Print result prediction device and printing system

Abstract

To provide a print result prediction device and a printing system that can enhance the accuracy of predicting the volume of printed solder.SOLUTION: A print result prediction device according to an embodiment predicts volume of solder printed by a printer that prints solder on a substrate. A calculation unit of the print result prediction device inputs printing conditions into a prediction model that has been trained through machine learning, and predicts the volume of solder that will be printed when next printing is performed under the input printing conditions. The printing conditions include mask information, solder information, substrate information, and device parameters. The mask information relates to a mask used in printing. The solder information relates to the solder used in printing. The substrate information includes concavo-convex information relating to convex portions provided on the substrate used in printing. The device parameters indicate operation of the printer during printing.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a print result prediction device and a printing system. [Background technology]

[0002] The manufacturing of mounting boards involves a printing process in which solder is printed onto the board using a printer, a mounting process in which components are mounted onto the board using a surface mounter, and a reflow process in which heating is performed in a reflow furnace to bond the components to the board. The operation of the printer in the printing process is specified by the printer's device parameters. The volume of solder printed on the board varies depending on printing conditions such as the printer's device parameters. In such a printing process, defects can occur, such as excessive or insufficient volume of printed solder. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-076323 Summary of the Invention [Problem to be solved by the invention]

[0004] The problem to be solved by the present invention is to provide a print result prediction device and a printing system that can improve the prediction accuracy of the volume of printed solder. [Means for solving the problem]

[0005] A print result prediction device according to an embodiment predicts the volume of solder printed by a printer that prints solder on a substrate by filling openings in a mask placed on the substrate with solder. The print result prediction device includes a calculation unit. The calculation unit inputs printing conditions into a prediction model trained by machine learning, and predicts the volume of solder that will be printed through the openings in the mask when the next printing is performed under the input printing conditions. The printing conditions include mask information, solder information, substrate information, and equipment parameters. The mask information relates to the mask used in printing. The solder information relates to the solder used in printing. The substrate information includes concavo-convex information relating to convex portions provided on the substrate used in printing. The equipment parameters indicate the operation of the printer during printing. [Brief explanation of the drawings]

[0006] [Figure 1] FIG. 1 is a block diagram illustrating a printing system including a print result prediction device according to an embodiment. [Figure 2] 2(a) and 2(b) are schematic plan views illustrating a substrate and a mask used in the printing process. [Figure 3] 3(a) to 3(c) are schematic cross-sectional views illustrating the printing process performed by the printing machine. [Figure 4] FIG. 4 is a schematic diagram illustrating the prediction performed by the print result prediction device according to the embodiment. [Figure 5] 5(a) to 5(h) are schematic cross-sectional views illustrating the printing process. [Figure 6] 6(a) to 6(h) are schematic cross-sectional views illustrating the printing process. [Figure 7] FIG. 7 is a schematic diagram illustrating image entropy including silk information. [Figure 8] FIG. 8 is a schematic cross-sectional view illustrating the printing process performed by the printing machine. [Figure 9] FIG. 9 is a graph illustrating the achievement rate of the accuracy of the predicted results of the volume of the printed solder. [Figure 10] FIG. 10 is a schematic diagram illustrating a modified example of the prediction performed by the print result prediction device according to the embodiment. [Figure 11] FIG. 11 is a schematic diagram illustrating the prediction performed by the result prediction device according to the embodiment. [Figure 12] FIG. 12 is a schematic plan view illustrating a part of the substrate. [Figure 13] 13(a) and 13(b) are schematic plan views illustrating a portion of the substrate, and FIG. 13(c) is a graph illustrating the unevenness of the substrate. [Figure 14] FIG. 14 is a schematic view illustrating a substrate and a mask in a printing process. [Figure 15] FIG. 15 is a graph illustrating the relationship between the distance between the protrusion and the pad and the rate of increase in the volume of the solder. [Figure 16] FIG. 16 is a schematic diagram illustrating another example of prediction performed by the result prediction device according to the embodiment. [Figure 17] FIG. 17 is a graph illustrating the predicted error of the printed solder volume. [Figure 18] FIG. 18 is a schematic plan view illustrating an enlarged example of a portion of the substrate. [Figure 19] FIG. 19 is a schematic diagram illustrating the learning of a prediction model. [Figure 20] FIG. 20 is a schematic diagram illustrating the operation of the printing system according to the embodiment. [Figure 21] FIG. 21 is a schematic diagram illustrating the configuration of a print result prediction device according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0007] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the present specification and the drawings, elements similar to those already explained are given the same reference numerals and detailed explanations will be omitted as appropriate.

