Injection parameter generation system, injection parameter generation method, and injection parameter generation program

Abstract

The present application provides a jet parameter generation system and the like that can improve the convenience of a user. A jet parameter generation system according to one embodiment of the present disclosure includes a data acquisition unit and a parameter generation unit that generates a predetermined jet parameter using a predetermined analysis method in which a predetermined input parameter is set as an explanatory variable and the predetermined jet parameter is set as an objective variable. The parameter generation unit determines which of a first reference for setting a voltage value that results in a droplet amount of a liquid that becomes a reference and a second reference for setting a voltage value that results in an ejection speed of a liquid that becomes a reference is selected, selects a first explanatory variable set in the case where it is determined that the first reference is selected, and on the other hand, selects a second explanatory variable set in the case where it is determined that the second reference is selected, and generates the predetermined jet parameter by using only the selected one of the first explanatory variable set or the second explanatory variable set and using the predetermined analysis method.

Description

Technical Field

[0001] This disclosure relates to a system for generating injection parameters, a method for generating injection parameters, and a program for generating injection parameters. Background Technology

[0002] Liquid jet recording devices equipped with liquid jet heads are used in various fields, and various types of liquid jet heads have been developed as liquid jet heads (for example, see Patent Document 1).

[0003] Prior technology literature [Patent Documents] [Patent Document 1] Japanese Patent Application Publication No. 2016-203393. Summary of the Invention

[0004] [The problem the invention aims to solve] In such liquid injection heads, improved user convenience is required. Therefore, it is desirable to provide an injection parameter generation system, injection parameter generation method, and injection parameter generation program that enhance user convenience.

[0005] [Solution to the problem] One embodiment of the present disclosure relates to a jet parameter generation system that generates predetermined jet parameters. These predetermined jet parameters are used when generating a drive signal that is applied to a jetting section of the jetting liquid and has one or more pulses. The jet parameter generation system includes: a data acquisition unit that acquires predetermined input parameters and a selection indication signal input from an external source as input data; and a parameter generation unit that generates the predetermined jet parameters based on the selection indication signal and the predetermined input parameters using a predetermined analysis method that sets the predetermined input parameters as explanatory variables and the predetermined jet parameters as target variables. The parameter generation unit determines which of the above-mentioned references to select, the first reference and the second reference, based on the voltage value of the peak value of the pulse in the drive signal. The first reference is a reference used to set the voltage value of the liquid droplet volume that becomes the reference, and the second reference is a reference used to set the voltage value of the liquid ejection velocity that becomes the reference. If the first reference is selected, the first set of explanatory variables included in the predetermined input parameters is selected as the explanatory variable. On the other hand, if the second reference is selected, the second set of explanatory variables included in the predetermined input parameters is selected as the explanatory variable. The predetermined injection parameters are generated by using only the selected first set of explanatory variables or the second set of explanatory variables and the predetermined analysis method.

[0006] One embodiment of this disclosure relates to a method for generating predetermined injection parameters, which are used when generating a drive signal having one or more pulses applied to a jetting section of the jetting liquid. The injection parameter generation method includes: acquiring predetermined input parameters and an externally input selection indication signal as input data; and generating the predetermined injection parameters based on the selection indication signal and the predetermined input parameters using a predetermined analysis method that sets the predetermined input parameters as explanatory variables and the predetermined injection parameters as target variables. When generating the predetermined injection parameters, regarding the voltage value of the peak value of the pulse in the drive signal, it is determined which of the first and second references to select is chosen based on the selection indication signal indicating which reference is selected as the first reference and the second reference. The first reference is a reference used to set the voltage value of the droplet volume of the liquid that becomes the reference, and the second reference is a reference used to set the voltage value of the ejection velocity of the liquid that becomes the reference. If it is determined that the first reference is selected, the first set of explanatory variables included in the predetermined input parameters is selected as the explanatory variable. On the other hand, if it is determined that the second reference is selected, the second set of explanatory variables included in the predetermined input parameters is selected as the explanatory variable. The predetermined injection parameters are generated by using only the selected first set of explanatory variables or the second set of explanatory variables and the predetermined analysis method.

[0007] One embodiment of the present disclosure relates to a jet parameter generation program that generates predetermined jet parameters used when generating a drive signal having one or more pulses applied to a jetting part of the jetting liquid. The jet parameter generation program causes a computer to execute: acquiring predetermined input parameters and an externally input selection indication signal as input data; and generating the predetermined jet parameters based on the selection indication signal and the predetermined input parameters using a predetermined analysis method that sets the predetermined input parameters as explanatory variables and the predetermined jet parameters as target variables. When generating the predetermined injection parameters, regarding the voltage value of the peak value of the pulse in the drive signal, it is determined which of the first and second references to select is chosen based on the selection indication signal indicating which reference is selected as the first reference and the second reference. The first reference is a reference used to set the voltage value of the droplet volume of the liquid that becomes the reference, and the second reference is a reference used to set the voltage value of the ejection velocity of the liquid that becomes the reference. If it is determined that the first reference is selected, the first set of explanatory variables included in the predetermined input parameters is selected as the explanatory variable. On the other hand, if it is determined that the second reference is selected, the second set of explanatory variables included in the predetermined input parameters is selected as the explanatory variable. The predetermined injection parameters are generated by using only the selected first set of explanatory variables or the second set of explanatory variables and the predetermined analysis method.

[0008] [The effects of the invention] The injection parameter generation system, injection parameter generation method, and injection parameter generation program according to one embodiment of this disclosure can improve user convenience. Attached Figure Description

[0009] Figure 1 This is a schematic perspective view showing a schematic configuration example of a liquid jet recording device according to one embodiment of the present disclosure.

[0010] Figure 2 It means Figure 1 The schematic diagram shows a simplified example of the liquid injection head.

[0011] Figure 3 This is a functional block diagram illustrating an example configuration of the injection parameter generation system involved in the implementation method.

[0012] Figure 4 It means Figure 3 The physical block diagram of the information processing device shown is an example of its configuration.

[0013] Figure 5 It means Figure 3 , Figure 4 A block diagram illustrating a detailed example of the structure of a machine learning model.

[0014] Figure 6 This is a timing diagram that schematically illustrates an example of the configuration of drive signals.

[0015] Figure 7 This is a diagram illustrating an example of the predetermined input parameters involved in the implementation method.

[0016] Figure 8 This is a graph representing an example of the analysis results showing the importance of each input parameter involved in Comparative Example 1.

[0017] Figure 9A This is a graph illustrating an example of the correspondence between the SVM predicted values ​​and the measured values ​​involved in Comparative Example 1.

[0018] Figure 9B This is a graph illustrating an example of the correspondence between the predicted and measured values ​​of the RF involved in Comparative Example 1.

[0019] Figure 10 This is a flowchart illustrating an example of the injection parameter generation process involved in the implementation method.

[0020] Figure 11A This is a diagram illustrating an example of the results of an analysis of the importance of the first set of explanatory variables involved in the implementation method.

[0021] Figure 11B This is a diagram illustrating an example of the results of an analysis of the importance of the second set of explanatory variables involved in the implementation method.

[0022] Figure 12A This indicates that only using Figure 11A The figure shown is an example of the correspondence between SVM predictions and measured values ​​in the case of the first set of illustrative variables.

[0023] Figure 12B This indicates that only using Figure 11A The figure shown is an example of the correspondence between RF predicted values ​​and measured values ​​in the case of the first set of illustrative variables.

[0024] Figure 13A This indicates that only using Figure 11B The figure shown is an example of the correspondence between SVM predicted values ​​and measured values ​​in the case of the second set of illustrative variables.

[0025] Figure 13B This indicates that only using Figure 11B The figure shown is an example of the correspondence between RF predicted values ​​and measured values ​​in the case of the second set of illustrative variables.

[0026] Figure 14 This is a block diagram illustrating an example of the structure of the machine learning model involved in Variation Example 1.

[0027] Figure 15 This is a block diagram illustrating a general configuration example of the liquid jet recording device involved in Comparative Example 2.

[0028] Figure 16 This is a graph representing an example of the viscosity information involved in Comparative Example 2.

[0029] Figure 17 This is a graph showing an example of the various characteristic curves involved in Comparative Example 2.

[0030] Figure 18 This is a flowchart illustrating an example of the conversion process involved in Variation Example 1.

[0031] Figure 19 This is a diagram showing an example of the various characteristic curves involved in variation example 1.

[0032] Figure 20 This is a diagram representing an example of the given input parameters involved in Variation Example 1.

[0033] Figure 21 This is a flowchart illustrating the generation process of the characteristic table involved in Variation Example 1.

[0034] Figure 22 This is a graph representing an example of the analysis results showing the importance of each input parameter involved in Comparative Example 3.

[0035] Figure 23A This is a diagram illustrating an example of the analysis results regarding the importance of the first set of explanatory variables involved in Variation Example 1.

[0036] Figure 23B This is a diagram illustrating an example of the analysis results regarding the importance of the second set of explanatory variables involved in Variation Example 1.

[0037] Figure 24A This indicates that only using Figure 23A The figure shown is an example of the correspondence between SVM predictions and measured values ​​in the case of the first set of illustrative variables.

[0038] Figure 24B This indicates that only using Figure 23A The figure shown is an example of the correspondence between RF predicted values ​​and measured values ​​in the case of the first set of illustrative variables.

[0039] Figure 25A This indicates that only using Figure 23B The figure shown is an example of the correspondence between SVM predicted values ​​and measured values ​​in the case of the second set of illustrative variables.

[0040] Figure 25B This indicates that only using Figure 23B The figure shown is an example of the correspondence between RF predicted values ​​and measured values ​​in the case of the second set of illustrative variables.

[0041] Figure 26 This is a block diagram illustrating an example of the structure of the machine learning model involved in Variation Example 2.

[0042] Figure 27 This is a diagram illustrating an example of the given input parameters involved in Variation Example 2.

[0043] Figure 28 This is a graph illustrating an example of the analysis results showing the importance of each input parameter involved in Comparative Example 4.

[0044] Figure 29A This is a diagram illustrating an example of the analysis results regarding the importance of the first set of explanatory variables involved in Variation Example 2.

[0045] Figure 29B This is a diagram illustrating an example of the analysis results regarding the importance of the second set of explanatory variables involved in Variation Example 2.

[0046] Figure 30A This indicates that only using Figure 29A The figure shown is an example of the correspondence between SVM predictions and measured values ​​in the case of the first set of illustrative variables.

[0047] Figure 30B This indicates that only using Figure 29A The figure shown is an example of the correspondence between RF predicted values ​​and measured values ​​in the case of the first set of illustrative variables.

[0048] Figure 31A This indicates that only using Figure 29B The figure shown is an example of the correspondence between SVM predicted values ​​and measured values ​​in the case of the second set of illustrative variables.

[0049] Figure 31B This indicates that only using Figure 29B The figure shown is an example of the correspondence between RF predicted values ​​and measured values ​​in the case of the second set of illustrative variables.

[0050] Figure 32 This is a block diagram illustrating an example of the configuration of the injection parameter generation system involved in Modification Example 3.

[0051] Figure 33 This is a block diagram illustrating an example of the configuration of the injection parameter generation system involved in Modification Example 4.

[0052] Figure 34This is a block diagram illustrating an example of the configuration of the injection parameter generation system involved in Modification Example 5.

[0053] Figure 35 This is a block diagram illustrating an example of the configuration of the information processing unit involved in Modification Example 6. Detailed Implementation

[0054] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Furthermore, the description will proceed in the following order.

[0055] 1. Implementation method (Example of an information processing device that houses the information processing unit outside the liquid jet recording device) 2. Variations Variation Example 1 (Example when the given injection parameters are conversion coefficients) Variation Example 2 (Example where the given injection parameters are voltage offset) Variation 3 (Example of placing the information processing unit inside a server outside the liquid jet recording device) Variation 4 (Example of placing the information processing unit inside the liquid jet head of the liquid jet recording device) Modification 5 (Example of placing the information processing unit outside the liquid jet head inside the liquid jet recording device) Modification Example 6 (Example where the signal generation unit is further located within the information processing unit) 3. Other variations <1. Implementation Method> [A. Overall Structure of Printer 1] Figure 1 The schematic diagram of a printer 1, which is a liquid jet recording apparatus according to one embodiment of this disclosure, is shown in a perspective view. The printer 1 is an inkjet printer that uses ink 9, which will be described later, to record (print) images or text on recording paper P, which is the recording medium.

[0056] like Figure 1 As shown, printer 1 includes a pair of transport mechanisms 2a and 2b, an ink tank 3, an ink supply tube 30, an inkjet head 4, and a scanning mechanism 6. These components are housed within a frame 10 of a predetermined shape. Furthermore, in the accompanying drawings used in this specification, the scale of each component has been appropriately altered to make them recognizable.

[0057] Here, printer 1 corresponds to a specific example of the "liquid jet recording apparatus" in this disclosure, and inkjet head 4 (inkjet heads 4Y, 4M, 4C, and 4K, described later) corresponds to a specific example of the "liquid jet head" in this disclosure. Additionally, ink 9 corresponds to a specific example of the "liquid" in this disclosure.

[0058] like Figure 1 As shown, transport mechanisms 2a and 2b are mechanisms that transport the recording paper P along the transport direction d (X-axis direction). These transport mechanisms 2a and 2b each have a grid roller 21, a pinch roller 22, and a drive mechanism (not shown). The drive mechanism is a mechanism that rotates the grid roller 21 about an axis (rotates in the ZX plane), and is, for example, composed of a motor.

[0059] (Ink can 3) Ink container 3 is a container that holds ink 9 inside. In this example, ink container 3 is as follows: Figure 1 As shown, four types of ink containers are provided, each individually holding one of four colors of ink 9: yellow (Y), magenta (M), cyan (C), and black (K). Specifically, there is an ink container 3Y for yellow ink 9, an ink container 3M for magenta ink 9, an ink container 3C for cyan ink 9, and an ink container 3K for black ink 9. These ink containers 3Y, 3M, 3C, and 3K are arranged side-by-side along the X-axis within the frame 10.

[0060] Furthermore, ink containers 3Y, 3M, 3C, and 3K are identical in composition except for the color of the ink 9 they contain, and are therefore referred to as ink containers 3 below.

[0061] (Inkjet head 4) The inkjet head 4 is a head that records (prints) images or text by ejecting (ejecting) droplets of ink 9 from the recording paper P through multiple nozzles (nozzle orifices Hn), which will be described later. In this example, the inkjet head 4 is as follows: Figure 1 As shown, four types of inkjet heads are also provided, each individually ejecting ink 9 of four different colors contained in the ink tanks 3Y, 3M, 3C, and 3K. Specifically, there is an inkjet head 4Y that ejects yellow ink 9, an inkjet head 4M that ejects magenta ink 9, an inkjet head 4C that ejects cyan ink 9, and an inkjet head 4K that ejects black ink 9. These inkjet heads 4Y, 4M, 4C, and 4K are arranged side-by-side along the Y-axis within the housing 10.

[0062] Furthermore, inkjet heads 4Y, 4M, 4C, and 4K are identical in construction except for the color of the ink 9 they use; therefore, they will be collectively referred to as inkjet head 4 below. A detailed example of the construction of this inkjet head 4 will be described later. Figure 2 ).

[0063] The ink supply tube 30 is the tube through which ink 9 is supplied from the ink tank 3 toward the inkjet head 4. The ink supply tube 30 is, for example, a flexible tube with a degree of flexibility that can follow the movement of the scanning mechanism 6 described below.

