CN117621609A - Automatic parameter adjustment method of gravure printing machine - Google Patents
Automatic parameter adjustment method of gravure printing machine Download PDFInfo
- Publication number
- CN117621609A CN117621609A CN202311663502.8A CN202311663502A CN117621609A CN 117621609 A CN117621609 A CN 117621609A CN 202311663502 A CN202311663502 A CN 202311663502A CN 117621609 A CN117621609 A CN 117621609A
- Authority
- CN
- China
- Prior art keywords
- layer
- neural network
- printing
- output
- input
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B41—PRINTING; LINING MACHINES; TYPEWRITERS; STAMPS
- B41F—PRINTING MACHINES OR PRESSES
- B41F9/00—Rotary intaglio printing presses
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B41—PRINTING; LINING MACHINES; TYPEWRITERS; STAMPS
- B41F—PRINTING MACHINES OR PRESSES
- B41F33/00—Indicating, counting, warning, control or safety devices
- B41F33/16—Programming systems for automatic control of sequence of operations
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Printing Methods (AREA)
Abstract
The invention discloses a parameter automatic adjustment method of a gravure printing machine, which comprises the steps of establishing a neural network model, embedding the neural network model into a printing control system, and obtaining three key adjustment parameters in the printing process by inputting the transverse and longitudinal deviation of printing, so as to control the printing machine to realize automatic adjustment; the method can efficiently, accurately and automatically adjust the printing machine; the printing machine is suitable for different types of printed matters, and has good universality and adaptability; the efficiency and the accuracy of the adjustment of the printing machine can be obviously improved, and the labor cost and the error rate are reduced.
Description
Technical Field
The invention belongs to the technical field of printing equipment, and relates to an automatic parameter adjusting method of a gravure printing machine.
Background
Conventional printer adjustments typically require manual adjustment of printer parameters, which is time consuming and labor intensive and requires a skilled technician to accurately make the adjustments. Due to human subjectivity and inconsistency, it is difficult for even experienced technicians to ensure that each adjustment results in an ideal printing result. Furthermore, conventional printer control systems are typically unchanged, and it is difficult to cope with the demands of different types of printed matter, which limits the diversity and complexity of the printed matter. These problems lead to low production efficiency of printed matter and difficulty in ensuring product quality.
Accordingly, there is a need for an efficient, accurate, automated printer adjustment method and system to meet the production needs of different types of printed matter. The development of artificial intelligence and neural networks has made this possible. By training a learning model, particularly A Neural Network (ANN) model, automatic adjustment of the printing machine can be realized, the accuracy and efficiency of adjustment are remarkably improved, and the workload of manual adjustment is reduced. In addition, the updating and improvement of the control system of the printing machine can also greatly improve the diversity and complexity of the printed matters so as to adapt to the market demands.
Disclosure of Invention
The invention aims to provide an automatic parameter adjustment method for a gravure printing machine, which has the characteristics of high efficiency, accuracy and automation.
The technical scheme adopted by the invention is that the parameter automatic adjustment method of the intaglio printing press is specifically to build a neural network model, then embed the neural network model into a printing control system, and obtain three key adjustment parameters in the printing process by inputting the horizontal and longitudinal deviation of printing, so as to control the printing press to realize automatic adjustment.
The invention is also characterized in that:
wherein the three key parameters include oven temperatureBlower air volume->And printing speed->
The automatic parameter adjusting method of the intaglio printing press is implemented according to the following steps:
step 1, a four-layer neural network system is established, and the neural network system is embedded in a printing control system;
step 2, outputting by a neural network in the operation process of the printing control system, and obtaining the optimal oven temperature under the working condition by the printing control systemBlower air volume->And printing speed->Parameter values.
The four-layer neural network specifically comprises:
the four-layer neural network comprises 2 input layer nodes which respectively represent transverse deviationAnd longitudinal deviation->The system also comprises two hidden layers, comprising 12 nodes, used for performing intermediate calculation; the output layer has 3 nodes corresponding to the temperature of the ovenBlower air volume->And printing speed->
Wherein the input layer function of the neural network is:
in the method, in the process of the invention,output value representing input layer,/->An input value representing an ith neuron;
wherein hidden layer input and output functions of the neural network are respectively:
the activation functions of the neural network input layer and the hidden layer are as follows:
in the formula (6), x represents the output values of the input layer and the hidden layerAnd->e is a mathematical constant.
The input and output functions of the output layer of the neural network are respectively as follows:
in the method, in the process of the invention,and->Weighting coefficients for each layer; alpha is the bias of each layer;
the three outputs of the output layer respectively correspond to the temperature of the ovenBlower air volume->And printing speed->The activation function of the output layer node is as follows:
in the formula (9), x represents the output value of the output layere is a mathematical constant.
