Method for exploring the composition and manufacturing conditions of phthalocyanine pigments for color filters, information processing apparatus, and program

Abstract

To improve a technology for searching a composition and a production condition of a phthalocyanine pigment for a color filter.SOLUTION: A search method includes the steps of: training a prediction model on the basis of teacher data with composition analysis information, a pigmentation condition and a distribution condition of phthalocyanine crude as explanatory variables and with the brightness, film thickness and contrast of a color filter as objective variables; calculating a first prediction data group by grid search based on a lower-limit value and an upper-limit value of teacher data; determining a second prediction group on the basis of a model application range determined by the first prediction data group and the teacher data; determining a third prediction data group on the basis of the second prediction data group and a condition related to feasibility; and determining an optimum composition and a production condition from the third prediction data group.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a method for searching the composition and production conditions of phthalocyanine pigments for color filters, an information processing apparatus, and a program. [Background Art]

[0002] Conventionally, techniques for searching for new materials by machine learning have been known. For example, as an example of using machine learning for color materials, there is a paint manufacturing method in which learning data is subjected to machine learning to generate an artificial intelligence model, and target color data is input thereto to obtain candidate composition data (Patent Document 1). As another example, there is a color matching method in which the color value of a sample color is measured, and the blending ratio of a color material is obtained using a neural network trained based on combination data of basic color materials (Patent Document 2). As an example of using machine learning for pigments, there is a method in which a learning model is created for the relationship between coating films prepared from 30 types of luster pigments and image feature amounts, and the learning model is used to identify luster pigments (Patent Document 3). There is also an example where, for an adhesive composition, the optimal blending ratio obtained by the design of experiments is traced as an example to evaluate the properties, and the amounts of acrylate and maleic acid in the optimal blending ratio are described in the claims (Patent Document 4). [Prior Art Documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2021-188046 [Patent Document 2] Japanese Patent Application Laid-Open No. 11-341297 [Patent Document 3] Japanese Patent Application Laid-Open No. 2007-218895 [Patent Document 4] Japanese National Publication of International Patent Application No. 2003-519713 [Brief Summary of the Invention] [Problem to be Solved by the Invention]

[0004] While methods for calculating optimal compositions using inverse analysis have been known for some time, these methods often include compositions and manufacturing conditions with unreliable predicted values ​​when performing optimization, such as grid search. Furthermore, the calculated predicted values ​​may include conditions that are theoretically impossible in actual manufacturing, meaning that experimental verification is still frequently necessary. In addition, there are no existing examples focusing on methods for exploring the composition and manufacturing conditions of phthalocyanine pigments for color filters. Thus, there was room for improvement in the technology for exploring the composition and manufacturing conditions of phthalocyanine pigments for color filters.

[0005] In view of these circumstances, the purpose of this disclosure is to improve the techniques for exploring the composition and manufacturing conditions of phthalocyanine pigments for color filters. [Means for solving the problem]

[0006] (Note 1) A method for exploring the composition and manufacturing conditions of a phthalocyanine pigment for a color filter according to one embodiment of this disclosure is: In a color filter in which phthalocyanine crude is pigmentized, dispersed with a dispersant, and coated and dried on a glass substrate, a method for exploring the composition and manufacturing conditions of a phthalocyanine pigment for a color filter, which is performed by an information processing device, The process involves training a predictive model based on training data where the compositional analysis information of phthalocyanine crude, pigmentation conditions, and dispersion conditions are used as explanatory variables, and the brightness, film thickness, and contrast of the color filter are used as dependent variables. The steps include generating a first set of prediction data by performing a grid search based on the lower and upper limits of the aforementioned training data, A step of generating a second set of prediction data based on the model application range determined by the first set of prediction data and the training data, The steps include generating a third set of prediction data based on the second set of prediction data and the conditions related to feasibility, The steps include determining the optimal composition and manufacturing conditions based on the third set of predicted data, Includes.

[0007] (Note 2) A method for exploring the composition and manufacturing conditions of a phthalocyanine pigment for a color filter according to one embodiment of this disclosure is the exploration method described in (Note 1), The scope of application of the aforementioned model is determined based on k-nearest neighbors, one-class support vector machines, or ensemble learning.

[0008] (Note 3) A method for exploring the composition and manufacturing conditions of a phthalocyanine pigment for a color filter according to one embodiment of the present disclosure is the exploration method described in (Note 1) or (Note 2), The conditions for the aforementioned feasibility are that all of the following equations (1) to (4) are satisfied. 16Br > 15Br1Cl > 14Br2Cl...(1) 16Br > 15Br1H > 14Br2H (2) 15Br1Cl > 14Br1Cl1H···(3) 15Br1H > 14Br1Cl1H···(4) However, 16Br, 15Br1Cl, 14Br2Cl, 15Br1H, 14Br2H, and 14Br1Cl1H represent the mass spectral intensity ratios (in %) of 16Br phthalocyanine, 15Br1Cl phthalocyanine, 14Br2Cl phthalocyanine, 15Br1H phthalocyanine, 14Br2H phthalocyanine, and 14Br1Cl1H phthalocyanine in the phthalocyanine crude, respectively.