[0064] (Scanning mechanism 6) The scanning mechanism 6 is a mechanism that causes the inkjet head 4 to scan along the width direction (Y-axis direction) of the recording paper P. For example... Figure 1 As shown, the scanning mechanism 6 has: a pair of guide rails 61a and 61b extending along the Y-axis; a carriage 62 supported by the guide rails 61a and 61b in a movable manner; and a drive mechanism 63 that moves the carriage 62 along the Y-axis.

[0065] The drive mechanism 63 includes: a pair of pulleys 631a and 631b disposed between guide rails 61a and 61b; a seamless belt 632 wound between these pulleys 631a and 631b; and a drive motor 633 that drives the pulleys 631a to rotate. Additionally, the aforementioned four types of inkjet heads 4Y, 4M, 4C, and 4K are arranged side-by-side along the Y-axis on the carriage 62.

[0066] Furthermore, the scanning mechanism 6 and the aforementioned transport mechanisms 2a and 2b constitute a moving mechanism that causes the inkjet head 4 and the recording paper P to move relative to each other.

[0067] [B. Detailed Composition of Inkjet Head 4] Next, refer to Figure 2 A detailed example of the structure of the inkjet head 4 will be provided.

[0068] Figure 2 This is a schematic example of the general configuration of the inkjet head 4.

[0069] like Figure 2 As shown, the inkjet head 4 has a nozzle plate 41, an actuator plate 42, and a drive unit 49.

[0070] Furthermore, the nozzle plate 41 and the actuator plate 42 correspond to a specific example of the "spray section" in this disclosure.

[0071] (Nozzle plate 41) The nozzle plate 41 is a plate made of thin film materials such as polyimide or metal materials, such as... Figure 2 As shown, it has multiple nozzle holes Hn with ink ejection 9 (refer to...) Figure 2 (The dashed arrows in the image). These nozzle holes Hn are spaced apart by a predetermined interval and are formed side by side in a straight line (in this example, along the X-axis).

[0072] (Actuator plate 42) The actuator plate 42 is a plate made of a piezoelectric material such as PZT (lead zirconate titanate). Multiple channels (not shown) are provided on the actuator plate 42. These channels function as pressure chambers for applying pressure to the ink 9, and are arranged side-by-side in a parallel manner at predetermined intervals. Each channel is divided by a drive wall (not shown) made of a piezoelectric material, forming a concave groove when viewed in cross-section.

[0073] In such a channel, there are ejection channels for dispensing ink 9 and pseudo-channels (non-ejection channels) for not dispensing ink 9. In other words, ink 9 is filled into the ejection channels, while ink 9 is not filled into the pseudo-channels. In addition, each ejection channel is connected to the nozzle orifice Hn in the nozzle plate 41, while each pseudo-channel is not connected to the nozzle orifice Hn. These ejection channels and pseudo-channels are arranged alternately side by side along a predetermined direction.

[0074] On the opposing inner surfaces of the aforementioned drive wall, drive electrodes (not shown) are respectively provided. Among these drive electrodes, there is a common electrode (common electrode) provided on the inner surface facing the ejection channel and an active electrode (individual electrode) provided on the inner surface facing the pseudo-channel. The drive circuit in the drive substrate (not shown) is electrically connected to these drive electrodes via a plurality of lead-out electrodes formed on the flexible substrate (not shown). Thus, a drive voltage Vd (drive signal Sd) is applied to each drive electrode from the drive circuit including the drive section 49 via the flexible substrate.

[0075] (Drive Unit 49) The drive unit 49 applies the aforementioned drive voltage Vd (drive signal Sd) to the actuator plate 42, causing the aforementioned ejection channel to expand or contract, thereby causing ink 9 to be ejected from each nozzle orifice Hn (performing an ejection action) (see reference). Figure 2 Specifically, the drive unit 49 uses the drive signal Sd generated in the signal generation unit 48, which will be described later, to perform such a jetting action.

[0076] [C. Overall Structure of Injection Parameter Generation System 5] Next, refer to Figures 3-6 An example of the overall configuration of the jetting parameter generation system 5 (characteristic table generation system) comprising a printer 1 having the inkjet head 4 described above will be described.

[0077] Figure 3 The following block diagram (functional block diagram) illustrates an example of the configuration of the injection parameter generation system 5 according to this embodiment. Figure 4 Represented by a block diagram (physical block diagram) Figure 3 An example of the configuration of the information processing device 7 (described later) is shown. Additionally, Figure 5 Represented by a block diagram Figure 3 , Figure 4 A detailed example of the structure of machine learning model 74 is shown.

[0078] Furthermore, the injection parameter generation method (characteristic table generation method) described in this embodiment is specifically executed in the injection parameter generation system 5 (characteristic table generation system) described in this embodiment, and will therefore be described below. The same applies to the variations (variations 1-6) described later.

[0079] Injection parameter generation system 5 is a system for generating predetermined injection parameters Prj, which are used when generating the aforementioned drive signal Sd. Furthermore, in this injection parameter generation system 5 (characteristic table generation system), a predetermined predicted voltage characteristic table TPvp (refer to...) is generated based on the thus generated injection parameters Prj. Figure 3 ).like Figure 3 As shown, the jetting parameter generation system 5 includes an information processing unit 7 and a printer 1 with the aforementioned inkjet head 4. Furthermore, the printer 1 and the information processing unit 7 are interconnected via a network 50.

[0080] Furthermore, such a network 50 can be a network that communicates using, for example, a communication protocol (TCP / IP) standardly used in the Internet. The network 50 can also be a secure network that communicates using, for example, a network with its own communication protocol. Additionally, the network 50 can be, for example, the Internet, an intranet, or a local area network (LAN). The connection between such a network 50 and the printer 1, and the connection between the network 50 and the information processing device 7, can be, for example, a wired LAN (Local Area Network) such as Ethernet (registered trademark), or a wireless LAN such as Wi-Fi (registered trademark), or a mobile telephone line, etc.

[0081] (Information processing device 7) The information processing device 7 is a device located outside the printer 1, and is composed of, for example, a PC (Personal Computer). Figure 3 As shown in the (functional block diagram), the information processing device 7 has an input unit 71, a display unit 72, an information processing unit 73, and a machine learning model 74.

[0082] Furthermore, such an information processing device 7 corresponds to a specific example of the "external device" in this disclosure.

[0083] The input unit 71 receives instructions from external sources (e.g., a user) and outputs the received instructions to the information processing unit 73. Such an input unit 71 may be configured as, for example, a keyboard or a mouse. Alternatively, the input unit 71 may also be configured as, for example, a touch panel provided on the display unit 72 (display surface) of the information processing device 7.

[0084] The display unit 72 displays an image based on an image signal output from the information processing unit 73. Such a display unit 72 is constructed using a display of various types (e.g., a liquid crystal display, a CRT (Cathode Ray Tube) display, an organic EL (Electro Luminescence) display, etc.).

[0085] Information Processing Department 73 is the part that performs various information processing tasks, such as... Figure 3 As shown, it includes a data acquisition unit 731, a parameter generation unit 732, and a table generation unit 733. Additionally, as... Figure 4 As shown in the physical block diagram, this information processing unit 73 is constructed using a control unit 75, a storage unit 76, and a network interface (IF) 77. Furthermore, in this… Figure 4 In the example, the input unit 71, display unit 72, control unit 75, storage unit 76 and network IF 77 are interconnected via bus 70.

[0086] like Figure 3 As shown, the data acquisition unit 731 acquires the following data (input data) via the aforementioned input unit 71 or network 50. That is, the data acquisition unit 731 acquires the predetermined measured viscosity characteristic table TMvi, the predetermined selection indication signal Ss input from the outside, and the predetermined input parameter Prin, which will be described later, as input data.

[0087] like Figure 3 As shown, the parameter generation unit 732 generates the aforementioned predetermined injection parameter Prj based on the selection instruction signal Ss and the input parameter Prin obtained by the data acquisition unit 731 using a predetermined analysis method. This predetermined analysis method is an analysis method that sets the input parameter Prin as a descriptive variable and the injection parameter Prj as a target variable. Furthermore, in the example of this embodiment, as... Figure 3 , Figure 4 As shown, the parameter generation unit 732 uses the analysis method of the machine learning model 74 described below to generate the injection parameter Prj based on the input parameter Prin.

[0088] Such a machine learning model 74 is a predictive model obtained by performing machine learning as described above, with the input parameter Prin set as the explanatory variable and the injection parameter Prj set as the objective variable. Additionally, as... Figure 5 As shown, if the machine learning model 74 is input with input parameter Prin (explanatory variable), then it generates (predicts) injection parameter Prj (objective variable) based on the learning results, and outputs the generated injection parameter Prj.

[0089] Here, for example, Figure 5 As shown in the illustration, in this embodiment, the following situation will be mainly described: as an example of such an injection parameter Prj, the injection parameter Prj is generated with at least the voltage sensitivity Vr, which will be described later. That is, the voltage sensitivity Vr corresponds to a specific example of the "predetermined injection parameter" in this disclosure.

[0090] Furthermore, examples of analytical methods (prediction methods) using the aforementioned machine learning model 74 include, for instance, Support Vector Machine (SVM), Random Forest (RF), and Multiple Regression Analysis.

[0091] like Figure 3 As shown, the table generation unit 733 performs a predetermined conversion process using at least one of the measured viscosity characteristic table TMvi and the jetting parameter Prj to generate a predicted voltage characteristic table TPvp. The measured viscosity characteristic table TMvi is acquired by the data acquisition unit 731, and the jetting parameter Prj is generated by the parameter generation unit 732. The predicted voltage characteristic table TPvp generated in this way is supplied via the network 50 to the signal generation unit 48, which will be described later, in the inkjet head 4 of the printer 1.

[0092] Furthermore, in the modified example 1 described later, the details of the predetermined conversion process, the measured viscosity characteristic table TMvi, and the predicted voltage characteristic table TPvp will be explained. Additionally, the details of each process in such an information processing unit 73 (data acquisition unit 731, parameter generation unit 732, and table generation unit 733) will also be explained later.

[0093] Figure 4 The control unit 75 shown includes a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit), and executes various programs stored in the storage unit 76, for example. Specifically, for example... Figure 4 As shown, the control unit 75 executes the program 730 stored in the storage unit 76. This program 730 is used to perform the various processes in the information processing unit 73 (data acquisition unit 731, parameter generation unit 732, and table generation unit 733) described above. Specifically, this program 730 is used to execute the various functions of the information processing unit 73 (data acquisition unit 731, parameter generation unit 732, and table generation unit 733) via the computer (control unit 75).

[0094] Storage unit 76 is the part that stores various programs or data executed by control unit 75. For example... Figure 4As shown, the storage unit 76 stores the aforementioned program 730 as an example of various programs, and stores the aforementioned machine learning model 74 as an example of various data. This storage unit 76 is constructed using, for example, RAM (Random Access Memory), ROM (Read Only Memory), auxiliary storage devices (hard disks, etc.).

[0095] like Figure 4 As shown, network IF 77 is a communication interface used to communicate with printer 1 via network 50.

[0096] (Signal generation unit 48) Here, in Figure 3 In the example shown, the inkjet head 4, in addition to the aforementioned nozzle plate 41, actuator plate 42, and drive unit 49, also has a signal generation unit 48. As described above, the signal generation unit 48 uses the predicted voltage characteristic table TPvp generated by the table generation unit 733 in the information processing device 7 to generate a drive signal Sd having one or more pulses (pulse width Wp, voltage value Vp showing the peak value).

[0097] Here, Figure 6 (A)- Figure 6 (C) Examples of the configuration of such a drive signal Sd are schematically shown in timing diagrams. Furthermore, in these... Figure 6 (A)- Figure 6 In (C), the horizontal axis represents time t, and the vertical axis represents the driving voltage Vd in the driving signal Sd (in this example, it is a positive voltage).

[0098] first, Figure 6 (A) shows a drive signal Sd with one pulse (pulse Pa), which is an example of the so-called "one drop" case. This pulse Pa is set during the ON period between the rise timing and the fall timing, and as an example of the pulse width Wp and voltage value Vp mentioned above, it has a pulse width Wpa1 and a voltage value Vp1.

[0099] On the other hand, regarding Figure 6The drive signal Sd shown in (B), as a pulse applicable to the so-called "multi-pulse mode," has the following two pulses (pulse Pa, Pb) (an example of the so-called "two-fall" case). That is, two pulses Pa and Pb are provided as such pulses (ON period). In addition, an off period ("OFF1") is provided between these two pulses Pa and Pb. Furthermore, as an example of the pulse width Wp and voltage value Vp mentioned above, pulse Pa has a pulse width Wpa2 and a voltage value Vp2, and pulse Pb has a pulse width Wpb2 and a voltage value Vp2.

[0100] Similarly, regarding Figure 6 The drive signal Sd shown in (C), as a pulse applicable to the above-described "multi-pulse mode," has the following three pulses (pulses Pa, Pb, and Pc) (an example of the so-called "three-fall" case). That is, as such pulses (ON period), three pulses Pa, Pb, and Pc are provided. Furthermore, an off period ("OFF1") is provided between pulses Pa and Pb, and an off period ("OFF2") is provided between pulses Pb and Pc. In addition, as an example of the above-described pulse width Wp and voltage value Vp, pulse Pa has a pulse width Wpa3 and a voltage value Vp3, pulse Pb has a pulse width Wpb3 and a voltage value Vp3, and pulse Pc has a pulse width Wpc3 and a voltage value Vp3.

[0101] Furthermore, each pulse Pa, Pb, and Pc in these driving signals Sd becomes a positive pulse that expands the aforementioned ejection channel during the High state and contracts the ejection channel during the Low state.

[0102] Here, the signal generation unit 48 sets the pulse width Wp and voltage value Vp in such pulses (pulses Pa, Pb, Pc), and generates a drive signal Sd using pulses having the set pulse width Wp and voltage value Vp. Specifically, the signal generation unit 48 uses the aforementioned predicted voltage characteristic table TPvp to determine the voltage value Vp of the pulse, and generates the drive signal Sd using pulses having the determined voltage value Vp.

[0103] Furthermore, the voltage value Vp mentioned above corresponds to a specific example of a "peak value" in this disclosure. Additionally, the "pulse" mentioned above includes not only, for example, Figure 6 The rectangular wave shown also includes pulses of the concept of waveforms such as trapezoidal waves, triangular waves, and stepped waves, as follows.

[0104] [Actions and their functions / effects] (A. Basic operations of printer 1) In this printer 1, a recording action (printing action) is performed on the recording paper P, such as for images or text, as follows. Furthermore, as the initial state, it is set to... Figure 1 The four ink tanks 3 (3Y, 3M, 3C, 3K) shown are each fully filled with ink 9 of the corresponding color (four colors). In addition, the ink 9 in the ink tank 3 is filled into the inkjet head 4 via the ink supply tube 30.

[0105] In this initial state, if printer 1 is activated, the grid rollers 21 in transport mechanisms 2a and 2b rotate, thereby transporting the recording paper P between the grid rollers 21 and the pinch rollers 22 along the transport direction d (X-axis direction). Simultaneously with this transport action, the drive motor 633 in drive mechanism 63 rotates the pulleys 631a and 631b, thereby actuating the seamless belt 632. As a result, the carriage 62 is guided by guide rails 61a and 61b and simultaneously reciprocates along the width direction (Y-axis direction) of the recording paper P. Then, at this time, the inkjet heads 4 (4Y, 4M, 4C, 4K) appropriately eject four colors of ink 9 onto the recording paper P, thereby performing a recording action on the recording paper P for images or text.