The beneficial effects of the invention are as follows:
the automatic parameter adjusting method of the intaglio printing press has the following advantages:
(1) Efficient, accurate, automated printer adjustment;
the invention realizes the automation of the adjustment of the printing machine, reduces the manual intervention to the minimum, and greatly improves the production efficiency and the quality of the printed matter. The data of the printed matter can be acquired in real time through the neural network model, the quality of the printed matter is judged through recognition and analysis, and the parameters of the printer are automatically adjusted to achieve the optimal printing effect. The automatic adjustment function can be quickly adapted to the change of the printed matter, so that the production efficiency and accuracy of the printed matter are improved;
(2) The printing machine is suitable for different types of printed matters, and has good universality and adaptability;
in the neural network model training process, a large amount of printing sample data with different types and specifications are used, so that the model has good universality and adaptability. Therefore, whether the model changes in the type or specification of the printed matter, the model can be quickly adapted to the changes and provide an optimal printer parameter adjustment scheme, so that the stability and consistency of the quality of the printed matter are ensured;
(3) The efficiency and the accuracy of the adjustment of the printing machine can be obviously improved, and the labor cost and the error rate are reduced;
the traditional printing machine adjustment requires a great deal of manual intervention, which is not only inefficient, but also prone to errors. According to the invention, the automatic adjustment of the printing machine is realized by using the neural network model, so that manual intervention is avoided, the efficiency and accuracy of the adjustment of the printing machine are improved, meanwhile, the labor cost and the error rate can be reduced, the production cost is reduced, and the production benefit is improved.
Drawings
Fig. 1 is a block diagram of a neural network model of a gravure printing machine in the parameter automatic adjustment method of the gravure printing machine of the present invention.
Detailed Description
The invention will be described in detail below with reference to the drawings and the detailed description.
The invention provides a parameter automatic adjustment method of a gravure printing machine, which is specifically shown in the following embodiment:
embodiment 1 the method for automatically adjusting parameters of a gravure printing machine of the present invention is specifically contemplated as follows:
the invention provides a brand new printing machine automatic adjustment method based on a neural network, which specifically comprises the following steps: establishing a neural network model for the printer; the model is utilized to realize automatic adjustment of the printing machine; the purpose is to provide a high-efficiency, accurate and automatic printing machine adjusting method so as to meet the production requirements of different types of printed matters; the system has good expandability and maintainability, can be continuously updated and optimized, and is suitable for continuously changing market demands;
example 2 the automatic parameter adjustment method of the intaglio printing press according to the present invention is characterized as follows:
a neural network model for printing; the neural network is a deep learning model which trains itself by using print sample data to achieve accuracy and stability of automatic adjustment of the printer. In the training process, the model gradually improves the recognition and control accuracy of the model by learning and optimizing the input printing sample data. The printed neural network model includes multiple layers of input layers, hidden layers, output layers, and the like. Through a back propagation algorithm, the model can automatically extract and learn the characteristics in control, and through continuously adjusting the weight and the bias parameters, the more accurate and stable adjustment result of the printing process is realized;
and realizing automatic adjustment of the printing machine through the model. The trained neural network model can input the printing data acquired in real time, judge the quality of the printed matter through recognition and analysis, and automatically adjust the parameters of the printer to achieve the optimal printing effect. The automatic adjustment function of the invention can reduce manual intervention, improve production efficiency and quality of printed matter, and save cost and reduce loss in the production process.
Embodiment 3 the automatic parameter adjustment method of the intaglio printing press according to the present invention is specifically as follows:
building a neural network model, embedding the neural network model into a printing control system, and obtaining three key adjustment parameters in the printing process by inputting the horizontal and longitudinal deviation of printing so as to control a printing machine to realize automatic adjustment;
as shown in FIG. 1, the present invention adopts a control method of a four-layer neural network comprising 2 input layer nodes, each representing a lateral deviationAnd longitudinal deviation->The system also comprises two hidden layers, comprising 12 nodes, used for performing intermediate calculation; the output layer has 3 nodes, which correspond to the oven temperature +.>Blower air volume->And printing speed->
Wherein the input layer function of the neural network is:
in the method, in the process of the invention,output value representing input layer,/->An input value representing an ith neuron;
wherein hidden layer input and output functions of the neural network are respectively:
the activation functions of the neural network input layer and the hidden layer are as follows:
in the formula (6), x represents the output values of the input layer and the hidden layerAnd->e is a mathematical constant.