[0008] FIG. 1 is a block diagram illustrating a printing system including a print result prediction device according to an embodiment. As shown in FIG. 1, a printing system 200 according to the embodiment includes a print result prediction device 100, a printing machine 110, and an inspection machine 120.

[0009] The printer 110 performs a printing process to print solder on the board. The printer 110 repeats the printing process. That is, the printer 110 performs the printing process sequentially on multiple boards, printing solder on each of the multiple boards. The inspection machine 120 inspects the shape and amount (volume) of the solder printed on the board by the printer 110, as well as the height and presence or absence of defects.

[0010] The print result prediction device 100 is an information processing device (information processing system) that predicts the volume of solder that will be printed on a board by the printing process of a printer 110.

[0011] The print result prediction device 100 includes an acquisition unit 10 and a calculation unit 11. The acquisition unit 10 acquires information from outside the print result prediction device 100. For example, the acquisition unit 10 includes a communication module, a communication interface, or a connection terminal for communicating with external devices. For example, the acquisition unit 10 is communicatively connected to external devices such as a printing machine 110 or an inspection device 120, and receives information from the external devices. Any method, such as wired or wireless, can be used for communication. The acquisition unit 10 may also include an input interface (such as a keyboard or touch panel) for a user to input information to the print result prediction device 100. The acquisition unit 10 accepts information input by the user. In this way, the acquisition unit 10 acquires various types of information. The calculation unit 11 is capable of communicating with the acquisition unit 10 and can acquire the information acquired by the acquisition unit 10.

[0012] The calculation unit 11 or the acquisition unit 10 may be communicably connected to a storage unit 13 (storage device). The storage unit 13 stores, for example, information about the board, information about the mask, and a prediction model used to predict the volume of the solder to be printed. The calculation unit 11 can acquire the information stored in the storage unit 13. The storage unit 13 may be a part of the print result prediction device 100.

[0013] The calculation unit 11 calculates an estimated value of the volume of solder to be printed on the board by the printing process, for example, based on information acquired from at least one of the printer 110, the inspection machine 120, and the memory unit 13. Specifically, the calculation unit 11 inputs printing conditions into a prediction model and predicts the volume of solder to be printed when the next printing process is performed under the input printing conditions.

[0014] The printing conditions are a combination of various parameters that indicate the characteristics of the printing process. Carrying out a printing process under the input printing conditions means carrying out a printing process that has the characteristics indicated by each parameter of the printing conditions. Details of the input printing conditions will be described later with reference to FIG. 4.

[0015] The printing process by the printing machine 110 will be described with reference to FIGS. 2(a) to 3(c). 2(a) and 2(b) are schematic plan views illustrating a substrate and a mask used in the printing process. 2(a) illustrates a portion of the substrate S onto which the printer 110 prints solder. FIG. 2(b) illustrates a portion of the mask M used to print the solder onto the substrate S.

[0016] As shown in FIG. 2(a), the substrate S has a base material B and a pad P (conductive portion). The base material B is, for example, an insulating layer containing an insulator such as resin. Wiring made of metal is provided within the substrate S. The pad P is electrically connected to the wiring provided within the substrate S and is exposed on the surface of the substrate S. The pad P is, for example, copper foil. A plurality of pads P are provided on one substrate S.

