distribution theory to obtain the normal distribution variance of the diffusion range of each ink material on different paper materials, establish a comparison table of ink materials, paper materials and diffusion normal distribution variance, and import the comparison table into the printing control system;

[0116] When printing, obtain the ink material parameters and paper quality data used for printing, query the comparison table based on the ink material parameters and paper quality data, and determine the normal distribution variance of the ink diffusion range on the paper;

[0117] At the current printing speed, the diffusion data of the ink used for printing on the paper plane is detected. The diffusion data includes the lateral diffusion data and the longitudinal diffusion data. The ink diffusion coefficient is calculated using the following formula:

[0118]

[0119] In the above formula, Indicates the ink diffusion coefficient at the current printing speed; It represents the normal distribution variance of the spread of the ink used in printing on the paper; represents a natural constant; Indicates the lateral diffusion data of ink on the paper plane; Indicates the longitudinal diffusion data of ink on the paper plane;

[0120] The ink diffusion coefficient at the current printing speed is compared with the set diffusion threshold. If it exceeds the set deviation range, the printing speed is optimized and adjusted; if the ink diffusion coefficient is greater than the diffusion threshold, the printing speed is increased, otherwise the printing speed is reduced.

[0121] Specifically, printing quality will be affected by the diffusion effect of ink on paper, that is, there is a corresponding relationship between printing quality and ink diffusion range, and different diffusion ranges correspond to different printing qualities. Through the diffusion experiment of ink on paper, the normal distribution analysis method can be used to determine the normal distribution variance of the diffusion range statistics according to the printing quality requirements. The normal distribution variance can reflect the printing quality to a certain extent; however, the diffusion of ink on paper is also determined by the amount of ink printed at a single point, and the amount of ink printed at a single point is related to the printing speed. Therefore, this scheme constructs a quantitative analysis relationship between ink diffusion and the normal distribution variance that reflects printing quality through the above formula. The normal distribution variance obtained from the real-time detection of diffusion data is used to calculate the ink diffusion coefficient, and the ink diffusion coefficient is compared with the diffusion threshold determined to ensure printing quality requirements. Value comparison, if the deviation of the diffusion threshold exceeds the set deviation range, it means that the current printing speed is unreasonable. Among them, if the ink diffusion coefficient is greater than the diffusion threshold, it means that the amount of ink printed at a single point is too much. This is because the printing speed is too slow, which makes the single point inking time long. The printing speed should be appropriately increased to reduce the single point inking time, thereby reducing the amount of ink printed at a single point; conversely, the printing speed is too fast, the single point inking time is insufficient, resulting in insufficient single point printing ink, and there are breakpoints in the printed lines, so the printing speed needs to be reduced; this scheme uses the quantitative calculation of the above formula to achieve both printing quality control and optimize printing efficiency.

[0122] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article 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, article or device.