[0009] (Note 4) A method for exploring the composition and manufacturing conditions of a phthalocyanine pigment for a color filter according to one embodiment of the present disclosure is the exploration method described in any one of (Note 1) to (Note 3), The third set of predicted data is further determined based on the conditions related to the ideal composition.

[0010] (Note 5) A method for exploring the composition and manufacturing conditions of a phthalocyanine pigment for a color filter according to one embodiment of this disclosure is the exploration method described in (Note 4), The condition for the aforementioned ideal composition is that it satisfies the following equation (5). 100-(16Br+15Br1Cl+15Br1H+14Br2Cl+14Br1Cl1H+14Br2H+AlPc) < 5...(5) However, 16Br, 15Br1Cl, 15Br1H, 14Br2Cl, 14Br1Cl1H, 14Br2H, and AlPc represent the mass spectral intensity ratios (in %) of 16Br phthalocyanine, 15Br1Cl phthalocyanine, 15Br1H phthalocyanine, 14Br2Cl phthalocyanine, 14Br1Cl1H phthalocyanine, 14Br2H phthalocyanine, and impurities in the phthalocyanine crude, respectively.

[0011] (Note 6) A method for exploring the composition and manufacturing conditions of a phthalocyanine pigment for a color filter according to one embodiment of the present disclosure is the exploration method described in any one of (Note 1) to (Note 5), The aforementioned optimal composition and manufacturing conditions are determined based on luminance.

[0012] (Note 7) A method for exploring the composition and manufacturing conditions of a phthalocyanine pigment for a color filter according to one embodiment of the present disclosure is the exploration method described in any one of (Note 1) to (Note 5), The aforementioned optimal composition and manufacturing conditions are determined based on brightness and film thickness.

[0013] (Note 8) An information processing apparatus according to one embodiment of the present disclosure is: In a color filter in which phthalocyanine crude is pigmentized, dispersed with a dispersant, and coated and dried on a glass substrate, an information processing apparatus is provided which includes a control unit for searching for the composition and manufacturing conditions of the phthalocyanine pigment for the color filter, The control unit, A predictive model was trained based on training data in which the compositional analysis information of phthalocyanine crude, pigmentation conditions, and dispersion conditions were used as explanatory variables, and the brightness, film thickness, and contrast of the color filter were used as dependent variables. A first set of prediction data is generated by a grid search based on the lower and upper limits of the aforementioned training data. generating a second prediction data group based on a model application range defined by the first prediction data group and the teacher data, generating a third prediction data group based on the second prediction data group and conditions relating to feasibility, determining an optimal composition and manufacturing conditions based on the third prediction data group.

[0014] (Supplementary Note 9) A program according to an embodiment of the present disclosure, in a color filter produced by pigmenting phthalocyanine crude, adding a dispersant, performing dispersion, applying the resulting mixture onto a glass substrate and drying the same, the program is for searching for the composition and manufacturing conditions of a phthalocyanine pigment for a color filter executed by an information processing apparatus, and causes a computer to: train a prediction model based on teacher data that uses composition analysis information of phthalocyanine crude, pigmentation conditions and dispersion conditions as explanatory variables, and uses the luminance, film thickness and contrast of a color filter as objective variables; generate a first prediction data group by grid search based on lower limit values and upper limit values of the teacher data; generate a second prediction data group based on a model application range defined by the first prediction data group and the teacher data; generate a third prediction data group based on the second prediction data group and conditions relating to feasibility, determine an optimal composition and manufacturing conditions based on the third prediction data group; and execute the above steps.

Effects of the Invention

[0015] According to the method for searching for the composition and manufacturing conditions of a phthalocyanine pigment for a color filter, the information processing apparatus, and the program according to an embodiment of the present disclosure, the technique for searching for the composition and manufacturing conditions of a phthalocyanine pigment for a color filter can be improved.

Brief Description of Drawings

[0016] [Figure 1]This block diagram shows a schematic configuration of an information processing device that performs a technique for exploring the composition and manufacturing conditions of phthalocyanine pigments for color filters according to one embodiment of the present disclosure. [Figure 2] This flowchart shows a method for exploring the composition and manufacturing conditions of a phthalocyanine pigment for color filters according to one embodiment of the present disclosure. [Figure 3] This is an overview diagram of the first prediction data set. [Figure 4] This is an overview diagram of the second prediction data set. [Figure 5] This is a conceptual diagram showing the scope of application of the model. [Figure 6] This is an overview diagram of the third prediction data set. [Figure 7] This is a schematic diagram showing a modified version of the third prediction data set. [Modes for carrying out the invention]

[0017] Hereinafter, the techniques for exploring the composition and manufacturing conditions of phthalocyanine pigments for color filters according to the embodiments of this disclosure will be described with reference to the drawings.