The input and output functions of the output layer of the neural network are respectively as follows:
in the method, in the process of the invention,and->Weighting coefficients for each layer; alpha is the bias of each layer;
the three outputs of the output layer respectively correspond to the temperature of the ovenBlower air quantityAnd printing speed->The activation function of the output layer node is as follows:
in the formula (9), x represents the output value of the output layere is a mathematical constant.
The invention can obtain the optimal oven temperature under the working condition by the output of the neural network in the operation process and the parameters shown in the following table 1Blower air volume->And printing speed->Parameter values; the optimization method can help us find the optimal parameter combination to improve the operation efficiency and performance of the system; the automatic adjustment function can also reduce manual intervention, improve production efficiency and printing quality, and save cost and reduce loss in the production process.
Table 1 neural network model parameter table for intaglio printing press
Claims (7)
1. The automatic parameter adjusting method for the intaglio printing press is characterized by comprising the steps of building a neural network model, embedding the neural network model into a printing control system, and obtaining three key adjusting parameters in the printing process by inputting the transverse and longitudinal deviation of printing, so as to control the printing press to realize automatic adjustment.
2. The method for automatically adjusting parameters of a gravure printing machine according to claim 1, wherein the three key parameters include oven temperatureBlower air volume->And printing speed->
3. The automatic parameter adjustment method of a gravure printing machine according to claim 1, characterized by being implemented in particular by the following steps:
step 1, a four-layer neural network system is established, and the neural network system is embedded in a printing control system;
step 2, outputting by a neural network in the operation process of the printing control system, and obtaining the optimal oven temperature under the working condition by the printing control systemBlower air volume->And printing speed->Parameter values.
4. The automatic parameter adjustment method of an intaglio printing press according to claim 2, wherein said four-layer neural network is specifically:
the four-layer neural network comprises 2 input layer nodes which respectively represent transverse deviationAnd longitudinal deviation->The system also comprises two hidden layers, comprising 12 nodes, used for performing intermediate calculation; the output layer has 3 nodes, which correspond to the oven temperature +.>Blower air volume->And printing speed->
5. The method for automatically adjusting parameters of a gravure printing press according to claim 4, wherein the input layer function of the neural network is:
in the method, in the process of the invention,output value representing input layer,/->Representing the input value of the ith neuron.
6. The method for automatically adjusting parameters of a gravure printing press according to claim 5, wherein hidden layer input and output functions of the neural network are respectively:
the activation functions of the neural network input layer and the hidden layer are as follows:
in the formula (6), x represents the output values of the input layer and the hidden layerY j (2) (t) and->e is a mathematical constant.
7. The method for automatically adjusting parameters of a gravure printing press according to claim 6, wherein the input and output functions of the output layer of the neural network are respectively:
in the method, in the process of the invention,and->Weighting coefficients for each layer; alpha is the bias of each layer;
the three outputs of the output layer respectively correspond to the temperature of the ovenBlower air volume->And printing speed->The activation function of the output layer node is as follows:
in the formula (9), x represents the output value Y of the output layer l (4) (t), e is a mathematical constant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311663502.8A CN117621609A (en) | 2023-12-06 | 2023-12-06 | Automatic parameter adjustment method of gravure printing machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311663502.8A CN117621609A (en) | 2023-12-06 | 2023-12-06 | Automatic parameter adjustment method of gravure printing machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117621609A true CN117621609A (en) | 2024-03-01 |
Family
ID=90019756
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311663502.8A Pending CN117621609A (en) | 2023-12-06 | 2023-12-06 | Automatic parameter adjustment method of gravure printing machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117621609A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118636582A (en) * | 2024-05-24 | 2024-09-13 | 陕西北人印刷机械有限责任公司 | Automatic optimization and adjustment method of gravure printing process parameters |
| CN119795753A (en) * | 2024-12-30 | 2025-04-11 | 西安交通大学 | An intelligent control method for transverse expansion and contraction registration error of a paper gravure printing machine and related equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1367079A (en) * | 2001-01-24 | 2002-09-04 | 海德堡印刷机械股份公司 | Method for regulating printing technical parameters of printing machine and other parameters related to printing process |
