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

Abstract

To provide an injection parameter generation system, etc. capable of improving convenience of a user.SOLUTION: An injection parameter generation system includes: a data acquisition unit; and a parameter generation unit for generating a predetermined injection parameter using a predetermined analysis method with a predetermined input parameter as an explanatory variable, and with a predetermined injection parameter as an objective variable. The parameter generation part determines which standard is to be selected out of, a first standard for setting a voltage value to a voltage value by which a standard liquid droplet quantity is obtained and a second standard for setting a voltage value to a voltage value by which a standard liquid discharge speed is obtained, and when it is determined that the first standard is to be selected, selects a first explanatory variable group while when it is determined that the second standard is to be selected, the parameter generation part selects a second explanatory variable group. The parameter generation part generates the predetermined injection parameter by using the predetermined analysis method using only one of the selected first and second explanatory variable groups.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present disclosure relates to an injection parameter generation system, an injection parameter generation method, and an injection parameter generation program. [Background technology]

[0002] Liquid jet recording apparatuses equipped with liquid jet heads are used in a variety of fields, and various types of liquid jet heads have been developed (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2016-203393 Summary of the Invention [Problem to be solved by the invention]

[0004] In such a liquid jet head, there is a demand for improving user convenience. It is desirable to provide a jetting parameter generation system, a jetting parameter generation method, and a jetting parameter generation program that can improve user convenience. [Means for solving the problem]

[0005] An ejection parameter generation system according to one embodiment of the present disclosure is a system for generating predetermined ejection parameters that are applied to an ejection unit that ejects liquid and are used when generating a drive signal having one or more pulses, and includes: a data acquisition unit that acquires a selection instruction signal input from outside and predetermined input parameters as input data; and a parameter generation unit that generates the predetermined ejection parameters based on the selection instruction signal and the predetermined input parameters using a predetermined analysis method that uses the predetermined input parameters as explanatory variables and the predetermined ejection parameters as target variables. The parameter generation unit determines which of the first and second criteria to select based on the selection instruction signal indicating which of the following criteria has been selected: a first criteria for setting the voltage value indicating the peak value of the pulse in the drive signal to a voltage value at which a reference droplet volume of the liquid is obtained, and a second criteria for setting the voltage value at which a reference ejection speed of the liquid is obtained; and if it determines to select the first criteria, it selects a first group of explanatory variables included in the specified input parameters as the explanatory variables, while if it determines to select the second criteria, it selects a second group of explanatory variables included in the specified input parameters as the explanatory variables, and generates the specified ejection parameters by utilizing the specified analysis method using only one of the selected first or second groups of explanatory variables.

[0006] An ejection parameter generation method according to one embodiment of the present disclosure is a method for generating predetermined ejection parameters that are applied to an ejection section that ejects liquid and are used when generating a drive signal having one or more pulses, and includes acquiring a selection instruction signal input from outside and predetermined input parameters as input data, and generating the predetermined ejection parameters based on the selection instruction signal and the predetermined input parameters using a predetermined analysis method that uses the predetermined input parameters as explanatory variables and the predetermined ejection parameters as target variables. When generating the predetermined ejection parameters, a determination is made as to which of the first and second criteria to select based on the selection instruction signal indicating which of the following criteria has been selected: a first criteria for setting the voltage value indicating the peak value of the pulse in the drive signal to a voltage value at which a reference droplet volume of the liquid is obtained, and a second criteria for setting the voltage value at which a reference ejection speed of the liquid is obtained; and if it is determined that the first criteria should be selected, a first group of explanatory variables included in the predetermined input parameters is selected as the explanatory variables, while if it is determined that the second criteria should be selected, a second group of explanatory variables included in the predetermined input parameters is selected as the explanatory variables, and the predetermined ejection parameters are generated by utilizing the predetermined analysis method using only one of the selected first or second groups of explanatory variables.

[0007] An ejection parameter generation program according to one embodiment of the present disclosure is a program for generating predetermined ejection parameters that are applied to an ejection unit that ejects liquid and are used when generating a drive signal having one or more pulses, and is configured to cause a computer to acquire a selection instruction signal input from outside and predetermined input parameters as input data, and generate the predetermined ejection parameters based on the selection instruction signal and the predetermined input parameters using a predetermined analysis method that uses the predetermined input parameters as explanatory variables and the predetermined ejection parameters as target variables. When generating the predetermined ejection parameters, a determination is made as to which of the first and second criteria to select based on the selection instruction signal indicating which of the following criteria has been selected: a first criteria for setting the voltage value indicating the peak value of the pulse in the drive signal to a voltage value at which a reference droplet volume of the liquid is obtained, and a second criteria for setting the voltage value at which a reference ejection speed of the liquid is obtained; and if it is determined that the first criteria should be selected, a first group of explanatory variables included in the predetermined input parameters is selected as the explanatory variables, while if it is determined that the second criteria should be selected, a second group of explanatory variables included in the predetermined input parameters is selected as the explanatory variables, and the predetermined ejection parameters are generated by utilizing the predetermined analysis method using only one of the selected first or second groups of explanatory variables. [Effects of the Invention]

[0008] According to the injection parameter generation system, the injection parameter generation method, and the injection parameter generation program according to an embodiment of the present disclosure, it is possible to improve user convenience. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a schematic perspective view illustrating an example of a schematic configuration of a liquid jet recording apparatus according to an embodiment of the present disclosure. [Figure 2]2 is a schematic diagram illustrating an example of a schematic configuration of the liquid jet head illustrated in FIG. 1. [Figure 3] FIG. 1 is a functional block diagram illustrating an example of the configuration of an injection parameter generation system according to an embodiment. [Figure 4] FIG. 4 is a physical block diagram illustrating an example of the configuration of the information processing device illustrated in FIG. 3. [Figure 5] FIG. 5 is a block diagram illustrating an example of a detailed configuration of the machine learning model illustrated in FIGS. 3 and 4. [Figure 6] FIG. 4 is a timing diagram schematically illustrating an example of the configuration of a drive signal. [Figure 7] FIG. 4 is a diagram illustrating an example of predetermined input parameters according to the embodiment. [Figure 8] FIG. 10 is a diagram illustrating an example of an analysis result of the importance of each input parameter according to Comparative Example 1. [Figure 9A] FIG. 10 is a diagram illustrating an example of a correspondence relationship between an SVM predicted value and an actual measurement value according to Comparative Example 1. [Figure 9B] FIG. 10 is a diagram illustrating an example of a correspondence relationship between an RF predicted value and an actual measurement value according to Comparative Example 1. [Figure 10] 6 is a flowchart illustrating an example of a process for generating an injection parameter according to an embodiment. [Figure 11A] FIG. 10 is a diagram illustrating an example of an importance analysis result of a first explanatory variable group according to the embodiment. [Figure 11B] FIG. 10 is a diagram illustrating an example of an importance analysis result of a second explanatory variable group according to the embodiment. [Figure 12A] 11B is a diagram illustrating an example of the correspondence between SVM predicted values ​​and actual measured values ​​when only the first explanatory variable group shown in FIG. 11A is used. FIG. [Figure 12B] 11B is a diagram illustrating an example of the correspondence relationship between RF predicted values ​​and actual measured values ​​when only the first explanatory variable group shown in FIG. 11A is used. FIG. [Figure 13A] FIG. 11C is a diagram illustrating an example of the correspondence between SVM predicted values ​​and actual measured values ​​when only the second explanatory variable group shown in FIG. 11B is used. [Figure 13B] FIG. 11C is a diagram illustrating an example of the correspondence relationship between RF predicted values ​​and actual measured values ​​when only the second explanatory variable group shown in FIG. 11B is used. [Figure 14] FIG. 10 is a block diagram illustrating an example of the configuration of a machine learning model according to Modification 1. [Figure 15] FIG. 10 is a block diagram illustrating an example of the schematic configuration of a liquid jet recording apparatus according to Comparative Example 2. [Figure 16] FIG. 10 is a diagram illustrating an example of viscosity information according to Comparative Example 2. [Figure 17] 10 is a diagram illustrating an example of various characteristic curves according to Comparative Example 2. FIG. [Figure 18] 10 is a flowchart illustrating an example of a conversion process according to Modification 1. [Figure 19] 10A and 10B are diagrams illustrating examples of various characteristic curves according to Modification 1. [Figure 20] FIG. 10 is a diagram illustrating an example of predetermined input parameters according to Modification 1. [Figure 21] 10 is a flowchart showing a process of generating a characteristic table according to Modification 1. [Figure 22] FIG. 11 is a diagram illustrating an example of an importance analysis result of each input parameter according to Comparative Example 3. [Figure 23A] FIG. 10 is a diagram illustrating an example of the results of an importance analysis of a first explanatory variable group according to Modification 1. [Figure 23B] FIG. 10 is a diagram illustrating an example of the results of an importance analysis of a second explanatory variable group according to Modification 1. [Figure 24A] FIG. 23B is a diagram illustrating an example of the correspondence between SVM predicted values ​​and actual measured values ​​when only the first explanatory variable group shown in FIG. 23A is used. [Figure 24B] FIG. 23B is a diagram illustrating an example of the correspondence relationship between RF predicted values ​​and actual measured values ​​when only the first explanatory variable group shown in FIG. 23A is used. [Figure 25A] FIG. 23C is a diagram illustrating an example of the correspondence between SVM predicted values ​​and actual measured values ​​when only the second explanatory variable group shown in FIG. 23B is used. [Figure 25B] FIG. 23C is a diagram illustrating an example of the correspondence relationship between RF predicted values ​​and actual measured values ​​when only the second explanatory variable group shown in FIG. 23B is used. [Figure 26] FIG. 10 is a block diagram illustrating an example of the configuration of a machine learning model according to Modification 2. [Figure 27] FIG. 10 is a diagram illustrating an example of predetermined input parameters according to Modification 2. [Figure 28] FIG. 13 is a diagram illustrating an example of an analysis result of the importance of each input parameter according to Comparative Example 4. [Figure 29A] FIG. 10 is a diagram illustrating an example of the results of an importance analysis of a first explanatory variable group according to Modification 2. [Figure 29B] FIG. 10 is a diagram illustrating an example of the results of an importance analysis of a second explanatory variable group according to Modification 2. [Figure 30A] FIG. 29B is a diagram illustrating an example of the correspondence between SVM predicted values ​​and actual measured values ​​when only the first explanatory variable group shown in FIG. 29A is used. [Figure 30B] FIG. 29B is a diagram illustrating an example of the correspondence relationship between RF predicted values ​​and actual measured values ​​when only the first explanatory variable group shown in FIG. 29A is used. [Figure 31A] FIG. 29C is a diagram illustrating an example of the correspondence between SVM predicted values ​​and actual measured values ​​when only the second explanatory variable group shown in FIG. 29B is used. [Figure 31B] FIG. 29C is a diagram illustrating an example of the correspondence relationship between RF predicted values ​​and actual measured values ​​when only the second explanatory variable group shown in FIG. 29B is used. [Figure 32] FIG. 11 is a block diagram showing an example of the configuration of an injection parameter generation system according to a third modification. [Figure 33] FIG. 10 is a block diagram showing an example of the configuration of an injection parameter generation system according to a fourth modified example. [Figure 34] FIG. 13 is a block diagram showing an example of the configuration of an injection parameter generation system according to a fifth modified example. [Figure 35] FIG. 13 is a block diagram illustrating an example of the configuration of an information processing unit according to Modification 6. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. The description will be made in the following order. 1. Embodiment (Example in which the information processing section is provided in an information processing device outside the liquid jet recording device) 2. Variations Modification 1 (Example in which the predetermined injection parameter is a conversion coefficient) Modification 2 (Example in which the predetermined injection parameter is the voltage shift amount) Modification 3 (Example in which the information processing unit is provided in a server external to the liquid jet recording apparatus) Modification 4 (Example in which the information processing section is provided inside the liquid jet head in the liquid jet recording apparatus) Modification 5 (Example in which the information processing section is provided outside the liquid jet head in the liquid jet recording apparatus) Modification 6 (Example in which a signal generating unit is further provided in the information processing unit) 3. Other Modifications

[0011] <1. Embodiment> [A. Overall configuration of Printer 1] 1 is a schematic perspective view showing an example of the general configuration of a printer 1 as a liquid jet recording apparatus according to an embodiment of the present disclosure. The printer 1 is an inkjet printer that records (prints) images, characters, etc. on recording paper P as a recording medium using ink 9, which will be described later.

[0012] 1, the printer 1 includes a pair of transport mechanisms 2a and 2b, an ink tank 3, an ink supply pipe 30, an inkjet head 4, and a scanning mechanism 6. Each of these components is housed in a housing 10 having a predetermined shape. Note that in the drawings used in the description of this specification, the scale of each component has been appropriately changed so that each component is large enough to be recognizable.

[0013] Here, the printer 1 corresponds to a specific example of a "liquid jet recording apparatus" in the present disclosure, the inkjet heads 4 (inkjet heads 4Y, 4M, 4C, and 4K described below) correspond to a specific example of a "liquid jet head" in the present disclosure, and the ink 9 corresponds to a specific example of a "liquid" in the present disclosure.

[0014] As shown in Fig. 1, the transport mechanisms 2a and 2b are mechanisms that transport the recording paper P along the transport direction d (X-axis direction). Each of these transport mechanisms 2a and 2b has a grid roller 21, a pinch roller 22, and a drive mechanism (not shown). This drive mechanism is a mechanism that rotates the grid roller 21 around its axis (rotates it in the ZX plane), and is composed of, for example, a motor.

[0015] (Ink Tank 3) The ink tanks 3 are tanks that contain ink 9. In this example, as shown in FIG. 1, four types of ink tanks 3 are provided, each containing four colors of ink 9: yellow (Y), magenta (M), cyan (C), and black (K). That is, an ink tank 3Y that contains yellow ink 9, an ink tank 3M that contains magenta ink 9, an ink tank 3C that contains cyan ink 9, and an ink tank 3K that contains black ink 9 are provided. These ink tanks 3Y, 3M, 3C, and 3K are arranged side by side in the X-axis direction within the housing 10.

[0016] The ink tanks 3Y, 3M, 3C, and 3K have the same configuration except for the color of the ink 9 they contain, and therefore will be collectively referred to as ink tank 3 in the following description.