[0018] In each figure, identical or corresponding parts are denoted by the same reference numerals. In the description of this embodiment, the description of identical or corresponding parts will be omitted or simplified as appropriate.

[0019] First, an overview of this embodiment will be described. The exploration technique according to one embodiment of this disclosure targets the composition and manufacturing conditions of phthalocyanine pigments for color filters. The color filter according to this embodiment is manufactured by pigmentizing phthalocyanine crude, dispersing it with a dispersant, and coating and drying it on a glass substrate. The composition and manufacturing conditions include the composition of the phthalocyanine crude, the pigmentization conditions, and the dispersion conditions. Furthermore, the color filter mainly has three characteristics: brightness, film thickness, and contrast. Therefore, in the exploration technique according to one embodiment of this disclosure, a predictive model is trained based on training data in which the compositional analysis information of the phthalocyanine crude, the pigmentization conditions, and the dispersion conditions are used as explanatory variables, and the brightness, film thickness, and contrast of the color filter are used as objective variables. In this disclosure, brightness includes both the concept of monochromatic brightness when the pigment is evaluated alone, and the concept of toned brightness when it is evaluated mixed with other pigments. Similarly, film thickness in this disclosure includes both the concept of monochromatic film thickness when the pigment is evaluated alone, and the concept of toned film thickness when it is evaluated mixed with other pigments. Furthermore, in the search technique according to one embodiment of this disclosure, a first prediction data set is generated by grid search based on lower and upper limits of training data. Subsequently, a second prediction data set is generated based on the model application range determined by the first prediction data set and training data. Subsequently, a third prediction data set is generated based on the second prediction data set and feasibility conditions. Finally, the optimal composition and manufacturing conditions are determined based on the third prediction data set.

[0020] As described above, according to the method for exploring the composition and manufacturing conditions of phthalocyanine pigments for color filters, a predictive model is trained based on training data in which the compositional analysis information of phthalocyanine crude, pigmentation conditions, and dispersion conditions are used as explanatory variables, and the brightness, film thickness, and contrast of the color filter are used as objective variables. Then, a first set of predicted data is generated by grid search, a second set of predicted data is generated based on the model's applicability range, and a third set of predicted data is generated based on feasibility conditions. Finally, the optimal composition and manufacturing conditions are determined based on the third set of predicted data. Therefore, according to this embodiment, the method for exploring the composition and manufacturing conditions of phthalocyanine pigments for color filters is improved in that it is possible to explore compositions and manufacturing conditions that take into account the model's applicability range and feasibility.

[0021] (Configuration of information processing device) Next, the components of the information processing device 10 will be described in detail. The information processing device 10 is any device used by the user. For example, a personal computer, a server computer, a general-purpose electronic device, or a dedicated electronic device can be used as the information processing device 10.

[0022] As shown in Figure 1, the information processing device 10 comprises a control unit 11, a storage unit 12, an input unit 13, and an output unit 14.

[0023] The control unit 11 includes at least one processor, at least one dedicated circuit, or a combination thereof. The processor is a general-purpose processor such as a CPU (central processing unit) or GPU (graphics processing unit), or a dedicated processor specialized for a specific process. The dedicated circuit is, for example, an FPGA (field-programmable gate array) or an ASIC (application-specific integrated circuit). The control unit 11 controls each part of the information processing device 10 and executes processes related to the operation of the information processing device 10.

[0024] The storage unit 12 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or at least two combinations thereof. The semiconductor memory is, for example, RAM (random access memory) or ROM (read-only memory). The RAM is, for example, SRAM (static random access memory) or DRAM (dynamic random access memory). The ROM is, for example, EEPROM (electrically erasable programmable read-only memory). The storage unit 12 functions, for example, as a main memory, auxiliary memory, or cache memory. The storage unit 12 stores data used for the operation of the information processing device 10 and data obtained by the operation of the information processing device 10.

[0025] The input unit 13 includes at least one input interface. The input interface may be, for example, a physical key, a capacitive key, a pointing device, or a touchscreen integrated with a display. Alternatively, the input interface may be, for example, a microphone that accepts voice input or a camera that accepts gesture input. The input unit 13 accepts operations to input data used for the operation of the information processing device 10. Instead of being integrated into the information processing device 10, the input unit 13 may be connected to the information processing device 10 as an external input device. Any connection method can be used, for example, USB (Universal Serial Bus), HDMI (registered trademark) (High-Definition Multimedia Interface), or Bluetooth (registered trademark).

[0026] The output unit 14 includes at least one output interface. The output interface is, for example, a display that outputs information as video. The display is, for example, an LCD (liquid crystal display) or an organic EL (electroluminescence) display. The output unit 14 displays and outputs data obtained by the operation of the information processing device 10. Instead of being provided in the information processing device 10, the output unit 14 may be connected to the information processing device 10 as an external output device. Any connection method can be used, for example, USB, HDMI (registered trademark), or Bluetooth (registered trademark).

[0027] The functions of the information processing device 10 are realized by executing a program according to this embodiment on a processor corresponding to the information processing device 10. In other words, the functions of the information processing device 10 are realized by software. The program causes the computer to perform the operations of the information processing device 10, thereby causing the computer to function as the information processing device 10. That is, the computer functions as the information processing device 10 by performing the operations of the information processing device 10 according to the program.

[0028] In this embodiment, the program can be recorded on a computer-readable recording medium. The computer-readable recording medium includes non-temporary computer-readable media, such as magnetic recording devices, optical discs, magneto-optical recording media, or semiconductor memory. The program can be distributed, for example, by selling, transferring, or lending portable recording media such as DVDs (digital versatile discs) or CD-ROMs (compact disc read-only memory) on which the program is recorded. Alternatively, the program may be distributed by storing it on the storage of an external server and transmitting it from the external server to other computers. The program may also be provided as a program product.

[0029] Some or all of the functions of the information processing device 10 may be implemented by a dedicated circuit corresponding to the control unit 11. In other words, some or all of the functions of the information processing device 10 may be implemented by hardware.

[0030] Referring to the flowchart in Figure 2, a method for exploring the composition and manufacturing conditions of a phthalocyanine pigment for a color filter according to one embodiment of this disclosure is shown.

[0031] Step S101: The control unit 11 of the information processing device 10 trains a predictive model. Specifically, the control unit 11 trains a predictive model based on training data in which the compositional analysis information of phthalocyanine crude, pigmentation conditions, and dispersion conditions are used as explanatory variables, and the brightness, film thickness, and contrast of the color filter are used as objective variables. In order to calculate brightness and film thickness, the phthalocyanine pigment of this disclosure is mixed with yellow pigment or purple pigment to fine-tune the color. Examples of yellow pigments include CI Pigment Yellow (PY) 1, 2, 3, 4, 5, 6, 10, 12, 13, 14, 15, 16, 17, 18, 24, 31, 32, 34, 35, 35:1, 36, 36: 1, 37, 37:1, 40, 42, 43, 53, 55, 60, 61, 62, 63, 65, 73, 74, 77, 81, 83, 93, 94, 95, 97, 98, 100, 101, 104, 106, 108, 109, 110, 113, 114, 115, 116, 117, 118, 119, 120, 126, 127, 12 8, 129, 138, 139, 150, 151, 152, 153, 154, 155, 156, 161, 162, 164, 166, 167, 168, 169, 170, 171, 172, 173, 174, 175, 176, 177, 179, 180, 181, 182, 185, 187, 199, 231, etc. are used as purple pigments. CI Pigment Violet 1, 1:1, 2, 2:2, 3, 3:1, 3:3, 5, 5:1, 14, 15, 16, 19, 23, 25, 27, 29, 31, 32, 37, 39, 42, 44, 47, 49, 50, etc. are used as purple pigments.

[0032] Step S102: The control unit 11 generates a first set of prediction data. Specifically, the control unit 11 generates a first set of prediction data by performing a grid search based on the lower and upper limits of the training data.

[0033] Figure 3 shows an example of the first prediction data set. The first prediction data set is obtained by changing each explanatory variable in predetermined steps from a lower limit to an upper limit, within the range of possible values ​​for each explanatory variable in the training data, and inputting all combinations of such explanatory variables into the prediction model trained in step S101. In this embodiment, the explanatory variables are the compositional analysis information of phthalocyanine crude, the pigmentation conditions, and the dispersion conditions. In other words, the start value, end value, and step of each of these explanatory variables are determined to determine the input data, and output data corresponding to all such input data is obtained based on the prediction model. In other words, the first prediction data is a combination of this input data and output data. Figure 3 plots the first prediction data set with relative luminance on the horizontal axis and relative film thickness on the vertical axis. The first prediction data set is shown by the set of plots 100.

[0034] Step S103: The control unit 11 generates a second set of prediction data. Specifically, the control unit 11 generates a second set of prediction data based on the model application range defined by the first set of prediction data and the training data. Here, the model application range may be determined based on k-nearest neighbors, one-class support vector machine, or ensemble learning.

[0035] Figure 4 shows an example of the second prediction data set. Figure 4 plots the second prediction data set with relative luminance on the horizontal axis and relative film thickness on the vertical axis. The model application range of the second prediction data set shown in Figure 4 is determined based on the k-nearest neighbor method. Specifically, the model application range is determined as follows. The second prediction data set is represented by plot set 200.

[0036] (a) First, the explanatory variables X of the training data (composition analysis information of phthalocyanine crude and pigmentation conditions) are standardized for each variable. This standardization transforms the explanatory variables so that the mean is 0 and the standard deviation is 1. Specifically, the variable transformation is performed by subtracting the mean from each data point and dividing by the standard deviation.

[0037] (b) Next, the explanatory variables from the grid search results are standardized. Specifically, for each variable, the variable transformation process is performed by subtracting the mean of the training data obtained in (a) from each data point and dividing by the standard deviation.

[0038] (c) Next, the distance between each training data point and its five neighboring training data points is calculated. The average of these distances is also calculated.

[0039] (d) The calculation results from (c) above are sorted in ascending order, and the distance from which 96% of the training data is included is set as the threshold for the model's applicability range.

[0040] (e) Next, the distance between the grid search result to be evaluated and the five neighboring training data points is calculated, and the average distance is calculated. Figure 5 shows a conceptual diagram of the calculation of the distance related to the grid search result to be evaluated. The average of the distances between d1 and d5 corresponds to the average distance.

[0041] (f) If the average distance is less than the threshold for the model's applicability range, it is determined to be within the model's applicability range. On the other hand, if the average distance is greater than or equal to the threshold for the model's applicability range, it is determined to be outside the model's applicability range.

[0042] (g) Processes (e) and (f) above are performed on all grid search results, and the grid search results within the model's application range are determined as the second prediction data set.

[0043] The above examples of (a)–(f) show that the parameters k and α of the k-nearest neighbors method are 5 and 0.96, respectively. However, the parameter settings are not limited to these, and different parameter settings may be used.

[0044] Step S104: The control unit 11 generates a third prediction data set. Specifically, the control unit 11 generates a third prediction data set based on the second prediction data set and the conditions related to feasibility.

[0045] The third prediction data set was generated based on the following equations (1) to (4) as conditions related to feasibility. In other words, the third prediction data set is a data set extracted from the second prediction data set that satisfies all of the following equations (1) to (4). 16Br > 15Br1Cl > 14Br2Cl...(1) 16Br > 15Br1H > 14Br2H (2) 15Br1Cl > 14Br1Cl1H···(3) 15Br1H > 14Br1Cl1H···(4) However, in formulas (1) to (4), 16Br, 15Br1Cl, 14Br2Cl, 15Br1H, 14Br2H, and 14Br1Cl1H represent the mass spectral intensity ratios (in %) of 16Br phthalocyanine, 15Br1Cl phthalocyanine, 14Br2Cl phthalocyanine, 15Br1H phthalocyanine, 14Br2H phthalocyanine, and 14Br1Cl1H phthalocyanine in the phthalocyanine crude, respectively.

[0046] Figure 6 shows an example of the third prediction data set. Figure 6 plots the third prediction data set with relative luminance on the horizontal axis and relative film thickness on the vertical axis. The third prediction data set is represented by plot set 300.

[0047] Step S105: The control unit 11 determines the optimal composition and manufacturing conditions. Specifically, the control unit 11 determines the optimal composition and manufacturing conditions based on the third prediction data group.

[0048] Various methods can be used to determine the optimal composition and manufacturing conditions. For example, the optimal composition and manufacturing conditions may be determined based on luminance. Specifically, the control unit 11 may determine the composition and manufacturing conditions with the maximum luminance among the third prediction data group as the optimal composition and manufacturing conditions. Alternatively, for example, the optimal composition and manufacturing conditions may be determined based on luminance and film thickness. Specifically, the control unit 11 may determine the composition and manufacturing conditions with the film thickness at any target value and the maximum luminance as the optimal composition and manufacturing conditions.

[0049] As described above, according to the method for exploring the composition and manufacturing conditions of phthalocyanine pigments for color filters, a predictive model is trained based on training data in which the compositional analysis information of phthalocyanine crude, pigmentation conditions, and dispersion conditions are used as explanatory variables, and the brightness, film thickness, and contrast of the color filter are used as objective variables. Then, a first set of predicted data is generated by grid search, a second set of predicted data is generated based on the model's applicability range, and a third set of predicted data is generated based on feasibility conditions. Finally, the optimal composition and manufacturing conditions are determined based on the third set of predicted data. Therefore, according to this embodiment, the method for exploring the composition and manufacturing conditions of phthalocyanine pigments for color filters is improved in that it is possible to explore compositions and manufacturing conditions that take into account the model's applicability range and feasibility.

[0050] Here, the third prediction data group may be further determined based on conditions relating to the ideal composition. The conditions relating to the ideal composition are, for example, that the following equation (5) is satisfied. In other words, the third prediction data group may be a data group extracted from the second prediction data group that satisfies not only equations (1) to (4) above, but also the following equation (5). 100-(16Br+15Br1Cl+15Br1H+14Br2Cl+14Br1Cl1H+14Br2H+AlPc) < 5...(5) However, in equation (5), 16Br, 15Br1Cl, 15Br1H, 14Br2Cl, 14Br1Cl1H, 14Br2H, and AlPc represent the mass spectral intensity ratios (in %) of 16Br phthalocyanine, 15Br1Cl phthalocyanine, 15Br1H phthalocyanine, 14Br2Cl phthalocyanine, 14Br1Cl1H phthalocyanine, 14Br2H phthalocyanine, and impurities in the phthalocyanine crude, respectively. Figure 7 shows the third prediction data set related to the modified example. Figure 7 plots the third prediction data set related to the modified example, with the horizontal axis representing relative luminance and the vertical axis representing relative film thickness. The set of plots 400 in Figure 7 corresponds to the third prediction data set related to the modified example.

[0051] (Examples) The following describes examples using the optimal composition and manufacturing conditions determined by this embodiment. Here, the compositional analysis information of phthalocyanine crude with the optimal composition and manufacturing conditions determined by this embodiment is considered the ideal composition.

[0052] First, zinc phthalocyanine was produced using phthalonitrile, ammonia, and zinc chloride as raw materials. The 1-chloronaphthalene solution after the reaction showed light absorption in the 750-850 nm range. 270 parts of sulfuryl chloride (Fujifilm Wako Pure Chemical Industries, Ltd., product code: 190-04815), 315 parts of anhydrous aluminum chloride (Kanto Chemical Co., Ltd., product code: 01156-00), 43 parts of sodium chloride (Tokyo Chemical Industries, Ltd., product code: S0572), and 116 parts of bromine (Fujifilm Wako Pure Chemical Industries, Ltd., product code: 026-02405) were mixed, and 84 parts of the zinc phthalocyanine prepared above were added to the resulting mixture. 465 parts of bromine were added dropwise, and the mixture was heated to 80°C over 22 hours. Then, the temperature was raised to 130°C over 3 hours, and the reaction mixture was separated into water to precipitate the crude polyhalogenated zinc phthalocyanine pigment. This aqueous slurry was filtered, washed with 60°C water, and then redissolved in water. The obtained slurry was filtered again, washed with hot water at 60°C, and dried at 90°C to obtain 173 parts of crude zinc phthalocyanine polyhalide pigment. This was further processed into a pigment to obtain zinc phthalocyanine polyhalide pigment. The results of mass spectrometry (JEOL Ltd., JMS-S3000) of this zinc phthalocyanine polyhalide pigment are shown in Table 1. As shown in Table 1, it can be seen that a phthalocyanine pigment with a composition close to the ideal composition can be obtained by the above manufacturing method. Table 1 also includes, as a comparative example, compositional conditions with the best brightness and film thickness, selected using only machine learning and grid search.

[0053] [Table 1]

[0054] In Table 1, the values ​​for 16Br, 15Br1Cl, 15Br1H, 14Br2Cl, 14Br1Cl1H, and 14Br2H are expressed as relative differences from the ideal composition based on the intensity ratio of the mass spectrum (in %). Since these relative differences are within the experimental error range, it can be seen that the examples are phthalocyanine pigments with a composition almost identical to the ideal composition. Here, the threshold for the knn distance is 2.61. Values ​​above this threshold indicate that the model is outside the applicable range, and values ​​below this threshold indicate that the model is within the applicable range. Since the knn distance values ​​for the ideal composition and the examples are lower than the threshold, it can be seen that they are within the applicable range of the model. The large difference in knn distance between the ideal composition and the examples is thought to be due to influences other than the main composition (pigmentation conditions, amount of impurities). Furthermore, it can be seen that the examples, like the ideal composition, also satisfy the feasibility relationship. On the other hand, it can be seen that the comparative examples do not satisfy the feasibility relationship.

[0055] There are no particular limitations on the method for producing the zinc halide phthalocyanine pigment in this embodiment. For example, it can be done using, in combination with, or by reference to the methods described in Japanese Patent Nos. 6455748, 6744002, 6819823, 6819824, 6819825, 6989050, 6870785, 6923106, and WO2022 / 004261.