| US20070216918A1 (en) * | 2006-03-15 | 2007-09-20 | Quad/Tech, Inc. | Virtual ink desk and method of using same |
| CN108918527A (en) * | 2018-05-15 | 2018-11-30 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of printed matter defect inspection method based on deep learning |
| CN111605305A (en) * | 2020-04-29 | 2020-09-01 | 陕西北人印刷机械有限责任公司 | Paper transverse deformation control device and control method thereof |
| CN114779624A (en) * | 2022-05-17 | 2022-07-22 | 西安理工大学 | BP neural network PID gravure printing machine rewinding correction control system and control method |
| CN115284733A (en) * | 2022-08-31 | 2022-11-04 | 西门子（中国）有限公司 | Starting control system and method for gravure printing machine |
-
2023
- 2023-12-06 CN CN202311663502.8A patent/CN117621609A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1367079A (en) * | 2001-01-24 | 2002-09-04 | 海德堡印刷机械股份公司 | Method for regulating printing technical parameters of printing machine and other parameters related to printing process |
| US20070216918A1 (en) * | 2006-03-15 | 2007-09-20 | Quad/Tech, Inc. | Virtual ink desk and method of using same |
| CN108918527A (en) * | 2018-05-15 | 2018-11-30 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of printed matter defect inspection method based on deep learning |
| CN111605305A (en) * | 2020-04-29 | 2020-09-01 | 陕西北人印刷机械有限责任公司 | Paper transverse deformation control device and control method thereof |
| CN114779624A (en) * | 2022-05-17 | 2022-07-22 | 西安理工大学 | BP neural network PID gravure printing machine rewinding correction control system and control method |
| CN115284733A (en) * | 2022-08-31 | 2022-11-04 | 西门子（中国）有限公司 | Starting control system and method for gravure printing machine |
Non-Patent Citations (2)
| Title |
|---|
| 伍秋涛: "《实用塑料凹版印刷技术》", 30 June 2007, 印刷工业出版社, pages: 120 - 124 * |
| 贺毅岳: "《基于机器学习的量化投资建模研究》", 31 October 2021, 中国经济出版社, pages: 227 - 230 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118636582A (en) * | 2024-05-24 | 2024-09-13 | 陕西北人印刷机械有限责任公司 | Automatic optimization and adjustment method of gravure printing process parameters |
| CN119795753A (en) * | 2024-12-30 | 2025-04-11 | 西安交通大学 | An intelligent control method for transverse expansion and contraction registration error of a paper gravure printing machine and related equipment |
| CN119795753B (en) * | 2024-12-30 | 2025-10-21 | 西安交通大学 | An intelligent control method for transverse expansion and contraction registration error of a paper gravure printing machine and related equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117621609A (en) | Automatic parameter adjustment method of gravure printing machine | |
| CN111045326B (en) | Tobacco shred drying process moisture prediction control method and system based on recurrent neural network | |
| CN116852665B (en) | An intelligent adjustment method for injection molding process parameters based on hybrid model | |
| CN114757111B (en) | Intelligent equipment health management method based on digital twinning technology | |
| CN120085623A (en) | A production method for wire protection plastic casing based on optimization algorithm | |
| CN110070228A (en) | A BP neural network wind speed prediction method based on neuron branch evolution | |
| CN112947094A (en) | Temperature control PID parameter self-adjusting method for rotary cement kiln | |
| CN114881134A (en) | Federal domain adaptation method applied to data isomerism | |
| CN111553118B (en) | Multidimensional continuous optimization variable global optimization method based on reinforcement learning | |
| CN115409272A (en) | Dynamic flexible optimization method of production process based on regression decision tree | |
| CN119128663A (en) | A park management system and method based on digital twin platform | |
| CN120535101A (en) | A coagulant intelligent dosing control method and system based on image recognition and multi-parameter modeling | |
| CN119536429A (en) | A greenhouse environment control method and system based on artificial intelligence | |
| CN115356912A (en) | A PID Parameter Tuning Method Based on Adaptive Particle Swarm Genetic Algorithm | |
| CN116740530B (en) | A method for determining the lithography process window based on unsupervised learning | |
| CN116260709B (en) | A method and system for fault location in communication networks based on fault propagation relationships | |
| CN118779938B (en) | Design flow-based clothing platemaking production monitoring method and system | |
| CN117171591B (en) | Method for analyzing dynamic change of fault correlation of numerical control machine tool | |
| CN112379650A (en) | Gradient constrained coal-fired unit heat value correction method | |
| CN109101683B (en) | Model updating method for pyrolysis kettle of coal quality-based utilization and clean pretreatment system | |
| CN119067285A (en) | Carbon emission accounting method and system based on blockchain and Internet of Things | |
| CN114781945A (en) | Load distribution method, equipment, terminal and storage medium for cogeneration unit | |
| CN113752506A (en) | Intelligent setting method for temperature PID controller parameters of injection molding machine charging barrel | |
| CN119468301A (en) | A smart heating integrated control method and system | |
| CN115829016B (en) | Adjustment method and device for wireless modem based on neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |