Ink printing discoloration detection method and system
By using a neural network model to predict friction parameters and detect the composition of discolored ink on paper, the accuracy problem of ink printing discoloration detection was solved, and more objective and accurate detection results were achieved.
Patent Information
- Application Number
- CN202210766785.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-07-01
- Publication Date
- 2025-09-30
- Estimated Expiration
- 2042-07-01
AI Technical Summary
In the prior art, the accuracy of ink printing discoloration detection is affected by manual operation and subjective observation, resulting in inaccurate detection results.
A neural network model is used to predict friction parameters, and combined with the substrate material, the decolorization level of the ink is automatically determined by detecting the composition parameters of the decolorized ink bonded to the paper, avoiding manual observation.
The accuracy of ink printing discoloration detection is improved, the influence of subjective factors is reduced, and the objectivity and reliability of the detection results are ensured.
Smart Images
Figure CN115290553B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of printing technology, and in particular to a method and system for detecting discoloration of ink printing. Background Art
[0002] Printed materials are an important part of modern people's daily life and work, such as newspapers, books, magazines and product packaging. Therefore, the quality of printed materials directly affects people's daily life and work.
[0003] Among them, ink printing discoloration is an important factor affecting the quality of printed products. Therefore, in order to ensure the quality of printed products, in the existing technology, white paper is pasted on the bottom of the friction block, and the friction block is manually operated to rub back and forth on the surface of the printed product several times. Then, the coloring on the white paper is manually observed to determine the ink printing discoloration.
[0004] However, manual friction can affect the accuracy of ink printing discoloration detection, and judging the ink printing discoloration by manually observing the coloring situation can also affect the accuracy of ink printing discoloration detection due to subjectivity.
[0005] Therefore, how to accurately detect the discoloration of ink printing is a technical problem that those skilled in the art urgently need to solve. Summary of the Invention
[0006] The present application provides a method and system for detecting ink discoloration in printing, so as to accurately detect the discoloration of ink in printing.
[0007] To solve the above technical problems, this application provides the following technical solutions:
[0008] A method for detecting discoloration of ink printing comprises the following steps: step S110, collecting component parameters of the ink to be printed, and aggregating the component parameters of the ink to be printed to form a component parameter set of the ink to be printed; step S120, printing on a substrate using the ink to be printed to form a printed product, and rubbing a detection paper and the printed product according to pre-acquired friction parameters; step S130, collecting component parameters of the discoloration ink adhered to the detection paper after the friction, and aggregating the component parameters of the discoloration ink to form a component parameter set of the discoloration ink; step S140, obtaining a discoloration level of the ink to be printed based on the discoloration ink component parameter set and the component parameter set of the ink to be printed.
[0009] In the ink printing discoloration detection method as described above, preferably, the component information of the ink to be printed and its corresponding content information are collected, each component information and its corresponding content information are used as a set of component parameters, and all the collected component parameters of the ink to be printed are combined to form a component parameter set of the ink to be printed.
[0010] In the ink printing discoloration detection method as described above, preferably, the friction parameters include: friction pressure, friction speed, friction times and friction environment temperature.
[0011] The ink printing discoloration detection method as described above, wherein preferably, the friction parameters are predicted in advance, includes the following sub-steps: step S121, taking the ink component parameter set to be printed and the material parameters of the substrate as inputs of the neural network model; step S122, the neural network model analyzes the input printing ink component parameter set and the material parameters of the substrate, and outputs the friction pressure, friction speed, friction number and friction environment temperature.
[0012] In the ink printing discoloration detection method as described above, preferably, if the obtained discoloration level of the ink to be printed is greater than a predetermined value, a substrate with a discoloration resistance less than a predetermined value is selected; if the obtained discoloration level of the ink to be printed is not greater than the predetermined value, a substrate with a discoloration resistance not less than the predetermined value is selected.
[0013] An ink printing discoloration detection system comprises: a collection unit, a printing unit, a detection unit and a discoloration level acquisition unit; the collection unit collects component parameters of the ink to be printed, and aggregates the component parameters of the ink to be printed to form a component parameter set of the ink to be printed; the printing unit uses the ink to be printed to print on a substrate to form a printed product, and the detection unit rubs the detection paper and the printed product according to pre-acquired friction parameters; the collection unit collects component parameters of the discoloration ink adhered to the detection paper after the friction, and aggregates the component parameters of the discoloration ink to form a component parameter set of the discoloration ink; the discoloration level acquisition unit obtains the discoloration level of the ink to be printed based on the discoloration ink component parameter set and the component parameter set of the ink to be printed.