[0123] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A printing efficiency optimization method for intelligent adjustment of digital printing parameters, characterized in that: The steps include: S1. Data collection and processing: collecting and processing the real-time data of digital printing based on artificial intelligence, and processing the real-time data of digital printing based on artificial intelligence to determine the characteristic data of digital printing based on artificial intelligence; S2. Model training and printing efficiency prediction: Train the printing efficiency prediction model based on deep learning, analyze the digital printing feature data based on artificial intelligence, predict the printing efficiency of the digital printing press, and determine the printing efficiency prediction results of the digital printing press; S3. Printing efficiency optimization: optimize the printing efficiency of the digital printing press according to the printing efficiency prediction results of the digital printing press, automatically and intelligently adjust the digital printing parameters, and conduct real-time tracking, prediction and optimization of the printing efficiency of the digital printing press after the automatic and intelligent adjustment of the digital printing parameters, so as to optimize the printing efficiency of the digital printing press; In S1, real-time data of digital printing based on artificial intelligence is collected, including: Based on intelligent monitoring equipment, the printing speed of the digital printing machine during the printing process is monitored and collected in real time to obtain digital printing speed parameters; Based on intelligent monitoring equipment, the printing pressure of the digital printing machine during the printing process is monitored and collected in real time to obtain digital printing pressure parameters; Based on intelligent monitoring equipment, the number and size of the digital printing machine nozzles during the printing process are monitored and collected in real time to obtain digital printing nozzle parameters; Based on intelligent monitoring equipment, the amount of ink used by the digital printing press during the printing process is monitored and collected in real time to obtain the digital printing ink usage parameters; Based on intelligent monitoring equipment, the temperature, humidity and air flow speed of the digital printing machine during the printing process are monitored and collected in real time to obtain digital printing environment parameters; Based on intelligent monitoring equipment, the color, clarity and glossiness of the digital printing press during the printing process are monitored and collected in real time to obtain digital printing quality parameters; Based on intelligent monitoring equipment, the paper type, thickness, surface tension and ink absorption of the digital printing press during the printing process are monitored and collected in real time to obtain the digital printing paper type parameters; Wherein, based on digital printing speed parameters, digital printing pressure parameters, digital printing nozzle parameters, digital printing ink usage parameters, digital printing environment parameters, digital printing quality parameters and digital printing paper type parameters, the real-time digital printing data based on artificial intelligence is determined; Also includes: Save the digital printing real-time data after standardization and normalization; collect and save the digital printing fault data, and mark the digital printing real-time data according to the digital printing fault data; Based on big data analysis technology, a printing fault prediction model is constructed. The printing fault prediction model uses a neural network machine learning algorithm to perform prediction training on real-time digital printing data, and compares the training results with the marked content. If the training results do not match the marked content, the parameters of the printing fault prediction model are optimized and adjusted until the training results match the marked content. Through the trained printing fault prediction model, the real-time data of the currently printed digital printing is used as input data to predict printing faults and obtain fault prediction results; If the fault prediction result indicates that there is a fault risk, that is, it is predicted that a fault may occur, a fault cause diagnosis and analysis is performed to obtain the predicted fault cause; Further analyze the cause of the fault and use fault diagnosis analysis, combined with the equipment's operating data and maintenance records, to accurately locate the fault; Based on the cause of the fault and the precise location of the fault in the predictive analysis results, preventive measures and maintenance treatment plans are generated, and sent to and reminded maintenance personnel to perform equipment maintenance and troubleshoot potential faults, thereby ensuring printing efficiency.

2. The printing efficiency optimization method for intelligent adjustment of digital printing parameters according to claim 1, characterized in that: In S1, the real-time data of digital printing based on artificial intelligence is processed, including: Acquire and clean real-time data of digital printing based on artificial intelligence; Among them, the real-time data of digital printing based on artificial intelligence is checked based on the data processing tool, duplicate values, missing values ​​and abnormal values ​​in the real-time data of digital printing based on artificial intelligence are found, and the duplicate values, missing values ​​and abnormal values ​​in the real-time data of digital printing based on artificial intelligence are processed; For duplicate values ​​in the AI-based digital printing real-time data, the duplicate values ​​are deleted and the unique digital printing data record is retained; For missing values ​​in the real-time data of digital printing based on artificial intelligence, deletion, filling or interpolation methods are used to process the missing values ​​so that the missing values ​​are removed or completed; For outliers in the real-time data of digital printing based on artificial intelligence, deletion, replacement or correction methods are used to process the outliers so that the outliers are removed or normalized.

3. The printing efficiency optimization method of intelligently adjusting digital printing parameters according to claim 2, characterized in that: In S1, the real-time data of digital printing based on artificial intelligence is processed, and further includes: Acquire the AI-based digital printing real-time data after cleaning, and convert the AI-based digital printing real-time data after cleaning; Among them, the format and type of the cleaned artificial intelligence-based digital printing real-time data are converted to a standardized format, the dimensional difference between the artificial intelligence-based digital printing real-time data is reduced, and the standardized digital printing real-time data is determined; Integrate the standardized digital printing real-time data into a unified view, and verify the integrated digital printing real-time data to determine whether the integrated digital printing real-time data conforms to the expected format and structure. After verification, store the integrated digital printing real-time data in the database, and back up and store the integrated digital printing real-time data.

