Characteristic table generating system, characteristic table generating method, and characteristic table generating program

Abstract

To provide a characteristic table generations system capable of improving convenience of a user.SOLUTION: A characteristic table generation system for generating a prediction voltage characteristic table for regulating a prediction characteristic curve includes: a data acquisition part for acquiring each of a measured viscosity characteristic table regulating a measured characteristic curve between viscosity and a temperature of a liquid and a predetermined parameter as input data; a conversion coefficient generation part for generating a conversion coefficient on the basis of the predetermined parameter using a first analysis method as a predetermined analysis method for setting the predetermined parameter at an explanatory variable and setting a conversion coefficient when performing conversion processing from the measured characteristic curve to the prediction characteristic curve as an objective variable; and a table generation part for generating the prediction voltage characteristic table by performing the conversion processing using the measured viscosity characteristic table and the conversion coefficient generated by the conversion coefficient generation part.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present disclosure relates to a characteristic table generating system, a characteristic table generating method, and a characteristic table generating program. [Background technology]

[0002] 2. Description of the Related Art 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] JP 2012-187850 A Summary of the Invention [Problem to be solved by the invention]

[0004] In such a liquid ejection head, there is a demand for improving user convenience. It is desirable to provide a characteristic table generating system, a characteristic table generating method, and a characteristic table generating program that are capable of improving user convenience. [Means for solving the problem]

[0005] A characteristic table generating system according to one embodiment of the present disclosure is a system for generating a predicted voltage characteristic table that specifies a predicted characteristic curve between a voltage value indicating a pulse peak value based on a predetermined reference value in a drive signal that is applied to an ejection unit that ejects a liquid and has one or more pulses, and a temperature. The system includes a data acquisition unit that acquires, as input data, an actual viscosity characteristic table that specifies an actual characteristic curve between the viscosity of the liquid and temperature, and predetermined parameters, a conversion coefficient generating unit that generates a conversion coefficient based on the predetermined parameters using a first analysis method as a predetermined analysis method, in which the predetermined parameters are explanatory variables and a conversion coefficient used when performing a conversion process from the actual characteristic curve to the predicted characteristic curve is an objective variable, and a table generating unit that generates the predicted voltage characteristic table by performing the conversion process using the actual viscosity characteristic table and the conversion coefficient generated by the conversion coefficient generating unit.

[0006] A characteristic table generating method according to one embodiment of the present disclosure is a method for generating a predicted voltage characteristic table that specifies a predicted characteristic curve between temperature and a voltage value indicating a peak value of a pulse of a driving signal having one or more pulses, the driving signal being applied to an ejection section that ejects liquid, the voltage value indicating the peak value of the pulse being based on a predetermined reference value, the voltage value being based on a predetermined reference value, the method including: acquiring, as input data, an actual viscosity characteristic table that specifies an actual characteristic curve between the viscosity of the liquid and temperature, and predetermined parameters; generating a conversion coefficient based on the predetermined parameters using a first analysis method as a predetermined analysis method, the first analysis method using the predetermined parameters as explanatory variables and a conversion coefficient used when performing a conversion process from the actual characteristic curve to the predicted characteristic curve as an objective variable; and generating the predicted voltage characteristic table by performing the conversion process using the actual viscosity characteristic table and the generated conversion coefficient.

[0007] A characteristic table generating program according to one embodiment of the present disclosure is a program for generating a predicted voltage characteristic table that specifies a predicted characteristic curve between temperature and a voltage value indicating a peak value of a pulse, the peak value being based on a predetermined reference value, in a drive signal that is applied to an ejection section that ejects liquid and has one or more pulses. The program is configured to cause a computer to execute the following steps: acquire an actual viscosity characteristic table that specifies an actual characteristic curve between the viscosity of the liquid and temperature, and predetermined parameters as input data; generate a conversion coefficient based on the predetermined parameters using a first analysis method as a predetermined analysis method, in which the predetermined parameters are explanatory variables and a conversion coefficient used when performing a conversion process from the actual characteristic curve to the predicted characteristic curve is an objective variable; and generate the predicted voltage characteristic table by performing the conversion process using the actual viscosity characteristic table and the generated conversion coefficient. Effect of the Invention

[0008] According to a characteristic table generating system, a characteristic table generating method, and a characteristic table generating program according to an embodiment of the present disclosure, it is possible to improve user convenience. [Brief description 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. [Diagram 2] 2 is a schematic diagram illustrating an example of a schematic configuration of the liquid jet head illustrated in FIG. [Diagram 3] 1 is a functional block diagram illustrating an example of the configuration of a characteristic table generating system according to an embodiment. [Figure 4] 4 is a physical block diagram illustrating an example of the configuration of the information processing device illustrated in FIG. 3. [Diagram 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 illustrating an example of a configuration of a drive signal. [Figure 7] FIG. 1 is a block diagram illustrating an example of a schematic configuration of a liquid jet recording apparatus according to a comparative example. [Figure 8] FIG. 11 is a diagram illustrating an example of viscosity information according to a comparative example. [Figure 9] 6A to 6C are diagrams illustrating an example of various characteristic curves according to a comparative example. [Figure 10] 11 is a flowchart illustrating an example of a conversion process according to an embodiment. [Figure 11] 5A to 5C are diagrams illustrating examples of various characteristic curves according to the embodiment. [Figure 12] FIG. 4 is a diagram illustrating an example of a predetermined parameter according to the embodiment. [Figure 13] FIG. 13 is a diagram illustrating an example of an importance analysis result of each parameter shown in FIG. [Figure 14] 4 is a flowchart showing a process of generating a characteristic table according to an embodiment. [Figure 15] FIG. 13 is a diagram illustrating an example of predicted values ​​and actual measured values ​​by machine learning according to the embodiment. [Figure 16A] 16 is a diagram illustrating an example of a correspondence relationship between an SVM predicted value and an actual measurement value illustrated in FIG. 15. [Figure 16B] 16 is a diagram illustrating an example of a correspondence relationship between an RF predicted value and an actual measurement value illustrated in FIG. 15. FIG. [Figure 17A] 14 is a diagram illustrating an example of a correspondence relationship between an RF predicted value and an actual measurement value when only some of the parameters shown in FIG. 13 are used. FIG. [Figure 17B] 14 is a diagram illustrating an example of a correspondence relationship between an RF predicted value and an actual measurement value when only some of the parameters shown in FIG. 13 are used. FIG. [Figure 17C] 14 is a diagram illustrating an example of a correspondence relationship between an RF predicted value and an actual measurement value when only some of the parameters shown in FIG. 13 are used. FIG. [Figure 18] FIG. 1 is a block diagram illustrating an example of the configuration of a machine learning model according to a first modified example. [Figure 19] FIG. 11 is a diagram illustrating an example of predetermined parameters according to the first modification. [Figure 20] FIG. 20 is a diagram illustrating an example of an importance analysis result of each parameter shown in FIG. 19. [Figure 21] FIG. 11 is a diagram illustrating an example of predicted values ​​and actual measured values ​​by machine learning according to Modification Example 1. [Figure 22A] 22 is a diagram illustrating an example of a correspondence relationship between an SVM predicted value and an actual measurement value illustrated in FIG. 21. FIG. [Figure 22B] 22 is a diagram illustrating an example of a correspondence relationship between an RF predicted value and an actual measurement value illustrated in FIG. 21. FIG. [Figure 23] 21 is a diagram illustrating an example of a correspondence relationship between an RF predicted value and an actual measurement value in a case where only some of the parameters shown in FIG. 20 are used. FIG. [Figure 24] FIG. 11 is a block diagram illustrating an example of the configuration of a machine learning model according to Modification Example 2. [Diagram 25] FIG. 11 is a diagram illustrating an example of a predetermined parameter according to Modification 2. [Figure 26] FIG. 26 is a diagram illustrating an example of an importance analysis result of each parameter shown in FIG. 25. [Figure 27] FIG. 11 is a diagram illustrating an example of predicted values ​​and actual measured values ​​by machine learning according to Modification Example 2. [Figure 28A] 28 is a diagram illustrating an example of a correspondence relationship between an SVM predicted value and an actual measurement value illustrated in FIG. 27. [Figure 28B] 28 is a diagram illustrating an example of a correspondence relationship between an RF predicted value and an actual measurement value illustrated in FIG. 27. [Figure 29A] 27 is a diagram illustrating an example of a correspondence relationship between an RF predicted value and an actual measurement value in a case where only some of the parameters shown in FIG. 26 are used. FIG. [Figure 29B] 27 is a diagram illustrating an example of a correspondence relationship between an RF predicted value and an actual measurement value in a case where only some of the parameters shown in FIG. 26 are used. FIG. [Figure 29C] 27 is a diagram illustrating an example of a correspondence relationship between an RF predicted value and an actual measurement value in a case where only some of the parameters shown in FIG. 26 are used. FIG. [Diagram 30] FIG. 13 is a block diagram illustrating an example of the configuration of a characteristic table generating system according to a third modified example. [Diagram 31] FIG. 13 is a block diagram illustrating an example of the configuration of a characteristic table generating system according to a fourth modified example. [Diagram 32]FIG. 13 is a block diagram illustrating an example of the configuration of a characteristic table generating system according to a fifth modified example. [Diagram 33] FIG. 23 is a block diagram illustrating an example of the configuration of an information processing unit according to Modification 6. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[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 an information processing section is provided in an information processing device outside a liquid jet recording device) 2. Variations Modification 1 (an example in which a machine learning model with voltage sensitivity as a response variable is further provided) Modification 2 (an example in which a machine learning model is further provided with the voltage shift amount as the objective variable) Modification 3 (Example in which the information processing section 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 of 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. Preferred 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 device according to an embodiment of the present disclosure. The printer 1 is an inkjet printer that uses ink 9, which will be described later, to record (print) images, characters, and the like on recording paper P as a recording medium.

[0012] 1, the printer 1 includes a pair of transport mechanisms 2a, 2b, an ink tank 3, an ink supply tube 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 each of the drawings used in the description of this specification, the scale of each component has been appropriately changed so that each component is of a recognizable size.

[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 the transport mechanisms 2a and 2b has a grid roller 21, a pinch roller 22, and a drive mechanism (not shown). The drive mechanism is a mechanism that rotates the grid roller 21 around its axis (rotates it in the ZX plane), and is composed of, for example, a motor.

[0015] (Ink Tank 3) The ink tank 3 is a tank that contains ink 9. In this example, as shown in Fig. 1, four types of ink tanks are provided, each of which contains 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] In addition, the ink tanks 3Y, 3M, 3C, and 3K have the same configuration except for the color of the ink 9 they contain, so they will be collectively referred to as the 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 from a plurality of nozzles (nozzle holes Hn) to be described later onto the recording paper P to record (print) images, characters, and the like. In this example, as shown in FIG. 1, the inkjet head 4 is provided with four types of heads that eject the four colors of ink 9 contained in the ink tanks 3Y, 3M, 3C, and 3K, respectively. That is, the inkjet head 4Y ejects the yellow ink 9, the inkjet head 4M ejects the magenta ink 9, the inkjet head 4C ejects the cyan ink 9, and the inkjet head 4K ejects the 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 the 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 having a flexibility sufficient to follow the operation of the scanning mechanism 6 described below.

[0020] (Scanning mechanism 6) The scanning mechanism 6 is a mechanism for scanning 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 extending along the Y-axis direction, a carriage 62 movably supported on these guide rails 61a, 61b, and a drive mechanism 63 for moving the carriage 62 along the Y-axis direction.

[0021] The drive mechanism 63 has 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. In addition, the four types of inkjet heads 4Y, 4M, 4C, and 4K described above are arranged on the carriage 62 in the Y-axis direction.

[0022] The scanning mechanism 6 and the transport mechanisms 2a and 2b described above form 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 for ejecting ink 9 (see the dashed arrows in Fig. 2). These nozzle holes Hn are formed in a 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 a 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 in a predetermined direction.

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

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

[0032] [C. Overall configuration of characteristic table generation system 5] Next, an example of the overall configuration of a characteristic table generating system 5 including the printer 1 having the above-mentioned inkjet head 4 will be described with reference to FIGS.

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

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

[0035] The characteristic table generating system 5 is a system that generates a predicted voltage characteristic table TPvp (characteristic table that specifies a predicted characteristic curve CPvp between a voltage value Vp indicating a peak value of a pulse of the driving signal Sd based on a predetermined reference value (described later) and an environmental temperature Ta (described later). As shown in Fig. 3, the characteristic table generating system 5 includes a printer 1 having the inkjet head 4 described above, and an information processing device 7. The printer 1 and the information processing device 7 are connected to each other via a network 50.

[0036] The network 50 is a network that communicates using a communication protocol (TCP / IP) that is commonly used on the Internet. The network 50 may be a secure network that communicates using a communication protocol unique to the network. The network 50 may be the Internet, an intranet, or a local area network. The network 50 may be connected to the printer 1 and the information processing device 7 via a wired LAN (Local Area Network) 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, for example, by 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 with, for example, a keyboard, a mouse, etc. Also, the input unit 71 may be configured with, 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 displays 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 section that performs various types of information processing, and has a data acquisition unit 731, a conversion coefficient generation unit 732, and a table generation unit 733, as shown in Fig. 3. Moreover, such information processing unit 73 is configured using a control unit 75, a storage unit 76, and a network IF (Interface) 77, as shown in Fig. 4 (physical block diagram). In the example of Fig. 4, the input unit 71, the display unit 72, the control unit 75, the storage unit 76, and the network IF 77 are each connected to one another via a bus 70.

[0042] 3, the data acquisition unit 731 acquires the following data (input data) via the above-mentioned input unit 71, the network 50, etc. That is, the data acquisition unit 731 acquires, as input data, a measured viscosity characteristic table TMvi (a characteristic table that specifies a measured characteristic curve CMvi between the viscosity Vi of the ink 9 and the environmental temperature Ta) described later and predetermined parameters Pr described later.

[0043] As shown in Fig. 3, the conversion coefficient generating unit 732 uses a predetermined analysis method (first analysis method) based on the parameters Pr acquired by the data acquiring unit 731 to generate a conversion coefficient Kc for a predetermined conversion process (conversion process from the above-mentioned actual characteristic curve CMvi to the above-mentioned predicted characteristic curve CPvp: see Figs. 10 and 11) described later. This predetermined analysis method is an analysis method that uses the above-mentioned parameters Pr as explanatory variables and the above-mentioned conversion coefficient Kc as a response variable. In the example of this embodiment, as shown in Figs. 3 and 4, the conversion coefficient generating unit 732 generates the conversion coefficient Kc based on the parameters Pr by utilizing an analysis method using the machine learning model 74 described below.

[0044] As described above, the machine learning model 74 is a prediction model obtained by performing machine learning using the parameters Pr as explanatory variables and the conversion coefficient Kc as a response variable. As shown in Fig. 5, when the parameters Pr (explanatory variables) are input, the machine learning model 74 generates (predicts) the conversion coefficient Kc (response variable) based on the learning result and outputs the generated conversion coefficient Kc.

[0045] Examples of analytical methods (prediction methods) using such machine learning models 74 include Support Vector Machines (SVM), Random Forests (RF), and multiple regression analysis.

[0046] 3, the table generating unit 733 generates the predicted voltage characteristics table TPvp by performing the above-mentioned predetermined conversion process using the actual viscosity characteristics table TMvi acquired by the data acquiring unit 731 and the conversion coefficient Kc generated by the conversion coefficient 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.

[0047] The details of each process in the information processing unit 73 (the data acquisition unit 731, the conversion coefficient generating unit 732, and the table generating unit 733) will be described later.

[0048] The control unit 75 shown in FIG. 4 includes a central processing unit (CPU) and a graphics processing unit (GPU), and executes various programs stored in the storage unit 76, for example. Specifically, the control unit 75 executes a program 730 stored in the storage unit 76, for example, as shown in FIG. 4. The program 730 is a program for executing each process in the information processing unit 73 (the data acquisition unit 731, the conversion coefficient generation unit 732, and the table generation unit 733). Specifically, the program 730 is a program for causing a computer (the control unit 75) to execute each function in the information processing unit 73 (the data acquisition unit 731, the conversion coefficient generation unit 732, and the table generation unit 733).

[0049] The storage unit 76 is a part that stores various programs executed by the control unit 75 and various data. 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. Such 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), and the like.

[0050] The network IF 77 is a communication interface for communicating with the printer 1 via the network 50 as shown in FIG.

[0051] (Signal Generation Unit 48) Here, in the example shown in FIG. 3, the inkjet head 4 has a signal generating section 48 in addition to the nozzle plate 41, the actuator plate 42, and the driving section 49 described above.

[0052] This signal generating unit 48 generates a drive signal Sd having one or more pulses (pulse width Wp, voltage value Vp indicating the crest 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 schematic timing diagrams showing configuration examples of such a drive signal Sd. In these figures, the horizontal axis indicates time t, and the vertical axis indicates the drive voltage Vd (positive voltage in this example) of the drive signal Sd.

[0054] First, the drive signal Sd shown in Fig. 6A has one pulse (pulse Pa), which is an example of the 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 above-mentioned pulse width Wp and voltage value Vp.

[0055] On the other hand, the drive signal Sd shown in FIG. 6(B) has the following two pulses (pulses Pa, 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. Also, as an example of the above-mentioned pulse width Wp and voltage value Vp, the pulse Pa has a pulse width Wpa2 and a voltage value Vp2, and the pulse Pb has a pulse width Wpb2 and a voltage value Vp2.

[0056] Similarly, the drive signal Sd shown in FIG. 6C 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, as such pulses (ON periods), three pulses Pa, Pb, and Pc are provided. Note that an OFF period ("OFF1") is provided between the pulses Pa and Pb, and an OFF period ("OFF2") is provided between the pulses Pb and Pc. In addition, as an example of the above-mentioned pulse width Wp and voltage value Vp, the pulse Pa has a pulse width Wpa3 and a voltage value Vp3, the pulse Pb has a pulse width Wpb3 and a voltage value Vp3, and the pulse Pc has a pulse width Wpc3 and a voltage value Vp3.

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

[0058] Here, the signal generating unit 48, which will be described in detail later, sets the pulse width Wp and voltage value Vp of each of these pulses (pulses Pa, Pb, Pc), and generates the drive signal Sd using a pulse 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 voltage value Vp of the pulse, and generates the drive signal Sd using a pulse having the determined voltage value Vp.

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

[0060] [Operation and Effects] (A. Basic operation of Printer 1) In this printer 1, the recording operation (printing operation) of images, characters, etc. on the 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 fully filled with ink 9 of the corresponding color (four colors). The ink 9 in the ink tanks 3 is filled in the inkjet head 4 via the ink supply pipe 30.

[0061] In this initial state, when the printer 1 is operated, the grid rollers 21 in the transport mechanisms 2a and 2b rotate, and the recording paper P is transported 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, respectively, to operate the endless belt 632. As a result, the carriage 62 reciprocates 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) appropriately eject four colors of ink 9 onto the recording paper P, thereby recording images, characters, and the like onto 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 is performed using a shear mode 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 of the driving electrodes 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 is bent and deformed in a V shape around 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 is bulging. In this way, the volume of the ejection channel increases due to the bending deformation caused by the piezoelectric thickness slip effect at the pair of drive walls. This increase in the volume of the ejection channel leads to the ink 9 being guided into the ejection channel.

[0065] Next, the ink 9 guided into the ejection channel in this manner becomes a pressure wave and 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, which had once 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 (toward the recording paper P) (see Figs. 2 and 3). In this way, the ink jet head 4 ejects the ink 9 (ejects the ink), and as a result, the ink jet head 4 records (prints) images, characters, etc. on the recording paper P.

[0067] (C. Generation of characteristic table, etc.) Next, with reference to FIGS. 7 to 17 in addition to FIGS. 1 to 6, the generation operation (generation process) of the characteristic table (the above-mentioned predicted voltage characteristic table TPvp) in the characteristic table generation system 5 will be described in detail while comparing with comparative examples (FIGS. 7 to 9).

[0068] (C-1. Comparative example) 7 is a block diagram showing an example of the schematic configuration of a printer 101 as a liquid jet recording apparatus according to a comparative example. The printer 101 of the comparative example includes the nozzle plate 41, actuator plate 42, signal generating unit 48, and driving unit 49 described above in an inkjet head of the comparative example (not shown).

[0069] However, in the printer 101 of this comparative example, 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.

[0070] Fig. 8 shows an example of viscosity information Iv according to such a comparative example. Specifically, Fig. 8 shows an example of the correspondence (information including viscosity information Iv) between the environmental temperature Ta, the viscosity Vi (actual measurement value) of the ink 9, the voltage value Vp (actual measurement 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. 8 shows a characteristic curve between the viscosity Vi (actual measurement value) and the environmental temperature Ta (actual measurement characteristic curve CMvi), a characteristic curve between the voltage value Vp (actual measurement value) and the environmental temperature (actual measurement characteristic curve CMvp), and a characteristic curve between the difference value ΔV and the environmental temperature Ta.

[0071] The above-mentioned environmental temperature Ta corresponds to a specific example of "temperature" in the present disclosure.

[0072] Incidentally, the "viscosity Vi of the ink 9" referred to here means the static viscosity, and the same applies below. The viscosity Vi of the ink 9 is measured, for example, using 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).

[0073] In this comparative example, first, the viscosity information Iv as shown in Fig. 8 is obtained by detecting the change in the viscosity Vi of the ink 9 with respect to the change in the environmental temperature Ta (for example, performing measurements at five or more points). Also, as shown in Fig. 8, it is known that the change in the viscosity Vi of the ink 9 with respect to the environmental temperature Ta and the change in the voltage value Vp (the voltage value Vp at which a reference ejection speed is obtained) with respect to the environmental temperature Ta show similar change characteristics. Therefore, as shown in Fig. 8, the difference value ΔV between the viscosity Vi and the voltage value Vp shows a substantially constant value independent of the environmental temperature Ta.

[0074] 7, the signal generating unit 48 in this comparative example uses the similarity of the temperature change characteristics to subtract a difference value ΔV (negative value) calculated in advance from the value of the viscosity Vi (see the viscosity information Iv) at a certain environmental 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 this comparative example uses the relational expression Vp=(Vi-ΔV) (see FIG. 8) to obtain the voltage value Vp at a certain environmental temperature Ta.

[0075] Incidentally, the characteristic curve between the voltage value Vp and the ambient temperature Ta (the measured characteristic curve CMvp described above) generally has a different slope depending on the type of 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, such measured characteristic curve CMvp basically needs to be measured manually in advance. However, under limited conditions (for example, the above-mentioned case of "one drop" based on the ejection speed), it is possible to derive such measured characteristic curve CMvp without measuring it.

[0076] 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 this comparative example, it requires a huge amount of time and effort, and the workload and cost of work increase.

[0077] Here, FIG. 9 shows an example of various characteristic curves (measured characteristic curves CMvp and CMvi) according to a comparative example. Specifically, the measured characteristic curves CMvp shown in FIG. 9 show the cases where the number of pulses (the number of drops described above) is 1 drop (denoted as "1d"), 3 drops (denoted as "3d"), 7 drops (denoted as "7d"), and 9 drops (denoted as "9d"). Also, each measured characteristic curve CMvp shown in FIG. 9 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 speed is obtained when the ink 9 is ejected, and the voltage value Vp (denoted as "DV reference") at which a reference droplet volume (DV: Drop Volume) of the ink 9 is obtained. It should be noted that the driving waveforms used to obtain the various characteristic curves shown in FIG. 9 include the case of "common driving" (described later) for all conditions (number of drops).

[0078] In the example shown in Fig. 9, the slope of the measured characteristic curve CMvp differs depending on the type of pulse number (drop number) and the type of the above-mentioned predetermined reference value (Vj-based or DV-based), as described above. Therefore, if a single measured characteristic curve CMvp is reused when generating the drive signal Sd, for example, as in the viscosity information Iv of the comparative example shown in Fig. 8, the setting accuracy of the voltage value Vp will decrease due to differences in the slope depending on the type of pulse number, the type of the predetermined reference value, the type and role of each pulse, etc. In other words, it becomes difficult to set the voltage value Vp (peak value) of the pulse in the drive signal Sd with high accuracy.

[0079] Specifically, in this comparative example, for example, only a single voltage characteristics 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, to obtain the measured characteristic curve CMvp for each condition (such as for each type of pulse number), the amount of work required for actual measurements is enormous. For these reasons, the method of this comparative example may reduce the accuracy of setting the voltage value Vp as described above, increase the user's workload, and so on, which may impair user convenience.

[0080] (C-2. This embodiment) Therefore, in this embodiment, the aforementioned information processing unit 73 (program 730) uses the aforementioned predetermined decomposition method to generate a conversion coefficient Kc for the conversion process described below, and uses this conversion coefficient Kc to generate (automatically generate) the aforementioned characteristic table (predicted voltage characteristic table TPvp that specifies the predicted characteristic curve CPvp) at any time.

[0081] Here, FIG. 10 shows, in a flow chart, an example of a conversion process (corresponding to a specific example of the process in step S13 in FIG. 14 described later) according to this embodiment. Also, FIG. 11 shows an example of various characteristic curves (characteristic curves after execution of step S132 described later shown in FIG. 10) according to this embodiment. Specifically, FIG. 11 shows an example of various characteristic curves (the above-mentioned actual characteristic curve CMvi and the above-mentioned preliminary characteristic curve CPvp0 of the predicted characteristic curve CPvp, etc.) showing the correspondence between the viscosity Vi [mPa] or voltage value Vp of the ink 9 and the environmental temperature Ta [°C]. Note that the preliminary characteristic curve CMvp0 shown in FIG. 11 for the sake of convenience is a characteristic curve obtained by performing a predetermined process (a process for making the voltage value Vp=0 at a predetermined reference temperature Tr described later) on the above-mentioned actual characteristic curve CMvp so as to facilitate comparison (comparison of slope) with the above-mentioned preliminary characteristic curve CPvp0. Moreover, Fig. 12 shows an example of a predetermined parameter Pr according to this embodiment, and Fig. 13 shows an example of an importance analysis result of each parameter Pr shown in Fig. 12. Note that Fig. 12 shows the value of each parameter Pr for six samples ("Sample 1" to "Sample 6"). Moreover, the importance in the importance analysis result shown in Fig. 13 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.

[0082] (About conversion process) First, as shown in Fig. 10 and Fig. 11, in this embodiment, the conversion process using the conversion coefficient Kc is a process of converting the actual measurement characteristic curve CMvi (characteristic curve between the actual measurement value of the viscosity Vi and the environmental temperature Ta) into the predicted characteristic curve CPvp (characteristic curve between the predicted value of the voltage value Vp and the environmental temperature Ta). As shown in the example of Fig. 11, it can be seen that the preliminary characteristic curve CPvp0 obtained during such a conversion process accurately matches (almost matches) the preliminary characteristic curve CMvp0 for the actual measurement characteristic curve CMvp (characteristic curve between the actual measurement value of the voltage value Vp and the environmental temperature Ta).

[0083] Here, a specific example of such a conversion process (conversion process from the measured characteristic curve CMvi to the predicted characteristic curve CPvp) will be described with reference to FIGS.

[0084] In this conversion process, first, a multiplication process (CMvi×Kc) is performed in which the actual characteristic curve CMvi is multiplied by a conversion coefficient Kc (step S131 in FIG. 10). Next, a subtraction process is performed on the result of the multiplication process in step S131 so that the voltage value Vp=0 at a predetermined reference temperature Tr (in the example of FIG. 11, Tr=40° C.), thereby generating the above-mentioned preliminary characteristic curve CPvp0 (a preliminary characteristic curve between the predicted value of the voltage value Vp and the environmental temperature Ta) (step S132). That is, by such preliminary process (processing of steps S131 and S132), the preliminary characteristic curve CPvp0 as shown in FIG. 11 is generated from the actual characteristic curve CMvi using the conversion coefficient Kc. Note that the execution order of the processes of steps S131 and S132 in such preliminary process may be, for example, the reverse of the execution order of the example shown in FIG. 10 (step S132 is executed first, and step S131 is executed afterwards).

[0085] Next, an addition process (CPvp0+ΔVp) is performed to add a predetermined voltage shift amount ΔVp to the voltage value Vp in the preliminary characteristic curve CPvp0 so as to obtain the voltage value Vp in the (Vj-based or DV-based) described above in Fig. 9, and a final predicted characteristic curve CPvp is generated (step S133). In other words, the voltage value Vp after adding such a voltage shift amount ΔVp (the voltage value Vp in the predicted characteristic curve CPvp) corresponds to the voltage value Vp at which a reference ejection speed is obtained when the ink 9 is ejected, or the voltage value Vp at which a reference droplet volume of the ink 9 is obtained. In this manner, the final predicted characteristic curve CPvp is generated, and the series of conversion processes shown in Fig. 10 is completed.

[0086] Incidentally, a specific conversion equation for such a conversion process is expressed by the following equation (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

[0087] In addition, the formula (1) above excluding the conversion coefficient Kc is called the Arrhenius formula (law) and is generally well known. In addition, in this formula (1), the Arrhenius formula is divided by the conversion coefficient Kc, but this is because the calculation is performed using (viscosity value of ink 9 / actual value of voltage value Vp) in the analysis method using the machine learning model 74. Therefore, for example, in the case where the calculation is performed using (actual value of voltage value Vp / viscosity value of ink 9) in the analysis method using the machine learning model 74, the formula multiplying the above Arrhenius formula by the conversion coefficient Kc becomes the conversion formula for the above conversion process. In other words, it can be said that either of these may be used as the conversion formula for the conversion process.

[0088] (for a given parameter Pr) Here, as shown in FIG. 12, examples of the above-mentioned predetermined parameter Pr include the following (a) to (l).

[0089] (a) Number of drops (number of pulses) ... corresponds to the number of pulses contained in a unit period of the drive signal Sd 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 driving signal Sd is set so that the volume of the ejection channel when ejecting the ink 9 includes a change that shrinks more than the reference value) (c) Head type: A symbol indicating the type of inkjet head 4, etc. (d) Ink type: Types of ink 9 classified according to the main solvent of ink 9 ("Oil": ink 9 with oil-based solvent, "sol": ink 9 with organic solvent-based solvent, "UV": UV (ultraviolet) curing ink, "WB": ink 9 with water as the main solvent) (e) (Vj standard or DV standard) ... Parameter indicating which standard (Vj standard, DV standard) is used as described in FIG. 9 (f) Head rank value: This corresponds to the voltage value Vp at which a predetermined ejection speed is reached 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) Voltage sensitivity Vr during ejection (Vj reference or DV reference) ... A value equivalent to the amount of change per unit voltage in the ejection speed or droplet volume of the ink 9 when the ink 9 is ejected at the reference temperature Tr described above (unit: [m / s / V] or [pl / V]) (i) Surface tension value of ink 9 (unit: [mN / m]) (j) 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 sound speed in the ink 9, etc.)) (k) Voltage shift amount ΔVp (l) Target value of ejection speed or DV (droplet volume) of ink 9

[0090] 13, the following parameters Pr, among those shown in (a) to (l) above, have relatively high importance (contribution rate) when generating the conversion coefficient Kc using the machine learning model 74. That is, in the example shown in FIG. 13, the importance is relatively high in the following order: (j) specific gravity value (or the above-mentioned physical property value) of the ink 9, (a) number of drops, (g) viscosity value at the reference temperature Tr, (k) voltage shift amount ΔVp, (h) voltage sensitivity Vr during ejection, (l) ejection speed or DV target value of the ink 9, (d) ink type, (b) presence or absence of common drive, (i) surface tension value of the ink 9, (f) head rank value, (e) (based on Vj or DV), and (c) head type.

[0091] Therefore, in this embodiment, it is desirable that at least (j) the specific gravity value of the ink 9 (or the above-mentioned physical property value), which is the most important of these, is included as the above-mentioned predetermined parameter Pr. It can also be said that it is desirable to further include at least one parameter of relatively high importance (as an example, the second to fifth most important) among the remaining parameters shown in Fig. 13, that is, (a) the number of drops, (g) the viscosity value at the reference temperature Tr, (k) the voltage shift amount ΔVp, and (h) the voltage sensitivity Vr during ejection, as the above-mentioned predetermined parameter Pr.

[0092] (Details on the generation process of the characteristic table, etc.) Here, Fig. 14 is a flow diagram showing the generation process of the characteristics table (predicted voltage characteristics table TPvp) according to this embodiment. Among the series of processes (steps S10 to S16 described later) shown in Fig. 14, the processes of steps S11 to S13 described later correspond to the generation process of the predicted voltage characteristics table TPvp, and the processes of steps S14 and S15 described later correspond to the generation process of the drive signal Sd.

[0093] In the series of processes shown in Fig. 14, first, as a preliminary step, the information processing unit 73 (program 730) judges whether or not it is necessary to generate (update) a predicted voltage characteristics table TPvp that specifies the predicted characteristic curve CPvp described above (step S10). If it is judged that it is necessary to generate the predicted voltage characteristics table TPvp (step S10: Y), the process proceeds to a process of generating the predicted voltage characteristics table TPvp (steps S11 to S13) described below. On the other hand, if it is judged 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 pulse having a voltage value Vp (peak value) at the current stage is used to generate the drive signal Sd.

[0094] The following are examples of cases where it is necessary to generate the predicted voltage characteristics table TPvp. For example, these include when a predetermined time has passed, when a cartridge of the ink tank 3 is installed, when a predetermined operation signal is input to the printer 1 from the user, when a non-ejection period (idle period) of the ink 9 exceeds a predetermined time, etc. Other examples include when the color or type of the ink 9 in the ink tank 3 is changed, or when a different model of inkjet head 4 is installed in the printer 1. Furthermore, other examples include when at least one of the parameters Pr is changed, as shown in FIG. 12.

[0095] (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 actual viscosity characteristics table TMvi that defines the actual characteristic curve CMvi between the viscosity Vi of the ink 9 and the environmental temperature Ta, and the predetermined parameters Pr described above, by the method described above (step S11).

[0096] Next, the conversion coefficient generating unit 732 uses a predetermined analysis method (first analysis method) in which the parameters Pr acquired in step S11 are used as explanatory variables and the conversion coefficient Kc described above is used as a target variable to generate the conversion coefficient Kc based on the parameters Pr (step S12). Specifically, in the example of this embodiment, the conversion coefficient generating unit 732 uses the analysis method using the machine learning model 74 described above to generate the conversion coefficient Kc based on the parameters Pr.

[0097] Then, the table generating unit 733 generates the predicted voltage characteristics table TPvp (step S13) by performing the predetermined conversion process (see Figs. 10 and 11) described above 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 specifies the predicted characteristic curve CPvp between the voltage value Vp (peak value) of the pulse of the drive signal Sd and the environmental temperature Ta.

[0098] (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 generating unit 48 first uses the predicted voltage characteristics table TPvp generated in step S13 to obtain 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 obtain the voltage value Vp of the pulse.

[0099] Then, the signal generating unit 48 generates a driving signal Sd, for example, as shown in Figures 6(A) to 6(C) described above, using a pulse having the voltage value Vp calculated in step S14 and, for example, a preset pulse width Wp (step S15).

[0100] Incidentally, the above-mentioned pulse width Wp is determined, for example, based on the on-pulse peak (AP) of the pulse. This AP corresponds to half the period of the natural vibration period of the ink 9 in the ejection channel described above (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 becomes maximum when ejecting one normal droplet of ink 9 (ejecting one droplet). Also, this AP is determined, for example, by the shape of the ejection channel and the physical properties (specific gravity, etc.) of the ink 9.

[0101] Based on such an AP, the pulse width Wp is set, for example, as follows. That is, in the examples of the drive signal Sd shown in Figs. 6(A) to 6(C) (examples of so-called "1 drop", "2 drop", and "3 drop", respectively), the signal generating unit 48 sets the pulse width Wp as follows. That is, in the examples of Figs. 6(A) to 6(C), the signal generating unit 48 sets the pulse width Wp so that each of the above-mentioned pulse widths Wp satisfies the relationship shown in the following formulas (2) and (3) with respect to the AP. However, the examples are not limited to those shown in the formulas (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)

[0102] (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 manner, the ejection operation of the ink 9 described above is performed.

[0103] This completes the series of processes shown in FIG.

[0104] (C-3. ​​Example of prediction results using machine learning) Here, FIG. 15 shows an example of predicted values ​​and actual measured values ​​by machine learning according to the present embodiment. FIG. 16A shows an example of a correspondence relationship between the SVM predicted values ​​(described above) and actual measured values ​​shown in FIG. 15, and FIG. 16B shows an example of a correspondence relationship between the RF predicted values ​​(described above) and actual measured values ​​shown in FIG. 15. FIGS. 17A to 17C each show an example of a correspondence relationship between the RF predicted values ​​and actual measured values ​​when only some of the parameters shown in FIG. 13 are used. Specifically, FIG. 17A shows an example of such a correspondence relationship when only the parameter with the highest importance (specific gravity value of ink 9) described above is used among the parameters shown in FIG. 13. FIG. 17B shows an example of such a correspondence relationship when only two parameters with the first and second highest importance (specific gravity value of ink 9 and the number of drops) are used among the parameters shown in FIG. 13. Also, Fig. 17C shows an example of such a correspondence relationship when using only the two parameters (specific gravity of the ink 9 and voltage sensitivity Vr) with the first to fifth highest importance among the parameters shown in Fig. 13. On the other hand, Fig. 16A and Fig. 16B both show an example of the correspondence relationship between the predicted values ​​and the actual measured values ​​when using all the parameters shown in Fig. 12.

[0105] In the example shown in FIG. 15, the actual measured value of the conversion coefficient Kc and the predicted value of the conversion coefficient Kc by machine learning (SVM predicted value and RF predicted value) are shown in correspondence with each other for the six samples ("Sample 1" to "Sample 6"). In addition, in the examples shown in FIG. 16A, FIG. 16B, and FIG. 17A to FIG. 17C, the predicted value (SVM predicted value or RF predicted value) of the conversion coefficient Kc is set as the variable x, and the actual measured value of the conversion coefficient Kc is set as the variable y, and the (x, y) coordinates of each of a large number (562 samples) of samples are plotted. In addition, in these FIG. 16A, FIG. 16B, and FIG. 17A to FIG. 17C, an example of an equation (for example, an equation of a linear function specified by using the least squares method) showing the tendency of the correlation between these variables x and y is also shown.

[0106] First, in the example shown in FIG. 15, it can be seen that both the SVM predicted value and the RF predicted value can be predicted with high accuracy with respect to the actual measured value. Also, in each of the examples shown in FIG. 16A, FIG. 16B, and FIG. 17A to FIG. 17C, the slope in the equation of the linear function described above is approximately "1" and the intercept in the equation of the linear function described above is approximately "0", so that the predicted value (SVM predicted value and RF predicted value) and the actual measured value have the following relationship. That is, it can be seen that the predicted value and the actual measured value have a sufficient correlation to a practical extent when printing using the predicted value. Furthermore, when comparing each of the examples (examples of RF predicted values) shown in FIG. 16B and FIG. 17A to FIG. 17C (examples of the above-mentioned parameters are used), it can be seen that the matching accuracy (prediction accuracy) of the predicted value (RF predicted value) with respect to the actual measured value is relatively higher in the example shown in FIG. 16B (examples of the above-mentioned parameters are used) than in each of the examples shown in FIG. 17A to FIG. 17C (examples of the above-mentioned parameters are used). In addition, as described above, only the parameter with the highest importance (specific gravity of ink 9) is used in Fig. 17A, while the two parameters with the first and second highest importance are used in Fig. 17B, and the two parameters with the first and fifth highest importance are used in Fig. 17C. However, even if a combination of the other parameters shown in Figs. 12 and 13 and the specific gravity of ink 9 is used as an explanatory variable, it can be said that the prediction accuracy is higher than in the case of Fig. 17A (when only the specific gravity of ink 9 is used), just like in the cases of Figs. 17B and 17C.

[0107] (C-4. Actions and Effects) As described above, in the characteristic table generating system 5 of this embodiment, the conversion coefficient Kc is generated based on the predetermined parameter Pr by using the predetermined analysis method (first analysis method) described above. In addition, the predicted voltage characteristic table TPvp is generated by performing the conversion process described above using the actual viscosity characteristic table TMvi and the conversion coefficient Kc described above. As a result, in this embodiment, the following is obtained.

[0108] That is, the predicted voltage characteristic table TPvp that specifies the predicted characteristic curve CPvp between the voltage value Vp (peak value) and the environmental temperature Ta is automatically generated each time. This reduces the workload and work costs compared to the case where the characteristic curve between these voltage values ​​Vp and the environmental temperature Ta (the above-mentioned measured characteristic curve CMvp) is actually measured and acquired (for example, the case where the characteristic curve is actually measured and acquired for each type of the number of pulses included in the drive signal Sd) as in the above-mentioned comparative example. Also, as described above, the above-mentioned characteristic curve between the voltage value Vp and the environmental temperature Ta (the measured characteristic curve CMvp) generally has a different slope depending on the type of the number of pulses included in the drive signal Sd and the type and role of each pulse, and therefore the predicted voltage characteristic table TPvp is automatically generated each time, as shown below. That is, for example, compared to the case where a single characteristic curve is used repeatedly, the voltage value Vp (peak value) of the pulse in the drive signal Sd can be set with high accuracy.

[0109] For these reasons, in this embodiment, it is possible to improve the efficiency of the work required to obtain the characteristic curve (voltage characteristic table) between the above-mentioned voltage value Vp and the environmental temperature Ta, and to easily improve the setting accuracy of the voltage value Vp (peak value) of the pulse in the drive signal Sd. As a result, in this embodiment, it is possible to improve the convenience for the user.

[0110] In addition, in this embodiment, for example, the following effects can be obtained. Since the characteristic curve between the voltage value Vp and the ambient temperature Ta described above can be easily obtained, it becomes easy to perform voltage control that keeps the ejection speed and droplet volume of the ink 9 approximately 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 comparative example described above, expensive evaluation equipment (such as a temperature controller) used to obtain the measured characteristic curve CMvp is no longer necessary, making it possible to reduce costs.

[0111] In addition, in this embodiment, the above-mentioned predetermined parameter Pr includes at least the specific gravity of the ink 9 or a physical property value obtained using the specific gravity of the ink 9 (for example, the density of the ink 9 or the sound speed in the ink 9), and therefore the following is true. That is, when generating the conversion coefficient Kc as the objective variable using the above-mentioned predetermined analysis method with the parameter Pr as the explanatory variable, the conversion coefficient Kc is generated using the parameter with the highest importance (degree of contribution) (the specific gravity of the ink 9 or the physical property value), and therefore the generation accuracy of the conversion coefficient Kc (the prediction accuracy of the above-mentioned predicted characteristic curve CPvp) is improved. As a result, it is possible to generate the above-mentioned predicted voltage characteristics table TPvp with high accuracy.

[0112] Furthermore, in this embodiment, if the above-mentioned parameters Pr further include at least one of the above-mentioned number of drops (number of pulses), the viscosity value of the ink 9 at the reference temperature Tr, the voltage shift amount ΔVp, and the voltage sensitivity Vr of the ink 9, the following occurs. That is, the above-mentioned parameters (at least one of the above-mentioned parameters) having a relatively high degree of importance (degree of contribution) are further used together with the above-mentioned specific gravity of the ink 9 or the above-mentioned physical property value to generate the conversion coefficient Kc, so that the generation accuracy of this conversion coefficient Kc (prediction accuracy of the predicted characteristic curve CPvp) is further improved. As a result, it becomes possible to generate the predicted voltage characteristics table TPvp with even greater accuracy.

[0113] In addition, in this embodiment, the above-mentioned predetermined analysis method (first analysis method) is a method using the machine learning model 74, so that the predicted voltage characteristics table TPvp can be generated easily and accurately.

[0114] In this embodiment, the conversion process includes the preliminary process and the addition process, and the voltage value Vp after the addition of the voltage shift amount ΔVp (the voltage value Vp in the predicted characteristic curve CPvp) corresponds to the voltage value at which the reference discharge speed and droplet amount are obtained, as described above, so that: That is, such a voltage shift amount ΔVp can be easily set using the reference discharge speed and droplet amount, and it is possible to further improve user convenience.

[0115] Furthermore, in this embodiment, the signal generating unit 48 is further provided in the characteristic table generating system 5, so that the voltage value Vp (peak value) of the pulse in the drive signal Sd is found using the predicted voltage characteristic table TPvp generated by the table generating unit 733, and the drive signal Sd is generated using the pulse having the voltage value Vp. Therefore, the ejection operation of the ink 9 is performed using the drive signal Sd generated in this way, so that the ejection characteristics of the ink 9 can be easily improved. As a result, it is possible to further improve user convenience.

[0116] In addition, in this embodiment, the data acquisition unit 731, conversion coefficient generation unit 732, and table generation unit 733 described above are each provided outside the printer 1 (within the information processing device 7), so that the following is achieved. That is, for the inkjet head 4 and printer 1, while maintaining the existing configuration, 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.

[0117] <2. Modifications> Next, modified examples (modifications 1 to 6) of the above embodiment will be described. Note that the same components as those in the above embodiment will be given the same reference numerals, and the description will be omitted as appropriate.

[0118] [Variation 1] In the above embodiment, a case has been described in which a machine learning model 74 (first analysis method) with the conversion coefficient Kc as the objective variable has been provided. In the following variant example 1, however, an example will be described in which a machine learning model (second analysis method) with the above-mentioned voltage sensitivity Vr as the objective variable has been further provided.

[0119] (composition) Fig. 18 is a block diagram showing an example of the configuration of a machine learning model (machine learning model 74A) according to Modification 1, and Fig. 19 shows an example of a predetermined parameter Pr (see Fig. 18) according to Modification 1. Fig. 20 shows an example of an importance analysis result of each parameter Pr shown in Fig. 19. Note that Fig. 19 shows the value of each parameter Pr for six samples ("Sample1" to "Sample6").

[0120] FIG. 21 shows an example of a predicted value and an actual measurement value by machine learning according to the first modification. FIG. 22A shows an example of a correspondence relationship between an SVM predicted value (described above) and an actual measurement value shown in FIG. 21, and FIG. 22B shows an example of a correspondence relationship between an RF predicted value (described above) and an actual measurement value shown in FIG. 21. FIG. 23 shows an example of a correspondence relationship between an RF predicted value and an actual measurement value when only some of the parameters shown in FIG. 20 are used. Specifically, FIG. 23 shows an example of such a correspondence relationship when only the parameter with the highest importance (the target value of the discharge speed or DV shown in FIG. 20) is used among the parameters shown in FIG. 19. On the other hand, both FIG. 22A and FIG. 22B show an example of a correspondence relationship between a predicted value and an actual measurement value when all the parameters shown in FIG. 19 are used.

[0121] Details of Fig. 21, Fig. 22A, Fig. 22B, and Fig. 23 are the same as those of Fig. 15, Fig. 16A, Fig. 16B, and Fig. 17A to Fig. 17C in the embodiment. That is, in the example shown in Fig. 21, the actual measured value of voltage sensitivity Vr and the predicted value of voltage sensitivity Vr by machine learning (SVM predicted value and RF predicted value) are shown in association with each other for the six samples ("Sample 1" to "Sample 6") shown in Fig. 19. Also, in the example shown in Fig. 22A, Fig. 22B, and Fig. 23, the predicted value of voltage sensitivity Vr (SVM predicted value or RF predicted value) is set as variable x, and the actual measured value of voltage sensitivity Vr is set as variable y, and the (x, y) coordinates of each of the many (562) samples are plotted. In addition, Figures 22A, 22B, and 23 also show an example of an equation (e.g., a linear function equation identified using the least squares method) that indicates the tendency of the correlation between these variables x and y.

[0122] First, in this modification 1, the above-mentioned voltage sensitivity Vr is generated by using a predetermined analysis method (second analysis method) based on a predetermined parameter Pr acquired by the data acquisition unit 731. This predetermined analysis method is an analysis method that uses the above-mentioned parameter Pr as an explanatory variable and the above-mentioned voltage sensitivity Vr as a response variable.

[0123] Specifically, as shown in FIG. 18, for example, in this modification 1, the voltage sensitivity Vr is generated based on the parameter Pr by utilizing an analysis method using the machine learning model 74A. As described above, this machine learning model 74A is a prediction model obtained by performing machine learning with the parameter Pr as an explanatory variable and the voltage sensitivity Vr as an objective variable. Also, as shown in FIG. 18, when the parameter Pr (explanatory variable) is input, this machine learning model 74A generates (predicts) the voltage sensitivity Vr (objective variable) based on the learning result, and outputs the generated voltage sensitivity Vr. Note that a specific example of the analysis method (prediction method) using such a machine learning model 74A is the same as that given in the embodiment.

[0124] Here, specific examples of the above-mentioned predetermined parameter Pr in this variant example 1 include the following (a) to (g) and (i) to (l), which are also described in the embodiment, as shown in FIG.

[0125] (a) Number of drops (number of pulses) (b) Presence or absence of common drive (c) Head type (d) Ink type (e)(Vj standard or DV standard) (f) Head Rank Value (g) Viscosity value at reference temperature Tr (i) Surface tension value of ink 9 (j) Specific gravity of ink 9 (l) Target discharge velocity or DV (k) Voltage shift amount ΔVp

[0126] According to an example of the importance analysis result of each parameter Pr as an explanatory variable shown in FIG. 20, when generating the voltage sensitivity Vr using the machine learning model 74A, the following parameters Pr shown in (a) to (g) and (i) to (l) have relatively high importance (contribution rate) as described above. That is, in the example shown in FIG. 20, (l) the target value of the ejection speed or DV has relatively high importance (highest). Therefore, in this modification 1, it is desirable to at least include (l) the target value of the ejection speed or DV, which has the highest importance, as the above-mentioned predetermined parameter Pr.

[0127] In the example shown in Fig. 21, it can be seen that both the SVM predicted value and the RF predicted value can be predicted with high accuracy with respect to the actual measured value. Also, in each of the examples shown in Figs. 22A, 22B, and 23, the slope of the equation of the linear function described above (the equation showing the tendency of the correlation between the variables x and y) is approximately "1", and the intercept of the equation of the linear function is approximately "0". From these facts, in this modification 1, with respect to the voltage sensitivity Vr as the objective variable, the predicted value (SVM predicted value and RF predicted value) and the actual measured value have the following relationship. That is, as in the case of the embodiment described above, it can be seen that the predicted value and the actual measured value have a sufficient correlation to a practical extent when printing is performed using the predicted value. Furthermore, when comparing the examples (examples of RF predicted values) shown in Figures 22B and 23, it can be seen that the example shown in Figure 22B (an example in which all of the above-mentioned parameters are used) has a relatively higher matching accuracy between the predicted value (RF predicted value) and the actual measured value compared to the example shown in Figure 23 (a case in which only some of the above-mentioned parameters are used).

[0128] (Action and effect) In the first modification having such a configuration, basically, the same effects as those of the embodiment can be obtained by the same actions.

[0129] Furthermore, in particular, in this modified example 1, the voltage sensitivity Vr (one of the predetermined parameters Pr in the embodiment) described in the embodiment is also generated using a predetermined analysis method (second analysis method), and so the following occurs. That is, it is no longer necessary to obtain an actual measurement value of this voltage sensitivity Vr in advance, further reducing the workload and work costs. Also, compared to, for example, the case where a single value is reused, the value of this voltage sensitivity Vr can be set with high accuracy. This makes it possible to further improve user convenience.

[0130] Furthermore, in this variant example 1 as well, similarly to the embodiment, the above-mentioned specified analysis method (second analysis method) is a method using machine learning model 74A, so that it is possible to easily and accurately predict the voltage sensitivity Vr as the objective variable.

[0131] [Variation 2] In the above embodiment, a case where a machine learning model 74 (first analysis method) with the conversion coefficient Kc as the objective variable is provided is described, but in the following Modification 2, an example where a machine learning model (third analysis method) with the voltage shift amount ΔVp as the objective variable is further provided is described. Note that, for example, both Modification 2 and Modification 1 may be used in combination.

[0132] (composition) Fig. 24 is a block diagram showing an example of the configuration of a machine learning model (machine learning model 74B) according to Modification 2, and Fig. 25 shows an example of a predetermined parameter Pr (see Fig. 24) according to Modification 2. Fig. 26 shows an example of an importance analysis result of each parameter Pr shown in Fig. 25. Note that Fig. 25 shows the value of each parameter Pr for six samples ("Sample1" to "Sample6").

[0133] FIG. 27 shows an example of predicted values ​​and actual measured values ​​by machine learning according to the second modification. FIG. 28A shows an example of a correspondence relationship between the SVM predicted values ​​(described above) and actual measured values ​​shown in FIG. 27, and FIG. 28B shows an example of a correspondence relationship between the RF predicted values ​​(described above) and actual measured values ​​shown in FIG. 27. FIGS. 29A to 29C each show an example of a correspondence relationship between the RF predicted values ​​and actual measured values ​​when only some of the parameters shown in FIG. 26 are used. Specifically, FIG. 29A shows an example of such a correspondence relationship when only the parameter with the highest importance (the viscosity value at the reference temperature Tr) described above is used among the parameters shown in FIG. 26. FIG. 29B shows an example of such a correspondence relationship when only two parameters with the highest and second highest importance (the viscosity value at the reference temperature Tr and the presence or absence of common drive) are used among the parameters shown in FIG. 26. Moreover, Fig. 29C shows an example of such a correspondence relationship when using only the parameter with the seventh highest importance (the surface tension value of the ink 9) among the parameters shown in Fig. 26. On the other hand, Fig. 28A and Fig. 28B both show an example of the correspondence relationship between the predicted values ​​and the actual measured values ​​when using all the parameters shown in Fig. 25.

[0134] Details of these Figs. 27, 28A, 28B, 29A to 29C are the same as those of Figs. 15, 16A, 16B, 17A to 17C in the embodiment. That is, in the example shown in Fig. 27, the actual measurement value of the voltage shift amount ΔVp described above and the predicted value of the voltage shift amount ΔVp by machine learning (SVM predicted value and RF predicted value) are shown in association with each other for the six samples ("Sample 1" to "Sample 6") shown in Fig. 25. Also, in the example shown in Figs. 28A, 28B, 29A to 29C, the predicted value (SVM predicted value or RF predicted value) of the voltage shift amount ΔVp is set as a variable x, and the actual measurement value of the voltage shift amount ΔVp is set as a variable y, and the (x, y) coordinates of each of the many (562) samples are plotted. In addition, Figures 28A, 28B, and 29A to 29C also show an example of an equation (e.g., a linear function equation identified using the least squares method) that indicates the tendency of the correlation between these variables x and y.

[0135] First, in this modification 2, the above-mentioned voltage shift amount ΔVp is generated by using a predetermined analysis method (third analysis method) based on a predetermined parameter Pr acquired by the data acquisition unit 731. This predetermined analysis method is an analysis method that uses the above-mentioned parameter Pr as an explanatory variable and the above-mentioned voltage shift amount ΔVp as a response variable.

[0136] Specifically, as shown in FIG. 24, for example, in this modification 2, an analysis method using the machine learning model 74B is used to generate a voltage shift amount ΔVp based on the parameter Pr. As described above, this machine learning model 74B is a prediction model obtained by performing machine learning with the parameter Pr as an explanatory variable and the voltage shift amount ΔVp as an objective variable. Also, as shown in FIG. 24, when the parameter Pr (explanatory variable) is input, this machine learning model 74B generates (predicts) a voltage shift amount ΔVp (objective variable) based on the learning result, and outputs the generated voltage shift amount ΔVp. Note that a specific example of an analysis method (prediction method) using such a machine learning model 74B is the same as that given in the embodiment.

[0137] Here, specific examples of the above-mentioned predetermined parameter Pr in this variant example 2 include the following (a) to (j) and (l), which are also described in the embodiment and variant example 1, as shown in FIG.

[0138] (a) Number of drops (number of pulses) (b) Presence or absence of common drive (c) Head type (d) Ink type (e)(Vj standard or DV standard) (f) Head Rank Value (g) Viscosity value at reference temperature Tr (h) Voltage sensitivity Vr during ejection (based on Vj or DV) (i) Surface tension value of ink 9 (j) Specific gravity of ink 9 (l) Target discharge velocity or DV

[0139] 26, when generating the voltage shift amount ΔVp using the machine learning model 74B, the following parameters Pr shown in (a) to (j) and (l) have relatively high importance (contribution rate) as described above: (g) viscosity value at reference temperature Tr, (b) presence or absence of common drive, (f) head rank value, (c) head type, (j) specific gravity value of ink 9, (h) voltage sensitivity Vr during ejection, (i) surface tension value of ink 9, (l) target value of ejection speed or DV, (a) number of drops, (d) ink type, (e) (based on Vj or DV).

[0140] Therefore, in this modified example 2, it is desirable to include at least one of (g) the viscosity value at the reference temperature Tr and (b) the presence or absence of common drive, which are relatively important (for example, the first and second most important), as the above-mentioned predetermined parameters Pr. Furthermore, it can be said that it is desirable to further include at least one of the parameters of relatively high importance (for example, the third to seventh most important) among the remaining parameters shown in Fig. 26, that is, (f) the head rank value, (c) the head type, (j) the specific gravity value of the ink 9, (h) the voltage sensitivity Vr during ejection, and (i) the surface tension value of the ink 9, as the above-mentioned predetermined parameters Pr.

[0141] In the example shown in Fig. 27, it can be seen that both the SVM predicted value and the RF predicted value can be predicted with high accuracy with respect to the actual measured value. Also, in each of the examples shown in Figs. 28A, 28B, and 29A to 29C, the slope of the equation of the linear function described above (the equation showing the tendency of the correlation between the variables x and y) is approximately "1", and the intercept of the equation of the linear function is approximately "0". From these facts, in this modification 2, the predicted value (SVM predicted value and RF predicted value) and the actual measured value have the following relationship with respect to the voltage shift amount ΔVp as the objective variable. That is, as in the case of the embodiment and modification 1 described above, it can be seen that the predicted value and the actual measured value have a sufficient correlation to a practical extent when printing is performed using the predicted value. Furthermore, when comparing the examples (examples of RF predicted values) shown in Figure 28B and Figures 29A to 29C, it can be seen that the example shown in Figure 28B (an example when all of the above-mentioned parameters are used) has a relatively higher matching accuracy between the predicted value (RF predicted value) and the actual measured value compared to the examples shown in Figures 29A to 29C (when only some of the above-mentioned parameters are used).

[0142] (Action and effect) In the second modification having such a configuration, basically, the same effects as those of the embodiment can be obtained by the same actions.

[0143] In particular, in this modified example 2, the voltage shift amount ΔVp (parameter used in the addition process described in the embodiment) described in the embodiment is also generated using a predetermined analysis method (third analysis method), as follows. That is, it is no longer necessary to obtain an actual measurement value for this voltage shift amount ΔVp in advance, which further reduces the workload and cost of work. Also, compared to, for example, the case where a single value is reused, the value of this voltage shift amount ΔVp can be set with high accuracy. This makes it possible to further improve user convenience.

[0144] Furthermore, in this variant example 2, as in the embodiment and variant example 1, the above-mentioned specified analysis method (third analysis method) is a method using machine learning model 74B, so that it is possible to easily and accurately predict the voltage shift amount ΔVp as the objective variable.

[0145] [Variation 3] (composition) 30 is a block diagram showing an example of the configuration of a characteristic table generating system 5A according to Modification 3. The characteristic table generating 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, the information processing device 7A, and the server 8 are connected to each other via a network 50. In other words, the characteristic table generating system 5A corresponds to the characteristic table generating system 5 according to the embodiment, in which an information processing device 7A is provided instead of the information processing device 7, and a server 8 is further provided.

[0146] In this third modification, the above-mentioned server 8 corresponds to a specific example of an "external device" in the present disclosure.

[0147] As shown in Fig. 30, the information processing device 7A has a bus 70, an input unit 71, a display unit 72, a control unit 75, a storage unit 76A, and a network IF 77 as physical block configurations. That is, the 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, the storage unit 76A does not store the program 730 and the machine learning model 74 described in the embodiment. Therefore, the information processing device 7A corresponds to, for example, a PC having a general (general-purpose) configuration.

[0148] As shown in FIG. 30, the server 8 has a bus 80, a control unit 85, a storage unit 86, and a network IF 87 as a physical block configuration. 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 configuration 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. 30, the storage unit 86 stores the program 730 and the machine learning model 74 described in the embodiment. As shown in parentheses in FIG. 30, in addition to such machine learning model 74, the machine learning models 74A and 74B described in the modified examples 1 and 2 may be provided, and the same applies to modified examples 4 to 6 described later.

[0149] Thus, in the characteristic table generating system 5A of the third modified example, unlike the characteristic table generating system 5 of the embodiment, the predicted voltage characteristic table TPvp described above is generated in the server 8 instead of the information processing device 7A. The predicted voltage characteristic table TPvp generated in this manner is supplied from the server 8 to the signal generating unit 48 in the inkjet head 4 of the printer 1 via the network 50, as shown in FIG.

[0150] (Action and effect) In the third modification having such a configuration, the characteristic table generating system 5A as a whole basically operates in the same manner as the characteristic table generating system 5 of the embodiment, and can provide the same effects.

[0151] In particular, in this modification 3, the data acquisition unit 731, the conversion coefficient generation unit 732, and the table generation unit 733 (the program 730) are provided outside the printer 1 (inside the server 8), so that the following is achieved. That is, as in the case of the embodiment described above, the inkjet head 4 and the printer 1 can maintain their existing configurations while the predicted voltage characteristics table TPvp can be automatically generated in the server 8 described above. Also, in this modification 3, as described above, the information processing device 7A can use an existing (general-purpose) configuration, and the same effect as in the embodiment can be obtained by using the server 8 that functions as a cloud server, for example. As a result, in this modification 3, it is possible to further improve the convenience for the user.

[0152] [Variation 4] (composition) 31 is a block diagram showing an example of the configuration of a characteristic table generating system 5B according to the fourth modification. The characteristic table generating system 5B according to the fourth modification 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, the characteristic table generating system 5B corresponds to the characteristic table generating system 5 according to the embodiment, in which the information processing device 7 is replaced with the information processing device 7A described above, and the printer 1 and the inkjet head 4B are replaced with the printer 1B and the inkjet head 4B, respectively.

[0153] 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.

[0154] 31, in this modification 4, the above-mentioned information processing unit 73 (data acquisition unit 731, conversion coefficient generation unit 732, and table generation unit 733), in other words, the above-mentioned program 730, is provided in the inkjet head 4B. The above-mentioned machine learning model 74 is also provided in this 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.

[0155] (Action and effect) In the fourth modification having such a configuration, the characteristic table generating system 5B as a whole basically operates in the same manner as the characteristic table generating system 5 of the embodiment, and can provide the same effects.

[0156] In particular, in this modification 4, the data acquisition unit 731, the conversion coefficient generation unit 732, and the table generation unit 733 are each provided in the printer 1B, as described below. That is, unlike the embodiment and modification 3, it is no longer necessary to prepare the data acquisition unit 731, the conversion coefficient generation unit 732, and the table generation unit 733 in an external device (information processing device 7 or server 8). This allows the printer 1B itself to automatically generate the predicted voltage characteristics table TPvp, thereby making it possible to further improve user convenience.

[0157] Furthermore, in this fourth modification, the data acquisition unit 731, conversion coefficient generation unit 732, and table generation unit 733 are provided in the inkjet head 4B built into the printer 1B, so that the following is true. That is, the inkjet head 4B itself can automatically generate the predicted voltage characteristics table TPvp while maintaining the existing configuration of the printer 1B itself other than the inkjet head 4B. As a result, it is possible to further improve user convenience.

[0158] [Variation 5] (composition) 32 is a block diagram showing an example of the configuration of a characteristic table generating system 5C according to Modification 5. The characteristic table generating system 5C according to 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, the characteristic table generating system 5C corresponds to the characteristic table generating system 5 according to the embodiment, in which 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.

[0159] The above-described printer 1C corresponds to a specific example of a "liquid jet recording apparatus" in the present disclosure.

[0160] In this modification 5, as shown in FIG. 32, the above-mentioned information processing unit 73 (data acquisition unit 731, conversion coefficient generation unit 732, and table generation unit 733), in other words, the above-mentioned program 730, is provided in the printer 1C, similarly to modification 4 (FIG. 31). Also, the above-mentioned machine learning model 74 is provided in the printer 1C, similarly to modification 4. However, as shown in FIG. 32, in this modification 5, unlike modification 4, both of the information processing unit 73 (program 730) and the machine learning model 74 are disposed outside the inkjet head 4 in the printer 1C.

[0161] (Action and effect) In the modified example 5 having such a configuration, the characteristic table generating system 5C as a whole basically operates in the same manner as the characteristic table generating system 5 of the embodiment, and can provide the same effects.

[0162] Also, in this modification 5, similarly to the above modification 4, the data acquisition unit 731, the conversion coefficient generation unit 732, and the table generation unit 733 are each provided within the printer 1C, so that the following is true: That is, similarly to the case of modification 4, the printer 1C itself can automatically generate the predicted voltage characteristics table TPvp, and as a result, it is possible to further improve user convenience.

[0163] [Variation 6] (composition) 33 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 conversion coefficient generation unit 732, and a table generation unit 733) described in the embodiment and the like, further including 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 each process performed in the signal generation unit 48 described above.

[0164] The configuration of such information processing unit 73D (program 730D) corresponds to, for example, the embodiment and modification 3, where the configuration and functions of the signal generating unit 48 are further provided in an external device (information processing device 7 or server 8) of the printer 1 in addition to the information processing unit 73 (program 730). In other words, unlike these embodiment and modification 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.

[0165] (Action and effect) 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.

[0166] 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 that the operation of the signal generating unit 48 (the operation of generating the drive signal Sd) can also be executed collectively in the information processing unit 73D (program 730D). As a result, it is possible to further improve the convenience for the user.

[0167] <3. Other Modifications> While the present disclosure has been described above by way of embodiments and modified examples, the present disclosure is not limited to these embodiments and can be modified in various ways.

[0168] For example, in the above embodiment, the configuration of each member in the printer and the inkjet head (shape, arrangement, number, etc.) is specifically described, but the present invention is not limited to the above embodiment, and other shapes, arrangements, numbers, etc. may be used. Specifically, for example, in the above embodiment, the shuttle type printer in which the inkjet head moves is described as an example, but the present invention is not limited to this example, and the present invention may be a single-pass type printer in which the inkjet head is fixed. In addition, in the above embodiment, the ink tank is accommodated in a predetermined housing, but the present invention is not limited to this example, and the ink tank may be disposed outside the housing. Furthermore, in the above embodiment, the signal generating unit is mainly described as an example in which the signal generating unit is provided in the inkjet head, but the present invention is not limited to this example, and the signal generating unit may be provided outside the inkjet head in the printer.

[0169] In addition, various types of inkjet head structures can be applied. That is, for example, it may be a so-called side shoot type inkjet head that ejects ink 9 from the center of the extension direction of each ejection channel in the actuator plate. Or, it may be a so-called edge shoot type inkjet head that ejects ink 9 along the extension direction of each ejection channel. Furthermore, the printer system is not limited to the systems described in the above embodiments, and various systems such as a thermal system (thermal system on-demand type) and a MEMS (Micro Electro Mechanical Systems) system can be applied.

[0170] Furthermore, in the above embodiment and the like, a non-circulation type 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, for example, the present disclosure can also be applied to a circulation type inkjet head in which the ink 9 is circulated between the ink tank and the inkjet head.

[0171] In addition, in the above embodiment, examples of the characteristic table (predicted voltage characteristic table TPvp) and the generation process of the drive signal Sd are specifically described, but the present invention is not limited to the examples described in the above embodiment, and other methods may be used to generate the characteristic table and the drive signal Sd. Specifically, in the above embodiment, a method using a machine learning model is described as an example of the above-mentioned predetermined analysis method (first to third analysis methods), but the present invention is not limited to this method, and other analysis methods may be used. In addition, the above-mentioned predetermined parameter Pr is not limited to the various parameters described in the above embodiment, and other parameters may be added (or replaced) to the analysis method. Furthermore, in the above embodiment, the present invention is described by taking as an example a case where both the pulse width Wp and the voltage value (peak value) Vp of the pulse are set (automatically adjusted) and then the drive signal Sd is generated, but the present invention is not limited to this example. That is, for example, the drive signal Sd may be generated after setting only the pulse width Wp of the pulse width Wp and the voltage value Vp. In addition, in the above embodiment, the voltage values ​​Vp of the multiple pulses are all the same value, but for example, the voltage values ​​Vp of the multiple pulses may not be the same value (at least some of the voltage values ​​Vp may be different values). Even in such a case, it is possible to perform the generation process of the predicted voltage characteristics table TPvp described in the above embodiment by using each of the multiple types of voltage values ​​Vp as an explanatory variable.

[0172] In the above embodiment, the pulses (pulses Pa, Pb, Pc) that expand the volume in each ejection channel are described as pulses (positive pulses) that expand the volume in the high state, but this is not limited to the above case. That is, the pulses may not only expand the volume in the high state and contract the volume in the low state, but may also expand the volume in the low state and contract the volume in the high state. Conversely, the pulses may expand the volume in the low state and contract the volume in the high state. In addition, even in the case of such negative pulses, the "common drive" can be applied as long as the method has the same function as the "common drive" described above.

[0173] 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 the pulse for assisting the ejection of droplets include a pulse for contracting the volume in each ejection channel and a pulse (auxiliary pulse) for pulling back a part of the ejected droplet. In addition, 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 even if such a pulse for assisting the ejection of droplets is added, it does not affect the contents of the present disclosure described so far.

[0174] Furthermore, the series of processes described in the above embodiments and the like 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 and used, or may be installed in the computer from a network or a recording medium and used. Note that examples of recording media (non-transient computer-readable recording media) on which such programs are recorded include various media such as floppy (registered trademark) disks, CD (Compact Disk)-ROMs, DVD (Digital Versatile Disc)-ROMs, and hard disks.

[0175] Furthermore, in the above 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 other apparatuses other than inkjet printers. In other words, the "liquid jet head" (inkjet head) of the present disclosure may be applied to other apparatuses other than inkjet printers. Specifically, for example, the "liquid jet head" of the present disclosure may be applied to apparatuses such as facsimiles and on-demand printers.

[0176] In addition, the various examples described above may be applied in any combination.

[0177] It should be noted that the effects described in this specification are merely examples and are not limiting, and other effects may also be obtained.

[0178] The present disclosure can also be configured as follows. (1) A system for generating a predicted voltage characteristic table that specifies a predicted characteristic curve between a voltage value indicating a peak value of a pulse based on a predetermined reference value and a temperature in a drive signal that is applied to an ejection unit that ejects liquid and has one or more pulses, the system comprising: a data acquisition unit that acquires, as input data, an actual viscosity characteristic table that defines an actual characteristic curve between the viscosity and temperature of the liquid, and predetermined parameters; a conversion coefficient generating unit that generates the conversion coefficient based on the predetermined parameters by using a first analysis method as a predetermined analysis method, the first analysis method being an explanatory variable and a conversion coefficient used in performing a conversion process from the actual characteristic curve to the predicted characteristic curve being an objective variable; a table generating unit that generates the predicted voltage characteristics table by performing the conversion process using the actual viscosity characteristics table and the conversion coefficient generated by the conversion coefficient generating unit; A characteristic table generating system comprising: (2) The predetermined parameters include at least the specific gravity of the liquid or a physical property value obtained by using the specific gravity of the liquid. The characteristic table generating system according to (1) above. (3) The conversion process includes: a preliminary process of generating a preliminary characteristic curve showing a relationship between a voltage value and a temperature from the actual characteristic curve using the conversion coefficient; 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 parameters are: a drop number corresponding to the number of pulses included in a unit period of the drive signal; and base a viscosity value of the liquid at a sub-temperature; the voltage shift amount; The abovea voltage sensitivity of the liquid, which corresponds to a change per unit voltage in the ejection speed of the liquid or the droplet volume of the liquid when the liquid is ejected at a reference temperature; and Further includes at least one parameter of The characteristic table generating system according to (2) above. (4) using a second analysis method as a predetermined analysis method, in which a target value of the ejection speed of the liquid or a droplet volume of the liquid is used as an explanatory variable and a voltage sensitivity of the liquid is used as a response variable; The voltage sensitivity of the liquid is generated based on a target value of the ejection speed of the liquid or the droplet volume of the liquid. The characteristic table generating system according to (3) above. (5) The conversion process includes: a preliminary process of generating a preliminary characteristic curve showing a relationship between a voltage value and a temperature from the actual characteristic curve using the conversion coefficient; 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 A voltage value after adding the voltage shift amount is When the liquid is ejected from the ejection portion, The predetermined reference value corresponds to a voltage value at which a reference ejection speed of the liquid is obtained, or a voltage value at which a reference droplet volume of the liquid is obtained, as the predetermined reference value. A characteristic table generating system according to any one of (1) to (4) above. (6) a viscosity value of the liquid at a reference temperature; A parameter indicating the presence or absence of a common drive in the drive signal; At least one of the parameters is included as an explanatory variable, Using a third analysis method as a predetermined analysis method, the voltage shift amount is set as a response variable, The voltage shift amount is generated based on the explanatory variables including the at least one parameter. The characteristic table generating system according to (5) above. (7) As the explanatory variables in the third analysis method, 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 is a value specific to a liquid ejection head having the ejection unit; and A parameter indicating a type of the liquid jet head; The specific gravity of the liquid; The above a voltage sensitivity of the liquid, which corresponds to a change per unit voltage in the ejection speed of the liquid or the droplet volume of the liquid when the liquid is ejected at a reference temperature; and the surface tension value of the liquid; Further includes at least one parameter of The characteristic table generating system according to (6) above. (8) The predetermined analysis method is The predetermined parameters are input and the conversion coefficients are output. A characteristic table generating system according to any one of (1) to (7) above. (9) The apparatus further includes a signal generating unit that uses the predicted voltage characteristics table generated by the table generating unit to determine a peak value of the pulse, and generates the drive signal using the pulse having the determined peak value. A characteristic table generating system according to any one of (1) to (8) above. (10) the data acquisition unit, the conversion coefficient generation unit, and the table generation unit, The liquid jet recording apparatus includes a liquid jet head having the ejection unit, and the liquid jet head is provided in an external device located outside the liquid jet recording apparatus. A characteristic table generating system according to any one of (1) to (9) above. (11) the data acquisition unit, the conversion coefficient generation unit, and the table generation unit, The liquid ejection head includes a liquid ejection unit. The liquid ejection unit is disposed in a liquid ejection recording apparatus. A characteristic table generating system according to any one of (1) to (9) above. (12) the data acquisition unit, the conversion coefficient generation unit, and the table generation unit, The liquid ejection head is provided with The characteristic table generating system according to (11) above. (13) A method for generating a predicted voltage characteristic table that specifies a predicted characteristic curve between a voltage value indicating a peak value of a pulse, based on a predetermined reference value, and temperature, in a drive signal that is applied to an ejection unit that ejects liquid and has one or more pulses, the method comprising: acquiring, as input data, an actual viscosity characteristic table that defines an actual characteristic curve between the viscosity and temperature of the liquid, and predetermined parameters; generating the conversion coefficient based on the predetermined parameters by using a first analysis method as a predetermined analysis method, the first analysis method having the predetermined parameters as explanatory variables and a conversion coefficient used in performing a conversion process from the actual characteristic curve to the predicted characteristic curve as a response variable; performing the conversion process using the actual viscosity characteristics table and the generated conversion coefficient to generate the predicted voltage characteristics table; A method for generating a characteristic table comprising: (14) A program for generating a predicted voltage characteristic table that specifies a predicted characteristic curve between a voltage value indicating a peak value of a pulse based on a predetermined reference value and a temperature in a drive signal that is applied to an ejection unit that ejects liquid and has one or more pulses, the program comprising: acquiring, as input data, an actual viscosity characteristic table that defines an actual characteristic curve between the viscosity and temperature of the liquid, and predetermined parameters; generating the conversion coefficient based on the predetermined parameters by using a first analysis method as a predetermined analysis method, the first analysis method having the predetermined parameters as explanatory variables and a conversion coefficient used in performing a conversion process from the actual characteristic curve to the predicted characteristic curve as a response variable; performing the conversion process using the actual viscosity characteristics table and the generated conversion coefficient to generate the predicted voltage characteristics table; Have your computer run A program that generates property tables. (15) A non-transient computer-readable recording medium having recorded thereon a program for generating a predicted voltage characteristic table that defines a predicted characteristic curve between a voltage value indicating a peak value of a pulse, the voltage value being based on a predetermined reference value, and a temperature, in a drive signal that is applied to an ejection unit that ejects liquid and has one or more pulses, the predicted voltage characteristic table defining a predicted characteristic curve between the voltage value and a temperature, the predicted voltage characteristic table comprising: acquiring, as input data, an actual viscosity characteristic table that defines an actual characteristic curve between the viscosity and temperature of the liquid, and predetermined parameters; generating the conversion coefficient based on the predetermined parameters by using a first analysis method as a predetermined analysis method, the first analysis method having the predetermined parameters as explanatory variables and a conversion coefficient used in performing a conversion process from the actual characteristic curve to the predicted characteristic curve as a response variable; performing the conversion process using the actual viscosity characteristics table and the generated conversion coefficient to generate the predicted voltage characteristics table; A characteristic table generating program is recorded on the computer, Recording medium. [Explanation of symbols]

[0179] Reference Signs List 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 tube, 4 (4Y, 4M, 4C, 4K), 4B... inkjet head, 41... nozzle plate, 42... actuator plate, 48... signal generating unit, 49... driving unit, 5, 5A, 5B, 5C... characteristic table generating system , 50... network, 6... scanning mechanism, 61a, 61b... guide rail, 62... carriage, 63... drive mechanism, 631a, 631b... pulley, 632... endless belt, 633... drive 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... conversion coefficient 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...difference 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, Pr...parameter, Kc...conversion coefficient, TMvi...measured viscosity characteristics table, TPvp...predicted voltage characteristics table, CMvi, CMvp...measured characteristic curve, CPvp0...preliminary characteristic curve, CPvp...predicted characteristic curve, t...time.

Claims

1. A system for generating a predicted voltage characteristic table that specifies a predicted characteristic curve between a voltage value indicating a peak value of a pulse based on a predetermined reference value and a temperature in a drive signal that is applied to an ejection unit that ejects liquid and has one or more pulses, the system comprising: a data acquisition unit that acquires, as input data, an actual viscosity characteristic table that defines an actual characteristic curve between the viscosity and temperature of the liquid, and predetermined parameters; a conversion coefficient generating unit that generates the conversion coefficient based on the predetermined parameters by using a first analysis method as a predetermined analysis method, the first analysis method being an explanatory variable and a conversion coefficient used in performing a conversion process from the actual characteristic curve to the predicted characteristic curve being an objective variable; a table generating unit that generates the predicted voltage characteristics table by performing the conversion process using the actual viscosity characteristics table and the conversion coefficient generated by the conversion coefficient generating unit; A characteristic table generating system comprising:

2. The predetermined parameters include at least the specific gravity of the liquid or a physical property value obtained by using the specific gravity of the liquid. The characteristic table generating system according to claim 1 .

3. The conversion process includes: a preliminary process of generating a preliminary characteristic curve showing a relationship between a voltage value and a temperature from the actual characteristic curve using the conversion coefficient; 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 parameters are: 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; the voltage shift amount; a voltage sensitivity of the liquid, which corresponds to an amount of change per unit voltage in an ejection speed of the liquid or a droplet volume of the liquid when the liquid is ejected at the reference temperature; and and further including at least one parameter of The characteristic table generating system according to claim 2 .

4. using a second analysis method as a predetermined analysis method, in which a target value of the ejection speed of the liquid or a droplet volume of the liquid is used as an explanatory variable and a voltage sensitivity of the liquid is used as a response variable; The voltage sensitivity of the liquid is generated based on a target value of the ejection speed of the liquid or the droplet volume of the liquid. The characteristic table generating system according to claim 3 .

5. The conversion process includes: a preliminary process of generating a preliminary characteristic curve showing a relationship between a voltage value and a temperature from the actual characteristic curve using the conversion coefficient; 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 A voltage value after adding the voltage shift amount is When the liquid is ejected from the ejection portion, The predetermined reference value corresponds to a voltage value at which a reference ejection speed of the liquid is obtained, or a voltage value at which a reference droplet volume of the liquid is obtained, as the predetermined reference value.

5. The characteristic table generating system according to claim 1.

6. a viscosity value of the liquid at a reference temperature; A parameter indicating the presence or absence of a common drive in the drive signal; At least one of the parameters is included as an explanatory variable, Using a third analysis method as a predetermined analysis method, in which the voltage shift amount is a response variable, The voltage shift amount is generated based on the explanatory variables including the at least one parameter. The characteristic table generating system according to claim 5 .

7. As the explanatory variables in the third analysis method, 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 is a value specific to a liquid ejection head having the ejection unit; and A parameter indicating a type of the liquid jet head; The specific gravity of the liquid; a voltage sensitivity of the liquid, which corresponds to an amount of change per unit voltage in an ejection speed of the liquid or a droplet volume of the liquid when the liquid is ejected at the reference temperature; and the surface tension value of the liquid; and further including at least one parameter of The characteristic table generating system according to claim 6.

8. The predetermined analysis method is The predetermined parameters are input and the conversion coefficients are output. The characteristic table generating system according to any one of claims 1 to 7.

9. The apparatus further includes a signal generating unit that uses the predicted voltage characteristics table generated by the table generating unit to determine a peak value of the pulse, and generates the drive signal using the pulse having the determined peak value. The characteristic table generating system according to any one of claims 1 to 8.

10. the data acquisition unit, the conversion coefficient generation unit, and the table generation unit, The liquid jet recording apparatus includes a liquid jet head having the ejection unit, and the liquid jet head is provided in an external device located outside the liquid jet recording apparatus. The characteristic table generating system according to any one of claims 1 to 9.

11. the data acquisition unit, the conversion coefficient generation unit, and the table generation unit, The liquid ejection head includes a liquid ejection unit. The liquid ejection unit is disposed in a liquid ejection recording apparatus. The characteristic table generating system according to any one of claims 1 to 9.

12. the data acquisition unit, the conversion coefficient generation unit, and the table generation unit, The liquid ejection head is provided with The characteristic table generating system according to claim 11.

13. A method for generating a predicted voltage characteristic table that specifies a predicted characteristic curve between a voltage value indicating a peak value of a pulse, based on a predetermined reference value, and a temperature, in a drive signal that is applied to an ejection unit that ejects liquid and has one or more pulses, the method comprising: acquiring, as input data, an actual viscosity characteristic table that defines an actual characteristic curve between the viscosity and temperature of the liquid, and predetermined parameters; generating the conversion coefficient based on the predetermined parameters by using a first analysis method as a predetermined analysis method, the first analysis method having the predetermined parameters as explanatory variables and a conversion coefficient used in performing a conversion process from the actual characteristic curve to the predicted characteristic curve as a response variable; performing the conversion process using the actual viscosity characteristics table and the generated conversion coefficient to generate the predicted voltage characteristics table; A method for generating a characteristic table comprising:

14. A program for generating a predicted voltage characteristic table that specifies a predicted characteristic curve between a voltage value indicating a peak value of a pulse based on a predetermined reference value and a temperature in a drive signal that is applied to an ejection unit that ejects liquid and has one or more pulses, the program comprising: acquiring, as input data, an actual viscosity characteristic table that defines an actual characteristic curve between the viscosity and temperature of the liquid, and predetermined parameters; generating the conversion coefficient based on the predetermined parameters by using a first analysis method as a predetermined analysis method, the first analysis method having the predetermined parameters as explanatory variables and a conversion coefficient used in performing a conversion process from the actual characteristic curve to the predicted characteristic curve as a response variable; performing the conversion process using the actual viscosity characteristics table and the generated conversion coefficient to generate the predicted voltage characteristics table; Have your computer run A program that generates property tables.

Images