[0014] In the ink printing discoloration detection system as described above, preferably, the collection unit collects the component information of the ink to be printed and its corresponding content information, takes each component information and its corresponding content information as a set of component parameters, and combines all the collected component parameters of the ink to be printed together to form a component parameter set of the ink to be printed.
[0015] In the ink printing discoloration detection system as described above, preferably, the friction parameters include: friction pressure, friction speed, friction times and friction environment temperature.
[0016] The ink printing discoloration detection system as described above, wherein, preferably, further includes: a friction parameter prediction unit, the friction parameter prediction unit includes: an input subunit, a neural network model and an output subunit; the input subunit inputs the ink component parameter set to be printed and the material parameters of the substrate to the neural network model; the neural network model analyzes the input printing ink component parameter set and the material parameters of the substrate, and the output subunit outputs the friction pressure, friction speed, friction times and friction environment temperature.
[0017] In the ink printing discoloration detection system as described above, preferably, if the obtained discoloration level of the ink to be printed is greater than a predetermined value, a substrate with an anti-discoloration ability less than a predetermined value is selected; if the obtained discoloration level of the ink to be printed is not greater than the predetermined value, a substrate with an anti-discoloration ability not less than the predetermined value is selected.
[0018] Compared to the aforementioned background technology, the ink discoloration detection method and system provided by this application utilizes a neural network model to obtain friction parameters and also considers the substrate material when calculating the friction parameters, thereby improving the accuracy of ink discoloration detection. Furthermore, the ink discoloration detection method and system provided by this application detects the compositional parameters of the discolored ink adhered to the test paper, thus avoiding manual observation of the discoloration condition. This further reduces subjective factors and improves the accuracy of ink discoloration detection. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.
[0020] Figure 1 This is a flow chart of the ink printing discoloration detection method provided in an embodiment of the present application;
[0021] Figure 2 Schematic diagram of an ink printing discoloration detection system provided in an embodiment of the present application. DETAILED DESCRIPTION
[0022] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended only to explain the present invention and are not to be construed as limiting the present invention.
[0023] Example 1
[0024] See also Figure 1 , Figure 1 This is a flow chart of the ink printing discoloration detection method provided in an embodiment of the present application.
[0025] The present application provides a method for detecting discoloration of ink printing, comprising the following steps:
[0026] Step S110: collecting component parameters of the ink to be printed, and grouping the component parameters of the ink to be printed together to form a component parameter set of the ink to be printed;
[0027] Ink is a crucial material used in printing, creating designs and text on substrates through printing or inkjet printing. Ink is a viscous, colloidal fluid formed by uniformly mixing primary and secondary ingredients and repeatedly rolling them. Primary ingredients include pigments, which can range from azo pigments to phthalocyanine pigments, and binders, which are made from small amounts of natural resins, synthetic resins, cellulose, rubber derivatives, and the like dissolved in a drying oil or solvent. Auxiliary ingredients include fillers (e.g., barium sulfate, talc, kaolin, calcium carbonate, aluminum hydroxide), diluents (e.g., oligoamidine oil, mineral oil), diluents (e.g., white ink, clear oil, gloss paste), anti-skinning agents (e.g., organic reducing agents, antioxidants), anti-offset agents (e.g., corn starch), slip agents (e.g., microcrystalline wax, synthetic wax), and other additives (e.g., dispersants, wetting agents, desiccants, stabilizers).
[0028] Collect the component information of the ink to be printed and its corresponding content information, take each component information and its corresponding content information as a set of component parameters, and combine all the collected component parameters of the ink to be printed to form a component parameter set A = {(a1, b1), (a2, b2) ... (a i 、b i )…(a n 、b n )}, where a1 is the first component information of the ink to be printed, b1 is the content information corresponding to the first component information, a2 is the second component information of the ink to be printed, b2 is the content information corresponding to the second component information, a i is the i-th component information of the ink to be printed, b i is the content information corresponding to the i-th component information, a n is the nth component information of the ink to be printed, b n For example: a1 represents the azo pigment in the ink to be printed, b1 represents the content of the azo pigment, a2 represents the resin in the ink to be printed, b2 represents the content of the resin, a i Represents the drying oil in the ink to be printed, b iRepresents the content of drying oil, a n represents the barium sulfate in the ink to be printed, b n Represents the content of barium sulfate.
[0029] Step S120: Printing ink on a substrate to form a printed product, and rubbing the test paper against the printed product according to pre-acquired friction parameters;
[0030] The friction parameters include friction pressure, friction speed, friction times, and friction environment temperature. These friction parameters are pre-predicted using a neural network model. Specifically, the pre-prediction of friction parameters includes the following sub-steps:
[0031] Step S121: using the ink composition parameter set to be printed and the material parameters of the substrate as inputs to the neural network model;
[0032] Among them, after the ink is printed on substrates of different materials, its discoloration will be different. Therefore, in order to avoid the influence of the substrate material on the ink discoloration and to comprehensively judge the ink discoloration level, the substrate material needs to be considered when obtaining the friction parameters. Therefore, when the ink composition parameter set to be printed is A={(a1, b1), (a2, b2)…(a i 、b i )…(a n 、b n )}When inputting it into the neural network model, the material parameter c of the printing material also needs to be input into the neural network model.
[0033] The neural network model in this application needs to be pre-built and trained. Specifically, when building the neural network model, according to the formula Obtain the number of neurons L in the hidden layer, where f is a constant between [1, 10] and can be selected according to actual needs. Then, n+1 is used as the number of neurons in the input layer, 4 is used as the number of neurons in the output layer, and L is used as the number of neurons in the hidden layer to construct a neural network model. After constructing the neural network model, the neural network model is trained. Specifically, the network can be trained using the neural network toolbox in MATLAB to obtain the neural network model used in this application.
[0034] Step S122: The neural network model analyzes the input printing ink component parameter set and the material parameters of the substrate, and outputs the friction pressure, friction speed, friction times, and friction environment temperature;
[0035] Among them, the neural network model in this application is T1 represents the friction pressure, α1 represents the influence weight of the friction pressure on the output of the neural network model, T2 represents the friction speed, α2 represents the influence weight of the friction speed on the output of the neural network model, T3 represents the number of frictions, α3 represents the influence weight of the number of frictions on the output of the neural network model, T4 represents the friction environment temperature, α4 represents the influence weight of the friction environment temperature on the output of the neural network model; W1 is the weight from the input layer to the hidden layer of the neural network model, W2 is the weight from the hidden layer to the output layer of the neural network model, β1 is the threshold from the input layer to the hidden layer of the neural network model, β2 is the threshold from the hidden layer to the output layer of the neural network model, μ(x) is the input of the neural network model, σ(x) is a logarithmic function. Specifically, Among them, e is a natural constant.
[0036] The ink component parameter set A to be printed and the material parameter c of the substrate are input into the neural network model. The neural network model analyzes the input printing ink component parameter set and the material parameter of the substrate according to the above formula to obtain the friction pressure T1, friction speed T2, friction number T3 and friction environment temperature T4.
[0037] Step S130: collecting component parameters of the decolorizing ink adhered to the test paper after the friction, and combining the component parameters of the decolorizing ink to form a decolorizing ink component parameter set;
[0038] After the test paper is rubbed against the printed matter, traces of decolorized ink will be left on the test paper, that is, some or all of the component information and corresponding content information of the decolorized ink will be left on the test paper. In this application, the component information and corresponding content information of the decolorized ink left on the test paper are collected, and each component information and corresponding content information are used as a set of component parameters. All component parameters collected from the test paper are combined to form a decolorized ink component parameter set C = {(c1, d1), (c2, d2) ... (c j d j )…(c m d m )}, where c1 is the first component information of the decolorizing ink, d1 is the content information corresponding to the first component information, c2 is the second component information of the decolorizing ink, d2 is the content information corresponding to the second component information, c j is the jth component information of the decolorizing ink, d j is the content information corresponding to the jth component information, c m is the mth component information of the decolorizing ink, d mFor example, c1 represents the azo pigment in the decolorizing ink, d1 represents the content of the azo pigment, c2 represents the resin in the decolorizing ink, d2 represents the content of the resin, c j Represents rubber derivatives in decolorized inks, d j Represents the content of rubber derivatives, c m Represents the oligomeric amidine oil in the decolorizing ink, d m Represents the content of oligomeric amidine oil.
[0039] Step S140: Obtaining a decolorization level of the ink to be printed based on the decolorization ink component parameter set and the component parameter set of the ink to be printed;
[0040] After obtaining the parameter set of the ink composition to be printed and the parameter set of the decolorized ink composition, according to the formula The decolorization grade Q of the ink to be printed is obtained, wherein S represents the deviation factor of each component parameter.
[0041] After obtaining the decolorization level of the ink to be printed, a suitable substrate material can be selected for printing based on the decolorization level of the ink to be printed. For example, if the decolorization level of the ink to be printed is greater than a predetermined value, it indicates that the ink to be printed is not easily decolorized. In this case, cellophane with a weaker decolorization resistance or book paper with a stronger decolorization resistance can be selected. If the decolorization level of the ink to be printed is not greater than the predetermined value, it indicates that the ink to be printed is easily decolorized. In this case, book paper with a stronger decolorization resistance can be selected.
[0042] Example 2
[0043] See also Figure 2 , Figure 2 Schematic diagram of an ink printing discoloration detection system provided in an embodiment of the present application.
[0044] The present application provides an ink printing discoloration detection system 200 , comprising: a collection unit 210 , a printing unit 220 , a detection unit 230 and a discoloration level obtaining unit 240 .
[0045] The collecting unit 210 collects the component parameters of the ink to be printed, and aggregates the component parameters of the ink to be printed to form a component parameter set of the ink to be printed.
[0046] Ink is a crucial material used in printing, creating designs and text on substrates through printing or inkjet printing. Ink is a viscous, colloidal fluid formed by uniformly mixing primary and secondary ingredients and repeatedly rolling them. Primary ingredients include pigments, which can range from azo pigments to phthalocyanine pigments, and binders, which are made from small amounts of natural resins, synthetic resins, cellulose, rubber derivatives, and the like dissolved in a drying oil or solvent. Auxiliary ingredients include fillers (e.g., barium sulfate, talc, kaolin, calcium carbonate, aluminum hydroxide), diluents (e.g., oligoamidine oil, mineral oil), diluents (e.g., white ink, clear oil, gloss paste), anti-skinning agents (e.g., organic reducing agents, antioxidants), anti-offset agents (e.g., corn starch), slip agents (e.g., microcrystalline wax, synthetic wax), and other additives (e.g., dispersants, wetting agents, desiccants, stabilizers).
[0047] Collect the component information of the ink to be printed and its corresponding content information, take each component information and its corresponding content information as a set of component parameters, and combine all the collected component parameters of the ink to be printed to form a component parameter set A = {(a1, b1), (a2, b2) ... (a i 、b i )…(a n 、b n )}, where a1 is the first component information of the ink to be printed, b1 is the content information corresponding to the first component information, a2 is the second component information of the ink to be printed, b2 is the content information corresponding to the second component information, a i is the i-th component information of the ink to be printed, b i is the content information corresponding to the i-th component information, a n is the nth component information of the ink to be printed, b n For example: a1 represents the azo pigment in the ink to be printed, b1 represents the content of the azo pigment, a2 represents the resin in the ink to be printed, b2 represents the content of the resin, a i Represents the drying oil in the ink to be printed, b i Represents the content of drying oil, a n represents the barium sulfate in the ink to be printed, b n Represents the content of barium sulfate.
[0048] The printing unit 220 prints on a substrate using ink to be printed to form a printed product, and the detection unit 230 rubs the detection paper against the printed product according to pre-acquired friction parameters.
[0049] The friction parameters include friction pressure, friction speed, friction times, and friction environment temperature. These friction parameters are pre-predicted using a neural network model. The ink printing discoloration detection system 200 also includes a friction parameter prediction unit 250, which pre-predicts the friction parameters. Specifically, the friction parameter prediction unit 250 includes an input subunit 251, a neural network model 252, and an output subunit 253.
[0050] The input subunit 251 inputs the parameter set of the ink composition to be printed and the material parameters of the substrate to the neural network model 252 .
[0051] Among them, after the ink is printed on substrates of different materials, its discoloration will be different. Therefore, in order to avoid the influence of the substrate material on the ink discoloration and to comprehensively judge the ink discoloration level, the substrate material needs to be considered when obtaining the friction parameters. Therefore, when the ink composition parameter set to be printed is A={(a1, b1), (a2, b2)…(a i 、b i )…(a n 、b n )}When inputting it into the neural network model, the material parameter c of the printing material also needs to be input into the neural network model.
[0052] The neural network model in this application needs to be pre-built and trained. Specifically, when building the neural network model, according to the formula Obtain the number of neurons L in the hidden layer, where f is a constant between [1, 10] and can be selected according to actual needs. Then, n+1 is used as the number of neurons in the input layer, 4 is used as the number of neurons in the output layer, and L is used as the number of neurons in the hidden layer to construct a neural network model. After constructing the neural network model, the neural network model is trained. Specifically, the network can be trained using the neural network toolbox in MATLAB to obtain the neural network model used in this application.
[0053] The neural network model 252 analyzes the input printing ink component parameter set and the material parameters of the substrate, and the output subunit 253 outputs the friction pressure, friction speed, friction times and friction environment temperature.
[0054] Among them, the neural network model in this application is T1 represents the friction pressure, α1 represents the influence weight of the friction pressure on the output of the neural network model, T2 represents the friction speed, α2 represents the influence weight of the friction speed on the output of the neural network model, T3 represents the number of frictions, α3 represents the influence weight of the number of frictions on the output of the neural network model, T4 represents the friction environment temperature, α4 represents the influence weight of the friction environment temperature on the output of the neural network model; W1 is the weight from the input layer to the hidden layer of the neural network model, W2 is the weight from the hidden layer to the output layer of the neural network model, β1 is the threshold from the input layer to the hidden layer of the neural network model, β2 is the threshold from the hidden layer to the output layer of the neural network model, μ(x) is the input of the neural network model, σ(x) is a logarithmic function. Specifically, Among them, e is a natural constant.
[0055] The ink component parameter set A to be printed and the material parameter c of the substrate are input into the neural network model. The neural network model analyzes the input printing ink component parameter set and the material parameter of the substrate according to the above formula to obtain the friction pressure T1, friction speed T2, friction number T3 and friction environment temperature T4.
[0056] The collecting unit 210 collects the component parameters of the decolorized ink adhered to the test paper after the friction, and collects the component parameters of the decolorized ink to form a decolorized ink component parameter set.
[0057] After the test paper is rubbed against the printed matter, traces of decolorized ink will be left on the test paper, that is, some or all of the component information and corresponding content information of the decolorized ink will be left on the test paper. In this application, the component information and corresponding content information of the decolorized ink left on the test paper are collected, and each component information and corresponding content information are used as a set of component parameters. All component parameters collected from the test paper are combined to form a decolorized ink component parameter set C = {(c1, d1), (c2, d2) ... (c j d j )…(c m d m )}, where c1 is the first component information of the decolorizing ink, d1 is the content information corresponding to the first component information, c2 is the second component information of the decolorizing ink, d2 is the content information corresponding to the second component information, c j is the jth component information of the decolorizing ink, d j is the content information corresponding to the jth component information, c m is the mth component information of the decolorizing ink, d mFor example, c1 represents the azo pigment in the decolorizing ink, d1 represents the content of the azo pigment, c2 represents the resin in the decolorizing ink, d2 represents the content of the resin, c j Represents rubber derivatives in decolorized inks, d j Represents the content of rubber derivatives, c m Represents the oligomeric amidine oil in the decolorizing ink, d m Represents the content of oligomeric amidine oil.
[0058] The decolorization level obtaining unit 240 obtains the decolorization level of the ink to be printed according to the decolorization ink component parameter set and the component parameter set of the ink to be printed.
[0059] After obtaining the parameter set of the ink composition to be printed and the parameter set of the decolorized ink composition, according to the formula The decolorization grade Q of the ink to be printed is obtained, wherein S represents the deviation factor of each component parameter.
[0060] After obtaining the decolorization level of the ink to be printed, a suitable substrate material can be selected for printing based on the decolorization level of the ink to be printed. For example, if the decolorization level of the ink to be printed is greater than a predetermined value, it indicates that the ink to be printed is not easily decolorized. In this case, cellophane with a weaker decolorization resistance or book paper with a stronger decolorization resistance can be selected. If the decolorization level of the ink to be printed is not greater than the predetermined value, it indicates that the ink to be printed is easily decolorized. In this case, book paper with a stronger decolorization resistance can be selected.
[0061] Because the friction parameters in this application are obtained through a neural network model and the substrate material is taken into account when calculating the friction parameters, the accuracy of ink print discoloration detection is improved. Furthermore, when performing ink print discoloration detection, this application avoids manual observation of the discoloration by detecting the composition parameters of the discolored ink adhered to the test paper, further eliminating subjective factors and improving the accuracy of ink print discoloration detection.
[0062] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.
[0063] In addition, it should be understood that although this specification is described in terms of implementation methods, not every implementation method contains only one independent technical solution. This narrative method of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other implementation methods that can be understood by those skilled in the art.
Claims
1. A method for detecting discoloration of ink printing, characterized in that: The steps include: Step S110: collecting component parameters of the ink to be printed, and grouping the component parameters of the ink to be printed together to form a component parameter set of the ink to be printed; Step S120: Printing ink on a substrate to form a printed product, and rubbing the test paper against the printed product according to pre-acquired friction parameters; Predicting friction parameters in advance includes the following sub-steps: Step S121: using the ink composition parameter set to be printed and the material parameters of the substrate as inputs to the neural network model; According to the formula Obtain the number of neurons in the hidden layer, L, where f is a constant between [1,10], n+1 is the number of neurons in the input layer, and 4 is the number of neurons in the output layer; Step S122: The neural network model analyzes the input printing ink component parameter set and the material parameters of the substrate, and outputs friction parameters: friction pressure, friction speed, friction times, and friction environment temperature; Step S130: collecting component parameters of the decolorizing ink adhered to the test paper after the friction, and combining the component parameters of the decolorizing ink to form a decolorizing ink component parameter set; Step S140: Obtaining a decolorization level of the ink to be printed based on the decolorization ink component parameter set and the component parameter set of the ink to be printed; According to the formula Obtain the decolorization grade Q of the ink to be printed, where S represents the deviation factor of each component parameter, a i is the i-th component information of the ink to be printed, b i is the content information corresponding to the i-th component information, n is the number of component information of the ink to be printed, c j is the jth component information of the decolorizing ink, d j is the content information corresponding to the j-th component information, and m is the number of component information of the decolorizing ink.
2. The ink printing decolorization detection method according to claim 1, characterized in that: Collect the component information of the ink to be printed and its corresponding content information, take each component information and its corresponding content information as a set of component parameters, and combine all the collected component parameters of the ink to be printed to form a component parameter set of the ink to be printed.
3. The ink printing decolorization detection method according to claim 1 or 2, characterized in that: If the obtained decolorization level of the ink to be printed is greater than a predetermined value, a substrate having a decolorization resistance less than a predetermined value is selected; If the obtained decolorization level of the ink to be printed is not greater than a predetermined value, a printing material having a decolorization resistance not less than a predetermined value is selected.
4. An ink printing discoloration detection system, characterized in that: include: An acquisition unit, a printing unit, a detection unit, a discoloration level acquisition unit, and a friction parameter prediction unit, wherein the friction parameter prediction unit includes an input subunit, a neural network model, and an output subunit; The collecting unit collects the composition parameters of the ink to be printed and aggregates the composition parameters of the ink to be printed to form a set of composition parameters of the ink to be printed; the printing unit prints the ink to be printed on a substrate to form a printed product, and the detecting unit rubs the detection paper against the printed product according to the friction parameters obtained in advance; The input subunit inputs the parameter set of the ink composition to be printed and the material parameters of the substrate into the neural network model; According to the formula Obtain the number of neurons in the hidden layer, L, where f is a constant between [1,10], n+1 is the number of neurons in the input layer, and 4 is the number of neurons in the output layer; The neural network model analyzes the input printing ink composition parameter set and substrate material parameters, and the output subunit outputs friction parameters: friction pressure, friction speed, friction times and friction environment temperature; The collecting unit collects the composition parameters of the decolorizing ink adhered to the test paper after the friction, and collects the composition parameters of the decolorizing ink to form a decolorizing ink composition parameter set; The decolorization level obtaining unit obtains the decolorization level of the ink to be printed according to the decolorization ink component parameter set and the component parameter set of the ink to be printed; According to the formula Obtain the decolorization grade Q of the ink to be printed, where S represents the deviation factor of each component parameter, a i is the i-th component information of the ink to be printed, b i is the content information corresponding to the i-th component information, n is the number of component information of the ink to be printed, c j is the jth component information of the decolorizing ink, d j is the content information corresponding to the j-th component information, and m is the number of component information of the decolorizing ink.
5. The ink printing discoloration detection system according to claim 4, characterized in that: The collection unit collects the component information of the ink to be printed and its corresponding content information, takes each component information and its corresponding content information as a set of component parameters, and combines all the collected component parameters of the ink to be printed to form a component parameter set of the ink to be printed.
6. The ink printing discoloration detection system according to claim 4 or 5, characterized in that: If the obtained decolorization level of the ink to be printed is greater than a predetermined value, a substrate having a decolorization resistance less than a predetermined value is selected; If the obtained decolorization level of the ink to be printed is not greater than a predetermined value, a printing material having a decolorization resistance not less than a predetermined value is selected.