[0017] (inkjet head 4) The inkjet head 4 is a head that ejects (discharges) droplets of ink 9 onto recording paper P from a plurality of nozzles (nozzle holes Hn) described below to record (print) images, characters, etc. In this example, as shown in FIG. 1, the inkjet head 4 is provided with four types of heads that individually eject the four colors of ink 9 contained in the ink tanks 3Y, 3M, 3C, and 3K. That is, the inkjet head 4Y ejects yellow ink 9, the inkjet head 4M ejects magenta ink 9, the inkjet head 4C ejects cyan ink 9, and the inkjet head 4K ejects black ink 9. These inkjet heads 4Y, 4M, 4C, and 4K are arranged side by side along the Y-axis direction within the housing 10.

[0018] In addition, the inkjet heads 4Y, 4M, 4C, and 4K have the same configuration except for the color of ink 9 they use, and therefore will be collectively referred to as the inkjet head 4 below. An example of the detailed configuration of the inkjet head 4 will be described later (FIG. 2).

[0019] The ink supply pipe 30 is a pipe through which the ink 9 is supplied from the ink tank 3 to the inkjet head 4. The ink supply pipe 30 is made of, for example, a flexible hose that is flexible enough to follow the operation of the scanning mechanism 6, which will be described below.

[0020] (Scanning mechanism 6) The scanning mechanism 6 is a mechanism that scans the inkjet head 4 along the width direction (Y-axis direction) of the recording paper P. As shown in Fig. 1, the scanning mechanism 6 has a pair of guide rails 61a, 61b that extend along the Y-axis direction, a carriage 62 that is movably supported on these guide rails 61a, 61b, and a drive mechanism 63 that moves the carriage 62 along the Y-axis direction.

[0021] The drive mechanism 63 includes a pair of pulleys 631a, 631b arranged between the guide rails 61a, 61b, an endless belt 632 wound between the pulleys 631a, 631b, and a drive motor 633 that rotates the pulley 631a. The four types of inkjet heads 4Y, 4M, 4C, and 4K described above are arranged on the carriage 62 along the Y-axis.

[0022] The scanning mechanism 6 and the transport mechanisms 2a and 2b described above constitute a movement mechanism that moves the inkjet head 4 and the recording paper P relative to each other.

[0023] [B. Detailed Configuration of Inkjet Head 4] Next, a detailed configuration example of the inkjet head 4 will be described with reference to FIG.

[0024] FIG. 2 is a schematic diagram showing an example of the general configuration of the inkjet head 4. As shown in FIG.

[0025] As shown in FIG. 2, the inkjet head 4 includes a nozzle plate 41, an actuator plate 42, and a driving unit 49.

[0026] The nozzle plate 41 and the actuator plate 42 correspond to a specific example of an "ejection portion" in the present disclosure.

[0027] (Nozzle plate 41) The nozzle plate 41 is a plate made of a film material such as polyimide or a metal material, and as shown in Fig. 2, has a plurality of nozzle holes Hn that eject ink 9 (see the dashed arrows in Fig. 2). These nozzle holes Hn are aligned in a straight line (along the X-axis direction in this example) at predetermined intervals.

[0028] (actuator plate 42) The actuator plate 42 is a plate made of a piezoelectric material such as PZT (lead zirconate titanate). This actuator plate 42 is provided with a plurality of channels (not shown). These channels function as pressure chambers for applying pressure to the ink 9, and are arranged parallel to each other at a predetermined interval. Each channel is defined by a driving wall (not shown) made of a piezoelectric material, and is a concave groove portion in cross-sectional view.

[0029] These channels include ejection channels for ejecting ink 9 and dummy channels (non-ejection channels) that do not eject ink 9. In other words, the ejection channels are filled with ink 9, while the dummy channels are not filled with ink 9. Furthermore, each ejection channel communicates with a nozzle hole Hn in the nozzle plate 41, while each dummy channel does not communicate with the nozzle hole Hn. These ejection channels and dummy channels are arranged alternately along a predetermined direction.

[0030] The opposing inner surfaces of the drive walls are provided with drive electrodes (not shown). These drive electrodes include 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 dummy channel. These drive electrodes are electrically connected to the drive circuit on the drive substrate (not shown) via multiple extraction electrodes formed on a flexible substrate (not shown). This allows a drive voltage Vd (drive signal Sd) to be applied to each drive electrode from the drive circuit including the drive unit 49 via the flexible substrate.

[0031] (Driver 49) The drive unit 49 applies the drive voltage Vd (drive signal Sd) to the actuator plate 42 to expand or contract the ejection channels, thereby ejecting ink 9 from each nozzle hole Hn (performing an ejection operation) (see FIG. 2). Specifically, the drive unit 49 performs such an ejection operation using a drive signal Sd generated by a signal generation unit 48, which will be described later.

[0032] [C. Overall Configuration of Injection Parameter Generation System 5] Next, with reference to FIGS. 3 to 6, an example of the overall configuration of an ejection parameter generation system 5 (characteristic table generation system) configured to include the printer 1 having the inkjet head 4 described above will be described.

[0033] Fig. 3 is a block diagram (functional block diagram) showing an example of the configuration of the injection parameter generation system 5 according to this embodiment, and Fig. 4 is a block diagram (physical block diagram) showing an example of the configuration of the information processing device 7 (described later) shown in Fig. 3. Also, Fig. 5 is a block diagram showing an example of the detailed configuration of the machine learning model 74 shown in Figs. 3 and 4.

[0034] The injection parameter generation method (characteristic table generation method) according to this embodiment is embodied in the injection parameter generation system 5 (characteristic table generation system) according to this embodiment, and will be described below together. This also applies to the modified examples (modified examples 1 to 6) described later.

[0035] The ejection parameter generation system 5 is a system that generates predetermined ejection parameters Prj used when generating the drive signal Sd described above. In addition, this ejection parameter generation system 5 (characteristics table generation system) generates a predetermined predicted voltage characteristics table TPvp based on the ejection parameters Prj generated in this manner (see FIG. 3). As shown in FIG. 3, this ejection parameter generation system 5 includes a printer 1 having the inkjet head 4 described above, and an information processing device 7. In addition, the printer 1 and the information processing device 7 are connected to each other via a network 50.

[0036] Such a network 50 is a network that performs communication using, for example, a communication protocol (TCP / IP) that is commonly used on the Internet. This network 50 may also be a secure network that performs communication using a communication protocol unique to that network. This network 50 may also be, for example, the Internet, an intranet, or a local area network. The connection between this network 50 and the printer 1 and information processing device 7 may be, for example, a wired local area network (LAN) such as Ethernet (registered trademark), or a wireless LAN such as Wi-Fi (registered trademark), or a mobile phone line.

[0037] (Information processing device 7) The information processing device 7 is a device located outside the printer 1, and is configured by, for example, a PC (Personal Computer), etc. As shown in FIG. 3 (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.

[0038] Such an information processing device 7 corresponds to a specific example of an "external device" in the present disclosure.

[0039] The input unit 71 receives instructions from the outside (for example, a user) and outputs the received instructions to the information processing unit 73. Such an input unit 71 is configured by, for example, a keyboard, a mouse, etc. Furthermore, the input unit 71 may be configured by, for example, a touch panel provided on the display unit 72 (display surface) of the information processing device 7.

[0040] The display unit 72 displays an image based on a video signal output from the information processing unit 73. Such a display unit 72 is configured using a display of various types (for example, a liquid crystal display, a CRT (Cathode Ray Tube) display, an organic EL (Electro Luminescence) display, etc.).

[0041] The information processing unit 73 is a unit that performs various types of information processing, and as shown in Fig. 3, has a data acquisition unit 731, a parameter generation unit 732, and a table generation unit 733. As shown in Fig. 4 (physical block diagram), the information processing unit 73 is configured using a control unit 75, a storage unit 76, and a network IF (Interface) 77. In the example of Fig. 4, the input unit 71, display unit 72, control unit 75, storage unit 76, and network IF 77 are each connected to one another via a bus 70.

[0042] 3, the data acquiring unit 731 acquires the following data (input data) via the input unit 71, the network 50, etc. That is, the data acquiring unit 731 acquires, as input data, a predetermined measured viscosity characteristics table TMvi, a predetermined selection instruction signal Ss input from the outside, and predetermined input parameters Prin, which will be described later.

[0043] As shown in Fig. 3, the parameter generation unit 732 generates the aforementioned predetermined injection parameters Prj by using a predetermined analysis method based on the selection instruction signal Ss and the input parameters Prin acquired by the data acquisition unit 731. This predetermined analysis method is an analysis method that uses the aforementioned input parameters Prin as explanatory variables and the aforementioned injection parameters Prj as objective variables. In addition, in the example of this embodiment, as shown in Figs. 3 and 4, the parameter generation unit 732 generates the injection parameters Prj based on the input parameters Prin by utilizing an analysis method that uses a machine learning model 74, which will be described below.

[0044] As described above, such a machine learning model 74 is a prediction model obtained by performing machine learning using the input parameter Prin as an explanatory variable and the injection parameter Prj as a response variable. Furthermore, as shown in Fig. 5, when the input parameter Prin (explanatory variable) is input, the machine learning model 74 generates (predicts) the injection parameter Prj (response variable) based on the learning result, and outputs the generated injection parameter Prj.

[0045] Here, in this embodiment, a case will be mainly described in which the injection parameter Prj is generated so as to include at least a voltage sensitivity Vr, which will be described later, as an example of such an injection parameter Prj, as shown in Fig. 5. In other words, this voltage sensitivity Vr corresponds to a specific example of the "predetermined injection parameter" in the present disclosure.

[0046] Examples of analytical methods (prediction methods) using the above-mentioned machine learning model 74 include support vector machines (SVMs), random forests (RFs), and multiple regression analysis.

[0047] 3, the table generating unit 733 generates the predicted voltage characteristics table TPvp by performing a predetermined conversion process using at least one of the measured viscosity characteristics table TMvi acquired by the data acquiring unit 731 and the ejection parameters Prj generated by the parameter generating unit 732. The predicted voltage characteristics table TPvp generated in this manner is supplied to a signal generating unit 48 (described later) in the inkjet head 4 of the printer 1 via the network 50.

[0048] The above-described predetermined conversion process, the measured viscosity characteristics table TMvi, and the predicted voltage characteristics table TPvp will be described in detail in Modification 1. The details of each process in the information processing unit 73 (the data acquiring unit 731, the parameter generating unit 732, and the table generating unit 733) will also be described in detail later.

[0049] The control unit 75 shown in FIG. 4 is configured to include a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit), and executes, for example, various programs stored in a storage unit 76. Specifically, the control unit 75 executes a program 730 stored in the storage unit 76, for example, as shown in FIG. 4. This program 730 is a program for executing each process in the information processing unit 73 (data acquisition unit 731, parameter generation unit 732, and table generation unit 733). Specifically, this program 730 is a program for causing a computer (control unit 75) to execute each function in the information processing unit 73 (data acquisition unit 731, parameter generation unit 732, and table generation unit 733).

[0050] The storage unit 76 is a part that stores various programs and various data executed by the control unit 75. As shown in Fig. 4, the storage unit 76 stores the above-mentioned program 730 as an example of such various programs, and stores the above-mentioned machine learning model 74 as an example of such various data. The storage unit 76 is configured using, for example, a RAM (Random Access Memory), a ROM (Read Only Memory), an auxiliary storage device (such as a hard disk), etc.

[0051] The network IF 77 is a communication interface for communicating with the printer 1 via the network 50, as shown in FIG.

[0052] (Signal generation unit 48) 3, the inkjet head 4 includes a signal generating unit 48 in addition to the nozzle plate 41, actuator plate 42, and drive unit 49. The signal generating unit 48 generates a drive signal Sd having one or more pulses (pulse width Wp, voltage value Vp indicating a peak value) using the predicted voltage characteristics table TPvp generated by the table generating unit 733 in the information processing device 7 as described above.

[0053] 6(A) to 6(C) are timing diagrams each showing an example of the configuration of such a drive signal Sd. In these figures, the horizontal axis represents time t, and the vertical axis represents the drive voltage Vd (positive voltage in this example) of the drive signal Sd.

[0054] 6A has one pulse (pulse Pa), which is an example of a so-called "one drop." This pulse Pa is an ON period provided between the rising and falling timings, and has a pulse width Wpa1 and a voltage value Vp1, which are examples of the pulse width Wp and voltage value Vp described above.

[0055] On the other hand, the drive signal Sd shown in FIG. 6(B) has the following two pulses (pulses Pa and Pb) as pulses to which the so-called "multi-pulse method" is applied (an example of the so-called "two-drop" case). That is, two pulses Pa and Pb are provided as such pulses (ON periods). Note that 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 described 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.

[0056] Similarly, the drive signal Sd shown in FIG. 6(C) has the following three pulses (pulses Pa, Pb, and Pc) as pulses to which the above-mentioned "multi-pulse method" is applied (an example of the so-called "3-drop" case). That is, three such pulses (ON periods) are provided: pulses Pa, Pb, and Pc. Note that an OFF period ("OFF1") is provided between pulses Pa and Pb, and an OFF period ("OFF2") is provided between pulses Pb and Pc. Furthermore, as examples of the above-mentioned pulse widths Wp and voltage values ​​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.

[0057] Each pulse Pa, Pb, and Pc in the drive signal Sd is a positive pulse that expands the ejection channel during the high state and contracts the ejection channel during the low state.

[0058] Here, the signal generating unit 48 sets the pulse width Wp and voltage value Vp for each of these pulses (pulses Pa, Pb, Pc), and generates the drive signal Sd using pulses having the set pulse width Wp and voltage value Vp. Specifically, the signal generating unit 48 uses the predicted voltage characteristics table TPvp described above to determine the pulse voltage value Vp, and generates the drive signal Sd using pulses having the determined voltage value Vp.

[0059] The voltage value Vp mentioned above corresponds to a specific example of a "peak value" in the present disclosure. The "pulse" mentioned above is a concept that includes not only a rectangular wave such as that shown in Fig. 6, but also waveforms such as a trapezoidal wave, a triangular wave, and a step wave, and the same applies hereinafter.

[0060] [Operation, Actions and Effects] (A. Basic operation of Printer 1) In this printer 1, the operation of recording (printing) images, characters, etc. onto recording paper P is performed as follows. Note that, in the initial state, each of the four types of ink tanks 3 (3Y, 3M, 3C, 3K) shown in Fig. 1 is assumed to be fully filled with ink 9 of the corresponding color (four colors). The ink 9 in the ink tanks 3 is also filled into the inkjet head 4 via the ink supply pipe 30.

[0061] When the printer 1 is operated in this initial state, the grid rollers 21 in the transport mechanisms 2a and 2b rotate, 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 operation, the drive motor 633 in the drive mechanism 63 rotates the pulleys 631a and 631b, thereby operating the endless belt 632. As a result, the carriage 62 moves back and forth along the width direction (Y-axis direction) of the recording paper P while being guided by the guide rails 61a and 61b. At this time, the inkjet heads 4 (4Y, 4M, 4C, 4K) eject four colors of ink 9 onto the recording paper P as appropriate, thereby recording images, characters, etc. on the recording paper P.

[0062] (B. Detailed Operation of Inkjet Head 4) Next, a detailed description will be given of the operation (jetting operation of the ink 9) of the inkjet head 4. That is, in this inkjet head 4, the ejection operation of the ink 9 using the shear mode is carried out as follows.

[0063] First, the driving unit 49 applies a driving voltage Vd (driving signal Sd) to the driving electrodes (common electrode and active electrode) in the actuator plate 42 (see FIGS. 2 and 3). Specifically, the driving unit 49 applies the driving voltage Vd to each driving electrode arranged on a pair of driving walls that define the ejection channel. This causes each of the pair of driving walls to deform so as to protrude toward the dummy channel adjacent to the ejection channel.

[0064] At this time, the drive wall undergoes a V-shaped bending deformation centered at the midpoint of the drive wall in the depth direction. This bending deformation of the drive wall causes the ejection channel to deform as if it were expanding. This bending deformation due to the piezoelectric thickness shear effect of the pair of drive walls increases the volume of the ejection channel. This increase in the volume of the ejection channel then guides ink 9 into the ejection channel.

[0065] Next, the ink 9 guided into the ejection channel in this way becomes a pressure wave that propagates inside the ejection channel. Then, at the moment when this pressure wave reaches the nozzle hole Hn of the nozzle plate 41 (or at a moment close to this moment), the drive voltage Vd applied to the drive electrode becomes 0 (zero) V. This causes the drive wall to return to its original state from the bent and deformed state described above, and the volume of the ejection channel that had temporarily increased returns to its original volume.

[0066] In this way, as the volume of the ejection channel returns to its original state, the pressure inside the ejection channel increases, and the ink 9 inside the ejection channel is pressurized. As a result, droplets of ink 9 are ejected through the nozzle holes Hn to the outside (towards the recording paper P) (see Figures 2 and 3). In this way, the ink jet head 4 performs a jetting operation (ejection operation) of the ink 9, and as a result, a recording operation (printing operation) of images, characters, etc. on the recording paper P is performed.

[0067] (C. Injection parameter generation operation) Next, referring to Figures 7 to 13B in addition to Figures 1 to 6, the generation operation (generation process) of the injection parameter Prj (when the voltage sensitivity is Vr as described above) in the injection parameter generation system 5 will be explained in detail, while comparing it with comparative examples (Figures 8, 9A, and 9B).

[0068] Incidentally, this voltage sensitivity Vr (voltage sensitivity Vr during ejection) is a value (unit: [pl / V] or [m / s / V]) equivalent to the change in the droplet volume (DV: Drop Volume) or ejection speed of the ink 9 per unit voltage when the ink 9 is ejected at the reference temperature Tr.

[0069] (C-1. Input parameter Prin) First, as shown in Fig. 7, examples of the above-mentioned predetermined input parameters Prin include the following (a) to (l). Fig. 7 shows an example of the input parameters Prin according to this embodiment. Note that Fig. 7 shows the values ​​of each input parameter Prin for six samples ("Sample1" to "Sample6").

[0070] (a) Number of drops (number of pulses) ... corresponds to the number of pulses contained in the unit period of the drive signal Sd as described in FIG. 6 (b) Presence or absence of common drive ("0": absent, "1": present, "2": special value) ... so-called common drive (a driving method in which the pulse of the drive signal Sd is set so that the volume of the ejection channel when ejecting ink 9 includes a change that shrinks from the reference value) (c) Head type: Symbol indicating the type of inkjet head 4 (d) Ink type: Types of ink 9 classified by the main solvent of the ink 9 ("Oil": oil-based ink 9, "sol": organic solvent-based ink 9, "UV": UV (ultraviolet) curable ink, "WB": water-based ink 9) (e) (DV standard or Vj standard) ... A parameter indicating whether the standard is a standard for setting the voltage value Vp to obtain a reference droplet volume of the ink 9 when the ink 9 is ejected ("DV standard") or a standard for setting the voltage value Vp to obtain a reference ejection velocity ("Vj standard"). (f) Head rank value: This corresponds to the voltage value Vp at which a predetermined ejection speed is achieved when a predetermined test liquid is ejected from the inkjet head 4, and is a value specific to 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 value of the ink 9 (or a physical property value obtained using the specific gravity value of the ink 9 (e.g., the density of the ink 9, the speed of sound in the ink 9, etc.)) (j) Target value of DV (droplet volume) or Vj (ejection velocity) of ink 9 (k) Voltage shift amount ΔVp (parameter used in the predetermined conversion process described above; details will be described later in Modification 1)

[0071] Incidentally, the "viscosity of the ink 9" referred to here means static viscosity, and the same applies hereinafter. The viscosity value of the ink 9 is measured using, for example, a rotational viscometer, a vibration viscometer, or a viscometer of another measurement type such as a capillary type or a falling ball type (a viscometer capable of measuring static viscosity).

[0072] (C-2. Comparative example 1) Here, Fig. 8 shows an example of the importance analysis result of each input parameter Prin according to Comparative Example 1. Fig. 9A shows an example of the correspondence relationship between the SVM predicted value and the actual measured value according to Comparative Example 1 (an example in which only the above-mentioned Vj criterion is extracted). Similarly, Fig. 9B shows an example of the correspondence relationship between the RF predicted value and the actual measured value according to Comparative Example 1 (an example in which only the above-mentioned Vj criterion is extracted). In Comparative Example 1, the above-mentioned predetermined analysis method is used under conditions in which both the above-mentioned DV criterion and the Vj criterion are mixed, as will be described in detail later.

[0073] Note that the importance in the importance analysis results shown in Fig. 8 means an index (contribution rate) that measures how much the division of the feature contributes to the classification of the target, and is calculated using a predetermined formula based on the so-called Gini impurity. This definition of importance will be the same hereinafter.

[0074] 9A and 9B, the (x, y) coordinates of a large number (562) of samples are plotted, where the actual measured value of voltage sensitivity Vr is variable x and the predicted value of voltage sensitivity Vr (SVM predicted value or RF predicted value) is variable y. Also shown in FIGS. 9A and 9B are examples of equations (for example, linear function equations determined using the least squares method) that indicate the tendency of the correlation between the variables x and y.

[0075] First, according to an example of the importance analysis result of each input parameter Prin as an explanatory variable shown in FIG. 8, when generating the injection parameter Prj (=voltage sensitivity Vr) using the machine learning model 74, the following have the highest importance (contribution rate): That is, among the input parameters Prin shown in (a) to (l) above, (j) the target value of DV or Vj has the highest importance. Furthermore, among such input parameters Prin, the importance of the other input parameters Prin is approximately "0 (zero)."

[0076] Therefore, in this comparative example 1, the above-mentioned (j) DV or Vj target value is used as the input parameter Prin, and the above-mentioned predetermined analysis method is used under conditions that mix both the DV standard and the Vj standard.

[0077] 9A and 9B, for example, in Comparative Example 1, there may be cases where the prediction accuracy when generating the ejection parameter Prj decreases. Specifically, in each example shown in FIGS. 9A and 9B (examples in which only the Vj reference is extracted), the slope of the equation of the linear function described above is nearly "0," and the intercept of the equation of the linear function described above is significantly larger than "0." Therefore, in each example shown in FIGS. 9A and 9B, the predicted values ​​(SVM predicted values ​​and RF predicted values) and the actual measured values ​​have the following relationship. In other words, when printing using the predicted values, it cannot be said that there is a sufficient correlation between the predicted values ​​and the actual measured values.

[0078] In this way, in Comparative Example 1, when an importance analysis is performed under conditions in which both the DV standard and the Vj standard are mixed, there are cases in which the importance (contribution) of a specific input parameter Prin among the input parameters Prin is characteristically large. In such cases, for example, when a predetermined analysis method is used using only the specific input parameter Prin with characteristically large importance, as described above, the prediction accuracy of the injection parameter Prj based on the DV standard or the Vj standard may be reduced. Specifically, in the examples shown in FIGS. 9A and 9B, the prediction accuracy of the injection parameter Prj based on the Vj standard is reduced. As a result, there is a risk that the convenience for the user may be reduced in Comparative Example 1.

[0079] (C-3. ​​Generation process of injection parameter Prj in this embodiment) Therefore, in the injection parameter generating system 5 of this embodiment, when generating the injection parameter Prj, it is determined which of the above-mentioned DV standard and Vj standard to select based on the above-mentioned selection instruction signal Ss. The generation process of the injection parameter Prj of this embodiment will be described in detail below.

[0080] The above-mentioned DV criterion corresponds to a specific example of the "first criterion" in the present disclosure. The above-mentioned Vj criterion corresponds to a specific example of the "second criterion" in the present disclosure.

[0081] FIG. 10 is a flowchart showing an example of the process for generating the injection parameter Prj according to this embodiment.

[0082] In the processing example shown in FIG. 10, first, the parameter generating unit 732 determines whether to select the DV standard or the Vj standard based on the selection instruction signal Ss indicating which of the above-mentioned DV standard and Vj standard is being selected (steps S1 and S2).

[0083] Here, for example, if it is determined that the DV criterion should be selected (step S2: Y), the parameter generation unit 732 selects a first explanatory variable group Prin1 (see FIG. 11A, described later) included in the above-mentioned input parameters Prin as explanatory variables in a predetermined analysis method (for example, the machine learning model 74) (step S31). On the other hand, if it is determined that the Vj criterion should be selected (step S2: N), the parameter generation unit 732 selects a second explanatory variable group Prin2 (see FIG. 11B, described later) included in the input parameters Prin as explanatory variables in the predetermined analysis method (step S32).

[0084] The parameter generation unit 732 then uses only one of the first explanatory variable set Prin1 or the second explanatory variable set Prin2 selected in this manner to generate predetermined injection parameters by utilizing a predetermined analysis method (e.g., machine learning model 74) (step S4).

[0085] This completes the series of processes shown in FIG.

[0086] 11A shows an example of the importance analysis result for the first explanatory variable set Prin1 according to this embodiment. Also, FIG. 11B shows an example of the importance analysis result for the second explanatory variable set Prin2 according to this embodiment. In the examples of FIGS. 11A and 11B, the injection parameter Prj serving as the objective variable is the voltage sensitivity Vr, as described above.

[0087] 11A, the first explanatory variable set Prin1 according to this embodiment includes, for example, at least one of the following parameters among the above-mentioned input parameters Prin. That is, in the example of FIG. 11A, the following parameters are mainly included: (j) target value of DV, (a) number of drops, and (k) voltage shift amount ΔVp. Also, as shown in FIG. 11A, the importance (contribution) of these parameters increases in this order.

[0088] 11A, the target value of (j) DV has a relatively high (highest) importance. Therefore, in this embodiment, it is desirable that at least the target value of (j) DV, which has the highest importance, be included in the first explanatory variable set Prin1. Furthermore, in this embodiment, it is desirable that at least one of (a) the number of drops and (k) the voltage shift amount ΔVp, which have the second and third highest importance as described above, be further included in the first explanatory variable set Prin1.

[0089] 11B, the second explanatory variable set Prin2 according to this embodiment includes, for example, at least one of the following parameters among the aforementioned input parameters Prin. In other words, in the example of FIG. 11B, the following parameters are mainly included: (b) presence or absence of common drive, (a) number of drops, (f) head rank value, (k) voltage shift amount 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, (j) target value of Vj, and (d) ink type. Furthermore, as shown in FIG. 11B, the importance (contribution) of these parameters increases in this order.

[0090] 11B, (b) whether or not common drive is used and (a) the number of drops are each relatively highly important (first and second highest). Therefore, in this embodiment, it is desirable that at least one of (b) whether or not common drive is used and (a) the number of drops, which are relatively highly important, be included in the second explanatory variable set Prin2. Furthermore, in this embodiment, it is desirable that at least one of (f) head rank value, (k) voltage shift amount 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, which are next most important (third to ninth highest), be included in the second explanatory variable set Prin2.

[0091] 12A and 12B show an example of the correspondence between predicted values ​​(SVM predicted values, RF predicted values) and actual measured values ​​when only the first explanatory variable set Prin1 shown in Fig. 11A is used. Also, Fig. 13A and 13B show an example of the correspondence between predicted values ​​(SVM predicted values, RF predicted values) and actual measured values ​​when only the second explanatory variable set Prin2 shown in Fig. 11B is used.

[0092] 12A, 12B, 13A, and 13B are similar to those in the above-described FIGS. 9A and 9B. That is, in each of the examples shown in FIGS. 12A, 12B, 13A, and 13B, the actual measured value of voltage sensitivity Vr is set as variable x, and the predicted value (SVM predicted value or RF predicted value) of voltage sensitivity Vr is set as variable y. The (x, y) coordinates of a large number (562 samples) of samples are plotted. Also shown in FIGS. 12A, 12B, 13A, and 13B are examples of equations (e.g., linear function equations determined using the least squares method) that indicate the correlation tendency between the variables x and y.

[0093] 12A, 12B, 13A, and 13B, unlike the case of Comparative Example 1 described above (FIGS. 9A and 9B), the slope of the equation of the linear function described above is approximately "1," and the intercept of the equation of this linear function is approximately "0." Therefore, in this embodiment, unlike Comparative Example 1 described above, the predicted values ​​(SVM predicted value and RF predicted value) and the actual measured values ​​have the following relationship with respect to voltage sensitivity Vr as the objective variable. In other words, it can be seen that the predicted values ​​and the actual measured values ​​have a sufficient correlation to a degree that is practical for printing using the predicted values.

[0094] (D. Actions and Effects) As described above, in the injection parameter generation system 5 of this embodiment, it is determined which of the above-mentioned DV standard and Vj standard to select based on the selection instruction signal Ss. Then, the injection parameter Prj is generated by using only one of the first explanatory variable group Prin1 and the second explanatory variable group Prin2 selected according to the determination result of such standard, by utilizing the above-mentioned predetermined analysis method, as follows.