[0106] (B. Detailed operation of inkjet head 4) Next, the detailed operation (ink 9 ejection operation) in the inkjet head 4 will be explained. That is, in the inkjet head 4, the ink 9 is ejected using the cut (share) mode as follows.

[0107] First, the drive unit 49 applies a drive voltage Vd (drive signal Sd) to the aforementioned drive electrodes (common electrode and active electrode) within the actuator plate 42 (refer to...). Figure 2 , Figure 3 Specifically, the driving unit 49 applies a driving voltage Vd to each driving electrode disposed on a pair of driving walls, which are a pair of driving walls that divide the aforementioned ejection channel. As a result, these pairs of driving walls are deformed in such a way that they protrude toward the pseudo-channel side adjacent to the ejection channel.

[0108] At this point, the drive wall bends and deforms in a V-shape, centered on the middle position in the depth direction of the drive wall. Then, through this bending deformation of the drive wall, the ejection channel deforms as if bulging. Thus, through the bending deformation caused by the piezoelectric thickness slip effect at the pair of drive walls, the volume of the ejection channel increases. Then, through the increase in the volume of the ejection channel, ink 9 is guided into the ejection channel.

[0109] Next, the ink 9 guided into the ejection channel becomes a pressure wave and propagates into the interior of the ejection channel. Then, at the timing (or near the timing) when the pressure wave reaches the nozzle orifice Hn of the nozzle plate 41, the driving voltage Vd applied to the driving electrode becomes 0 (zero) V. As a result, the driving wall recovers from the aforementioned bent and deformed state, and as a result, the temporarily increased volume of the ejection channel returns to its original state.

[0110] Thus, as the volume of the ejection channel returns to its original state, the pressure inside the ejection channel increases, pressurizing the ink 9 within it. As a result, droplets of ink 9 are ejected to the outside through the nozzle orifice Hn (towards the recording paper P) (see reference). Figure 2 , Figure 3 This ejection action (ejection action) of ink 9 from inkjet head 4 results in the recording action (printing action) of images or text on recording paper P.

[0111] (C. Generation of injection parameters) Next, besides Figures 1-6 In addition, refer to Figures 7-13B , compared with the comparative example ( Figure 8 , Figure 9A , Figure 9B The comparison is made, and the generation action (generation process) of the injection parameter Prj in the injection parameter generation system 5 (in the case of the aforementioned voltage sensitivity Vr) is explained in detail.

[0112] Incidentally, the voltage sensitivity Vr (voltage sensitivity Vr at ejection) is the value of the change in voltage per unit of the droplet volume (DV) or ejection velocity of ink 9 when ink 9 is ejected at a reference temperature Tr (unit: [pl / V] or [m / s / V]).

[0113] (C-1. For the input parameter Prin) First, as mentioned above, the given input parameter Prin, such as Figure 7 As shown, as an example, the input parameter Prin is listed by (a)-(l) below. Figure 7 This represents an example of the input parameter Prin involved in this embodiment. Furthermore, in this... Figure 7 In the example, for 6 samples ("Sample 1" - "Sample 6"), the values ​​of each input parameter Prin are shown.

[0114] (a) Number of falls (pulse count)...equivalent to in Figure 6 The number of pulses included per unit period in the driving signal Sd, as mentioned above. (b) Presence or absence of common drive ("0": none, "1": yes, "2": special value)... The so-called common drive (the driving method of setting the pulse of the drive signal Sd in a manner including the following variation: the volume of the ejection channel when ink 9 is ejected shrinks compared to the reference value) (c) Type of inkjet head... Indicates the type of inkjet head 4, etc. (d) Types of inks... Types of inks 9 classified according to their main solvent ("Oil": inks 9 with oil-based solvents, "sol": inks 9 with organic solvents, "UV": UV (ultraviolet) curing inks, "WB": water-based inks 9 with water as the main solvent). (e) (DV reference or Vj reference)... This shows the parameter of which reference is used to obtain the voltage value Vp of the ink 9 as a reference when setting it to be ejected ink 9 ("DV reference") and the voltage value Vp of the ejection speed as a reference ("Vj reference") used to be set to be obtained. (f) Head grade value...equivalent to the voltage value Vp at a given ejection rate when a given inspection fluid is ejected from the inkjet head 4, and is an inherent value of the inkjet head 4 (unit: [V]). (g) Viscosity value at reference temperature Tr... Viscosity value of ink 9 at reference temperature Tr when ink 9 is heated and used (unit: [mPa]). (h) Surface tension value of ink 9 (unit: [mN / m]) (i) The specific gravity of ink 9 (or a physical parameter obtained using the specific gravity of ink 9, such as the density of ink 9 or the speed of sound in ink 9)). (j) Target value of DV (droplet volume) or Vj (ejection speed) for ink 9 (k) Voltage offset ΔVp (a parameter used in the aforementioned predetermined conversion process: details will be explained later in Variation 1) Incidentally, the "viscosity of ink 9" mentioned here refers to its still viscosity, and the same applies below. Furthermore, such viscosity values ​​for ink 9 are measured using a viscometer (capillary viscometer or falling ball viscometer) of the following measurement type: a rotational viscometer, a vibratory viscometer, or other types of viscometers capable of measuring still viscosity, such as capillary or falling ball viscometers.

[0115] (C-2. Comparative Example 1) Here, Figure 8 This is an example illustrating the results of the importance analysis of the input parameters Prin involved in Comparative Example 1. Additionally, Figure 9A This is an example illustrating the correspondence between the SVM predicted values ​​and the measured values ​​involved in Comparative Example 1 (an example where only the aforementioned Vj benchmark is extracted). Similarly, Figure 9B This is an example illustrating the correspondence between the predicted and measured values ​​of the RF involved in Comparative Example 1 (an example in the case of extracting only the aforementioned Vj benchmark). In this Comparative Example 1, although details will be described later, it is a case in which both the aforementioned DV benchmark and Vj benchmark are present, using the established analysis method described above.

[0116] also, Figure 8 The importance in the importance analysis results shown refers to an indicator (contribution rate) that infers how much the segmentation of its features contributes to the classification of the target. This importance is calculated using a pre-established formula based on the so-called Gini coefficient. The definition of such importance will remain the same thereafter.

[0117] In addition, Figure 9A , Figure 9B In the example shown, with the measured value of voltage sensitivity Vr set as variable x and the predicted value of voltage sensitivity Vr (SVM prediction or RF prediction) set as variable y, the (x, y) coordinates of many (562) samples are plotted. Furthermore, in these... Figure 9A , Figure 9B The text also includes an example of a formula that shows the trend of the correlation between these variables x and y (e.g., a formula for a first-order function specifically specified using the least squares method).

[0118] First, according to Figure 8 As an example of the importance analysis results of the input parameters Prin, which are shown as explanatory variables, when generating the injection parameter Prj (= voltage sensitivity Vr) using machine learning model 74, the input parameter Prin with the highest importance (contribution rate) is the following input parameter Prin. That is, it has the highest importance with respect to the target value of (j)DV or Vj among the input parameters Prin shown in (a)-(l) above. In addition, for the other input parameters Prin among such input parameters Prin, the importance is approximately "0 (zero)".

[0119] Therefore, in this Comparative Example 1, using only the target value of (j)DV or Vj as the input parameter Prin, the established analysis method described above is applied under the condition that both the DV benchmark and the Vj benchmark exist in a mixed manner.

[0120] Therefore, for example, such as Figure 9A , Figure 9B As shown, in Comparative Example 1, a decrease in prediction accuracy may occur when generating the injection parameter Prj. Specifically, in Figure 9A , Figure 9BIn the examples shown (examples where only the Vj baseline is extracted), the slope of the above-described linear function is approximately "0", and the intercept of the above-described linear function is much larger than "0". Therefore, in Figure 9A , Figure 9B In the examples shown, the predicted values ​​(SVM predicted values ​​and RF predicted values) and the measured values ​​are related as follows. That is, when using the predicted values ​​for printing, the predicted values ​​and the measured values ​​cannot be said to have a sufficient correlation.

[0121] Thus, in Comparative Example 1, as described above, when an importance analysis was performed with both the DV and Vj references present, there were cases where the importance (contribution) of the specifically designated input parameter Prin among the input parameters Prin was representatively increased. Furthermore, in such cases, for example, as described above, when only the specifically designated input parameter Prin with representatively high importance is used and a predetermined analysis method is employed, for example, the prediction accuracy of the injection parameter Prj under either the DV or Vj references may decrease. Specifically, in Figure 9A , Figure 9B In the examples shown, the prediction accuracy of the injection parameter Prj under the Vj baseline decreases. As a result, user convenience may decrease in Comparative Example 1.

[0122] (C-3. ​​Generation process of injection parameter Prj in this embodiment) Therefore, in the injection parameter generation system 5 of this embodiment, when generating the injection parameter Prj, it is determined which of the aforementioned DV reference and Vj reference to select based on the selection indication signal Ss. The generation process of the injection parameter Prj in this embodiment will be described in detail below.

[0123] Furthermore, the aforementioned DV benchmark corresponds to a specific example of the "first benchmark" in this disclosure. Additionally, the aforementioned Vj benchmark corresponds to a specific example of the "second benchmark" in this disclosure.

[0124] Here, Figure 10 The flowchart illustrates an example of the process for generating the injection parameter Prj involved in this embodiment.

[0125] exist Figure 10 In the processing example shown, firstly, the parameter generation unit 732 determines which of the DV and Vj references to select based on the selection indication signal Ss, which indicates which reference to select (steps S1 and S2).

[0126] Here, for example, if it is determined that a DV reference is selected (step S2: Y), the parameter generation unit 732 selects the first explanatory variable set Prin1 included in the input parameter Prin (refer to the explanation below). Figure 11A This is used as an explanatory variable in a predetermined analysis method (e.g., machine learning model 74) (step S31). On the other hand, for example, if it is determined that the Vj benchmark is selected (step S2: N), the parameter generation unit 732 selects the second explanatory variable set Pran2 included in the input parameter Pran (refer to the explanation later). Figure 11B ), which serves as an explanatory variable in the established analysis method (step S32).

[0127] Then, the parameter generation unit 732 uses only one of the selected first explanatory variable sets Prin1 or the second explanatory variable set Prin2 and utilizes a predetermined analysis method (e.g., machine learning model 74) to generate predetermined injection parameters (step S4).

[0128] above, Figure 10 The series of processes shown has ended.

[0129] Here, Figure 11A This is an example representing the importance analysis results of the first explanatory variable set Prin1 described above in this embodiment. Additionally, Figure 11B This is an example representing the importance analysis results in the second explanatory variable set Prin2 described above, as per this embodiment. Furthermore, in these... Figure 11A , Figure 11B In the example, the injection parameter Prj, which becomes the objective variable, is the voltage sensitivity Vr, as mentioned above.

[0130] like Figure 11A As shown, the first set of explanatory variables Prin1 involved in this embodiment includes at least one of the aforementioned input parameters Prin (for example, the parameters described below). That is, in Figure 11A In the example, the main components include (j) the target value of DV, (a) the number of drops, and (k) the voltage offset ΔVp. Additionally, as... Figure 11A As shown, their importance (contribution) increases relatively in order.

[0131] Specifically, in Figure 11AIn the example, the target value of (j)DV is of high importance (the highest). Therefore, in this embodiment, it is desirable that the first explanatory variable set Prin1 described above includes at least the target value of (j)DV, which has the highest importance. In addition, in this embodiment, as described above, it is desirable that the first explanatory variable set Prin1 also includes at least one of (a) the number of drops and (k) the voltage offset ΔVp, which have the second and third highest importance.

[0132] On the other hand, such as Figure 11B As shown, the second explanatory variable set Prin2 involved in this embodiment includes at least one of the aforementioned input parameters Prin (for example, the parameters described below). That is, in Figure 11B The examples mainly include (b) presence or absence of common drive, (a) number of drops, (f) head grade value, (k) voltage offset ΔVp, (c) head type, (i) specific gravity of ink 9, (h) surface tension of ink 9, (g) viscosity value at reference temperature Tr, (j) target value of Vj, and (d) ink type. Additionally, as... Figure 11B As shown, their importance (contribution) increases relatively in order.

[0133] Specifically, in Figure 11B In the example, the importance of (b) whether there is a common drive and (a) the number of drops are relatively high (first highest, second highest), respectively. Therefore, in this embodiment, it is desirable that the second explanatory variable set Prin2 mentioned above includes at least one of the following, which has a relatively high importance: (b) whether there is a common drive and (a) the number of drops. In addition, in this embodiment, as mentioned above, it is desirable that the second explanatory variable set Prin2 also includes at least one of the following, which has a relatively high importance: (f) head grade value, (k) voltage offset ΔVp, (c) head type, (i) specific gravity value of ink 9, (h) surface tension value of ink 9, (g) viscosity value at reference temperature Tr, and (j) target value of Vj.

[0134] Here, Figure 12A , Figure 12B They respectively indicate when using only Figure 11A The example shown illustrates the correspondence between predicted values ​​(SVM predicted values, RF predicted values) and observed values ​​in the case of the first illustrative variable set Prin1. Additionally, Figure 13A , Figure 13B They respectively indicate the use of only Figure 11B The second illustration shows an example of the correspondence between predicted values ​​(SVM predicted values, RF predicted values) and measured values ​​in the case of the variable set Prin2.

[0135] In addition, these Figure 12A , Figure 12B , Figure 13A , Figure 13B For details, see the aforementioned Figure 9A , Figure 9B The same applies. That is, in Figure 12A , Figure 12B , Figure 13A , Figure 13B In the examples shown, with the measured value of voltage sensitivity Vr set as variable x and the predicted value of voltage sensitivity Vr (SVM prediction or RF prediction) set as variable y, the (x, y) coordinates of many (562) samples are plotted. Furthermore, in these... Figure 12A , Figure 12B , Figure 13A , Figure 13B The text also includes an example of a formula that shows the trend of the correlation between these variables x and y (e.g., a formula for a first-order function specifically specified using the least squares method).

[0136] In these Figure 12A , Figure 12B , Figure 13A , Figure 13B In the examples shown, the situation is the same as that of Comparative Example 1 mentioned above ( Figure 9A , Figure 9B Unlike Comparative Example 1, the slope of the first-order function in the above-mentioned formula is approximately "1", and the intercept of the first-order function formula is approximately "0". Therefore, in this embodiment, unlike Comparative Example 1, the predicted value (SVM predicted value and RF predicted value) and the measured value have the following relationship regarding the voltage sensitivity Vr, which is the objective variable. That is, it is understood that the predicted value and the measured value have a sufficient correlation to achieve a practical level of printing using the predicted value.

[0137] (D. Function / Effect) As described above, in the injection parameter generation system 5 of this embodiment, it is determined which of the above-mentioned DV reference and Vj reference to select based on the selection indication signal Ss. Then, using only a first set of explanatory variables Prin1 or a second set of explanatory variables Prin2 selected according to the determination result of such reference, and using the established analysis method described above, the injection parameter Prj is generated, thus becoming as follows.

[0138] That is, for example, the decrease in the prediction accuracy of the injection parameter Prj, as in Comparative Example 1 described above (where a predetermined analysis method is used under conditions where both the DV and Vj references are mixed), is avoided. In other words, in this embodiment, the prediction accuracy of the injection parameter Prj can be improved compared to the case of Comparative Example 1. As a result, user convenience can be improved in this embodiment.

[0139] Furthermore, in this embodiment, the injection parameter Prj includes at least the aforementioned voltage sensitivity Vr, thus becoming as follows. That is, when using a predetermined analysis method to generate the voltage sensitivity Vr, the prediction accuracy of the voltage sensitivity Vr can be improved compared to the case of Comparative Example 1.

[0140] Furthermore, in this embodiment, the first explanatory variable set Prin1 includes at least the aforementioned target value of DV, and the second explanatory variable set Prin2 includes at least one of the aforementioned parameters indicating the presence or absence of a common drive and the number of drops, thus becoming as follows. That is, when generating the voltage sensitivity Vr using a predetermined analysis method, the voltage sensitivity Vr is generated using a parameter with the highest or second highest importance (contribution), thereby further improving the prediction accuracy of the voltage sensitivity Vr.

[0141] Furthermore, in this embodiment, the first explanatory variable set Prin1 includes the number of drops, and the second explanatory variable set Prin2 includes at least one parameter among the aforementioned head grade value, head type, specific gravity value of ink 9, surface tension value of ink 9, viscosity value at reference temperature Tr, and target value of DV, thus becoming as follows. That is, when generating voltage sensitivity Vr using a predetermined analysis method, further using these parameters with higher importance (contribution) to generate voltage sensitivity Vr can further improve the prediction accuracy of voltage sensitivity Vr.

[0142] Furthermore, in this embodiment, at least one of the first explanatory variable set Prin1 and the second explanatory variable set Prin2 includes the aforementioned voltage offset ΔVp, thus becoming as follows. That is, when generating the voltage sensitivity Vr using a predetermined analysis method, the prediction accuracy of the voltage sensitivity Vr can be further improved.

[0143] Furthermore, in this embodiment, the method of using machine learning model 74 is adopted as the established analysis method, so that the injection parameter Prj can be generated easily and with good accuracy.

[0144] Furthermore, in this embodiment, the table generation unit 733 and the signal generation unit 48 are further provided within the jet parameter generation system 5, resulting in the following: At least one of the generated jet parameters Prj is used to generate a predicted voltage characteristic table TPvp, and the voltage value Vp (peak value) of the pulse is determined using the generated predicted voltage characteristic table TPvp. A drive signal Sd is then generated using the pulse having this voltage value Vp. Therefore, the ink 9 is jetted using the generated drive signal Sd, thus easily improving the ink 9's ejection characteristics. As a result, user convenience is further enhanced.

[0145] Furthermore, in this embodiment, the aforementioned data acquisition unit 731, parameter generation unit 732, and table generation unit 733 are respectively provided outside the printer 1 (within the information processing device 7), thus achieving the following: That is, the original configuration of the inkjet head 4 and the printer 1 can be maintained, while the automatic generation of the jetting parameter Prj and the predicted voltage characteristic table TPvp can be performed simultaneously within the aforementioned information processing device 7. As a result, user convenience can be further improved.

[0146] <2. Variations> Next, variations of the above embodiments (variations 1-6) will be described. Furthermore, constituent elements identical to those in the above embodiments will be marked with the same symbols, and descriptions will be omitted as appropriate.

[0147] [Variation Example 1] In the above embodiments, the case where the predetermined injection parameter Prj includes at least the voltage sensitivity Vr has been described. In contrast, in the following variation 1, an example is described where the predetermined injection parameter Prj includes at least the conversion coefficient Kc of the aforementioned predetermined conversion process. That is, the conversion coefficient Kc corresponds to a specific example of the "determined injection parameter" in this disclosure.

[0148] Here, the aforementioned predetermined conversion process is the conversion process from the measured characteristic curve CMvi to the aforementioned predicted characteristic curve CPvp. Furthermore, the measured viscosity characteristic table TMvi will be explained in detail later; however, TMvi is a characteristic table that specifies the relationship between the viscosity Vi of ink 9 and the ambient temperature Ta, based on the measured characteristic curve CMvi. Similarly, the predicted voltage characteristic table TPvp will be explained in detail later; however, TPvp is a characteristic table that specifies the relationship between the voltage value Vp, representing the peak value of the pulse of the drive signal Sd based on a predetermined reference value, and the predicted characteristic curve CPvp, based on the ambient temperature Ta. Further details regarding these will be explained later.

[0149] (A. Composition) Figure 14 A block diagram illustrates an example of the structure of the machine learning model (machine learning model 74A) involved in Modification 1. Similar to the machine learning model 74 described in the embodiment, this machine learning model 74A is a prediction model obtained by performing machine learning by setting the input parameter Prin as an explanatory variable and the injection parameter Prj as the objective variable. Furthermore, as... Figure 14 As shown, if the machine learning model 74A is input with input parameters Prin (descriptive variables), it generates (predicts) injection parameters Prj (target variables) based on the learning results and outputs the generated injection parameters Prj. Furthermore, as described above, the machine learning model 74A generates the injection parameters Prj in a manner that includes at least the aforementioned transformation coefficients Kc, serving as an example of a given injection parameter Prj (see [reference]). Figure 14 ).

[0150] Similar to the implementation method, such a machine learning model 74A is used in the parameter generation unit 732. That is, the parameter generation unit 732 in this modified example 1 uses the analysis method using the machine learning model 74A to generate the injection parameter Prj (conversion coefficient Kc, etc.) based on the input parameter Prin. Furthermore, the specific example of the analysis method (prediction method) using such a machine learning model 74A is the same as the specific example listed in the implementation method.

[0151] (B. Details regarding conversion processing, etc.) Here, a comparative example (Comparative Example 2) is provided, detailing the predetermined conversion process, the measured viscosity characteristic table TMvi, and the predicted voltage characteristic table TPvp described above, and is explained below. Furthermore, details of each process in the information processing unit 73 (data acquisition unit 731, parameter generation unit 732, and table generation unit 733) described in the embodiment are also explained.

[0152] (B-1. Comparative Example 2) Figure 15 The block diagram illustrates a schematic example of the configuration of a printer 101, which is a liquid jet recording apparatus according to Comparative Example 2. The printer 101 of this comparative example includes the aforementioned nozzle plate 41, actuator plate 42, signal generation unit 48, and drive unit 49 in the inkjet head of Comparative Example 2 (not shown).

[0153] However, in the printer 101 of Comparative Example 2, unlike the printer 1 of the embodiment, the signal generation unit 48 uses the viscosity information Iv described below to set the voltage value Vp instead of the aforementioned predicted voltage characteristic table TPvp.

[0154] Figure 16 This represents an example of the viscosity information Iv involved in such a comparative example 2. Specifically, in this... Figure 16 The diagram illustrates an example of the correspondence between ambient temperature Ta and the viscosity Vi (measured value) of ink 9, the correspondence between ambient temperature Ta and the voltage value Vp (measured value) in the pulse of the drive signal Sd, and the correspondence between ambient temperature Ta and the difference ΔV (=Vi-Vp) between these viscosities Vi and voltage values ​​Vp (including viscosity information Iv). In other words, in this... Figure 16 The examples show the characteristic curves between viscosity Vi (measured value) and ambient temperature Ta (measured characteristic curve CMvi), voltage value Vp (measured value) and ambient temperature (measured characteristic curve CMvp), and the characteristic curve between the difference value ΔV and ambient temperature Ta.

[0155] Furthermore, the aforementioned ambient temperature Ta corresponds to a specific example of "temperature" in this disclosure.

[0156] In this comparative example 2, firstly, for example, as Figure 16 The viscosity information Iv shown is obtained by detecting the change in the viscosity Vi of ink 9 relative to the ambient temperature Ta (e.g., by performing measurements at multiple points, more than 5). Additionally, for example, as... Figure 16 As shown, the viscosity Vi of ink 9 varies with ambient temperature Ta, and the voltage value Vp (the voltage value Vp used as a reference for the dispensing speed) varies with ambient temperature Ta, exhibiting similar characteristics. Therefore, for example, as... Figure 16 As shown, the difference ΔV between these viscosities Vi and voltage values ​​Vp is independent of the ambient temperature Ta and shows a roughly constant value.

[0157] Moreover, such as Figure 16 As shown, the signal generation unit 48 in Comparative Example 2 utilizes the similarity of such temperature change characteristics to subtract a pre-calculated difference value ΔV (negative value) from the viscosity Vi value (refer to viscosity information Iv) at a certain ambient temperature Ta, thereby obtaining the voltage value Vp that serves as the reference for the discharge rate. That is, the signal generation unit 48 in Comparative Example 2 uses the relationship Vp = (Vi - ΔV) (refer to...) Figure 16 To calculate the voltage value Vp at a certain ambient temperature Ta.

[0158] However, the characteristic curve between voltage value Vp and ambient temperature Ta (the aforementioned measured characteristic curve CMvp) generally varies in slope and other characteristics depending on the type of pulses included in the drive signal Sd or the type / function of each pulse (e.g., including auxiliary pulses and other additional pulses, the type or function of each pulse). Therefore, in Comparative Example 2, it is essentially necessary to manually measure and obtain such a measured characteristic curve CMvp beforehand. Furthermore, if there are limited conditions (e.g., in the case of "one drop" as mentioned above, based on the ejection speed), then it is possible to derive the characteristic curve CMvp without actually measuring it.

[0159] Therefore, it is necessary to measure and obtain the aforementioned measured characteristic curve CMvp for each type of pulse number included in the drive signal Sd. Consequently, for the user of printer 101 in Comparative Example 2, this requires a significant amount of time or labor, increasing the workload or operating costs.

[0160] Here, Figure 17 This example illustrates one of the various characteristic curves (measured characteristic curve CMvp and measured characteristic curve CMvi) involved in Comparative Example 2. Specifically, in this... Figure 17 The measured characteristic curve CMvp shown illustrates various cases where the number of pulses (the aforementioned number of drops) is 1 drop (labeled "1d"), 3 drops (labeled "3d"), 7 drops (labeled "7d"), and 9 drops (labeled "9d"). Furthermore, in this… Figure 17 In the measured characteristic curves CMvp shown, the voltage value Vp is shown as a reference to a predetermined reference value. That is, in the measured characteristic curves CMvp shown in Figure 9, the voltage values ​​Vp (labeled "Vj reference") that are used as a reference for obtaining the ejection speed when the ink 9 is ejected and the voltage value Vp (labeled "DV reference") that is used as a reference for obtaining the droplet volume (DV) of the ink 9 are shown. Furthermore, in obtaining this Figure 17 The driving waveforms shown in the various characteristic curves are for all conditions (number of drops), including the case of "common drive" which will be discussed later.

[0161] In Figure 17 In the example shown, depending on the type of pulse count (number of drops) or the type of the aforementioned predetermined reference value (the Vj reference or DV reference), as described above, the slope of the measured characteristic curve CMvp varies. Therefore, for example, as... Figure 16As shown in Comparative Example 2 with viscosity information Iv, when generating the drive signal Sd, if a single measured characteristic curve CMvp is repeatedly used, the accuracy of setting the voltage value Vp decreases due to differences in the type of pulse number or the type of predetermined reference value, and the slope corresponding to the type / effect of each pulse. That is, it is difficult to accurately set the voltage value Vp (peak value) of the pulses in the drive signal Sd.

[0162] Specifically, in Comparative Example 2, for example, only a single voltage characteristic table can be created based on the measured characteristic curve CMvi (as mentioned above, in the case of "one drop" based on the output speed, etc.). Furthermore, as described above, obtaining the measured characteristic curve CMvp for each condition (each type of pulse number, etc.) requires a significant amount of manual measurement. Therefore, in the method of Comparative Example 2, the decrease in the accuracy of the voltage value Vp setting or the increase in the user's workload may compromise user convenience.

[0163] (B-2. Method of Variation 1) Therefore, in this variation 1, in the aforementioned information processing unit 73 (program 730), the aforementioned predetermined analysis method is used to generate the conversion coefficient Kc for the conversion process described below. Then, in this variation 1, the aforementioned characteristic table (the predicted voltage characteristic table TPvp specifying the predicted characteristic curve CPvp) is generated (automatically generated) at any time using the conversion coefficient Kc generated in this way.

[0164] Here, Figure 18 The flowchart illustrates an example of the transformation process involved in Variation Example 1, which will be discussed later (corresponding to the process discussed later). Figure 21 (A specific example of the processing in step S13). Additionally... Figure 19 This represents the various characteristic curves involved in this variation example 1 (execution) Figure 18 An example of the characteristic curve (shown after step S132, which will be explained later). Specifically, in this... Figure 19 The image shows an example of various characteristic curves (such as the aforementioned measured characteristic curve CMvi and the aforementioned predicted characteristic curve CPvp0, etc.) that show the relationship between the viscosity Vi [mPa] or voltage value Vp of ink 9 and the ambient temperature Ta [°C].

[0165] In addition, Figure 19 For convenience, the preliminary characteristic curve CMvp0 shown is a characteristic curve that has been pre-processed from the aforementioned measured characteristic curve CMvp (for the purpose of setting the voltage value Vp=0 at the predetermined reference temperature Tr, which will be described later) to facilitate comparison with the aforementioned preliminary characteristic curve CPvp0 (comparison of slopes).

[0166] in addition, Figure 20 This represents an example of the input parameter Prin involved in Variation Example 1. Furthermore, in this... Figure 20 The values ​​of the input parameter Prin are shown for each of the six samples ("Sample 1" - "Sample 6").

[0167] (For conversion processing) First, for example, such as Figure 18 , Figure 19 As shown, the conversion process using the conversion factor Kc is the same as described above, converting the measured characteristic curve CMvi to the predicted characteristic curve CPvp. Furthermore, as this... Figure 19 As the example shows, it can be understood that the preliminary characteristic curve CPvp0 obtained in such a conversion process is in good (approximately) consistent with the preliminary characteristic curve CMvp0 for the aforementioned measured characteristic curve CMvp.

[0168] Here, refer to Figure 18 , Figure 19 A specific example of such conversion processing will be provided.

[0169] In this conversion process, firstly, the measured characteristic curve CMvi is multiplied by the conversion coefficient Kc, and then multiplied (CMvi × Kc). Figure 18 Step S131). Next, the result of the multiplication process in step S131 is subtracted to ensure that at the given reference temperature Tr (at Figure 19 In the example, at Tr=40℃, the voltage value Vp=0, thereby generating the aforementioned preliminary characteristic curve CPvp0 (the preliminary characteristic curve between the predicted value of voltage Vp and the ambient temperature Ta) (step S132). That is, through such preliminary processing (the processing in steps S131 and S132), the conversion coefficient Kc is used to generate, for example, the characteristic curve CMvi from the measured characteristic curve. Figure 19 The preparatory characteristic curve CPvp0 is shown. Furthermore, the execution order of each process in steps S131 and S132 during such preparatory processing can, for example, be... Figure 18 The example shown is the reverse execution order (the order in which step S132 is executed first, followed by step S131).

[0170] Next, the voltage value Vp in the preliminary characteristic curve CPvp0 is added to a predetermined voltage offset ΔVp, and then summed (CPvp0 + ΔVp) to make it the voltage value Vp in the preliminary characteristic curve CPvp0. Figure 17The voltage value Vp under the aforementioned (DV reference or Vj reference) is used to generate the final predicted characteristic curve CPvp (step S133). That is, the voltage value Vp after such an added voltage offset ΔVp (the voltage value Vp in the predicted characteristic curve CPvp) corresponds to the voltage value Vp of the droplet amount of ink 9 used as a reference when the ink 9 is ejected, or the voltage value Vp of the ejection speed used as a reference. In this way, the final predicted characteristic curve CPvp is generated. Figure 18 The series of conversion processes shown has ended.

[0171] Incidentally, the specific conversion formula for such conversion processing uses the above-mentioned conversion coefficient Kc to be expressed by the following formula (1).

[0172] H: The viscosity value of ink 9 after conversion processing. H0: constant T: Absolute temperature (ambient temperature Ta) E: Activation energy k: Boltzmann constant Furthermore, the formula that removes the conversion coefficient Kc from the above formula (1) is called the Arrhenius formula (rule), which is a generally known formula. In formula (1), the conversion coefficient Kc is divided by the Arrhenius formula, but this is because when using the analysis method of machine learning model 74A, the calculation is performed using (the measured value of ink 9 viscosity / the measured value of voltage Vp). Therefore, for example, when using the analysis method of machine learning model 74A, if the calculation is performed using (the measured value of voltage Vp / the viscosity value of ink 9), the formula that multiplies the above Arrhenius formula by the conversion coefficient Kc becomes the conversion formula used in the above conversion process. That is, either of these formulas can be used as the conversion formula used in this conversion process.

[0173] (Regarding the input parameter Prin) Here, as a specific example of the aforementioned input parameter Prin in this variation 1, such as... Figure 20 As shown, the input parameters Prin are listed below as (a)-(k) and (l), which are also described in the embodiments.

[0174] (a) Number of drops (pulse count) (b) Whether there is a common driver (c) Head types (d) Types of ink (e) (DV benchmark or Vj benchmark) (f) Head Rank Value (g) Viscosity value at reference temperature Tr (l) Voltage sensitivity Vr during discharge (h) Surface tension value of ink 9 (i) Specific gravity of ink 9 (k) Voltage offset ΔVp (j) The target value of DV or Vj (Details regarding the generation and processing of characteristic tables, etc.) Here, Figure 21 The flowchart illustrates the generation process of the characteristic table (predicted voltage characteristic table TPvp) involved in Modification Example 1. Furthermore, this... Figure 21 The series of processes shown (steps S10-S16, which will be described later) includes steps S11-S13, which will be described later. Each of these steps corresponds to the generation process of the predicted voltage characteristic table TPvp, and each of these steps S14 and S15, which will be described later, corresponds to the generation process of the drive signal Sd.

[0175] In Figure 21 In the series of processes shown, firstly, as a previous stage, the information processing unit 73 (program 730) determines whether it is necessary to generate (update) the predicted voltage characteristic table TPvp, which specifies the predicted characteristic curve CPvp as described above (step S10). Here, if it is determined that the predicted voltage characteristic table TPvp needs to be generated (step S10: Y), the process proceeds to the generation process of the predicted voltage characteristic table TPvp described below (steps S11-S13). On the other hand, if it is determined that the predicted voltage characteristic table TPvp does not need to be generated (step S10: N), the process proceeds to step S15, which will be described later, and the driving signal Sd is generated using a pulse having the voltage value Vp (peak value) at the current stage.

[0176] Furthermore, for cases where the predicted voltage characteristic table TPvp needs to be generated, examples include the following: For example, cases where a predetermined time has elapsed, or where the ink cartridge 3 has been filled, or where a predetermined operation signal from the user has been input to the printer 1, or where the non-dispensing period (idle period) of the ink 9 has exceeded a predetermined time. Additionally, examples include cases where the color or type of ink 9 in the ink cartridge 3 has been changed, or where the printer 1 is equipped with an inkjet head 4 of another type. Moreover, examples include... Figure 20 The example shown illustrates the case where at least one of the input parameters Prin is changed.

[0177] (Steps S11-S13: Generation of the predicted voltage characteristic table TPvp) Next, in the process of generating the predicted voltage characteristic table TPvp (steps S11-S13), the data acquisition unit 731 first acquires the following data (input data). That is, the data acquisition unit 731 uses the aforementioned method to acquire the predetermined input parameter Prin and the measured viscosity characteristic table TMvi of the measured characteristic curve CMvi between the viscosity Vi of the specified ink 9 and the ambient temperature Ta, respectively, as input data (step S11).

[0178] Next, the parameter generation unit 732 uses a predetermined analysis method that sets the input parameter Prin obtained in step S11 as an explanatory variable and the conversion coefficient Kc, which is the injection parameter Prj, as the target variable, to generate the conversion coefficient Kc based on the input parameter Prin (step S12). Specifically, in this modified example 1, the parameter generation unit 732 uses the analysis method of the aforementioned machine learning model 74A to generate the conversion coefficient Kc based on the input parameter Prin.

[0179] Then, the table generation unit 733 uses the measured viscosity characteristic table TMvi obtained in step S11 and the conversion coefficient Kc generated in step S12 to perform the aforementioned predetermined conversion process (see reference). Figure 18 , Figure 19 This generates a predicted voltage characteristic table TPvp (step S13). Thus, as described above, a predicted voltage characteristic curve CPvp between the voltage value Vp (peak value) of the pulse of the specified drive signal Sd and the ambient temperature Ta is generated, along with a predicted voltage characteristic table TPvp.

[0180] (Steps S14 and S15: Generation and processing of drive signal Sd) Next, in the generation process of the drive signal Sd (steps S14 and S15), firstly, the signal generation unit 48 uses the predicted voltage characteristic table TPvp generated in step S13, and employs the aforementioned method (see...). Figure 6 The voltage value Vp (peak value) in the pulse of the drive signal Sd is determined (step S14). Specifically, the voltage value Vp of the pulse is determined by applying the current ambient temperature Ta to the predicted voltage characteristic table TPvp.

[0181] Then, the signal generation unit 48 uses a pulse having the voltage value Vp obtained in step S14 and, for example, a preset pulse width Wp, to generate, for example, as described above. Figure 6 (A)- Figure 6 (C) shows the drive signal Sd (step S15).

[0182] Incidentally, the pulse width Wp mentioned above is calculated based on, for example, the peak value (AP) of the conduction pulse in the pulse. This AP corresponds to half the period of the natural vibration cycle of the ink 9 within the aforementioned ejection channel (1AP = (natural vibration cycle of ink 9) / 2). Moreover, when the pulse width Wp is set to AP, the ejection speed (ejection efficiency) of the ink 9 is maximized when ejecting a normal amount of 1 drop of ink 9 (ejecting 1 drop). Furthermore, this AP is determined, for example, by the shape of the ejection channel or the physical parameters of the ink 9 (specific gravity, etc.).

[0183] Furthermore, based on such an AP, the pulse width Wp can be set, for example, as follows. That is, for example, if the aforementioned... Figure 6 (A)- Figure 6 In the example of the drive signal Sd shown in (C) (examples for the cases of "1 drop", "2 drops", and "3 drops" respectively), the signal generation unit 48 sets the pulse width Wp as follows. That is, in this... Figure 6 (A)- Figure 6 In example (C), the signal generation unit 48 sets the pulse width Wp such that, for example, the relationship between each pulse width Wp and AP as shown in equations (2) and (3) below is satisfied. However, not limited to the example shown in equations (2) and (3), each pulse width Wp can be appropriately set. (Step S16: Ink 9 ejection action) Next, the drive unit 49 applies the drive signal Sd generated in step S15 to the aforementioned actuator plate 42 inside the inkjet head 4, causing ink 9 to be ejected from the nozzle orifice Hn (step S16). In this way, the aforementioned ink 9 ejection operation is performed.

[0184] above, Figure 21 The series of processes shown has ended.

[0185] Thus, in the method of this variation 1, a conversion coefficient Kc is generated based on a predetermined input parameter Prin using a predetermined analysis method. The measured viscosity characteristic table TMvi and the conversion coefficient Kc are then used for conversion processing to generate a predicted voltage characteristic table TPvp. That is, a predicted voltage characteristic table TPvp is automatically generated each time, representing the predicted characteristic curve CPvp between a specified voltage value Vp (peak value) and the ambient temperature Ta.

[0186] Therefore, in Modification 1, for example, compared to the case where the characteristic curves (the aforementioned measured characteristic curves CMvp) between these voltage values ​​Vp and ambient temperature Ta are measured and obtained as in Comparative Example 2 (e.g., measured and obtained according to each type of pulse number included in the drive signal Sd), the workload or operating cost is reduced. Furthermore, the aforementioned characteristic curves (measured characteristic curves CMvp) between voltage values ​​Vp and ambient temperature Ta, as described above, generally have different slopes depending on the type of pulse number included in the drive signal Sd or the category / function of each pulse, thus automatically generating a predicted voltage characteristic table TPvp each time, resulting in the following. That is, for example, compared to the case of repeatedly using a single characteristic curve, the voltage value Vp (peak value) of the pulses in the drive signal Sd can be set with good accuracy.

[0187] Therefore, in Modification 1, the efficiency of using the characteristic curve (voltage characteristic table) between the voltage value Vp and the ambient temperature Ta can be improved, and the setting accuracy of the voltage value Vp (peak value) of the pulse in the drive signal Sd can be easily improved.

[0188] Alternatively, in this modified example 1, for example, the following effect can also be obtained.

[0189] • The characteristic curve between the voltage value Vp and the ambient temperature Ta can be easily obtained. Therefore, even if the number or type of pulses or the type / function of each pulse are different, it is easy to perform voltage control to keep the ink 9 ejection speed or droplet volume approximately constant.

[0190] • As in Comparative Example 2 mentioned above, the expensive evaluation device (temperature regulator, etc.) used to obtain the measured characteristic curve CMvp is not required, thus reducing costs.

[0191] (C. Comparative Example 3) However, in this modified example 1, as described in the embodiments, the following situation may occur depending on the conditions. That is, similar to the case of Comparative Example 1, when both the DV reference and the Vj reference exist together, and when using the established analysis method (Comparative Example 3), for example, there is a situation where the prediction accuracy of the injection parameter Prj under either the DV reference or the Vj reference decreases. Hereinafter, Comparative Example 3 will be described.

[0192] Figure 22 This is an example illustrating the results of the importance analysis of the input parameters Prin involved in Comparative Example 3. Figure 22In the example shown, when generating the ejection parameter Prj (= conversion coefficient Kc) using machine learning model 74A, the input parameter Prin, whose importance (contribution rate) increases relatively, is as follows: That is, in the order of (i) the specific gravity of ink 9, (a) the number of drops, (g) the viscosity value at the reference temperature Tr, (k) the voltage offset ΔVp, (l) the voltage sensitivity Vr at ejection, and (j) the target value of DV or Vj, as shown in (a)-(k) and (l) above, the importance increases.

[0193] Therefore, in Comparative Example 3, these parameters, such as Prin, are used selectively as input parameters, and a predetermined analysis method is employed under the condition that both the DV and Vj references are present. Consequently, as described above, in Comparative Example 3, similar to Comparative Example 1, for example, the prediction accuracy of the injection parameter Prj under either the DV or Vj reference may decrease. As a result, in Comparative Example 3, similar to Comparative Example 1, user convenience may decrease.

[0194] (D. Generation and processing of injection parameter Prj in variant example 1) Therefore, in this modified example 1, similar to the aforementioned implementation, when generating the conversion coefficient Kc as the injection parameter Prj, it is determined which reference, DV reference or Vj reference, to select based on the aforementioned selection indication signal Ss. Then, using only a first set of explanatory variables Pran1 or a second set of explanatory variables Pran2 selected based on the determination result of such reference, and employing a predetermined analysis method, the conversion coefficient Kc as the injection parameter Prj is generated.

[0195] Here, Figure 23A This is an example representing the importance analysis results in the first explanatory variable set Prin1 involved in Variation Example 1. Additionally, Figure 23B This is an example of the importance analysis results in the second explanatory variable set Prin2 involved in Variation Example 1.

[0196] like Figure 23A As shown, the first set of explanatory variables Prin1 involved in Variation Example 1 includes at least one of the aforementioned input parameters Prin (e.g., the parameters below). That is, in Figure 23A The examples include (i) the specific gravity of ink 9, (a) the number of drops, (g) the viscosity at the reference temperature Tr, (j) the target DV value, (k) the voltage offset ΔVp, (l) the voltage sensitivity Vr during ejection, (b) the presence or absence of a common drive, (h) the surface tension of ink 9, (f) the head grade value, (c) the head type, and (d) the ink type. Additionally, as... Figure 23AAs shown, their importance (contribution) increases relatively in order.

[0197] On the other hand, such as Figure 23B As shown, the second set of explanatory variables Prin2 involved in Variation Example 1 includes at least one of the aforementioned input parameters Prin (e.g., the parameters below). That is, in Figure 23B The examples include (i) the specific gravity of ink 9, (g) the viscosity at the reference temperature Tr, (a) the number of drops, (k) the voltage offset ΔVp, (l) the voltage sensitivity Vr during ejection, (d) the ink type, (h) the surface tension of ink 9, (f) the head grade value, (j) the target value of Vj, (c) the head type, and (b) whether there is a common drive. Additionally, as... Figure 23B As shown, their importance (contribution) increases relatively in order.

[0198] Here, Figure 24A , Figure 24B They respectively indicate the use of only Figure 23A The example shown illustrates the correspondence between predicted values ​​(SVM predictions, RF predictions) and observed values ​​in the case of the first illustrative variable set Prin1. Additionally, Figure 25A , Figure 25B They respectively indicate the use of only Figure 23B The second illustration shows an example of the correspondence between predicted values ​​(SVM predicted values, RF predicted values) and measured values ​​in the case of the variable set Prin2.

[0199] In addition, regarding Figure 24A , Figure 24B , Figure 25A , Figure 25B The details are the same as those mentioned above. Figure 12A , Figure 12B , Figure 13A , Figure 13B The same applies. That is, in Figure 24A , Figure 24B , Figure 25A , Figure 25B In the examples shown, the (x, y) coordinates of many (562) samples are plotted with the measured value of the transformation coefficient Kc set as variable x and the predicted value of the transformation coefficient Kc (SVM prediction or RF prediction) set as variable y. Furthermore, in these... Figure 24A , Figure 24B , Figure 25A , Figure 25B The text also includes an example of a formula that shows the trend of the correlation between these variables x and y (e.g., a formula for a first-order function specifically specified using the least squares method).

[0200] In these Figure 24A , Figure 24B , Figure 25A , Figure 25B In the examples shown, the situation is different from that of the implementation method ( Figure 12A , Figure 12B , Figure 13A , Figure 13B Similarly, the slope of the above-mentioned linear function formula is approximately "1", and the intercept of the linear function formula is approximately "0". Therefore, in this variation 1, unlike Comparative Example 3 above, the predicted values ​​(SVM predicted values ​​and RF predicted values) and the measured values ​​have the following relationship with respect to the transformation coefficient Kc, which is the objective variable. That is, it is understood that the predicted values ​​and the measured values ​​have a sufficient correlation to achieve a practical level of usability when using the predicted values ​​for printing.

[0201] (E. Function / Effect) Thus, in variation 1, the same effect can be achieved essentially through the same action as in the implementation method.

[0202] Furthermore, specifically in this modified example 1, the injection parameter Prj includes at least the conversion coefficient Kc from the predetermined conversion process described above, thus becoming as follows. That is, when generating the conversion coefficient Kc using the predetermined analysis method described above, the prediction accuracy of the conversion coefficient Kc can be improved compared to the case of Comparative Example 3. As a result, user convenience can also be further improved in this modified example 1.

[0203] [Variation Example 2] In the above embodiments, the case where the predetermined injection parameter Prj includes at least the voltage sensitivity Vr was described. In the above-described variation 1, the case where the predetermined injection parameter Prj includes at least the conversion coefficient Kc was described. In contrast, in the following variation 2, an example of the case where the predetermined injection parameter Prj includes at least the aforementioned voltage offset ΔVp will be described. That is, the voltage offset ΔVp corresponds to a specific example of the "determined injection parameter" in this disclosure.

[0204] (A. Composition) Figure 26 A block diagram illustrates the structure of the machine learning model (machine learning model 74B) involved in Variation Example 2. Similar to machine learning models 74 and 74A described so far, machine learning model 74B is a prediction model obtained by performing machine learning on the input parameter Prin as the explanatory variable and the injection parameter Prj as the objective variable. Furthermore, as... Figure 26As shown, if the machine learning model 74B is input with input parameters Prin (descriptive variables), it generates (predicts) injection parameters Prj (objective variables) based on the learning results and outputs the generated injection parameters Prj. Then, as described above, the machine learning model 74B generates injection parameters Prj in a manner that includes at least the voltage offset ΔVp mentioned above, as an example of a given injection parameter Prj (see reference). Figure 26 ).

[0205] Such a machine learning model 74B is used in the parameter generation unit 732 in the same way as in the embodiment and variation 1. That is, the parameter generation unit 732 in this variation 2 uses the analysis method of the machine learning model 74B to generate the injection parameters Prj (voltage offset ΔVp, etc.) based on the input parameters Prin. Furthermore, the specific example of the analysis method (prediction method) using such a machine learning model 74B is the same as the specific example listed in the embodiment.

[0206] (B. For the input parameter Prin) Figure 27 This represents an example of the input parameter Prin involved in Variation Example 2. Furthermore, in this... Figure 27 The values ​​of the input parameter Prin are shown for each of the six samples ("Sample 1" - "Sample 6").

[0207] As a specific example of the input parameter Prin in this variation 2, such as Figure 27 As shown, the input parameter Prin, which is also described in the embodiments and variations 1, is illustrated by (a)-(j) and (l) below.

[0208] (a) Number of drops (pulse count) (b) Whether there is a common driver (c) Head types (d) Types of ink (e) (DV benchmark or Vj benchmark) (f) Head Rank Value (g) Viscosity value at reference temperature Tr (l) Voltage sensitivity Vr during discharge (DV reference or Vj reference) (h) Surface tension value of ink 9 (i) Specific gravity of ink 9 (j) The target value of DV or Vj (C. Comparative Example 4) In this modified example 2, as described in the embodiments and modified example 1, the following situation may occur depending on the conditions. That is, similar to the cases in comparative examples 1 and 3, when both the DV reference and the Vj reference exist together, and when using a predetermined analysis method (comparative example 4), for example, there is a situation where the prediction accuracy of the injection parameter Prj under either the DV reference or the Vj reference decreases. Hereinafter, such comparative example 4 will be described.

[0209] Figure 28 This is an example illustrating the results of the importance analysis of the input parameters Prin involved in Comparative Example 4. Figure 28 In the example shown, when generating the injection parameter Prj (= voltage offset ΔVp) using machine learning model 74B, the input parameter Prin, whose importance (contribution rate) increases relatively, is the following input parameter Prin. That is, among the input parameters Prin shown in (a)-(j) and (l) above, their importance increases in the following order: (g) viscosity value at reference temperature Tr, (b) presence or absence of common drive, (f) head grade value, (c) head type, (i) specific gravity value of ink 9, (l) voltage sensitivity Vr at ejection, (h) surface tension value of ink 9, and (j) target value of DV or Vj.

[0210] Therefore, in Comparative Example 4, these parameters, Prin, are used selectively as input parameters, and a predetermined analysis method is employed while both the DV and Vj references are present. Consequently, as described above, in Comparative Example 4, similar to Comparative Examples 1 and 3, the prediction accuracy of the injection parameter Prj under either the DV or Vj reference may decrease. As a result, in Comparative Example 4, as in Comparative Examples 1 and 3, user convenience may decrease.

[0211] (D. Generation and processing of injection parameter Prj in variant example 2) Therefore, in this modified example 2, similar to the aforementioned implementation and modified example 1, when generating the voltage offset ΔVp as the injection parameter Prj, it is determined which reference, DV reference or Vj reference, to select based on the aforementioned selection indication signal Ss. Then, using only a first set of explanatory variables Pran1 or a second set of explanatory variables Pran2 selected based on the determination result of such reference, and employing a predetermined analysis method, the voltage offset ΔVp as the injection parameter Prj is generated.

[0212] Here, Figure 29A This is an example of the importance analysis results in the first explanatory variable set Prin1 involved in Variation Example 2. Additionally, Figure 29BThis is an example of the importance analysis results in the second explanatory variable set Prin2 involved in Variation Example 2.

[0213] like Figure 29A As shown, the first set of explanatory variables Prin1 involved in Variation Example 2 includes at least one of the aforementioned input parameters Prin (e.g., the parameters below). That is, in Figure 29A The examples include (b) presence or absence of common drive, (g) viscosity value at reference temperature Tr, (f) head grade value, (c) head type, (i) specific gravity value of ink 9, (h) surface tension value of ink 9, (l) voltage sensitivity Vr during dispensing, (j) target value of DV, (d) ink type, and (a) number of drops. Additionally, as... Figure 29A As shown, their importance (contribution) increases relatively in order.

[0214] On the other hand, such as Figure 29B As shown, the second set of explanatory variables, Prin2, involved in Variation Example 2, includes at least one of the aforementioned input parameters Prin (e.g., the parameters listed below). That is, in Figure 29B The examples include (l) voltage sensitivity Vr during ejection, (g) viscosity value at reference temperature Tr, (f) head grade value, (c) head type, (h) surface tension value of ink 9, (i) specific gravity value of ink 9, (b) presence or absence of common drive, (j) target value of Vj, (a) number of drops, and (d) ink type. Additionally, as... Figure 29B As shown, their importance (contribution) increases relatively in order.

[0215] Here, Figure 30A , Figure 30B They respectively indicate the use of only Figure 29A The example shown illustrates the correspondence between predicted values ​​(SVM predictions, RF predictions) and observed values ​​in the case of the first illustrative variable set Prin1. Additionally, Figure 31A , Figure 31B They respectively indicate the use of only Figure 29B The second illustration shows an example of the correspondence between predicted values ​​(SVM predicted values, RF predicted values) and measured values ​​in the case of the variable set Prin2.

[0216] In addition, regarding these Figure 30A , Figure 30B , Figure 31A , Figure 31B The details are the same as those mentioned above. Figure 12A , Figure 12B , Figure 13A , Figure 13B , Figure 24A , Figure 24B, Figure 25A , Figure 25B The same applies. That is, in Figure 30A , Figure 30B , Figure 31A , Figure 31B In the examples shown, with the measured value of voltage offset ΔVp set as variable x and the predicted value of voltage offset ΔVp (SVM prediction or RF prediction) set as variable y, the (x, y) coordinates of many (562) samples are plotted. Furthermore, in these... Figure 30A , Figure 30B , Figure 31A , Figure 31B The text also includes an example of a formula that shows the trend of the correlation between these variables x and y (e.g., a formula for a first-order function specifically specified using the least squares method).

[0217] In these Figure 30A , Figure 30B , Figure 31A , Figure 31B In the examples shown, the situation is different from that of the implementation method ( Figure 12A , Figure 12B , Figure 13A , Figure 13B ) or the case of variation 1 ( Figure 24A , Figure 24B , Figure 25A , Figure 25B Essentially the same, it becomes as follows. That is, the slope of the above-mentioned first-degree function formula is close to "1", and the intercept of the first-degree function formula is close to "0". Therefore, in this modified example 2, unlike the above-mentioned comparative example 4, the predicted value (SVM predicted value and RF predicted value) and the measured value have the following relationship regarding the voltage offset ΔVp as the objective variable. That is, it is understood that the predicted value and the measured value have a sufficient correlation to achieve a practical level of printing using the predicted value.

[0218] (E. Function / Effect) Thus, in variation 2, the same effect can be achieved essentially through the same action as in the implementation method.

[0219] Furthermore, specifically in this modified example 2, the injection parameter Prj includes at least the voltage offset ΔVp used in the predetermined conversion process described above, thus becoming as follows. That is, when generating the voltage offset ΔVp using the predetermined analysis method described above, the prediction accuracy of the voltage offset ΔVp can be improved compared to the case of Comparative Example 4. As a result, user convenience can also be further improved in this modified example 2.

[0220] [Variation Example 3] (constitute) Figure 32 The block diagram illustrates an example of the configuration of the jet parameter generation system 5A according to Modification 3. This jet parameter generation system 5A of Modification 3 includes a printer 1 with an inkjet head 4; and an information processing device 7A and a server 8 located external to the printer 1. Furthermore, the printer 1, the information processing device 7A, and the server 8 are interconnected via a network 50. That is, this jet parameter generation system 5A corresponds to a system in which, instead of the information processing device 7, an information processing device 7A is provided, and a server 8 is also provided.

[0221] Furthermore, in this variation 3, the aforementioned server 8 corresponds to a specific example of the "external device" in this disclosure.

[0222] Regarding the information processing device 7A, such as Figure 32 As shown, the physical block structure includes a bus 70, an input unit 71, a display unit 72, a control unit 75, a storage unit 76A, and a network IF 77. That is, this information processing device 7A corresponds to the following device: Regarding Figure 4 The information processing apparatus 7 of the illustrated embodiment has a storage unit 76A instead of a storage unit 76. Unlike the storage unit 76, the storage unit 76A does not store the program 730 and the machine learning model 74 described in the embodiment separately. Therefore, this information processing apparatus 7A is, for example, equivalent to a PC with a general configuration.

[0223] Regarding server 8, such as Figure 32 As shown, the physical block configuration includes a bus 80, a control unit 85, a storage unit 86, and a network IF 87. Furthermore, the control unit 85, the storage unit 86, and the network IF 87 are interconnected via the bus 80. The control unit 85 and the network IF 87 each have features consistent with the embodiment (…). Figure 4 The control unit 75 and network IF 77 in the embodiment have the same configuration. Additionally, the storage unit 86 also has the same configuration as in the embodiment (…). Figure 4 The storage unit 76 in the same configuration is as described above. That is, as shown in the example. Figure 32 As shown, the storage unit 86 stores the program 730 and the machine learning model 74 described in the embodiment, respectively. Furthermore, as in... Figure 32 As indicated by parentheses, in addition to such machine learning model 74, machine learning models 74A and 74B as described in variations 1 and 2 can also be provided, as can the variations 4-6 described later.

[0224] Thus, in the injection parameter generation system 5A of this modified example 3, unlike the injection parameter generation system 5 of the embodiment, the aforementioned predetermined injection parameters Prj (and the predicted voltage characteristic table TPvp) are generated in the server 8 instead of the information processing device 7A. Then, as... Figure 32 As shown, the predicted voltage characteristic table TPvp generated in this way is supplied from server 8 to signal generation unit 48 in inkjet head 4 of printer 1 via network 50.

[0225] (Function / Effect) In this modified example 3, the injection parameter generation system 5A can also be used as a whole to achieve the same effect as the injection parameter generation system 5 in the embodiment.

[0226] Furthermore, specifically in this variation 3, the aforementioned data acquisition unit 731, parameter generation unit 732, and table generation unit 733 (the aforementioned program 730) are respectively located outside the printer 1 (within the server 8), thus becoming as follows. That is, similar to the case of the aforementioned embodiment, the original configuration of the inkjet head 4 and the printer 1 can be maintained, and the automatic generation of the jetting parameter Prj and the predicted voltage characteristic table TPvp can be performed simultaneously within the aforementioned server 8. In addition, in this variation 3, as described above, the original (general) configuration of the information processing device 7A can also be used; for example, the server 8, which functions as a cloud server, can be used to obtain the same effect as in the embodiment. As a result, in this variation 3, user convenience can be further improved.

[0227] [Variation Example 4] (constitute) Figure 33 The block diagram illustrates an example configuration of the jet parameter generation system 5B involved in Modification 4. This jet parameter generation system 5B of Modification 4 includes the aforementioned information processing device 7A and a printer 1B with an inkjet head 4B. Furthermore, the printer 1B and the information processing device 7A are interconnected via a network 50. That is, this jet parameter generation system 5B corresponds to a system in which the aforementioned information processing device 7A is provided instead of the information processing device 7, and the printer 1B and the inkjet head 4B are provided instead of the printer 1 and the inkjet head 4, respectively.

[0228] Furthermore, the printer 1B described above corresponds to a specific example of the "liquid jet recording apparatus" in this disclosure. Additionally, the inkjet head 4B described above corresponds to a specific example of the "liquid jet head" in this disclosure.

[0229] In this variation 4, such as Figure 33As shown, the aforementioned information processing unit 73 (data acquisition unit 731, parameter generation unit 732, and table generation unit 733), in other words, the aforementioned program 730, is provided within the inkjet head 4B. Furthermore, the aforementioned machine learning model 74 is also provided within this inkjet head 4B. That is, in this modified example 4, unlike the implementation method and modified example 3, the information processing unit 73 (program 730) and the machine learning model 74 are respectively provided within the inkjet head 4B built into the printer 1B.

[0230] (Function / Effect) In this modified example 4, it can also be used as the entire injection parameter generation system 5B, and basically achieve the same effect by functioning in the same way as the injection parameter generation system 5 of the embodiment.

[0231] Furthermore, specifically in this variation 4, the data acquisition unit 731, parameter generation unit 732, and table generation unit 733 are each housed within the printer 1B, thus becoming as follows. That is, unlike the embodiment or variation 3, it is not necessary to prepare these data acquisition units 731, parameter generation unit 732, and table generation unit 733 separately in an external device (information processing device 7 or server 8) beforehand. As a result, the printer 1B itself can automatically generate the jetting parameter Prj and the predicted voltage characteristic table TPvp, thereby further improving user convenience.

[0232] Furthermore, in this modified example 4, the aforementioned data acquisition unit 731, parameter generation unit 732, and table generation unit 733 are respectively disposed within the inkjet head 4B of the printer 1B, thus becoming as follows: That is, the original configuration of the printer 1B itself, excluding the inkjet head 4B, can be maintained, while the inkjet head 4B itself automatically generates the jetting parameter Prj and the predicted voltage characteristic table TPvp. As a result, user convenience can be further improved.

[0233] [Variation Example 5] (constitute) Figure 34 The block diagram illustrates an example configuration of the jet parameter generation system 5C involved in Modification 5. This jet parameter generation system 5C of Modification 5 includes the aforementioned information processing device 7A and a printer 1C having the aforementioned inkjet head 4. Furthermore, the printer 1C and the information processing device 7A are interconnected via a network 50. That is, this jet parameter generation system 5C corresponds to a system in which the aforementioned information processing device 7A is provided instead of the information processing device 7, and the printer 1C is provided instead of the printer 1, in relation to the jet parameter generation system 5 of this embodiment.

[0234] Furthermore, the printer 1C described above corresponds to a specific example of the "liquid jet recording apparatus" in this disclosure.

[0235] In this variation 5, such as Figure 34 As shown, the aforementioned information processing unit 73 (data acquisition unit 731, parameter generation unit 732, and table generation unit 733), in other words, the previously described program 730 and its variant 4 ( Figure 33 Similarly, it is also installed inside printer 1C. Furthermore, the aforementioned machine learning model 74 is also installed inside printer 1C in the same way as in variant 4. However, as... Figure 34 As shown, in this modified example 5, unlike modified example 4, the information processing unit 73 (program 730) and the machine learning model 74 are all configured outside the inkjet head 4 within the printer 1C.

[0236] (Function / Effect) In this modified example 5, the injection parameter generation system 5C can also be used as a whole to achieve the same effect as the injection parameter generation system 5 in the embodiment.

[0237] Furthermore, in this particular variation 5, similar to variation 4 described above, the data acquisition unit 731, the parameter generation unit 732, and the table generation unit 733 are each housed within the printer 1C, thus becoming as follows. That is, similar to the case of variation 4, the printer 1C itself can automatically generate the jetting parameter Prj and the predicted voltage characteristic table TPvp, resulting in further improved user convenience.

[0238] [Variation Example 6] (constitute) Figure 35 The block diagram illustrates an example of the configuration of the information processing unit 73D (program 730D) involved in Modification 6. The information processing unit 73D of Modification 6 corresponds to an information processing unit that, in addition to the aforementioned signal generation unit 48, is provided in the information processing unit 73 (which includes a data acquisition unit 731, a parameter generation unit 732, and a table generation unit 733) described in the embodiments. In other words, the program 730D of Modification 6 corresponds to a program that, regarding the program 730 described in the embodiments, also includes the functions of each processing performed in the aforementioned signal generation unit 48.

[0239] The configuration of such an information processing unit 73D (program 730D) corresponds to the following configuration: for example, in addition to providing the information processing unit 73 (program 730) in the external device (information processing device 7 or server 8) of the printer 1 as in Embodiment 3 or Modification 3, the configuration or function of the signal generation unit 48 is also provided. That is, unlike these Embodiments or Modification 3, the following example corresponds to the following: the configuration or function of the signal generation unit 48 is not provided in the printer 1, but is provided in the external device (information processing device 7 or server 8) of the printer 1.

[0240] (Function / Effect) In this modified example 6, the same effect can be obtained essentially through the same action as in the implementation method.

[0241] Furthermore, in this particular variation 6, a signal generation unit 48 is also configured or functionally provided within the information processing unit 73D (program 730D). Therefore, the operation of the signal generation unit 48 (the generation of the drive signal Sd) can also be executed simultaneously within the information processing unit 73D (program 730D). As a result, user convenience can be further improved.

[0242] <3. Other variations> The present disclosure has been described above with examples of embodiments and modifications, but the present disclosure is not limited to these embodiments and can be modified in various ways.

[0243] For example, in the above embodiments, examples of the configuration (shape, arrangement, number, etc.) of each component in the printer and inkjet head are specifically listed for explanation, but the embodiments are not limited to those described above; other shapes, arrangements, numbers, etc., are also possible. Specifically, for example, the above embodiments illustrate a shuttle printer with a moving inkjet head, but the embodiments are not limited to this example; for example, a single-pass type printer with a fixed inkjet head could also be used. Furthermore, the above embodiments illustrate an example of an ink tank housed within a predetermined frame, but the embodiments are not limited to this example; the ink tank could also be located outside the frame. Moreover, the above embodiments primarily illustrate an example of a signal generation unit located inside the inkjet head, but the embodiments are not limited to this example; a signal generation unit could also be located outside the inkjet head within the printer.

[0244] Furthermore, various types of structures can be applied to the inkjet head. For example, it can be a side-jet type inkjet head that ejects ink 9 from the center of each ejection channel in the extension direction of the actuator plate. Alternatively, it can be an edge-jet type inkjet head that ejects ink 9 along the extension direction of each ejection channel. Moreover, the printer method is not limited to the methods described in the above embodiments, and various methods such as thermal (thermal on-demand type) or MEMS (Micro Electro Mechanical Systems) methods can be applied.

[0245] Furthermore, the embodiments described above exemplify a non-recirculating inkjet head that does not circulate ink 9 between the ink tank and the inkjet head, but this is not limited to that example. That is, for example, this disclosure can also be applied to a recirculating inkjet head that circulates ink 9 between the ink tank and the inkjet head.

[0246] Furthermore, in the above embodiments, examples of generating injection parameters Prj or characteristic tables (predicted voltage characteristic tables TPvp) and driving signals Sd are specifically given for illustration, but the methods are not limited to those listed in the above embodiments. That is, for example, other methods can also be used to generate injection parameters Prj or characteristic tables and driving signals Sd. Specifically, in the above embodiments, a method using a machine learning model is given as an example of the aforementioned established analysis method, but the methods are not limited to this method, and other analysis methods can also be used. In addition, the input parameter Prin is not limited to the various parameters listed in the above embodiments, and other parameters can be added (or replaced) in the analysis method.

[0247] Furthermore, in the above embodiments, examples were given illustrating the case where the drive signal Sd is generated based on both the pulse width Wp and the voltage value (peak value) Vp in the set (automatically adjusted) pulse, but this is not limited to this example. That is, for example, the drive signal Sd can also be generated based solely on the pulse width Wp in the set pulse and the pulse width Wp in the voltage value Vp. Moreover, in the above embodiments, examples were given illustrating the case where all voltage values ​​Vp in multiple pulses are the same, but for example, the voltage values ​​Vp in these multiple pulses may not be the same (at least some of the voltage values ​​Vp are different values). Even in such cases, the generation process of the predicted voltage characteristic table TPvp described in the above embodiments can be performed by using multiple types of voltage values ​​Vp as explanatory variables.

[0248] Furthermore, in the above embodiments, voltage sensitivity Vr, conversion coefficient Kc, and voltage offset ΔVp are listed as examples of injection parameters Prj, but the examples are not limited to these cases. That is, for example, two or more of these various parameters (voltage sensitivity Vr, conversion coefficient Kc, and voltage offset ΔVp, etc.) can be used in any combination as injection parameters Prj. In addition, for example, other parameters besides these parameters can also be used as injection parameters Prj.

[0249] Furthermore, in the above embodiments, the case where the pulses (pulses Pa, Pb, Pc) that expand the volume in each ejection channel are pulses that expand during the high state (positive pulses) has been described, but this is not a limitation. That is, not only can the pulses be configured to expand during the high state and contract during the low state, but conversely, they can also be configured to expand during the low state and contract during the high state (negative pulses). Moreover, in the case of such negative pulses, such a "common drive" can also be applied as long as it is a method that performs the same function as the aforementioned "common drive".

[0250] Furthermore, for example, during the off-state period immediately following the ON period, a pulse for assisting droplet ejection may be additionally applied. Examples of pulses assisting droplet ejection include pulses for contracting the volume within each ejection channel or pulses for pulling back a portion of the ejected droplet (auxiliary pulses). Additionally, the pulse applied immediately preceding the latter auxiliary pulse (the main pulse) has a pulse width, for example, less than the width of the ON pulse peak value (AP). Moreover, even if an additional pulse is applied to assist the ejection of such a droplet, it will not affect the content of this disclosure described so far.

[0251] Furthermore, the series of processes described in the above embodiments can be performed by hardware (circuit) or by software (program). In the case of software, the software consists of a set of programs for executing various functions via a computer. Each program can be used, for example, pre-loaded into the computer, or installed from a network or recording medium. Moreover, examples of recording media (non-transitory computer-readable recording media) for recording such programs include floppy disks (registered trademark), CD (Compact Disk)-ROM, DVD (Digital Versatile Disc)-ROM, hard disks, and various other media.

[0252] Furthermore, while the printer 1 (inkjet printer) was cited as a specific example of the "liquid jet recording apparatus" in the above embodiments, it is not limited to this example and can be applied to other devices besides inkjet printers. In other words, the "liquid jet head" (inkjet head) of this disclosure can also be applied to other devices besides inkjet printers. Specifically, for example, the "liquid jet head" of this disclosure can also be applied to devices such as fax machines or on-demand printing machines.

[0253] Furthermore, the various examples described so far can be applied in any combination.

[0254] Furthermore, the effects described in this specification are illustrative only and not limiting; other effects may also exist.

[0255] In addition, this disclosure can also be configured as follows. (1) A jet parameter generation system is a system for generating predetermined jet parameters, which are used in generating a drive signal having one or more pulses applied to a jetting section of the jetting liquid. The aforementioned injection parameter generation system has the following features: The data acquisition unit acquires predetermined input parameters and selection indication signals from external inputs as input data; and The parameter generation unit uses a predetermined analysis method that sets the aforementioned predetermined input parameters as explanatory variables and the aforementioned predetermined injection parameters as target variables to generate the aforementioned predetermined injection parameters based on the aforementioned selection indication signal and the aforementioned predetermined input parameters. The aforementioned parameter generation section: Regarding the voltage value of the peak value of the aforementioned pulse in the aforementioned drive signal, it is determined which of the aforementioned first and second references to select is based on the aforementioned selection indication signal indicating which reference is selected as the first reference and the second reference. The aforementioned first reference is a reference used to set the voltage value for obtaining the droplet quantity of the aforementioned liquid that becomes the reference, and the aforementioned second reference is a reference used to set the voltage value for obtaining the ejection velocity of the aforementioned liquid that becomes the reference. If the selection of the first benchmark is determined, the first set of explanatory variables included in the predetermined input parameters is selected as the aforementioned explanatory variables. Conversely, if the selection of the second benchmark is determined, the second set of explanatory variables included in the predetermined input parameters is selected as the aforementioned explanatory variables. The aforementioned predetermined injection parameters are generated by using only one of the aforementioned first or second set of explanatory variables and the aforementioned predetermined analysis method. (2) As described in (1) above, the injection parameter generation system, wherein, As mentioned above, the predetermined injection parameters It includes at least the voltage sensitivity of the aforementioned liquid, which is equivalent to the change in voltage per unit of the droplet volume or the ejection velocity of the aforementioned liquid when it is sprayed at a reference temperature. (3) As described in (2) above, the injection parameter generation system, wherein, As the first set of explanatory variables mentioned above, This includes at least the target value for the droplet volume of the aforementioned liquid. Furthermore, the aforementioned second set of explanatory variables includes at least one of the following parameters: The parameters indicating whether there is a common drive in the aforementioned drive signals are shown; and This is equivalent to the number of pulses included in a unit period of the aforementioned driving signal, or the number of drops. (4) As described in (3) above, the injection parameter generation system, As the first set of explanatory variables mentioned above, it also includes the aforementioned number of falls. Furthermore, as part of the aforementioned second set of explanatory variables, it also includes at least one parameter from the following: The head grade value is equivalent to the voltage value at which a predetermined ejection speed is achieved when a predetermined inspection liquid is ejected from the aforementioned spray section, and is a value inherent to a liquid spray head having the aforementioned spray section. The parameters for the aforementioned types of liquid injection heads are shown; The specific gravity of the aforementioned liquid; The surface tension value of the aforementioned liquid; The viscosity of the aforementioned liquid at the reference temperature; and The target value for the ejection rate of the aforementioned liquid. (5) As described in (3) or (4) above, the injection parameter generation system, wherein, The conversion process used in generating the aforementioned driving signal, from the measured characteristic curve of the viscosity versus temperature of the aforementioned liquid to the predicted characteristic curve of the voltage versus temperature, includes: Using the conversion coefficients used in the aforementioned conversion process, a preliminary characteristic curve showing the relationship between the aforementioned voltage value and temperature is generated from the aforementioned measured characteristic curve. The predicted characteristic curve is generated by adding the voltage offset to the aforementioned voltage values ​​in the aforementioned preliminary characteristic curve. As at least one of the aforementioned first set of explanatory variables and the aforementioned second set of explanatory variables, it also includes the aforementioned voltage offset. (6) As described in any of (1) to (5) above, the injection parameter generation system, wherein, The conversion process used in generating the aforementioned driving signal, from the measured characteristic curve of the viscosity versus temperature of the aforementioned liquid to the predicted characteristic curve of the voltage versus temperature, includes: Using the conversion coefficients used in the aforementioned conversion process, a preliminary characteristic curve showing the relationship between the aforementioned voltage value and temperature is generated from the aforementioned measured characteristic curve; and The predicted characteristic curve is generated by adding the voltage offset to the aforementioned voltage values ​​in the aforementioned preliminary characteristic curve. As the aforementioned predetermined injection parameters, at least the aforementioned conversion coefficient is included. (7) As described in (6) above, the injection parameter generation system, The first set of explanatory variables mentioned above includes at least one parameter from the following: The specific gravity of the aforementioned liquid; This is equivalent to the number of pulses included in a unit period of the aforementioned driving signal, or the number of drops. The viscosity value of the aforementioned liquid at the reference temperature; The target value for the ejection rate of the aforementioned liquid; The aforementioned voltage offset; The voltage sensitivity of the aforementioned liquid; This shows the parameters indicating whether there is a common drive among the aforementioned drive signals; The surface tension value of the aforementioned liquid; The head grade value is equivalent to the voltage value at which a predetermined ejection speed is achieved when a predetermined inspection liquid is ejected from the aforementioned spray section, and is a value inherent to a liquid spray head having the aforementioned spray section. The parameters for the aforementioned types of liquid injection heads are shown; and The parameters show the types of the aforementioned liquids classified according to their primary solvent. Furthermore, the aforementioned second set of explanatory variables includes at least one parameter from the following: The specific gravity of the aforementioned liquid; The viscosity value of the aforementioned liquid at the reference temperature; The aforementioned number of locations; The aforementioned voltage offset; The voltage sensitivity of the aforementioned liquid; The parameters for the aforementioned types of liquids are shown; The surface tension value of the aforementioned liquid; and The aforementioned head level value. (8) As described in any of (1) to (7) above, the injection parameter generation system, wherein, The conversion process used in generating the aforementioned driving signal, from the measured characteristic curve of the viscosity versus temperature of the aforementioned liquid to the predicted characteristic curve of the voltage versus temperature, includes: Using the conversion coefficients used in the aforementioned conversion process, a preliminary characteristic curve showing the relationship between the aforementioned voltage value and temperature is generated from the aforementioned measured characteristic curve; and The predicted characteristic curve is generated by adding the voltage offset to the aforementioned voltage values ​​in the aforementioned preliminary characteristic curve. As the aforementioned predetermined injection parameters, at least the aforementioned voltage offset is included. (9) As described in (8) above, the injection parameter generation system, The first set of explanatory variables mentioned above includes at least one parameter from the following: This shows the parameters indicating whether there is a common drive among the aforementioned drive signals; The viscosity value of the aforementioned liquid at the reference temperature; The head grade value is equivalent to the voltage value at which a predetermined ejection speed is achieved when a predetermined inspection liquid is ejected from the aforementioned spray section, and is a value inherent to a liquid spray head having the aforementioned spray section. The parameters for the aforementioned types of liquid injection heads are shown; The specific gravity of the aforementioned liquid; The surface tension value of the aforementioned liquid; The voltage sensitivity of the aforementioned liquid; The target value for the ejection rate of the aforementioned liquid; The parameters showing the types of the aforementioned liquids classified according to their primary solvent are as follows: This is equivalent to the number of pulses included in a unit period of the aforementioned driving signal, or the number of drops. Furthermore, the aforementioned second set of explanatory variables includes at least one parameter from the following: The voltage sensitivity of the aforementioned liquid; The viscosity value of the aforementioned liquid at the reference temperature; The aforementioned head level value; The parameters for the aforementioned types of liquid injection heads are shown; The surface tension value of the aforementioned liquid; The specific gravity of the aforementioned liquid; This shows the parameters indicating whether there is a common drive among the aforementioned drive signals; The target value for the ejection rate of the aforementioned liquid; The aforementioned number of locations; and The parameters for the aforementioned types of liquids are shown. (10) As described in any of (1) to (9) above, the injection parameter generation system, wherein, The aforementioned established analysis method is a method that uses a machine learning model, which is input with the aforementioned established input parameters and outputs the aforementioned established injection parameters. (11) The injection parameter generation system described in any of (1) to (10) above further comprises: The table generation unit uses at least one of the aforementioned predetermined injection parameters to perform a conversion process from the measured characteristic curve of the liquid's viscosity versus temperature to the predicted characteristic curve of the voltage value versus temperature, thereby generating a predicted voltage characteristic table of the predicted characteristic curve based on a measured viscosity characteristic table specifying the aforementioned measured characteristic curve; and The signal generation unit uses the aforementioned predicted voltage characteristic table generated by the aforementioned table generation unit to determine the peak value of the aforementioned pulse, and uses the aforementioned pulse having the determined aforementioned peak value to generate the aforementioned drive signal. (12) As described in any of (1) to (11) above, the injection parameter generation system, wherein, The aforementioned data acquisition unit and the aforementioned parameter generation unit are respectively housed in an external device, which is located outside the liquid jet recording device that has a built-in liquid jet head with the aforementioned jetting unit. (13) As described in any of (1) to (11) above, the injection parameter generation system, wherein, The aforementioned data acquisition unit and the aforementioned parameter generation unit, Each is installed in a liquid jet recording device that has a built-in liquid jet head with the aforementioned jet section. (14) As described in (13) above, the injection parameter generation system, The aforementioned data acquisition unit and the aforementioned parameter generation unit, They are respectively installed inside the aforementioned liquid injection head. (15) A method for generating injection parameters is a method for generating predetermined injection parameters, which are used when generating a drive signal having one or more pulses applied to a jetting section of the ejected liquid. The aforementioned methods for generating injection parameters include: The predetermined input parameters and the selection indication signal from the external input are respectively obtained as input data; and Using a predetermined analysis method that sets the aforementioned predetermined input parameters as explanatory variables and the aforementioned predetermined injection parameters as objective variables, the aforementioned predetermined injection parameters are generated based on the aforementioned selection indication signal and the aforementioned predetermined input parameters. When generating the aforementioned predetermined injection parameters: Regarding the voltage value of the peak value of the aforementioned pulse in the aforementioned drive signal, it is determined which of the aforementioned first and second references to select is based on the aforementioned selection indication signal indicating which reference is selected as the first reference and the second reference. The aforementioned first reference is a reference used to set the voltage value for obtaining the droplet quantity of the aforementioned liquid that becomes the reference, and the aforementioned second reference is a reference used to set the voltage value for obtaining the ejection velocity of the aforementioned liquid that becomes the reference. If the selection of the first benchmark is determined, the first set of explanatory variables included in the predetermined input parameters is selected as the aforementioned explanatory variables. Conversely, if the selection of the second benchmark is determined, the second set of explanatory variables included in the predetermined input parameters is selected as the aforementioned explanatory variables. The aforementioned predetermined injection parameters are generated by using only one of the aforementioned first or second set of explanatory variables and the aforementioned predetermined analysis method. (16) A jet parameter generation program is a program for generating predetermined jet parameters, which are used when generating a drive signal having one or more pulses applied to the jetting part of the jetting liquid. The aforementioned injection parameter generation program is executed by the computer: The predetermined input parameters and the selection indication signal from the external input are respectively obtained as input data; and Using a predetermined analysis method that sets the aforementioned predetermined input parameters as explanatory variables and the aforementioned predetermined injection parameters as objective variables, the aforementioned predetermined injection parameters are generated based on the aforementioned selection indication signal and the aforementioned predetermined input parameters. Furthermore, when generating the aforementioned predetermined injection parameters: Regarding the voltage value of the peak value of the aforementioned pulse in the aforementioned drive signal, it is determined which of the aforementioned first and second references to select is based on the aforementioned selection indication signal indicating which reference is selected as the first reference and the second reference. The aforementioned first reference is a reference used to set the voltage value for obtaining the droplet quantity of the aforementioned liquid that becomes the reference, and the aforementioned second reference is a reference used to set the voltage value for obtaining the ejection velocity of the aforementioned liquid that becomes the reference. If the selection of the first benchmark is determined, the first set of explanatory variables included in the predetermined input parameters is selected as the aforementioned explanatory variables. Conversely, if the selection of the second benchmark is determined, the second set of explanatory variables included in the predetermined input parameters is selected as the aforementioned explanatory variables. The aforementioned predetermined injection parameters are generated by using only one of the aforementioned first or second set of explanatory variables and the aforementioned predetermined analysis method. (17) A recording medium is a non-transitory computer-readable recording medium that records a program for generating predetermined injection parameters, which are used in generating a drive signal having one or more pulses applied to a jetting section of the jetting liquid. The recording medium records the injection parameter generation program. The aforementioned program for generating injection parameters is executed by the computer: The predetermined input parameters and the selection indication signal from the external input are respectively obtained as input data; and Using a predetermined analysis method that sets the aforementioned predetermined input parameters as explanatory variables and the aforementioned predetermined injection parameters as objective variables, the aforementioned predetermined injection parameters are generated based on the aforementioned selection indication signal and the aforementioned predetermined input parameters. Furthermore, the aforementioned injection parameter generation program, when generating the aforementioned predetermined injection parameters: Regarding the voltage value of the peak value of the aforementioned pulse in the aforementioned drive signal, it is determined which of the aforementioned first and second references to select is based on the aforementioned selection indication signal indicating which reference is selected as the first reference and the second reference. The aforementioned first reference is a reference used to set the voltage value for obtaining the droplet quantity of the aforementioned liquid that becomes the reference, and the aforementioned second reference is a reference used to set the voltage value for obtaining the ejection velocity of the aforementioned liquid that becomes the reference. If the selection of the first benchmark is determined, the first set of explanatory variables included in the predetermined input parameters is selected as the aforementioned explanatory variables. Conversely, if the selection of the second benchmark is determined, the second set of explanatory variables included in the predetermined input parameters is selected as the aforementioned explanatory variables. The aforementioned predetermined injection parameters are generated by using only one of the aforementioned first or second set of explanatory variables and the aforementioned predetermined analysis method.

[0273] [Symbol Explanation] 1, 1B, 1C... Printer; 10... Frame; 2a, 2b... Conveyor mechanism; 21... Grid roller; 22... Pinch roller; 3 (3Y, 3M, 3C, 3K)... Ink tank; 30... Ink supply pipe; 4 (4Y, 4M, 4C, 4K), 4B... Inkjet head; 41... Nozzle plate; 42... Actuator plate; 48... Signal generation unit; 49... Drive unit; 5, 5A, 5B, 5C... Ejection parameter generation system; 50... Network; 6... Scanning mechanism; 61a, 61b ...guide rail, 62...carriage, 63...drive mechanism, 631a, 631b...pulleys, 632...seamless belt, 633...drive motor, 7, 7A...information processing unit, 70...bus, 71...input unit, 72...display unit, 73, 73D...information processing unit, 730, 730D...program, 731...data acquisition unit, 732...parameter generation unit, 733...table generation unit, 74, 74A, 74B...machine learning model, 75...control unit, 76... …Storage section, 77…Network IF, 8…Server, 80…Bus, 85…Control section, 86…Storage section, 87…Network IF, 9…Ink, P…Recording paper, d…Transport direction, Hn…Nozzle orifice, Sd…Drive signal, Vd…Drive voltage, Vr…Voltage sensitivity, Ta…Ambient temperature, Tr…Reference temperature, Iv…Viscosity information, Vi…Viscosity, ΔV…Differential value, ΔVp…Voltage offset, Wp, Wpa1, Wpa2, Wpa 3. Wpb2, Wpb3, Wpc3…Pulse width; Vp, Vp1, Vp2, Vp3…Voltage value (peak value); Pa, Pb, Pc…Pulse; Ss…Selection indicator signal; Prin…Input parameter; Prj…Injection parameter; Kc…Conversion coefficient; TMvi…Measured viscosity characteristic table; TPvp…Predicted voltage characteristic table; CMvi, CMvp…Measured characteristic curve; CPvp0…Preliminary characteristic curve; CPvp…Predicted characteristic curve; t…Time.

Claims

1. A jet parameter generation system, which generates predetermined jet parameters used when generating a drive signal having one or more pulses applied to a jetting section of the jetting liquid. The injection parameter generation system includes: The data acquisition unit acquires predetermined input parameters and selection indication signals from external inputs as input data; and The parameter generation unit uses a predetermined analysis method that sets the predetermined input parameters as explanatory variables and the predetermined injection parameters as target variables to generate the predetermined injection parameters based on the selection indication signal and the predetermined input parameters. The parameter generation unit: Regarding the voltage value indicating the peak value of the pulse in the drive signal, the selection of either the first or second reference is determined based on the selection indication signal indicating which reference is chosen as the first or second reference. The first reference is a reference used to set a voltage value for obtaining the droplet quantity of the liquid that becomes the reference, and the second reference is a reference used to set a voltage value for obtaining the ejection velocity of the liquid that becomes the reference. If the first benchmark is selected, the first set of explanatory variables included in the predetermined input parameters is selected as the explanatory variable; conversely, if the second benchmark is selected, the second set of explanatory variables included in the predetermined input parameters is selected as the explanatory variable. The predetermined injection parameters are generated by using only one of the selected first or second set of explanatory variables and the predetermined analysis method.

2. The injection parameter generation system according to claim 1, wherein: As the predetermined injection parameters It includes at least the voltage sensitivity of the liquid, which is equivalent to the change in voltage per unit of the droplet volume or the ejection velocity of the liquid when the liquid is sprayed at a reference temperature.

3. The injection parameter generation system according to claim 2, wherein, As the first set of explanatory variables It should include at least the target value for the amount of liquid droplets. Furthermore, the second set of explanatory variables includes at least one of the following parameters: The parameters indicating whether there is a common drive in the drive signals are shown; and This is equivalent to the number of pulses included in a unit period of the driving signal, or the number of drops.

4. The injection parameter generation system according to claim 3, wherein, The first set of explanatory variables also includes the number of drops. Furthermore, as the second set of explanatory variables, it also includes at least one parameter from the following: The head grade value is equivalent to the voltage value at a predetermined ejection rate when a predetermined inspection liquid is ejected from the jet section, and is a value inherent to the liquid jet head having the jet section; The parameters indicating the type of liquid injection head are shown; The specific gravity of the liquid; The surface tension value of the liquid; The viscosity of the liquid at a reference temperature; and The target value for the rate at which the liquid is ejected.

5. The injection parameter generation system according to claim 3 or claim 4, wherein, The conversion process used in generating the drive signal, from the measured characteristic curve of the viscosity versus temperature of the liquid to the predicted characteristic curve of the voltage versus temperature, includes: Using the conversion coefficients used in the conversion process, a preliminary characteristic curve showing the relationship between the voltage value and temperature is generated from the measured characteristic curve; and The predicted characteristic curve is generated by adding the voltage offset to the voltage values ​​in the preliminary characteristic curve. As at least one of the first set of explanatory variables and the second set of explanatory variables, the voltage offset is also included.

6. The injection parameter generation system according to any one of claims 1 to 4, wherein, The conversion process used in generating the drive signal, from the measured characteristic curve of the viscosity versus temperature of the liquid to the predicted characteristic curve of the voltage versus temperature, includes: Using the conversion coefficients used in the conversion process, a preliminary characteristic curve showing the relationship between the voltage value and temperature is generated from the measured characteristic curve; and The predicted characteristic curve is generated by adding the voltage offset to the voltage values ​​in the preliminary characteristic curve. The predetermined injection parameters include at least the conversion coefficient.

7. The injection parameter generation system according to any one of claims 1 to 4, wherein, The conversion process used in generating the drive signal, from the measured characteristic curve of the viscosity versus temperature of the liquid to the predicted characteristic curve of the voltage versus temperature, includes: Using the conversion coefficients used in the conversion process, a preliminary characteristic curve showing the relationship between the voltage value and temperature is generated from the measured characteristic curve; and The predicted characteristic curve is generated by adding the voltage offset to the voltage values ​​in the preliminary characteristic curve. The predetermined injection parameters include at least the voltage offset.

8. The injection parameter generation system according to any one of claims 1 to 4, wherein, The established analysis method is a method that uses a machine learning model, which is input with the established input parameters and outputs the established injection parameters.

9. The injection parameter generation system according to any one of claims 1 to 4, wherein, It also has: The table generation unit uses at least one of the predetermined injection parameters to perform a conversion process from the measured characteristic curve between the viscosity and temperature of the liquid to the predicted characteristic curve between the voltage value and temperature, thereby generating a predicted voltage characteristic table that specifies the predicted characteristic curve based on the measured viscosity characteristic table that specifies the measured characteristic curve. and The signal generation unit uses the predicted voltage characteristic table generated by the table generation unit to determine the peak value of the pulse, and uses the pulse having the determined peak value to generate the drive signal.

10. The injection parameter generation system according to any one of claims 1 to 4, wherein, The data acquisition unit and the parameter generation unit are respectively housed in an external device, which is located outside the liquid jet recording device that has a built-in liquid jet head with the jetting unit.

11. The injection parameter generation system according to any one of claims 1 to 4, wherein, The data acquisition unit and the parameter generation unit Each is installed in a liquid jet recording device that has a built-in liquid jet head with the jet section.

12. The injection parameter generation system according to claim 11, wherein, The data acquisition unit and the parameter generation unit They are respectively installed inside the liquid injection head.

13. A method for generating injection parameters, wherein predetermined injection parameters are used when generating a drive signal having one or more pulses applied to a jetting section of the jetting liquid. The method for generating injection parameters includes: The predetermined input parameters and the selection indication signal from the external input are respectively obtained as input data; and The predetermined injection parameters are generated based on the selection indication signal and the predetermined input parameters using a predetermined analysis method that sets the predetermined input parameters as explanatory variables and the predetermined injection parameters as target variables. When generating the given injection parameters: Regarding the voltage value indicating the peak value of the pulse in the drive signal, the selection of either the first or second reference is determined based on the selection indication signal indicating which reference is chosen as the first or second reference. The first reference is a reference used to set a voltage value for obtaining the droplet quantity of the liquid that becomes the reference, and the second reference is a reference used to set a voltage value for obtaining the ejection velocity of the liquid that becomes the reference. If the first benchmark is selected, the first set of explanatory variables included in the predetermined input parameters is selected as the explanatory variable; conversely, if the second benchmark is selected, the second set of explanatory variables included in the predetermined input parameters is selected as the explanatory variable. The predetermined injection parameters are generated by using only one of the selected first or second set of explanatory variables and the predetermined analysis method.

14. A jet parameter generation program, which generates predetermined jet parameters used when generating a drive signal having one or more pulses applied to a jetting part of the jetting liquid. The injection parameter generation program is executed by the computer: The predetermined input parameters and the selection indication signal from the external input are respectively obtained as input data; and The predetermined injection parameters are generated based on the selection indication signal and the predetermined input parameters using a predetermined analysis method that sets the predetermined input parameters as explanatory variables and the predetermined injection parameters as target variables. Furthermore, when generating the predetermined injection parameters: Regarding the voltage value indicating the peak value of the pulse in the drive signal, the selection of either the first or second reference is determined based on the selection indication signal indicating which reference is chosen as the first or second reference. The first reference is a reference used to set a voltage value for obtaining the droplet quantity of the liquid that becomes the reference, and the second reference is a reference used to set a voltage value for obtaining the ejection velocity of the liquid that becomes the reference. If the first benchmark is selected, the first set of explanatory variables included in the predetermined input parameters is selected as the explanatory variable; conversely, if the second benchmark is selected, the second set of explanatory variables included in the predetermined input parameters is selected as the explanatory variable. The predetermined injection parameters are generated by using only one of the selected first or second set of explanatory variables and the predetermined analysis method.

Images