4. The printing efficiency optimization method of intelligently adjusting digital printing parameters according to claim 3, characterized in that: In S1, the real-time data of digital printing based on artificial intelligence is processed, and further includes: Acquire the converted standardized digital printing real-time data, and perform feature selection and extraction on the converted standardized digital printing real-time data; Among them, the information entropy of each feature in the real-time data of digital printing is calculated based on the information gain method, and then the feature with the largest information entropy is selected as the optimal feature to determine the most important feature vector for optimizing printing efficiency. The feature vector is extracted and reduced in dimension based on the principal component analysis method to reduce the data dimension and noise impact and determine the digital printing feature data based on artificial intelligence.

5. The printing efficiency optimization method for intelligent adjustment of digital printing parameters according to claim 4, characterized in that: In S2, training a printing efficiency prediction model based on deep learning includes: According to the printing efficiency optimization requirements based on intelligent adjustment of digital printing parameters, digital printing historical data are collected, and the collected digital printing historical data are divided to determine a training set and a test set; Based on deep learning technology, the deep learning model is trained with a training set so that the deep learning model can autonomously learn the printing efficiency prediction process, fit the relationship between digital printing parameters and printing efficiency, and predict the printing efficiency of the digital printing machine, and determine the printing efficiency prediction model based on deep learning; Based on the test set, the performance of the printing efficiency prediction model based on deep learning is tested to determine whether the printing efficiency prediction model based on deep learning can achieve the expected effect; Among them, when the printing efficiency prediction model based on deep learning cannot achieve the expected effect, the printing efficiency prediction model based on deep learning is optimized until the printing efficiency prediction model based on deep learning can achieve the expected effect.

6. The printing efficiency optimization method for intelligent adjustment of digital printing parameters according to claim 5, characterized in that: In S2, predicting the printing efficiency of the digital printing press includes: Obtain a printing efficiency prediction model based on deep learning, and deploy the printing efficiency prediction model based on deep learning in an actual printing efficiency optimization environment; The artificial intelligence-based digital printing feature data is input into the printing efficiency prediction model based on deep learning. The artificial intelligence-based digital printing feature data is analyzed according to the printing efficiency prediction model based on deep learning, and the printing efficiency of the digital printing press is predicted to determine the printing efficiency prediction result of the digital printing press.

7. The printing efficiency optimization method of intelligently adjusting digital printing parameters according to claim 6, characterized in that: In S3, the printing efficiency of the digital printing press is optimized, including: Obtain the printing efficiency prediction results of digital printing presses; When it is predicted that the printing efficiency of a digital printing press is lower than a preset standard efficiency, the digital printing parameters are automatically and intelligently adjusted according to the prediction result of the printing efficiency of the digital printing press, and the printing efficiency of the digital printing press after the automatic and intelligent adjustment of the digital printing parameters is tracked, predicted and optimized in real time to determine whether the printing efficiency of the digital printing press after the automatic and intelligent adjustment of the digital printing parameters can reach the preset standard efficiency, so as to optimize the printing efficiency of the digital printing press.

8. The printing efficiency optimization method for intelligent adjustment of digital printing parameters according to claim 1, characterized in that: Also includes: Through the diffusion experiment of different ink materials on different paper materials, the test data in the diffusion experiment is analyzed by using the normal distribution theory to obtain the normal distribution variance of the diffusion range of each ink material on different paper materials, establish a comparison table of ink materials, paper materials and diffusion normal distribution variance, and import the comparison table into the printing control system; When printing, obtain the ink material parameters and paper quality data used for printing, query the comparison table based on the ink material parameters and paper quality data, and determine the normal distribution variance of the ink diffusion range on the paper; At the current printing speed, the diffusion data of the ink used for printing on the paper plane is detected. The diffusion data includes the lateral diffusion data and the longitudinal diffusion data. The ink diffusion coefficient is calculated using the following formula: In the above formula, Indicates the ink diffusion coefficient at the current printing speed; It represents the normal distribution variance of the spread of the ink used in printing on the paper; represents a natural constant; Indicates the lateral diffusion data of ink on the paper plane; Indicates the longitudinal diffusion data of ink on the paper plane; Compare the ink diffusion coefficient at the current printing speed with the set diffusion threshold, and if it exceeds the set deviation range, optimize the printing speed; If the ink diffusion coefficient is greater than the diffusion threshold, the printing speed is increased, otherwise the printing speed is reduced.

Images