[0056] Table 2 below shows a comparison of the brightness, film thickness, and contrast of the ideal composition, examples, and marketed products. Here, the values ​​for brightness, film thickness, and contrast are shown as relative differences from the ideal composition, with the brightness, film thickness, and contrast of the polyhalide zinc phthalocyanine pigment set to 0. The marketed product here is a pigment manufactured by DIC, and its product name is FASTOGEN GREEN A110. In this example, to calculate the brightness, film thickness, and contrast, the phthalocyanine pigment of this example was mixed with a yellow pigment (pigment yellow Y138) to create a toned color. The method for measuring toned brightness and toned film thickness is based, for example, on the method described in paragraphs

[0080] -

[0082] ,

[0085] , and

[0086] of WO2018 / 051876. Specifically, 2.48 g of polyhalogenated zinc phthalocyanine pigment was dispersed for 2 hours in a paint shaker manufactured by Toyo Seiki Co., Ltd. using 0.3-0.4 mm zircon beads, along with 1.24 g of BYK-LPN6919 manufactured by BIC Chemie, 1.86 g of Unidick ZL-295 manufactured by DIC Corporation, and 10.92 g of propylene glycol monomethyl ether acetate, to obtain colored composition (1). 4.0 g of colored composition (1), 0.98 g of Unidick ZL-295 manufactured by DIC Corporation, and 0.22 g of propylene glycol monomethyl ether acetate were added and mixed in a paint shaker to obtain evaluation composition (1-A) for forming the green pixel portion of a color filter. Furthermore, 2.48 g of Pigment Yellow 138 (BASF Japan Ltd., Paliotol Yellow D0960) was dispersed for 2 hours in a paint shaker manufactured by Toyo Seiki Co., Ltd. using 0.3-0.4 mm zircon beads, along with 1.24 g of BYK-LPN6919 manufactured by BIC Chemie, 1.86 g of Unidick ZL-295 manufactured by DIC Corporation, and 10.92 g of propylene glycol monomethyl ether acetate, to obtain color composition (2). 4.0 g of color composition (2), 0.98 g of Unidick ZL-295 manufactured by DIC Corporation, and 0.22 g of propylene glycol monomethyl ether acetate were added and mixed in a paint shaker to obtain a color-tuning composition (2-A) for forming the green pixel portion of a color filter.An evaluation glass substrate (1-B) was obtained by mixing the color-tuning composition (2-A) and the evaluation composition (1-A) so that the chromaticity (x,y) = (0.286, 0.575), forming a film, and drying it. The brightness of this evaluation glass substrate (1-B) was measured using a Hitachi High-Tech Science Co., Ltd. U3900 spectrophotometer. The film thickness of this evaluation glass substrate (1-B) was measured using a Hitachi High-Tech Science Co., Ltd. VS1330 scanning white light interference microscope. Furthermore, the contrast of this evaluation glass substrate (1-B) was measured using a Tsubosaka Electric Co., Ltd. CT-1 contrast tester.

[0057] [Table 2]

[0058] As shown in Table 2, with respect to brightness, the ideal composition is slightly superior to the examples, but is generally equivalent. Here, a difference of about 0.05-0.10 in brightness can be considered experimental error. Furthermore, both the ideal composition and the examples are superior to market products in terms of brightness. Regarding film thickness, market products are slightly superior, but all three types are generally equivalent. A thinner film thickness is preferable. A difference of about 0.1 in film thickness can be considered experimental error. Regarding contrast, all three types are almost equivalent. A difference of about 500 in contrast can be considered experimental error. From these results, it can be seen that the polyhalide zinc phthalocyanine pigment according to the examples has brightness, film thickness, and contrast that are almost equivalent to the ideal composition. Furthermore, it can be seen that the polyhalide zinc phthalocyanine pigment according to the examples is superior to market products. In other words, by using the optimal composition and manufacturing conditions explored by the method for exploring the composition and manufacturing conditions of phthalocyanine pigment for color filters according to this embodiment, it is possible to actually manufacture phthalocyanine pigment for color filters that exhibit optimal physical properties.

[0059] In this embodiment, the subject was a color filter in which phthalocyanine crude is pigmented, dispersed with a dispersant, and coated and dried on a glass substrate. However, this technology can also be applied to color filter materials made from any other mixed composition material.

[0060] While this disclosure has been described based on the drawings and embodiments, it should be noted that those skilled in the art will find it easy to make various modifications and alterations based on this disclosure. Therefore, it should be noted that these modifications and alterations are within the scope of this disclosure. For example, the functions, etc., included in each means or each step, etc., can be rearranged in a logically consistent manner, and multiple means or steps, etc., can be combined into one or divided. [Explanation of Symbols]

[0061] 10 Information Processing Devices 11 Control Unit 12 Storage section 13 Input section 14 Output section 100, 200, 300, 400 sets

Claims

1. In a color filter in which phthalocyanine crude is pigmentized, dispersed with a dispersant, and coated and dried on a glass substrate, a method for exploring the composition and manufacturing conditions of a phthalocyanine pigment for a color filter, which is performed by an information processing device, The process involves training a predictive model based on training data where the compositional analysis information of phthalocyanine crude, pigmentation conditions, and dispersion conditions are used as explanatory variables, and the brightness, film thickness, and contrast of the color filter are used as dependent variables. The steps include generating a first set of prediction data by performing a grid search based on the lower and upper limits of the aforementioned training data, A step of generating a second set of prediction data based on the model application range determined by the first set of prediction data and the training data, The steps include generating a third set of prediction data based on the second set of prediction data and the conditions related to feasibility, The steps include determining the optimal composition and manufacturing conditions based on the aforementioned third set of predictive data, A method for exploring the composition and manufacturing conditions of phthalocyanine pigments for color filters, including [the specified element].

2. A search method according to claim 1, The aforementioned model application range is determined based on the k-nearest neighbor method, One-Class Support Vector Machine, or ensemble learning, and is a method for exploring the composition and manufacturing conditions of phthalocyanine pigments for color filters.

3. A search method according to claim 1, A method for exploring the composition and manufacturing conditions of phthalocyanine pigments for color filters, wherein the feasibility conditions described above satisfy all of the following equations (1) to (4). 16Br > 15Br1Cl > 14Br2Cl...(1) 16Br > 15Br1H > 14Br2H...(2) 15Br1Cl > 14Br1Cl1H・・・(3) 15Br1H > 14Br1Cl1H・・・(4) However, 16Br, 15Br1Cl, 14Br2Cl, 15Br1H, 14Br2H, and 14Br1Cl1H represent the mass spectral intensity ratios (in %) of 16Br phthalocyanine, 15Br1Cl phthalocyanine, 14Br2Cl phthalocyanine, 15Br1H phthalocyanine, 14Br2H phthalocyanine, and 14Br1Cl1H phthalocyanine in the phthalocyanine crude, respectively.

4. A search method according to claim 1, further, The third prediction data set further includes a method for exploring the composition and manufacturing conditions of phthalocyanine pigments for color filters, which are determined based on conditions related to the ideal composition.

5. A search method according to claim 4, A method for exploring the composition and manufacturing conditions of phthalocyanine pigments for color filters, wherein the conditions for the ideal composition satisfy the following formula (5). 100-(16Br+15Br1Cl+15Br1H+14Br2Cl+14Br1Cl1H+14Br2H+AlPc) < 5...(5) However, 16Br, 15Br1Cl, 15Br1H, 14Br2Cl, 14Br1Cl1H, 14Br2H, and AlPc represent the mass spectral intensity ratios (in %) of 16Br phthalocyanine, 15Br1Cl phthalocyanine, 15Br1H phthalocyanine, 14Br2Cl phthalocyanine, 14Br1Cl1H phthalocyanine, 14Br2H phthalocyanine, and impurities in the phthalocyanine crude, respectively.

6. A search method according to claim 1, A method for exploring the composition and manufacturing conditions of phthalocyanine pigments for color filters, wherein the aforementioned optimal composition and manufacturing conditions are determined based on luminance.

7. A search method according to claim 1, A method for exploring the composition and manufacturing conditions of phthalocyanine pigments for color filters, wherein the aforementioned optimal composition and manufacturing conditions are determined based on brightness and film thickness.

8. In a color filter in which phthalocyanine crude is pigmentized, dispersed with a dispersant, and coated and dried on a glass substrate, an information processing apparatus is provided which includes a control unit for searching for the composition and manufacturing conditions of the phthalocyanine pigment for the color filter, The control unit, A predictive model was trained based on training data in which the compositional analysis information of phthalocyanine crude, pigmentation conditions, and dispersion conditions were used as explanatory variables, and the brightness, film thickness, and contrast of the color filter were used as dependent variables. A first set of prediction data is generated by a grid search based on the lower and upper limits of the aforementioned training data. A second set of prediction data is generated based on the model application range determined by the first set of prediction data and the training data. Based on the aforementioned second set of prediction data and the conditions related to feasibility, a third set of prediction data is generated. An information processing device that determines the optimal composition and manufacturing conditions based on the third set of predicted data.

9. In a color filter in which phthalocyanine crude is converted into a pigment, dispersed with a dispersant, and coated and dried on a glass substrate, a program for searching for the composition and manufacturing conditions of the phthalocyanine pigment for the color filter, executed by an information processing device, is provided for a computer, The predictive model is trained based on training data in which the compositional analysis information of phthalocyanine crude, pigmentation conditions, and dispersion conditions are used as explanatory variables, and the brightness, film thickness, and contrast of the color filter are used as dependent variables. The first set of prediction data is generated by a grid search based on the lower and upper limits of the aforementioned training data, A second set of prediction data is generated based on the model application range determined by the first set of prediction data and the training data. Based on the aforementioned second set of prediction data and the conditions related to feasibility, a third set of prediction data is generated. Based on the aforementioned third set of predictive data, the optimal composition and manufacturing conditions are determined. A program that executes the command.

Images