[0095] That is, a decrease in the prediction accuracy of the injection parameter Prj, such as that in the case of the above-mentioned Comparative Example 1 (when a predetermined analysis method is used under conditions where both the DV standard and the Vj standard are mixed), is avoided. That is, in this embodiment, the prediction accuracy of the injection parameter Prj can be improved compared to the case of the above-mentioned Comparative Example 1, etc. As a result, in this embodiment, it is possible to improve convenience for the user.

[0096] In addition, in this embodiment, since at least the above-mentioned voltage sensitivity Vr is included as such injection parameters Prj, the following is true: When generating the voltage sensitivity Vr using a predetermined analysis method, it is possible to improve the prediction accuracy of the voltage sensitivity Vr compared to the case of the above-mentioned comparative example 1, etc.

[0097] Furthermore, in this embodiment, the first explanatory variable set Prin1 includes at least the target value of DV described above, and the second explanatory variable set Prin2 includes at least one of the parameter indicating the presence or absence of common drive and the number of drops described above, resulting in the following: When generating voltage sensitivity Vr using a predetermined analysis method, the voltage sensitivity Vr is generated using the parameters with the first or second highest importance (degree of contribution), making it possible to further improve the prediction accuracy of this voltage sensitivity Vr.

[0098] Additionally, in this embodiment, the first explanatory variable set Prin1 further includes the number of drops, and the second explanatory variable set Prin2 further includes at least one parameter from among the head rank value, head type, specific gravity value of the ink 9, surface tension value of the ink 9, viscosity value at the reference temperature Tr, and target value of DV, resulting in the following: When generating voltage sensitivity Vr using a predetermined analysis method, these parameters with relatively high importance (degree of contribution) are further used to generate voltage sensitivity Vr, making it possible to further improve the prediction accuracy of this voltage sensitivity Vr.

[0099] Furthermore, in this embodiment, since the aforementioned voltage shift amount ΔVp is further included as at least one of the first explanatory variable set Prin1 and the second explanatory variable set Prin2, the following occurs: When generating the voltage sensitivity Vr using a predetermined analysis method, it is possible to further improve the prediction accuracy of this voltage sensitivity Vr.

[0100] Furthermore, in this embodiment, the predetermined analysis method is a method using the machine learning model 74, so that the injection parameters Prj can be generated easily and accurately.

[0101] Additionally, in this embodiment, the ejection parameter generation system 5 is further provided with a table generation unit 733 and a signal generation unit 48, resulting in the following: That is, a predicted voltage characteristics table TPvp is generated using at least one of the generated ejection parameters Prj, and the voltage value Vp (peak value) of the pulse is determined using the predicted voltage characteristics table TPvp thus generated, and the drive signal Sd is generated using the pulse having that voltage value Vp. Therefore, the ejection operation of the ink 9 is performed using the drive signal Sd thus generated, and the ejection characteristics of the ink 9 can be easily improved. As a result, it is possible to further improve user convenience.

[0102] Additionally, in this embodiment, the data acquisition unit 731, parameter generation unit 732, and table generation unit 733 are each provided outside the printer 1 (inside the information processing device 7), resulting in the following: That is, for the inkjet head 4 and printer 1, while maintaining the existing configuration, the ejection parameters Prj and the predicted voltage characteristics table TPvp can be automatically generated within the information processing device 7. As a result, it is possible to further improve user convenience.

[0103] <2. Modifications> Next, modifications of the above embodiment (Modifications 1 to 6) will be described. Note that the same components as those in the above embodiment are given the same reference numerals, and descriptions thereof will be omitted where appropriate.

[0104] [Variation 1] In the above embodiment, the case where the predetermined injection parameter Prj includes at least the voltage sensitivity Vr has been described. In contrast to this, in the following Modification 1, an example where the predetermined injection parameter Prj includes at least the conversion coefficient Kc used in the above-mentioned predetermined conversion process will be described. In other words, this conversion coefficient Kc corresponds to one specific example of the "predetermined injection parameter" in the present disclosure.

[0105] Here, the above-mentioned predetermined conversion process is a conversion process from the above-mentioned measured characteristic curve CMvi to the above-mentioned predicted characteristic curve CPvp. Furthermore, the measured viscosity characteristic table TMvi, which will be described in detail later, is a characteristic table that defines the measured characteristic curve CMvi between the viscosity Vi of the ink 9 and the ambient temperature Ta. Furthermore, the predicted voltage characteristic table TPvp, which will be described in detail later, is a characteristic table that defines the predicted characteristic curve CPvp between the voltage value Vp indicating the peak value of the pulse of the drive signal Sd based on a predetermined reference value, and the ambient temperature Ta. These will be described in detail later.

[0106] (A.Configuration) FIG. 14 is a block diagram showing an example of the configuration of a machine learning model (machine learning model 74A) according to 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 using the input parameter Prin as an explanatory variable and the injection parameter Prj as a response variable. Furthermore, as shown in FIG. 14, when the input parameter Prin (explanatory variable) is input, this machine learning model 74A generates (predicts) the injection parameter Prj (response variable) based on the learning result, and outputs the generated injection parameter Prj. As described above, the machine learning model 74A is generated so as to include at least the conversion coefficient Kc described above as an example of the predetermined injection parameter Prj (see FIG. 14).

[0107] As in the embodiment, this machine learning model 74A is used in the parameter generation unit 732. That is, the parameter generation unit 732 in this Modification 1 utilizes an analysis method using the machine learning model 74A to generate injection parameters Prj (conversion coefficient Kc, etc.) based on the input parameters Prin. Note that specific examples of the analysis method (prediction method) using this machine learning model 74A are the same as those given in the embodiment.

[0108] (B. Details of conversion process, etc.) Here, the above-mentioned predetermined conversion process, the measured viscosity characteristics table TMvi, and the predicted voltage characteristics table TPvp will be described in detail below, with reference to a comparative example (comparative example 2). In addition, the 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 will also be described.

[0109] (B-1. Comparative example 2) 15 is a block diagram showing an example of the schematic configuration of a printer 101 as a liquid jet recording apparatus according to Comparative Example 2. The printer 101 of this comparative example includes the nozzle plate 41, actuator plate 42, signal generating unit 48, and driving unit 49 described above in the inkjet head of Comparative Example 2 (not shown).

[0110] However, in the printer 101 of this comparison example 2, unlike the printer 1 of the embodiment, the signal generating unit 48 sets the voltage value Vp using the viscosity information Iv described below instead of the predicted voltage characteristics table TPvp described above.

[0111] Fig. 16 shows an example of viscosity information Iv according to Comparative Example 2. Specifically, Fig. 16 shows an example of the correspondence (information including viscosity information Iv) between the ambient temperature Ta, the viscosity Vi (measured value) of the ink 9, the voltage value Vp (measured value) of the pulse of the drive signal Sd, and the difference value ΔV (=Vi-Vp) between the viscosity Vi and the voltage value Vp. In other words, the example of Fig. 16 shows a characteristic curve between the viscosity Vi (measured value) and the ambient temperature Ta (measured characteristic curve CMvi), a characteristic curve between the voltage value Vp (measured value) and the ambient temperature (measured characteristic curve CMvp), and a characteristic curve between the difference value ΔV and the ambient temperature Ta.

[0112] The above-mentioned environmental temperature Ta corresponds to a specific example of "temperature" in the present disclosure.

[0113] In this comparative example 2, first, viscosity information Iv, such as that shown in Fig. 16, is obtained by detecting changes in viscosity Vi of the ink 9 with respect to changes in the ambient temperature Ta (for example, by performing measurements at five or more points). Furthermore, as shown in Fig. 16, it is known that changes in viscosity Vi of the ink 9 with respect to the ambient temperature Ta and changes in voltage value Vp (voltage value Vp at which a reference ejection velocity is obtained) with respect to the ambient temperature Ta exhibit similar change characteristics. Therefore, as shown in Fig. 16, the difference value ΔV between the viscosity Vi and voltage value Vp exhibits a substantially constant value independent of the ambient temperature Ta.

[0114] 16, the signal generating unit 48 in Comparative Example 2 utilizes this similarity in temperature change characteristics to subtract a pre-calculated difference value ΔV (negative value) from the value of viscosity Vi (see viscosity information Iv) at a certain ambient temperature Ta to obtain a voltage value Vp at which a reference discharge speed can be obtained. That is, the signal generating unit 48 in Comparative Example 2 obtains the voltage value Vp at a certain ambient temperature Ta by using the relational expression Vp=(Vi-ΔV) (see FIG. 16).

[0115] Incidentally, the characteristic curve between the voltage value Vp and the ambient temperature Ta (the above-mentioned measured characteristic curve CMvp) generally has a different slope depending on the number of pulses included in the drive signal Sd and the type and role of each pulse (for example, the type and role of each pulse, including additional pulses such as auxiliary pulses). Therefore, in this comparative example 2, such measured characteristic curve CMvp basically needs to be obtained by manual measurement in advance. However, under limited conditions (for example, the above-mentioned case of "one drop" based on the ejection speed), such measured characteristic curve CMvp can be derived without actual measurement.

[0116] In this way, the above-mentioned measured characteristic curve CMvp needs to be obtained by actually measuring, for example, each type of pulse number included in the drive signal Sd. Therefore, for the user of the printer 101 of Comparative Example 2, this requires a huge amount of time and effort, and increases the workload and cost.

[0117] FIG. 17 shows examples of various characteristic curves (measured characteristic curve CMvp and measured characteristic curve CMvi) according to Comparative Example 2. Specifically, the measured characteristic curve CMvp shown in FIG. 17 shows the cases where the number of pulses (the number of drops) is 1 drop (denoted as "1d"), 3 drops (denoted as "3d"), 7 drops (denoted as "7d"), and 9 drops (denoted as "9d"). Each measured characteristic curve CMvp shown in FIG. 17 also shows a voltage value Vp based on a predetermined reference value. That is, each measured characteristic curve CMvp shown in FIG. 9 shows the voltage value Vp (denoted as "Vj reference") at which a reference ejection velocity is obtained when the ink 9 is ejected, and the voltage value Vp (denoted as "DV reference") at which a reference droplet volume (DV) of the ink 9 is obtained. The drive waveforms used to obtain the various characteristic curves shown in FIG. 17 include the "common drive" described below for all conditions (number of drops).

[0118] In the example shown in Fig. 17, the slope of the measured characteristic curve CMvp differs depending on the type of pulse number (drop number) and the type of the predetermined reference value (the aforementioned Vj reference or DV reference), as described above. Therefore, if a single measured characteristic curve CMvp is reused when generating the drive signal Sd, as in the viscosity information Iv of Comparative Example 2 shown in Fig. 16, the accuracy of setting the voltage value Vp will be reduced due to differences in the slope depending on the type of pulse number, the type of predetermined reference value, the type and role of each pulse, etc. In other words, it becomes difficult to accurately set the voltage value Vp (peak value) of the pulse in the drive signal Sd.

[0119] Specifically, in Comparative Example 2, for example, only a single voltage characteristic table (such as for "one drop" based on the ejection speed, as described above) can be created based on the measured characteristic curve CMvi. Also, as described above, obtaining the measured characteristic curve CMvp for each condition (such as for each type of pulse number) requires a huge amount of effort in actual measurements. For these reasons, the method of Comparative Example 2 may reduce the accuracy of setting the voltage value Vp and increase the user's workload, resulting in a loss of user convenience.

[0120] (B-2. Method of Modification 1) Therefore, in this modification 1, the information processing unit 73 (program 730) uses the predetermined decomposition method described above to generate the conversion coefficient Kc for the conversion process described below. Then, in this modification 1, the conversion coefficient Kc generated in this manner is used to generate (automatically generate) the above-mentioned characteristic table (predicted voltage characteristic table TPvp that defines the predicted characteristic curve CPvp) as needed.

[0121] Fig. 18 is a flow chart showing an example of a conversion process (corresponding to a specific example of the process in step S13 in Fig. 21) described below according to Modification 1. Fig. 19 shows examples of various characteristic curves (characteristic curves after execution of step S132 shown in Fig. 18, described below) according to Modification 1. Specifically, Fig. 19 shows examples of various characteristic curves (such as the measured characteristic curve CMvi described above and the preliminary characteristic curve CPvp0 of the predicted characteristic curve CPvp described above) that indicate the correspondence between the viscosity Vi [mPa] of the ink 9 or the voltage value Vp and the ambient temperature Ta [°C].

[0122] For the sake of convenience, the preliminary characteristic curve CMvp0 shown in FIG. 19 is a characteristic curve obtained by performing a predetermined process (a process for setting the voltage value Vp=0 at a predetermined reference temperature Tr, which will be described later) on the previously described actual characteristic curve CMvp, in order to facilitate comparison (comparison of slope) with the preliminary characteristic curve CPvp0.

[0123] Moreover, Fig. 20 shows an example of the input parameters Prin according to Modification 1. Note that Fig. 20 shows the values ​​of the input parameters Prin for six samples ("Sample1" to "Sample6").

[0124] (About the conversion process) 18 and 19, the conversion process using the conversion coefficient Kc is the process of converting the measured characteristic curve CMvi into the predicted characteristic curve CPvp, as described above. Furthermore, as shown in the example of Fig. 19, it can be seen that the preliminary characteristic curve CPvp0 obtained during this conversion process matches (almost matches) with high precision the preliminary characteristic curve CMvp0 for the measured characteristic curve CMvp described above.

[0125] Here, a specific example of such a conversion process will be described with reference to FIGS.

[0126] In this conversion process, first, a multiplication process (CMvi × Kc) is performed in which the measured characteristic curve CMvi is multiplied by a conversion coefficient Kc (step S131 in FIG. 18). Next, a subtraction process is performed on the result of the multiplication process in step S131 so that the voltage value Vp becomes 0 at a predetermined reference temperature Tr (in the example of FIG. 19, Tr = 40°C), thereby generating the preliminary characteristic curve CPvp0 (a preliminary characteristic curve between the predicted value of the voltage value Vp and the ambient temperature Ta) (step S132). That is, by this preliminary process (the processes of steps S131 and S132), the preliminary characteristic curve CPvp0 as shown in FIG. 19 is generated from the measured characteristic curve CMvi using the conversion coefficient Kc. Note that the execution order of the processes of steps S131 and S132 in this preliminary process may be reversed from the example shown in FIG. 18 (e.g., step S132 is executed first, followed by step S131).

[0127] Next, an addition process (CPvp0+ΔVp) is performed to add a predetermined voltage shift amount ΔVp to the voltage value Vp on the preliminary characteristic curve CPvp0 so as to obtain the voltage value Vp (based on DV or Vj) described above in Figure 17, and a final predicted characteristic curve CPvp is generated (step S133). In other words, the voltage value Vp after adding the voltage shift amount ΔVp (the voltage value Vp on the predicted characteristic curve CPvp) corresponds to the voltage value Vp at which a reference droplet volume of ink 9 is obtained when the ink 9 is ejected, or the voltage value Vp at which a reference ejection velocity is obtained. In this way, the final predicted characteristic curve CPvp is generated, and the series of conversion processes shown in Figure 18 is completed.

[0128] Incidentally, the specific conversion formula for such conversion processing is expressed by the following formula (1) using the above-mentioned conversion coefficient Kc. H=(H0×e (E / kT) ) / Kc ……(1) H: Viscosity value of ink 9 after conversion processing H0: Constant T: Absolute temperature (ambient temperature Ta) E: activation energy k: Boltzmann constant

[0129] Note that the formula (1) above, excluding the conversion coefficient Kc, is called the Arrhenius equation (law) and is generally well known. Furthermore, in formula (1), the Arrhenius equation is divided by the conversion coefficient Kc. This is because the analysis method using machine learning model 74A uses (viscosity value of ink 9 / measured value of voltage value Vp) for calculation. Therefore, for example, if the analysis method using machine learning model 74A uses (measured value of voltage value Vp / viscosity value of ink 9) for calculation, the formula for multiplying the Arrhenius equation by the conversion coefficient Kc becomes the conversion formula for the conversion process. In other words, either of these formulas may be used as the conversion formula for the conversion process.

[0130] (About the input parameter Prin) Here, specific examples of the aforementioned input parameter Prin in this variant example 1 include the following (a) to (k) and (l), which are also explained in the embodiment, as shown in Figure 20.

[0131] (a) Number of drops (number of pulses) (b) Presence or absence of common drive (c) Head type (d) Ink type (e)(DV standard or Vj standard) (f) Head rank value (g) Viscosity value at reference temperature Tr (l) Voltage sensitivity during ejection Vr (h) Surface tension value of ink 9 (i) Specific gravity of ink 9 (k) Voltage shift amount ΔVp (j) Target value of DV or Vj

[0132] (Details on the process of generating the characteristic table) 21 is a flowchart showing the process of generating the characteristics table (predicted voltage characteristics table TPvp) according to Modification 1. Of the series of processes (steps S10 to S16 described below) shown in FIG. 21, the processes of steps S11 to S13 described below correspond to the process of generating the predicted voltage characteristics table TPvp, and the processes of steps S14 and S15 described below correspond to the process of generating the drive signal Sd.

[0133] 21, first, as a preliminary step, the information processing unit 73 (program 730) determines whether or not it is necessary to generate (update) a predicted voltage characteristics table TPvp that defines the predicted characteristic curve CPvp described above (step S10). If it is determined that it is necessary to generate the predicted voltage characteristics table TPvp (step S10: Y), the process proceeds to the process of generating the predicted voltage characteristics table TPvp (steps S11 to S13) described below. On the other hand, if it is determined that it is not necessary to generate the predicted voltage characteristics table TPvp (step S10: N), the process proceeds to step S15 described below, where a drive signal Sd is generated using a pulse having a voltage value Vp (peak value) at the current stage.

[0134] The following are examples of cases where it is necessary to generate the predicted voltage characteristics table TPvp: when a predetermined time has elapsed, when a cartridge for the ink tank 3 has been installed, when a predetermined operation signal has been input to the printer 1 from the user, when the non-ejection period (idle period) of the ink 9 has exceeded a predetermined time, etc. Other examples include when the color or type of ink 9 in the ink tank 3 has been changed, or when a different model of inkjet head 4 has been installed in the printer 1. Another example is when at least one of the input parameters Prin has been changed, as shown in FIG. 20.

[0135] (Steps S11 to S13: Generation process of predicted voltage characteristics table TPvp) Next, in the process of generating the predicted voltage characteristics table TPvp (steps S11 to S13), first, the data acquisition unit 731 acquires the following data (input data): That is, the data acquisition unit 731 acquires, as input data, the measured viscosity characteristics table TMvi that defines the measured characteristic curve CMvi between the viscosity Vi of the ink 9 and the ambient temperature Ta, and the predetermined input parameter Prin described above, using the method described above (step S11).

[0136] Next, the parameter generating unit 732 generates a conversion coefficient Kc based on the input parameters Prin using a predetermined analysis method in which the input parameters Prin acquired in step S11 are used as explanatory variables and the conversion coefficient Kc as the injection parameters Prj is used as a response variable (step S12). Specifically, in this modified example 1, the parameter generating unit 732 generates the conversion coefficient Kc based on the input parameters Prin using an analysis method that uses the machine learning model 74A described above.

[0137] Then, the table generator 733 generates the predicted voltage characteristics table TPvp (step S13) by performing the predetermined conversion process described above (see FIGS. 18 and 19) using the measured viscosity characteristics table TMvi acquired in step S11 and the conversion coefficient Kc generated in step S12. In this way, as described above, the predicted voltage characteristics table TPvp is generated, which defines the predicted characteristic curve CPvp between the voltage value Vp (peak value) of the pulse of the drive signal Sd and the ambient temperature Ta.

[0138] (Steps S14 and S15: Generation of drive signal Sd) Next, in the process of generating the drive signal Sd (steps S14 and S15), the signal generator 48 first uses the predicted voltage characteristics table TPvp generated in step S13 to determine the voltage value Vp (peak value) of the pulse of the drive signal Sd by the method described above (see FIG. 6) (step S14). Specifically, the current ambient temperature Ta is applied to the predicted voltage characteristics table TPvp to determine the voltage value Vp of the pulse.

[0139] Then, the signal generating unit 48 generates a drive signal Sd, such as shown in Figures 6(A) to 6(C) above, using a pulse having the voltage value Vp calculated in step S14 and, for example, a preset pulse width Wp (step S15).

[0140] The pulse width Wp is calculated based on, for example, the on-pulse peak (AP) of the pulse. This AP corresponds to half the natural vibration period of the ink 9 in the ejection channel (1AP = (natural vibration period of the ink 9) / 2). When the pulse width Wp is set to AP, the ejection speed (ejection efficiency) of the ink 9 is maximized when ejecting one normal droplet of ink 9 (ejecting one droplet). The AP is determined by, for example, the shape of the ejection channel and the physical properties (specific gravity, etc.) of the ink 9.

[0141] Furthermore, based on such AP, the pulse width Wp is set, for example, as follows. That is, for example, in the examples of the drive signal Sd shown in FIGS. 6(A) to 6(C) (examples for so-called "1 drop," "2 drops," and "3 drops," respectively), the signal generation unit 48 sets the pulse width Wp as follows. That is, in the examples of FIGS. 6(A) to 6(C), the signal generation unit 48 sets the pulse width Wp so that, for example, each of the pulse widths Wp described above satisfies the relationships shown in the following equations (2) and (3) with respect to the AP. However, the examples are not limited to those shown in equations (2) and (3), and each pulse width Wp can be set as appropriate. (1.25×AP)≦(Wpa1,Wpa2,Wpa3,Wpb2,Wpb3,Wpc3)≦(1.75×AP)……(2) (Wpa1)≧(Wpa2,Wpb2)≧(Wpa3,Wpb3,Wpc3)……(3)

[0142] (Step S16: Ejection of ink 9) Next, the driving unit 49 applies the driving signal Sd generated in step S15 to the actuator plate 42 in the inkjet head 4, causing the ink 9 to be ejected from the nozzle holes Hn (step S16). In this way, the ejection operation of the ink 9 described above is performed.

[0143] This completes the series of processes shown in FIG.

[0144] In this way, in the method of Modification 1, a predetermined analysis method is used to generate a conversion coefficient Kc based on predetermined input parameters Prin, and a conversion process is performed using the actual viscosity characteristics table TMvi and the conversion coefficient Kc to generate a predicted voltage characteristics table TPvp. In other words, the predicted voltage characteristics table TPvp that defines a predicted characteristic curve CPvp between the voltage value Vp (peak value) and the ambient temperature Ta is automatically generated each time.

[0145] As a result, in Modification 1, the workload and costs are reduced compared to when the characteristic curve between these voltage values ​​Vp and the ambient temperature Ta (the aforementioned measured characteristic curve CMvp) is obtained by actually measuring (for example, by actually measuring and obtaining for each type of number of pulses included in the drive signal Sd), as in Comparative Example 2 described above. Furthermore, as described above, the characteristic curve between the voltage values ​​Vp and the ambient temperature Ta (the measured characteristic curve CMvp) generally has different slopes depending on the number of pulses included in the drive signal Sd and the type and role of each pulse. Therefore, the predicted voltage characteristic table TPvp is automatically generated each time, as shown below. In other words, the voltage values ​​Vp (peak values) of the pulses in the drive signal Sd can be set with higher accuracy compared to, for example, when a single characteristic curve is reused.

[0146] From these points, in variant example 1, it is possible to improve the work efficiency for obtaining the characteristic curve (voltage characteristic table) between the above-mentioned voltage value Vp and the ambient temperature Ta, and also to easily improve the setting accuracy of the voltage value Vp (peak value) of the pulse in the drive signal Sd.

[0147] Furthermore, in this modification 1, for example, the following effects can be obtained. Since the characteristic curve between the voltage value Vp and the ambient temperature Ta can be easily obtained, it is easy to control the voltage so that the ejection speed and droplet volume of the ink 9 are kept almost constant, even when, for example, the number and type of pulses described above, or the type and role of each pulse, are different. As in the above-described comparative example 2, an expensive evaluation device (such as a temperature controller) used to obtain the measured characteristic curve CMvp is no longer required, which makes it possible to reduce costs.

[0148] (C. Comparative Example 3) However, even in this modified example 1, as described above in the embodiment, the following cases may occur depending on the conditions. That is, similar to the case of the above-described comparative example 1, when a predetermined analysis method is used under conditions where both the DV standard and the Vj standard are mixed (comparative example 3), there may be cases where the prediction accuracy of the injection parameter Prj based on the DV standard or the Vj standard is reduced. Hereinafter, such comparative example 3 will be described.

[0149] Fig. 22 shows an example of the importance analysis results of each input parameter Prin according to Comparative Example 3. In the example shown in Fig. 22, when generating the ejection parameter Prj (=conversion coefficient Kc) using the machine learning model 74A, the input parameters Prin with relatively high importance (contribution rate) are as follows: Of the input parameters Prin shown in (a) to (k) and (l) above, the importance increases in the following order: (i) specific gravity value of the ink 9, (a) number of drops, (g) viscosity value at reference temperature Tr, (k) voltage shift amount ΔVp, (l) voltage sensitivity Vr during ejection, and (j) target value of DV or Vj.

[0150] Therefore, in Comparative Example 3, for example, these parameters are selectively used as the input parameter Prin, and a predetermined analysis method is used under conditions where both the DV standard and the Vj standard are mixed. Then, as described above, in Comparative Example 3 as well, similar to Comparative Example 1, the prediction accuracy of the injection parameter Prj based on the DV standard or the Vj standard may be reduced. As a result, in Comparative Example 3 as well, similar to Comparative Example 1, there is a risk that user convenience may be reduced.

[0151] (D. Generation Process of Injection Parameter Prj in Modification Example 1) Therefore, in this modified example 1, similarly to the above-described embodiment, when generating the conversion coefficient Kc as the injection parameter Prj, it is determined which of the DV standard and the Vj standard to select based on the above-described selection instruction signal Ss. Then, the conversion coefficient Kc as the injection parameter Prj is generated by utilizing a predetermined analysis method using only one of the first explanatory variable group Prin1 or the second explanatory variable group Prin2 selected according to the determination result of such standard.

[0152] 23A shows an example of the result of an importance analysis for the first explanatory variable set Prin1 according to Modification 1. FIG. 23B shows an example of the result of an importance analysis for the second explanatory variable set Prin2 according to Modification 1.

[0153] 23A, the first explanatory variable set Prin1 according to Modification Example 1 includes, for example, at least one of the following parameters among the aforementioned input parameters Prin. In other words, in the example of FIG. 23A, the following are included: (i) specific gravity value of the ink 9, (a) number of drops, (g) viscosity value at reference temperature Tr, (j) target value of DV, (k) voltage shift amount ΔVp, (l) voltage sensitivity during ejection Vr, (b) presence or absence of common drive, (h) surface tension value of the ink 9, (f) head rank value, (c) head type, and (d) ink type. Furthermore, as shown in FIG. 23A, the order of importance (contribution) increases relatively.

[0154] On the other hand, as shown in Fig. 23B, the second explanatory variable set Prin2 according to Modification Example 1 includes, for example, at least one of the following parameters among the aforementioned input parameters Prin. In other words, in the example of Fig. 23B, these include (i) the specific gravity value of the ink 9, (g) the viscosity value at the reference temperature Tr, (a) the number of drops, (k) the voltage shift amount ΔVp, (l) the voltage sensitivity Vr during ejection, (d) the ink type, (h) the surface tension value of the ink 9, (f) the head rank value, (j) the target value of Vj, (c) the head type, and (b) whether or not common drive is enabled. Furthermore, as shown in Fig. 23B, these parameters have relatively increasing importance (contribution) in this order.

[0155] 24A and 24B show an example of the correspondence between predicted values ​​(SVM predicted values, RF predicted values) and actual measured values ​​when only the first explanatory variable set Prin1 shown in Fig. 23A is used. Also, Fig. 25A and 25B show an example of the correspondence between predicted values ​​(SVM predicted values, RF predicted values) and actual measured values ​​when only the second explanatory variable set Prin2 shown in Fig. 23B is used.

[0156] 24A, 24B, 25A, and 25B are similar to those in the above-described FIGS. 12A, 12B, 13A, and 13B. In other words, in each of the examples shown in FIGS. 24A, 24B, 25A, and 25B, the actual measured value of the conversion coefficient Kc is set as the variable x, and the predicted value (SVM predicted value or RF predicted value) of the conversion coefficient Kc is set as the variable y. The (x, y) coordinates of each of a large number (562) of samples are plotted. Also shown in FIGS. 24A, 24B, 25A, and 25B are examples of equations (for example, linear function equations identified using the least squares method) that indicate the correlation tendency between the variables x and y.

[0157] 24A, 24B, 25A, and 25B, similarly to the embodiment (FIGS. 12A, 12B, 13A, and 13B), the slope of the equation of the linear function described above is approximately "1," and the intercept of the equation of this linear function is approximately "0." Therefore, unlike Comparative Example 3 described above, in Modification Example 1, with regard to the conversion coefficient Kc as the objective variable, the predicted values ​​(SVM predicted value and RF predicted value) and the actual measured values ​​have the following relationship: In other words, it can be seen that the predicted values ​​and the actual measured values ​​have a sufficient correlation to be practical for printing using the predicted values.

[0158] (E. Actions and Effects) In this way, in the first modification, basically, the same effects as those of the embodiment can be obtained through the same actions.

[0159] Furthermore, in particular, in this Modification 1, since the injection parameters Prj include at least the conversion coefficient Kc used in the predetermined conversion process described above, the following occurs: That is, when the conversion coefficient Kc is generated 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 described above. As a result, in this Modification 1 as well, it is possible to further improve user convenience.

[0160] [Variation 2] In the above embodiment, a case where the predetermined injection parameter Prj includes at least the voltage sensitivity Vr has been described, and in the above modification 1, a case where the predetermined injection parameter Prj includes at least the conversion coefficient Kc has been described. In contrast to this, in the following modification 2, an example where the predetermined injection parameter Prj includes at least the voltage shift amount ΔVp described above will be described. In other words, this voltage shift amount ΔVp corresponds to one specific example of the "predetermined injection parameter" in the present disclosure.

[0161] (A.Configuration) FIG. 26 is a block diagram showing an example of the configuration of a machine learning model (machine learning model 74B) according to Modification 2. Similar to the machine learning models 74 and 74A described above, this machine learning model 74B is a prediction model obtained by performing machine learning using the input parameter Prin as an explanatory variable and the injection parameter Prj as a response variable. Furthermore, as shown in FIG. 26, when the input parameter Prin (explanatory variable) is input, this machine learning model 74B generates (predicts) the injection parameter Prj (response variable) based on the learning result and outputs the generated injection parameter Prj. As described above, the machine learning model 74B is generated so as to include at least the voltage shift amount ΔVp described above as an example of the predetermined injection parameter Prj (see FIG. 26).

[0162] This machine learning model 74B is used in the parameter generation unit 732, similarly to the embodiment and Modification 1. That is, the parameter generation unit 732 in Modification 2 generates the injection parameters Prj (such as the voltage shift amount ΔVp) based on the input parameters Prin, by utilizing an analysis method using the machine learning model 74B. Note that specific examples of the analysis method (prediction method) using this machine learning model 74B are the same as those given in the embodiment.

[0163] (B. Input parameter Prin) Fig. 27 shows an example of input parameters Prin according to Modification 2. Note that Fig. 27 shows the values ​​of each input parameter Prin for six samples ("Sample1" to "Sample6").

[0164] Specific examples of the input parameter Prin in this modified example 2 include the following (a) to (j) and (l) as shown in FIG. 27 and also explained in the embodiment and modified example 1.

[0165] (a) Number of drops (number of pulses) (b) Presence or absence of common drive (c) Head type (d) Ink type (e)(DV standard or Vj standard) (f) Head rank value (g) Viscosity value at reference temperature Tr (l) Voltage sensitivity Vr during ejection (DV reference or Vj reference) (h) Surface tension value of ink 9 (i) Specific gravity of ink 9 (j) Target value of DV or Vj

[0166] (C. Comparative Example 4) Here, even in this Modification 2, as described above in the embodiment and Modification 1, the following cases may occur depending on the conditions. That is, similar to the cases of Comparative Examples 1 and 3 described above, when a predetermined analysis method is used under conditions in which both the DV standard and the Vj standard are mixed (Comparative Example 4), there may be cases in which the prediction accuracy of the injection parameter Prj based on the DV standard or the Vj standard is reduced. Hereinafter, such Comparative Example 4 will be described.

[0167] 28 shows an example of the importance analysis results of each input parameter Prin according to Comparative Example 4. In the example shown in FIG. 28, when generating the ejection parameter Prj (=voltage shift amount ΔVp) using the machine learning model 74B, the input parameters Prin with relatively high importance (contribution rate) are as follows: That is, among the input parameters Prin shown in (a) to (j) and (l) above, the importance increases in the following order: (g) viscosity value at reference temperature Tr, (b) presence or absence of common drive, (f) head rank value, (c) head type, (i) specific gravity value of the ink 9, (l) voltage sensitivity Vr during ejection, (h) surface tension value of the ink 9, and (j) target value of DV or Vj.

[0168] Therefore, in Comparative Example 4, for example, these parameters are selectively used as the input parameter Prin, and a predetermined analysis method is used under conditions where both the DV standard and the Vj standard are mixed. Then, as described above, in Comparative Example 4 as well, similar to Comparative Examples 1 and 3, the prediction accuracy of the injection parameter Prj based on the DV standard or the Vj standard may be reduced. As a result, in Comparative Example 4 as well, similar to Comparative Examples 1 and 3, there is a risk that user convenience may be reduced.

[0169] (D. Generation Process of Injection Parameter Prj in Modification 2) Therefore, in this Modification 2, similarly to the above-described embodiment and Modification 1, when generating the voltage shift amount ΔVp as the injection parameter Prj, it is determined which of the DV standard and the Vj standard to select based on the above-described selection instruction signal Ss. Then, the voltage shift amount ΔVp as the injection parameter Prj is generated by utilizing a predetermined analysis method using only one of the first explanatory variable set Prin1 or the second explanatory variable set Prin2 selected according to the result of the determination of such standard.

[0170] 29A shows an example of the result of an importance analysis for the first explanatory variable set Prin1 according to Modification 2. FIG. 29B shows an example of the result of an importance analysis for the second explanatory variable set Prin2 according to Modification 2.

[0171] 29A, the first explanatory variable set Prin1 according to Modification Example 2 includes, for example, at least one of the following parameters among the aforementioned input parameters Prin. In other words, in the example of FIG. 29A, the following are included: (b) presence or absence of common drive, (g) viscosity value at reference temperature Tr, (f) head rank value, (c) head type, (i) specific gravity value of ink 9, (h) surface tension value of ink 9, (l) voltage sensitivity Vr during ejection, (j) target value of DV, (d) ink type, and (a) number of drops. Furthermore, as shown in FIG. 29A, the order of importance (contribution) increases relatively.

[0172] On the other hand, as shown in Fig. 29B, the second explanatory variable set Prin2 according to Modification Example 2 includes, for example, at least one of the following parameters among the aforementioned input parameters Prin. That is, in the example of Fig. 29B, the following are included: (l) voltage sensitivity during ejection Vr, (g) viscosity value at reference temperature Tr, (f) head rank value, (c) head type, (h) surface tension value of the ink 9, (i) specific gravity value of the ink 9, (b) presence or absence of common drive, (j) target value of Vj, (a) number of drops, and (d) ink type. Also, as shown in Fig. 29B, the importance (contribution) of these parameters increases in this order.

[0173] 30A and 30B show an example of the correspondence between predicted values ​​(SVM predicted values, RF predicted values) and actual measured values ​​when only the first explanatory variable set Prin1 shown in Fig. 29A is used. Also, Fig. 31A and 31B show an example of the correspondence between predicted values ​​(SVM predicted values, RF predicted values) and actual measured values ​​when only the second explanatory variable set Prin2 shown in Fig. 29B is used.

[0174] 30A, 30B, 31A, and 31B are similar to those in FIGS. 12A, 12B, 13A, 13B, 24A, 24B, 25A, and 25B. In other words, in each of the examples shown in FIGS. 30A, 30B, 31A, and 31B, the actual measured value of the voltage shift amount ΔVp is set as variable x, and the predicted value (SVM predicted value or RF predicted value) of the voltage shift amount ΔVp is set as variable y. The (x, y) coordinates of each of a large number (562) of samples are plotted. Also shown in FIGS. 30A, 30B, 31A, and 31B are examples of equations (e.g., linear function equations determined using the least squares method) that indicate the correlation tendency between the variables x and y.

[0175] 30A, 30B, 31A, and 31B are basically similar to the embodiment (FIGS. 12A, 12B, 13A, and 13B) and Modification 1 (FIGS. 24A, 24B, 25A, and 25B) in that the following holds true. That is, the slope of the linear function approaches 1, and the intercept of the linear function approaches 0. Therefore, in Modification 2, unlike Comparative Example 4, the predicted values ​​(SVM predicted value and RF predicted value) and the actual measured values ​​have the following relationship with respect to the voltage shift amount ΔVp as the objective variable. That is, it can be seen that the predicted values ​​and the actual measured values ​​have a sufficient correlation to be practical for printing using the predicted values.

[0176] (E. Actions and Effects) In this way, in the second modification, basically, the same effects as those of the embodiment can be obtained through the same actions.

[0177] Furthermore, in particular, in this Modification 2, since the injection parameter Prj includes at least the voltage shift amount ΔVp used in the predetermined conversion process described above, the following occurs: That is, when generating the voltage shift amount ΔVp using the predetermined analysis method described above, the prediction accuracy of the voltage shift amount ΔVp can be improved compared to the case of Comparative Example 4 described above. As a result, in this Modification 2 as well, it is possible to further improve user convenience.

[0178] [Variation 3] (composition) 32 is a block diagram showing an example configuration of an ejection parameter generation system 5A according to Modification 3. This ejection parameter generation system 5A according to Modification 3 includes a printer 1 having an inkjet head 4, and an information processing device 7A and a server 8 located outside the printer 1. The printer 1, information processing device 7A, and server 8 are connected to each other via a network 50. In other words, this ejection parameter generation system 5A corresponds to the ejection parameter generation system 5 according to the embodiment, except that an information processing device 7A is provided instead of the information processing device 7, and a server 8 is also provided.

[0179] In this third modification, the above-described server 8 corresponds to a specific example of an "external device" in the present disclosure.

[0180] As shown in Fig. 32, the information processing device 7A has, as physical block configuration, a bus 70, an input unit 71, a display unit 72, a control unit 75, a storage unit 76A, and a network IF 77. In other words, this information processing device 7A corresponds to the information processing device 7 of the embodiment shown in Fig. 4, in which a storage unit 76A is provided instead of the storage unit 76. Unlike the storage unit 76, this storage unit 76A does not store the program 730 and the machine learning model 74 described in the embodiment. Therefore, this information processing device 7A corresponds to, for example, a PC or the like having a general (general-purpose) configuration.

[0181] As shown in FIG. 32, the server 8 has a physical block configuration including a bus 80, a control unit 85, a storage unit 86, and a network IF 87. The control unit 85, the storage unit 86, and the network IF 87 are connected to each other via the bus 80. The control unit 85 and the network IF 87 have the same configurations as the control unit 75 and the network IF 77 in the embodiment (FIG. 4), respectively. The storage unit 86 also has the same configuration as the storage unit 76 in the embodiment (FIG. 4). That is, as shown in FIG. 32, the storage unit 86 stores the program 730 and the machine learning model 74 described in the embodiment. As shown in parentheses in FIG. 32, in addition to the machine learning model 74, the machine learning models 74A and 74B described in Modifications 1 and 2 may be provided, and the same applies to Modifications 4 to 6 described below.

[0182] In this way, in the ejection parameter generation system 5A of this modified example 3, unlike the ejection parameter generation system 5 of the embodiment, the predetermined ejection parameters Prj (and the predicted voltage characteristics table TPvp) described above are generated in the server 8 instead of the information processing device 7A. The predicted voltage characteristics table TPvp generated in this way is supplied from the server 8 to the signal generation unit 48 in the inkjet head 4 of the printer 1 via the network 50, as shown in FIG.

[0183] (Actions and Effects) In the third modification having such a configuration, the injection parameter generation system 5A as a whole basically operates in the same manner as the injection parameter generation system 5 of the embodiment, and can obtain the same effects.

[0184] Furthermore, in particular, in this Modification 3, the aforementioned data acquisition unit 731, parameter generation unit 732, and table generation unit 733 (the aforementioned program 730) are each provided outside the printer 1 (inside the server 8), resulting in the following: That is, as in the case of the above-described embodiment, the inkjet head 4 and printer 1 can maintain their existing configurations while the ejection parameters Prj and the predicted voltage characteristics table TPvp can be automatically generated within the above-described server 8. Also, as described above, in this Modification 3, an existing (general-purpose) configuration can be used for the information processing device 7A, and the same effects as those of the embodiment can be obtained by using, for example, the server 8 functioning as a cloud server. As a result, this Modification 3 can further improve user convenience.

[0185] [Variation 4] (composition) 33 is a block diagram showing an example configuration of an ejection parameter generation system 5B according to Modification 4. This ejection parameter generation system 5B of Modification 4 includes a printer 1B having an inkjet head 4B and the information processing device 7A described above. The printer 1B and the information processing device 7A are connected to each other via a network 50. In other words, this ejection parameter generation system 5B corresponds to the ejection parameter generation system 5 of the embodiment, except that the information processing device 7A described above 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 4B, respectively.

[0186] The above-described printer 1B corresponds to a specific example of a "liquid jet recording apparatus" in the present disclosure, and the above-described inkjet head 4B corresponds to a specific example of a "liquid jet head" in the present disclosure.

[0187] 33, in this modification 4, the information processing unit 73 (data acquisition unit 731, parameter generation unit 732, and table generation unit 733), in other words, the program 730, is provided in the inkjet head 4B. The machine learning model 74 is also provided in the inkjet head 4B. In other words, in this modification 4, unlike the embodiment and modification 3, the information processing unit 73 (program 730) and the machine learning model 74 are each provided in the inkjet head 4B built into the printer 1B.

[0188] (Actions and Effects) In the fourth modification having such a configuration, the injection parameter generation system 5B as a whole basically operates in the same manner as the injection parameter generation system 5 of the embodiment, and can obtain the same effects.

[0189] Furthermore, in particular, in this modification 4, the data acquisition unit 731, parameter generation unit 732, and table generation unit 733 are each provided within the printer 1B, resulting in the following: That is, unlike the embodiment and modification 3, there is no need to prepare the data acquisition unit 731, parameter generation unit 732, and table generation unit 733 within an external device (information processing device 7 or server 8). This allows the printer 1B itself to automatically generate the ejection parameters Prj and the predicted voltage characteristics table TPvp, thereby further improving user convenience.

[0190] Furthermore, in this fourth modification, the data acquisition unit 731, parameter generation unit 732, and table generation unit 733 are each provided in the inkjet head 4B built into the printer 1B, resulting in the following: In other words, the inkjet head 4B itself can automatically generate the ejection parameters Prj and the predicted voltage characteristics table TPvp while maintaining the existing configuration of the printer 1B itself except for the inkjet head 4B. As a result, it is possible to further improve user convenience.

[0191] [Variation 5] (composition) 34 is a block diagram showing an example configuration of an ejection parameter generation system 5C according to Modification 5. This ejection parameter generation system 5C of Modification 5 includes a printer 1C having the inkjet head 4 described above, and the information processing device 7A described above. The printer 1C and the information processing device 7A are connected to each other via a network 50. In other words, this ejection parameter generation system 5C corresponds to the ejection parameter generation system 5 of the embodiment, except that the information processing device 7 is replaced with the information processing device 7A described above, and the printer 1C is replaced with the printer 1.

[0192] The above-described printer 1C corresponds to a specific example of a "liquid jet recording apparatus" in the present disclosure.

[0193] In this modification 5, as shown in FIG. 34, the information processing unit 73 (data acquisition unit 731, parameter generation unit 732, and table generation unit 733), in other words, the program 730, is provided in the printer 1C, as in modification 4 (FIG. 33). Also, the machine learning model 74 is provided in the printer 1C, as in modification 4. However, as shown in FIG. 34, in this modification 5, unlike modification 4, the information processing unit 73 (program 730) and the machine learning model 74 are both located outside the inkjet head 4 in the printer 1C.

[0194] (Actions and Effects) In the fifth modified example having such a configuration, the injection parameter generation system 5C as a whole basically operates in the same manner as the injection parameter generation system 5 of the embodiment, and can obtain the same effects.

[0195] Furthermore, in particular, in this modification 5, as in the above-described modification 4, the data acquisition unit 731, the parameter generation unit 732, and the table generation unit 733 are each provided within the printer 1C, so that the following occurs: That is, as in the case of modification 4, the printer 1C itself can automatically generate the ejection parameters Prj and the predicted voltage characteristics table TPvp, and as a result, it is possible to further improve user convenience.

[0196] [Variation 6] (composition) 35 is a block diagram showing an example of the configuration of an information processing unit 73D (program 730D) according to Modification 6. The information processing unit 73D of Modification 6 corresponds to the information processing unit 73 (having a data acquisition unit 731, a parameter generation unit 732, and a table generation unit 733) described in the embodiment and the like, further provided with the signal generation unit 48 described above. In other words, the program 730D of Modification 6 corresponds to the program 730 described in the embodiment and the like, further including the functions of the processes performed in the signal generation unit 48 described above.

[0197] The configuration of such information processing unit 73D (program 730D) corresponds to, for example, the embodiment and modified example 3, where the configuration and functions of the signal generating unit 48 are further provided in addition to the information processing unit 73 (program 730) in an external device (information processing device 7 or server 8) of the printer 1. In other words, unlike these embodiment and modified example 3, it corresponds to an example where the configuration and functions of the signal generating unit 48 are provided not in the printer 1 but in an external device (information processing device 7 or server 8) of the printer 1.

[0198] (Actions and Effects) In the sixth modification having such a configuration, the same effects as those of the embodiment can be obtained by basically operating in the same manner.

[0199] Furthermore, in particular, in this modification 6, the configuration and functions of the signal generating unit 48 are further provided in the information processing unit 73D (program 730D), so the operation of the signal generating unit 48 (the operation of generating the drive signal Sd) can also be executed collectively in this information processing unit 73D (program 730D), thereby further improving user convenience.

[0200] <3. Other Modifications> The present disclosure has been described above by giving embodiments and modifications, but the present disclosure is not limited to these embodiments and can be modified in various ways.

[0201] For example, in the above embodiments, specific configuration examples (shape, arrangement, number, etc.) of each component in the printer and inkjet head are described. However, the configuration is not limited to those described in the above embodiments, and other shapes, arrangements, numbers, etc. may be used. Specifically, for example, in the above embodiments, a shuttle-type printer in which the inkjet head moves is described as an example. However, the present invention is not limited to this example. For example, a single-pass printer in which the inkjet head is fixed may be used. Furthermore, in the above embodiments, the ink tank is housed in a predetermined housing. However, the present invention is not limited to this example. The ink tank may be located outside the housing. Furthermore, in the above embodiments, the signal generation unit is mainly described as being located inside the inkjet head. However, the present invention is not limited to this example. The signal generation unit may be located outside the inkjet head in the printer.

[0202] Furthermore, various types of inkjet head structures can be applied. For example, the inkjet head may be a so-called side-shoot type that ejects ink 9 from the center of the actuator plate in the extension direction of each ejection channel. Alternatively, the inkjet head may be a so-called edge-shoot type that ejects ink 9 along the extension direction of each ejection channel. Furthermore, the printer type is not limited to the types described in the above embodiments, and various types can be applied, such as a thermal type (thermal on-demand type) or a MEMS (Micro Electro Mechanical Systems) type.

[0203] Furthermore, in the above-described embodiment and the like, a non-circulation inkjet head in which the ink 9 is not circulated between the ink tank and the inkjet head has been described as an example, but the present disclosure is not limited to this example. That is, the present disclosure can also be applied to a circulation inkjet head in which the ink 9 is circulated between the ink tank and the inkjet head.

[0204] Additionally, in the above-described embodiments, specific examples of the injection parameter Prj, the characteristic table (predicted voltage characteristic table TPvp), the generation process of the drive signal Sd, etc. have been described, but the present invention is not limited to the examples described in the above-described embodiments. That is, for example, other methods may be used to perform the generation process of the injection parameter Prj, the characteristic table, and the drive signal Sd. Specifically, in the above-described embodiments, a method using a machine learning model has been described as an example of the predetermined analysis method described above, but the present invention is not limited to this method, and other analysis methods may be used. Furthermore, the input parameter Prin described above is not limited to the various parameters described in the above-described embodiments, and other parameters may be added to (or replaced with) the analysis method.

[0205] In the above embodiments, the drive signal Sd is generated after both the pulse width Wp and the voltage value (peak value) Vp of the pulse are set (automatically adjusted), but this is not a limitation. For example, the drive signal Sd may be generated after only the pulse width Wp is set. Furthermore, in the above embodiments, the voltage values ​​Vp of the multiple pulses are all the same. However, the voltage values ​​Vp of the multiple pulses may not be the same (at least some of the voltage values ​​Vp may be different). Even in such a case, it is possible to use multiple types of voltage values ​​Vp as explanatory variables to generate the predicted voltage characteristics table TPvp described in the above embodiments.

[0206] Furthermore, in the above-described embodiment, the voltage sensitivity Vr, the conversion coefficient Kc, and the voltage shift amount ΔVp are described as examples of the injection parameter Prj, but the present invention is not limited to these examples. That is, for example, any combination of two or more of these various parameters (such as the voltage sensitivity Vr, the conversion coefficient Kc, and the voltage shift amount ΔVp) may be used as the injection parameter Prj. Also, for example, parameters other than these parameters may be used as the injection parameter Prj.

[0207] Additionally, in the above-described embodiments, the pulses (pulses Pa, Pb, Pc) that expand the volume in each ejection channel are described as pulses (positive pulses) that expand the volume during a high state, but this is not limited to this. That is, they may not only expand during a high state and contract during a low state, but also, conversely, may be pulses (negative pulses) that expand during a low state and contract during a high state. Note that even in the case of such negative pulses, as long as the method exhibits the same function as the above-described "common drive," such "common drive" can be applied.

[0208] Furthermore, for example, a pulse for assisting the ejection of droplets may be additionally applied during the OFF period immediately following the ON period. Examples of pulses for assisting the ejection of droplets include a pulse for contracting the volume of each ejection channel and a pulse (auxiliary pulse) for pulling back a portion of the ejected droplets. Furthermore, the pulse (main pulse) applied immediately before the latter auxiliary pulse has a pulse width equal to or less than the width of the ON pulse peak (AP). Note that adding such a pulse for assisting the ejection of droplets does not affect the content of the present disclosure described above.

[0209] Furthermore, the series of processes described in the above embodiments may be performed by hardware (circuits) or software (programs). When performed by software, the software is composed of a group of programs for causing a computer to execute each function. Each program may be, for example, pre-installed in the computer, or may be installed into the computer from a network or a recording medium. Note that examples of recording media (non-transitory computer-readable recording media) on which such programs are recorded include various media such as floppy disks, CD (Compact Disk)-ROMs, DVD (Digital Versatile Disc)-ROMs, and hard disks.

[0210] Furthermore, in the above-described embodiment, the printer 1 (inkjet printer) has been described as a specific example of the "liquid jet recording apparatus" of the present disclosure, but the present disclosure is not limited to this example and can be applied to devices other than inkjet printers. In other words, the "liquid jet head" (inkjet head) of the present disclosure may be applied to devices other than inkjet printers. Specifically, the "liquid jet head" of the present disclosure may be applied to devices such as facsimiles and on-demand printers, for example.

[0211] Additionally, the various examples described above may be applied in any combination.

[0212] The effects described in this specification are merely examples and are not limiting, and other effects may also be present.

[0213] The present disclosure can also be configured as follows. (1) 1. A system for generating predetermined ejection parameters used in generating a drive signal having one or more pulses to be applied to an ejection unit that ejects liquid, the system comprising: a data acquisition unit that acquires, as input data, a selection instruction signal input from an external device and predetermined input parameters; a parameter generating unit that generates the predetermined injection parameters based on the selection instruction signal and the predetermined input parameters by using a predetermined analysis method that uses the predetermined input parameters as explanatory variables and the predetermined injection parameters as objective variables; Equipped with The parameter generation unit determining which of the first and second standards to select based on the selection instruction signal indicating which of the first and second standards is selected, the first standard for setting the voltage value indicating the peak value of the pulse in the drive signal to a voltage value that will provide a reference droplet volume of the liquid, and the second standard for setting the voltage value to a voltage value that will provide a reference ejection speed of the liquid; When it is determined that the first criterion is to be selected, a first group of explanatory variables included in the predetermined input parameters is selected as the explanatory variables, while when it is determined that the second criterion is to be selected, a second group of explanatory variables included in the predetermined input parameters is selected as the explanatory variables; The predetermined injection parameters are generated by using the predetermined analysis method with only one of the selected first and second explanatory variable groups. Injection parameter generation system. (2) The predetermined injection parameters are: The voltage sensitivity of the liquid, which corresponds to the amount of change per unit voltage in the droplet volume or the ejection speed of the liquid when the liquid is ejected at a reference temperature, is At least contains The injection parameter generation system according to (1) above. (3) As the first explanatory variable group, A target value of the droplet volume of the liquid is set as follows: At least includes As the second group of explanatory variables, a parameter indicating whether or not a common drive is present in the drive signal; a drop number corresponding to the number of pulses included in a unit period of the drive signal; and At least one of the parameters The injection parameter generation system according to (2) above. (4) The first explanatory variable group further includes the number of drops, and As the second group of explanatory variables, a head rank value, which corresponds to the voltage value at which a predetermined discharge speed is achieved when a predetermined test liquid is ejected from the ejection unit, and which is a value specific to a liquid ejection head having the ejection unit; and a parameter indicating the type of the liquid jet head; the specific gravity of the liquid; the surface tension value of the liquid; a viscosity value of the liquid at a reference temperature; a target value of the liquid ejection speed; and further including at least one parameter of The injection parameter generation system according to (3) above. (5) A conversion process from an actual characteristic curve between the viscosity and temperature of the liquid to a predicted characteristic curve between the voltage value and temperature, which is used when generating the drive signal, a preliminary process of generating a preliminary characteristic curve indicating a relationship between the voltage value and temperature from the actual characteristic curve using a conversion coefficient used in the conversion process; an addition process for generating the predicted characteristic curve by adding a voltage shift amount to the voltage value in the preliminary characteristic curve; Contains At least one of the first and second explanatory variable groups further includes the voltage shift amount. The injection parameter generation system according to (3) or (4) above. (6) A conversion process from an actual characteristic curve between the viscosity and temperature of the liquid to a predicted characteristic curve between the voltage value and temperature, which is used when generating the drive signal, a preliminary process of generating a preliminary characteristic curve indicating a relationship between the voltage value and temperature from the actual characteristic curve using a conversion coefficient used in the conversion process; an addition process for generating the predicted characteristic curve by adding a voltage shift amount to the voltage value in the preliminary characteristic curve; Contains The predetermined injection parameters include at least the conversion coefficient. The injection parameter generation system according to any one of (1) to (5) above. (7) As the first explanatory variable group, the specific gravity of the liquid; a drop number corresponding to the number of pulses included in a unit period of the drive signal; and a viscosity value of the liquid at a reference temperature; a target value of the liquid ejection speed; the voltage shift amount; the voltage sensitivity of the liquid; a parameter indicating whether or not a common drive is present in the drive signal; the surface tension value of the liquid; a head rank value, which corresponds to the voltage value at which a predetermined discharge speed is achieved when a predetermined test liquid is ejected from the ejection unit, and which is a value specific to a liquid ejection head having the ejection unit; and a parameter indicating the type of the liquid jet head; a parameter indicating the type of the liquid, which is classified by the main solvent of the liquid; and As the second group of explanatory variables, the specific gravity of the liquid; a viscosity value of the liquid at a reference temperature; The number of drops; the voltage shift amount; the voltage sensitivity of the liquid; a parameter indicating the type of the liquid; the surface tension value of the liquid; The head rank value; Contains at least one parameter from The injection parameter generation system according to (6) above. (8) A conversion process from an actual characteristic curve between the viscosity and temperature of the liquid to a predicted characteristic curve between the voltage value and temperature, which is used when generating the drive signal, a preliminary process of generating a preliminary characteristic curve indicating a relationship between the voltage value and temperature from the actual characteristic curve using a conversion coefficient used in the conversion process; an addition process for generating the predicted characteristic curve by adding a voltage shift amount to the voltage value in the preliminary characteristic curve; Contains The predetermined injection parameters include at least the voltage shift amount. The injection parameter generation system according to any one of (1) to (7) above. (9) As the first explanatory variable group, a parameter indicating whether or not a common drive is present in the drive signal; a viscosity value of the liquid at a reference temperature; a head rank value, which corresponds to the voltage value at which a predetermined discharge speed is achieved when a predetermined test liquid is ejected from the ejection unit, and which is a value specific to a liquid ejection head having the ejection unit; and a parameter indicating the type of the liquid jet head; the specific gravity of the liquid; the surface tension value of the liquid; the voltage sensitivity of the liquid; a target value of the liquid ejection speed; a parameter indicating the type of the liquid, which is classified by the main solvent of the liquid; a drop number corresponding to the number of pulses included in a unit period of the drive signal; and and As the second group of explanatory variables, the voltage sensitivity of the liquid; a viscosity value of the liquid at a reference temperature; The head rank value; a parameter indicating the type of the liquid jet head; the surface tension value of the liquid; the specific gravity of the liquid; a parameter indicating whether or not a common drive is present in the drive signal; a target value of the liquid ejection speed; The number of drops; a parameter indicating the type of the liquid; Contains at least one parameter from The injection parameter generation system according to (8) above. (10) The predetermined analysis method is A method using a machine learning model, in which the predetermined input parameters are input and the predetermined injection parameters are output. The injection parameter generation system according to any one of (1) to (9) above. (11) a table generating unit that generates a predicted voltage characteristic table that defines the predicted characteristic curve based on an actual viscosity characteristic table that defines the actual characteristic curve by performing a conversion process from an actual characteristic curve between the viscosity and temperature of the liquid to a predicted characteristic curve between the voltage value and temperature using at least one of the predetermined ejection parameters; a signal generating unit that calculates a peak value of the pulse using the predicted voltage characteristics table generated by the table generating unit, and generates the drive signal using the pulse having the calculated peak value; Further equipped with The injection parameter generation system according to any one of (1) to (10) above. (12) The data acquisition unit and the parameter generation unit each The liquid jet recording apparatus includes a liquid jet head having the ejection unit, and the liquid jet recording apparatus includes an external device. The injection parameter generation system according to any one of (1) to (11) above. (13) The data acquisition unit and the parameter generation unit each The liquid jet recording apparatus includes a liquid jet head having the jetting unit. The injection parameter generation system according to any one of (1) to (11) above. (14) The data acquisition unit and the parameter generation unit each The liquid ejection head is provided with The injection parameter generation system according to (13) above. (15) 1. A method for generating predetermined ejection parameters used in generating a drive signal having one or more pulses to be applied to an ejection unit that ejects liquid, the method comprising: acquiring a selection instruction signal input from an external device and a predetermined input parameter as input data; generating the predetermined injection parameters based on the selection instruction signal and the predetermined input parameters using a predetermined analysis method that uses the predetermined input parameters as explanatory variables and the predetermined injection parameters as objective variables; Including, When generating the predetermined injection parameters, determining which of the first and second standards to select based on the selection instruction signal indicating which of the first and second standards is selected, the first standard for setting the voltage value indicating the peak value of the pulse in the drive signal to a voltage value that will provide a reference droplet volume of the liquid, and the second standard for setting the voltage value to a voltage value that will provide a reference ejection speed of the liquid; When it is determined that the first criterion is to be selected, a first group of explanatory variables included in the predetermined input parameters is selected as the explanatory variables, while when it is determined that the second criterion is to be selected, a second group of explanatory variables included in the predetermined input parameters is selected as the explanatory variables; The predetermined injection parameters are generated by using the predetermined analysis method with only one of the selected first and second explanatory variable groups. Injection parameter generation method. (16) A program for generating predetermined ejection parameters that are applied to an ejection unit that ejects liquid and are used when generating a drive signal having one or more pulses, acquiring a selection instruction signal input from an external device and a predetermined input parameter as input data; generating the predetermined injection parameters based on the selection instruction signal and the predetermined input parameters using a predetermined analysis method that uses the predetermined input parameters as explanatory variables and the predetermined injection parameters as objective variables; and causing a computer to execute the above. When generating the predetermined injection parameters, determining which of the first and second standards to select based on the selection instruction signal indicating which of the first and second standards is selected, the first standard for setting the voltage value indicating the peak value of the pulse in the drive signal to a voltage value that will provide a reference droplet volume of the liquid, and the second standard for setting the voltage value to a voltage value that will provide a reference ejection speed of the liquid; When it is determined that the first criterion is to be selected, a first group of explanatory variables included in the predetermined input parameters is selected as the explanatory variables, while when it is determined that the second criterion is to be selected, a second group of explanatory variables included in the predetermined input parameters is selected as the explanatory variables; The predetermined injection parameters are generated by using the predetermined analysis method with only one of the selected first and second explanatory variable groups. Injection parameter generation program. (17) A non-transitory computer-readable recording medium having a program recorded thereon for generating predetermined ejection parameters, the program being applied to an ejection unit that ejects liquid and being used when generating a drive signal having one or more pulses, acquiring a selection instruction signal input from an external device and a predetermined input parameter as input data; generating the predetermined injection parameters based on the selection instruction signal and the predetermined input parameters using a predetermined analysis method that uses the predetermined input parameters as explanatory variables and the predetermined injection parameters as objective variables; and causing a computer to execute the above. When generating the predetermined injection parameters, determining which of the first and second standards to select based on the selection instruction signal indicating which of the first and second standards is selected, the first standard for setting the voltage value indicating the peak value of the pulse in the drive signal to a voltage value that will provide a reference droplet volume of the liquid, and the second standard for setting the voltage value to a voltage value that will provide a reference ejection speed of the liquid; When it is determined that the first criterion is to be selected, a first group of explanatory variables included in the predetermined input parameters is selected as the explanatory variables, while when it is determined that the second criterion is to be selected, a second group of explanatory variables included in the predetermined input parameters is selected as the explanatory variables; generating the predetermined injection parameters by utilizing the predetermined analysis method using only one of the selected first and second explanatory variable groups; The injection parameter generation program is recorded Recording medium. [Explanation of symbols]

[0214] 1, 1B, 1C... printer, 10... housing, 2a, 2b... transport 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 network, 6...scanning mechanism, 61a, 61b...guide rail, 62...carriage, 63...driving mechanism, 631a, 631b...pulley, 632...endless belt, 633...driving motor, 7, 7A...information processing device, 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 unit, 77...network IF, 8...server, 80...bus, 85...control unit, 86...storage unit, 87...network IF, 9...ink, P...recording paper, d...transport direction, Hn...nozzle hole, Sd...driving signal, Vd...driving voltage, Vr...voltage sensitivity, Ta...ambient temperature, Tr...reference temperature, Iv...viscosity information, Vi...viscosity, ΔV...differential value, ΔVp...voltage shift amount, Wp, Wpa1, Wpa2 ,Wpa3,Wpb2,Wpb3,Wpc3...pulse width, Vp,Vp1,Vp2,Vp3...voltage value (peak value), Pa,Pb,Pc...pulse, Ss...selection instruction 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. 1. A system for generating predetermined ejection parameters for use in generating a drive signal having one or more pulses to be applied to an ejector that ejects liquid, the system comprising: a data acquisition unit that acquires, as input data, a selection instruction signal input from an external device and predetermined input parameters; a parameter generating unit that generates the predetermined injection parameters based on the selection instruction signal and the predetermined input parameters by using a predetermined analysis method that uses the predetermined input parameters as explanatory variables and the predetermined injection parameters as objective variables; Equipped with The parameter generation unit determining which of the first and second standards to select based on the selection instruction signal indicating which of the first and second standards is selected, the first standard for setting the voltage value indicating the peak value of the pulse in the drive signal to a voltage value that will provide a reference droplet volume of the liquid, and the second standard for setting the voltage value to a voltage value that will provide a reference ejection speed of the liquid; When it is determined that the first criterion is to be selected, a first group of explanatory variables included in the predetermined input parameters is selected as the explanatory variables, while when it is determined that the second criterion is to be selected, a second group of explanatory variables included in the predetermined input parameters is selected as the explanatory variables; The predetermined injection parameters are generated by using the predetermined analysis method with only one of the selected first and second explanatory variable groups. Injection parameter generation system.

2. The predetermined injection parameters are: The voltage sensitivity of the liquid, which corresponds to the amount of change per unit voltage in the droplet volume or the ejection speed of the liquid when the liquid is ejected at a reference temperature, is At least contains The injection parameter generation system of claim 1 .

3. As the first explanatory variable group, A target value of the droplet volume of the liquid is set as follows: At least includes As the second explanatory variable group, a parameter indicating whether or not a common drive is present in the drive signal; a drop number corresponding to the number of pulses included in a unit period of the drive signal; and At least one of the parameters The injection parameter generation system according to claim 2 .

4. The first explanatory variable group further includes the number of drops, and As the second explanatory variable group, a head rank value, which corresponds to the voltage value at which a predetermined discharge speed is achieved when a predetermined test liquid is ejected from the ejection unit, and which is a value specific to a liquid ejection head having the ejection unit; and a parameter indicating the type of the liquid jet head; the specific gravity of the liquid; the surface tension value of the liquid; a viscosity value of the liquid at a reference temperature; a target value of the liquid ejection speed; and further including at least one parameter of The injection parameter generation system according to claim 3 .

5. As 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, a preliminary process of generating a preliminary characteristic curve indicating a relationship between the voltage value and temperature from the actual characteristic curve using a conversion coefficient used in the conversion process; an addition process for generating the predicted characteristic curve by adding a voltage shift amount to the voltage value in the preliminary characteristic curve; Contains By performing the conversion process, a predicted voltage characteristics table defining the predicted characteristic curve is generated based on an actual viscosity characteristics table defining the actual characteristic curve, and the drive signal is generated based on the predicted voltage characteristics table, At least one of the first and second explanatory variable groups further includes the voltage shift amount.

5. The injection parameter generation system according to claim 3 or 4.

6. A conversion process from an actual characteristic curve between the viscosity and temperature of the liquid to a predicted characteristic curve between the voltage value and temperature, a preliminary process of generating a preliminary characteristic curve indicating a relationship between the voltage value and temperature from the actual characteristic curve using a conversion coefficient used in the conversion process; an addition process for generating the predicted characteristic curve by adding a voltage shift amount to the voltage value in the preliminary characteristic curve; Contains By performing the conversion process, a predicted voltage characteristics table defining the predicted characteristic curve is generated based on an actual viscosity characteristics table defining the actual characteristic curve, and the drive signal is generated based on the predicted voltage characteristics table, The predetermined injection parameters include at least the conversion coefficient. The injection parameter generation system of claim 1 .

7. As 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, a preliminary process of generating a preliminary characteristic curve indicating a relationship between the voltage value and temperature from the actual characteristic curve using a conversion coefficient used in the conversion process; an addition process for generating the predicted characteristic curve by adding a voltage shift amount to the voltage value in the preliminary characteristic curve; Contains By performing the conversion process, a predicted voltage characteristics table defining the predicted characteristic curve is generated based on an actual viscosity characteristics table defining the actual characteristic curve, and the drive signal is generated based on the predicted voltage characteristics table, The predetermined injection parameters include at least the voltage shift amount. The injection parameter generation system of claim 1 .

8. The predetermined analysis method is A method using a machine learning model, in which the predetermined input parameters are input and the predetermined injection parameters are output. The injection parameter generation system according to any one of claims 1 to 7.

9. a table generating unit that generates a predicted voltage characteristic table that defines the predicted characteristic curve based on an actual viscosity characteristic table that defines the actual characteristic curve by performing a conversion process from an actual characteristic curve between the viscosity and temperature of the liquid to a predicted characteristic curve between the voltage value and temperature using at least one of the predetermined ejection parameters; a signal generating unit that calculates a peak value of the pulse using the predicted voltage characteristics table generated by the table generating unit, and generates the drive signal using the pulse having the calculated peak value; Further equipped with The injection parameter generation system according to any one of claims 1 to 8.

10. The data acquisition unit and the parameter generation unit each The liquid jet recording apparatus includes a liquid jet head having the ejection unit, and the liquid jet recording apparatus includes an external device. The injection parameter generation system according to any one of claims 1 to 9.

11. The data acquisition unit and the parameter generation unit each The liquid jet recording apparatus includes a liquid jet head having the jetting unit. The injection parameter generation system according to any one of claims 1 to 9.

12. The data acquisition unit and the parameter generation unit each The liquid ejection head is provided with The jetting parameter generation system of claim 11.

13. 1. A method for generating predetermined ejection parameters for use in generating a drive signal having one or more pulses to be applied to an ejector that ejects liquid, the method comprising: acquiring a selection instruction signal input from an external device and a predetermined input parameter as input data; generating the predetermined injection parameters based on the selection instruction signal and the predetermined input parameters using a predetermined analysis method that uses the predetermined input parameters as explanatory variables and the predetermined injection parameters as objective variables; Including, When generating the predetermined injection parameters, determining which of the first and second standards to select based on the selection instruction signal indicating which of the first and second standards is selected, the first standard for setting the voltage value indicating the peak value of the pulse in the drive signal to a voltage value that will provide a reference droplet volume of the liquid, and the second standard for setting the voltage value to a voltage value that will provide a reference ejection speed of the liquid; When it is determined that the first criterion is to be selected, a first group of explanatory variables included in the predetermined input parameters is selected as the explanatory variables, while when it is determined that the second criterion is to be selected, a second group of explanatory variables included in the predetermined input parameters is selected as the explanatory variables; The predetermined injection parameters are generated by using the predetermined analysis method with only one of the selected first and second explanatory variable groups. Injection parameter generation method.

14. A program for generating predetermined ejection parameters to be applied to an ejection unit that ejects liquid and to be used when generating a drive signal having one or more pulses, acquiring a selection instruction signal input from an external device and a predetermined input parameter as input data; generating the predetermined injection parameters based on the selection instruction signal and the predetermined input parameters using a predetermined analysis method that uses the predetermined input parameters as explanatory variables and the predetermined injection parameters as objective variables; and causing a computer to execute the above. When generating the predetermined injection parameters, determining which of the first and second standards to select based on the selection instruction signal indicating which of the first and second standards is selected, the first standard for setting the voltage value indicating the peak value of the pulse in the drive signal to a voltage value that will provide a reference droplet volume of the liquid, and the second standard for setting the voltage value to a voltage value that will provide a reference ejection speed of the liquid; When it is determined that the first criterion is to be selected, a first group of explanatory variables included in the predetermined input parameters is selected as the explanatory variables, while when it is determined that the second criterion is to be selected, a second group of explanatory variables included in the predetermined input parameters is selected as the explanatory variables; The predetermined injection parameters are generated by using the predetermined analysis method with only one of the selected first and second explanatory variable groups. Injection parameter generation program.

Images