[0017] Silk Sk may be printed on the surface of the substrate S as needed. The silk Sk is, for example, ink printed on the substrate, and has the shape of letters, symbols, or figures. The silk Sk displays, for example, information about the substrate S and information about the components mounted on the substrate S (such as model numbers and component orientations).

[0018] 2(b), the mask M is, for example, a plate-shaped metal mask having a plurality of openings H (holes). The position and shape of each opening H correspond to the position and shape of each pad P on the substrate S. In the printing process, solder is filled into each opening H, thereby adhering the solder onto each pad P corresponding to each opening H.

[0019] 3(a) to 3(c) are schematic cross-sectional views illustrating the printing process performed by the printing machine. As shown in FIG. 3(a), a mask M corresponding to the substrate S is placed on the substrate S to be printed. This covers the surface of the substrate S with the mask M. At this time, the pads P corresponding to the openings H of the mask M are exposed through the openings H.

[0020] Paste solder 20 is placed on the mask M. A squeegee 25 is moved along the upper surface of the mask M while being in contact with the upper surface of the mask M. In this way, the solder 20 on the mask M is spread and applied over the mask M by the squeegee 25.

[0021] As shown in FIG. 3(b), solder 20 is applied onto the mask M, so that the solder 20 fills each opening H of the mask M.

[0022] As shown in FIG. 3(c), the mask M is removed from above the substrate S. As a result, the solder 20 filled in each opening H of the mask M is transferred onto each pad P of the substrate S. In this way, the solder 20 is printed on the substrate S. That is, a layer of solder 20 having a shape corresponding to the opening H is formed.

[0023] The printer 110 uses, for example, one mask M to sequentially perform such a printing process on each of the plurality of substrates S. In this way, the printer 110 prints solder on each of the plurality of substrates S in sequence. The mechanisms for transporting the substrate or mask, moving the squeegee, and applying solder can be realized by appropriately using a driving device such as an actuator having a motor. For example, the control circuit of the printer 110 controls the operation of the driving device and causes the driving device to perform the operation specified by the device parameters.

[0024] The inspection machine 120 detects the volume of each solder 20 printed on each pad P through each opening H. The inspection machine 120, for example, optically measures the shape (height and width) of the solder 20 on each pad P and calculates the volume of each solder 20 on each pad P. The inspection machine 120, for example, irradiates light onto the solder 20 and measures the reflected light. However, the inspection machine 120 may detect the volume of the solder 20 by any method.

[0025] FIG. 4 is a schematic diagram illustrating the prediction performed by the print result prediction device according to the embodiment. For example, the printer 110 performs a printing process in which solder is printed on the pads P1 of the substrate S1 by filling the openings H1 of a mask M1 placed on the substrate S1 with solder. Note that the substrate S1, mask M1, openings H1, and pads P1 are examples of the substrate S, mask M, openings H, and pads P, respectively.

[0026] As described above, the printer 110 repeats this printing process. The inspector 120 (see FIG. 1) outputs volume information C4 indicating the volume of the solder printed on the substrate S1 through the opening H1 of the mask M1 in the previous (N-1th, where N is an integer equal to or greater than 2) printing process using the mask M1. The acquisition unit 10 (see FIG. 1) of the printing result prediction device 100 acquires the volume information C4.

[0027] The calculation unit 11 (see FIG. 1) of the print result prediction device 100 inputs printing conditions 16 into the prediction model 15, and predicts the volume of solder that will be printed on the board S1 through the opening H1 of the mask M1 when the next (next) printing process is performed using the mask M1 under the input printing conditions 16. That is, the calculation unit 11 inputs the printing conditions 16 into the prediction model 15, and causes it to output a predicted value of the volume of solder that will be printed on the board S1 through the opening H1 of the mask M1 when the Nth (next) printing process is performed using the mask M1. The prediction model 15 is a machine learning model that has previously learned the volumes of solder printed in the past through machine learning.

[0028] 4, the input printing conditions 16 include (1) mask information C1 regarding the mask M1 used in the printing process, (2) solder information C2 regarding the solder used in the printing process, (3) device parameters C3 indicating the operation of the printer 110 in the printing process, (4) volume information C4 indicating the volume of solder printed by the opening H1 of the mask M1 in the previous printing process, and (5) printing order C5 indicating the number of times the mask M1 was used in the printing process. The printing conditions 16 may further include (6) environmental information C6 for the printing process, and (7) board information C7 regarding the board S1 used in the printing process.

[0029] The mask information C1 includes, for example, the thickness of the mask M1 and the opening size (opening area) of the opening H1. The mask information C1 may also include coordinates of the opening H1. The mask information C1 may also include information on a processing method for the mask M1. The mask information C1 may also include the angle (taper angle) of the side surface of the opening H1. The mask information C1 may also include the material of the mask M1. The mask information C1 may also include rigidity information such as the Young's modulus of the mask M1. The processing method is a method for forming the opening H1 in the mask M1, such as laser processing or etching. For example, the calculation unit 11 reads the mask information C1 from the memory unit 13 (see FIG. 1). Alternatively, the mask information C1 (or the model number of the mask M1 to be used, etc.) may be input to the calculation unit 11 from an external device, such as the printing machine 110, via the acquisition unit 10.

[0030] The solder information C2 includes, for example, information on the particle size of the solder. The particle size of the solder is, for example, the average particle size of the solder used in the printing process. The solder information C2 may also include information such as the variation in the particle size of the solder, the viscosity of the solder, the thixotropic index, and the flux content. For example, the calculation unit 11 reads the solder information C2 from the memory unit 13. Alternatively, the solder information C2 (or the model number of the solder to be used, etc.) may be input to the calculation unit 11 from an external device such as the printer 110 via the acquisition unit 10. Alternatively, the solder information C2 may be estimated by a separate estimation system.

[0031] The device parameters C3 include, for example, the speed at which the squeegee 25 moves along the mask M1 (printing speed), the pressure at which the squeegee 25 contacts the mask M1 (printing pressure), the angle of the squeegee 25 relative to the mask M1 (squeegee angle), and the speed at which the substrate S1 is separated from the mask M1 (plate separation speed). The device parameters C3 may also include the distance (clearance) between the mask M1 and the substrate S1. The device parameters C3 may also include the frequency at which the mask is automatically cleaned (cleaning frequency). The device parameters C3 are a combination of multiple parameters, such as the printing speed and printing pressure.

[0032] The device parameter C3 input to the prediction model 15 is, for example, a candidate for the device parameter C3 in the next printing process. For example, the calculation unit 11 acquires the device parameter C3 from the printing press 110 or the memory unit 13. For example, the calculation unit 11 acquires multiple parameters representing operations that the printing press 110 can perform from the printing press 110 or the memory unit 13, and selects the device parameter C3 to be input to the prediction model 15 (a candidate for the device parameter C3 in the next printing process) from the multiple acquired parameters.

[0033] The volume information C4 is information acquired by the acquisition unit 10 from the inspection machine 120. The range of "solder volume" in the input and output of the calculation unit 11 and the prediction model 15 includes index values ​​corresponding to the solder volume. Specifically, for example, the print transfer rate or a numerical value convertible to the solder volume may be used. The print transfer rate is the ratio of the volume of the solder printed through an opening H (hole) in the mask to the volume of the opening H.

[0034] The printing order C5 is the number of times the mask M1 has been used in the printing process. That is, the input printing order C5 is information indicating the number of times the mask M1 has been used in the next printing process. In other words, the input printing order C5 is information indicating that the printing process using the mask M1 is the Nth time. For example, the calculation unit 11 acquires the number of times the mask M1 has been used from the printing press 110 via the acquisition unit 10. Alternatively, a signal indicating the execution of the printing process may be input to the calculation unit 11 from the printing press 110, and the calculation unit 11 may count the number of times the mask M1 has been used.

[0035] The environmental information C6 includes, for example, the temperature and humidity inside the printing press 110. The environmental information C6 may also include vibrations of the printing press 110. The temperature and humidity inside the printing press 110 are measured, for example, by a thermometer 111 or a hygrometer provided in the printing press 110. Alternatively, the temperature and humidity inside the printing press 110 may be measured by a thermometer 111 or a hygrometer built into the printing press 110. The vibrations of the printing press 110 are measured, for example, by a vibrometer provided in the printing press 110. The calculation unit 11 acquires the temperature and humidity measured by the thermometer 111 or the hygrometer and the vibrations measured by the vibrometer via the acquisition unit 10.

[0036] The board information C7 includes silk information about the silk provided on the board S1. In this example, the silk information is image entropy calculated from an image of the board S1 that displays the position and shape of the silk. Details of image entropy will be described later. The board information C7 is not limited to silk information, but may also include the thickness and number of layers of the board S1, the thickness of the copper foil on the pad P1, etc. The board information C7 may also include the application area of ​​the solder resist liquid applied to the surface of the board S1. The board information C7 may also include the warpage state of the board S1. For example, board information C7 such as silk information is input to the calculation unit 11 via the acquisition unit 10 from an external device 112 (computer or storage device) that stores design information for the board S1. Alternatively, for example, an image of the board S1 may be input to the calculation unit 11 from the external device 112, and the image entropy may be calculated based on the image acquired by the calculation unit 11. The calculation unit 11 may read the board information C7 or an image of the board S1 from the storage unit 13.

[0037] In addition, the printing conditions 16 may include rigidity information such as the thickness of the squeegee 25 used for printing, the length of the squeegee 25, the projection of the squeegee 25, the material of the squeegee 25, and the Young's modulus of the squeegee 25. The printing conditions 16 may also include the time elapsed since the solder was replenished in the printing machine 110, the amount of solder on the mask M1, the tension of the mask M1, etc. The printing conditions 16 may also include the type and position of a jig that supports the substrate S1 to be printed from below.

[0038] 5(a) to 5(h) are schematic cross-sectional views illustrating the printing process. 5(a) to 5(d) show an example of the (N-1)th printing step using the opening H1 of the mask M1. 5A, the side surface W1 of the opening H1 in the mask M1 may have irregularities. For example, depending on the processing method of the opening H1 when manufacturing the mask M1, the side surface W1 may become rough.

[0039] As shown in FIG. 5(b), the opening H1 is filled with solder 20, and then, as shown in FIG. 5(c), the mask M1 is separated from the substrate S1. As a result, as shown in FIG. 5(d), a portion 20a of the solder 20 filled in the opening H1 is printed on the pad P1 of the substrate S1. Another portion 20b of the solder 20 filled in the opening H1 adheres to the side surface W1 of the mask M1. For example, the amount of the portion 20b of the solder 20 adhering to the side surface W1 varies depending on the shape of the side surface W1, such as its roughness and irregularities. Therefore, the volume of the solder 20 printed on the substrate S1 (the volume of the portion 20a) is considered to reflect the shape of the side surface W1. The volume information C4 described with reference to FIG. 4 is, for example, the volume of the portion 20a of the solder 20 filled in the opening H1. Therefore, the volume information C4 reflects the shape of the side surface W1, such as its roughness and irregularities.

[0040] 5(e) to 5(h) show an example of the Nth printing process using the opening H1 in the mask M1. In the Nth printing process, solder is printed on pads P1 provided on a substrate S1 that is different from that in the (N-1)th printing process.

[0041] As shown in FIG. 5(e), in the Nth printing step, a portion 20b of the solder 20 deposited in the (N-1)th printing step remains on the side surface W1 of the opening H1. This opening H1 is filled with new solder 20 as shown in FIG. 5(f), and then the mask M1 is removed from the substrate S1 as shown in FIG. 5(g). As a result, a portion 20c of the solder 20 that was filled in the opening H1 is printed onto the substrate S1 as shown in FIG. An amount of solder 20 corresponding to the shape of the side surface W1, such as the roughness and irregularities, is deposited on the side surface W1 of the opening H1.

[0042] In this way, information on the shape of the side surface W1 of the opening H1, such as the roughness and irregularities, can be obtained from the volume of the solder 20 printed in the (N-1)th printing step (i.e., volume information C4). The volume of the solder 20 printed on the pad P1 of the substrate S1 in the Nth printing step (the volume of the portion 20c) varies depending on the shape of the side surface W1.

[0043] 6(a) to 6(h) are schematic cross-sectional views illustrating the printing process. 6(a) to 6(d) show an example of the (N-1)th printing process using the opening H1 of the mask M1. As shown in FIG. 6(a), the mask M1 is placed on the substrate S1. As shown in FIG. 6(b), solder 20 is filled into the opening H1 of the mask M1, and as shown in FIG. 6(c), the mask M1 is separated from the substrate S1. As a result, as shown in FIG. 6(d), a portion 20e of the solder 20 filled into the opening H1 is printed on the pad P1 of the substrate S1. Another portion 20f of the solder 20 filled into the opening H1 adheres to the side surface W1 of the mask M1.

[0044] 6(e) to 6(h) show an example of the Nth printing process using the opening H1 of the mask M1. As shown in FIG. 6(e), the mask M1 is placed on the substrate S1. In the Nth printing process, a portion 20f of the solder 20 deposited in the (N-1)th printing process remains on the side surface W1 of the opening H1. As shown in FIG. 6(f), new solder 20 is filled into the opening H1, and then, as shown in FIG. 6(g), the mask M1 is separated from the substrate S1. As a result, a portion 20g of the solder 20 filled in the opening H1 is printed onto the substrate S1, as shown in FIG. 6(h). Further solder 20 is deposited on the side surface W1 of the opening H1.

[0045] In this way, the volume of the solder 20 adhering to the side surface W1 of the opening H1 changes as the printing process is repeated. For example, as the number of times the printing process is performed, i.e., the number of times the mask M1 is used, increases, the volume of the solder 20 adhering to the side surface W1 increases, and the volume of the solder 20 printed on the substrate S1 decreases.

[0046] The number of times the mask M1 is used (i.e., the printing sequence C5) can provide information on the condition of the side surface W1, for example, the amount of solder 20 attached to the side surface W1. The volume of the solder 20 printed on the substrate S1 through the opening H1 varies depending on the condition of the side surface W1.

[0047] As described above, in the embodiment, the prediction model 15 receives as input the volume information C4 and printing order C5 in addition to the mask information C1, solder information C2, and equipment parameters C3. This makes it possible to predict the volume of the printed solder by taking into account the condition of the side surface W1 of the mask M1, such as the shape (irregularities and roughness) of the side surface W1 and contamination on the side surface W1 (e.g., the amount of solder adhered). According to the embodiment, it is possible to improve the accuracy of predicting the volume of the printed solder.

[0048] For example, it is difficult to directly measure the shape of the side surface W1 of the mask M1 or the amount of solder attached to the side surface W1. In contrast, in the embodiment, by using the volume information C4 and the printing order C5, information about the state of the side surface W1 of the mask M1 can be easily obtained.

[0049] For example, the solder adhering to the side surface W1 is removed by cleaning the mask M1. The number of uses of the mask M1 indicated by the printing sequence C5 is, for example, the number of uses after cleaning the mask M1, and is reset to zero by cleaning the mask M1.

[0050] FIG. 7 is a schematic diagram illustrating image entropy including silk information. For example, the silk information included in the board information C7 described with reference to Fig. 4 is based on the image IM1 of the board S1. The image IM1 is an image that displays the pad P1 and the periphery of the pad P1.

[0051] In this example, the silk information is information about the silk Sk around the pad P1, i.e., information about the position and shape of the silk around the pad on which the solder is printed by openings in a mask used in the printing process.

[0052] The periphery of the pad on which the solder is printed refers to a range of a predetermined size around the pad. The periphery of the pad on which the solder is printed is, for example, a square area with one side measuring approximately 1 to 10 cm and centered on the center of the pad. The image IM1 may be, for example, an image of the board S1 or a design drawing of the board S1.

[0053] For example, the silk information is the image entropy of an image displaying information about the silk Sk around the pad P1. For example, as shown in FIG. 7, an image IM2 is derived by extracting only the image of the silk Sk from the image IM1. A binarization process may be applied to the image IM2. In the binarization, pixels displaying the image of the silk Sk are colored black, and other pixels are colored white. Furthermore, for example, an image IM3 is derived by applying multiple dilation processes to the image IM2. In the dilation process, pixels adjacent to the image of the silk Sk displayed as black pixels in the image IM2 are replaced with black.

[0054] The image entropy of the image IM3 can be used as silk information. Image entropy (H) is expressed as H = -ΣP i log2P i It is calculated using the formula: where i is an index representing the gradation of the pixel value. Pi is the probability of the pixel of the i-th gradation appearing in the image. Image entropy (H) is calculated based on the sum for i.

[0055] The expansion process for deriving the image IM3 may be omitted as appropriate, and may be performed as needed. For example, the image entropy of the image IM2 may be used as the silk information.

[0056] FIG. 8 is a schematic cross-sectional view illustrating the printing process performed by the printing machine. 8, in the printing process, a mask M1 is placed on a substrate S1 on which silk Sk has been printed, for example. The substrate S1 is supported at a plurality of positions by a plurality of pins 115.

[0057] The silk Sk forms a convex portion that protrudes upward from the surface of the substrate S1. The silk Sk is located between the mask M1 and the substrate S1. If such silk Sk is present, the substrate S1 may bend due to force from a jig such as the pin 115. If the substrate S1 is bent, the distance between each pad P and the substrate S1 changes for each pad P depending on the position and shape of the silk Sk around each pad P. This changes the amount of solder 20 filled in each opening H on each pad P. In other words, the volume of solder printed on the pad P may change depending on the position and shape of the silk Sk.

[0058] In contrast, in an embodiment, the printing conditions 16 input to the prediction model 15 may include the silk information as described above. By taking the silk information into consideration when predicting the volume of the printed solder, the prediction accuracy can be further improved.

[0059] FIG. 9 is a graph illustrating the achievement rate of the accuracy of the predicted results of the volume of the printed solder. To calculate the achieved data rate shown in FIG. 9, the prediction model 15 predicts the volume value of each solder printed on each pad P through each opening H of the mask M. The volume of each solder printed on each pad P through each opening H is also measured. The achieved data rate is the ratio of the number of values ​​whose prediction error is smaller than a predetermined value (specification value) to the total number of predicted values. The prediction error is a value corresponding to the difference between the actual measured value of the solder volume and the predicted value of the solder volume.

[0060] "W / O Silk" in FIG. 9 is data when the printing conditions 16 input to the prediction model 15 do not include silk information. "Distance," "Amount," and "Entropy" are data when the printing conditions 16 input to the prediction model 15 include silk information. For "Distance," the silk information is the distance between the pad P and the silk Sk closest to the pad P. For "Amount," the silk information is the amount (e.g., area) of silk Sk around the pad P. For "Entropy," the silk information is the image entropy described with reference to FIG. 7.

[0061] As shown in Figure 9, by taking silk information into consideration, the prediction accuracy can be further improved. When the silk information includes image entropy calculated from the image of the substrate, the prediction accuracy can be further improved.

[0062] FIG. 10 is a schematic diagram illustrating a modified example of the prediction performed by the print result prediction device according to the embodiment. In the example of Fig. 4 described above, image entropy was used for the silk information of the substrate information C7. The example of Fig. 10 differs from the example described with reference to Fig. 4 in that an image of the substrate S1 is used for the substrate information C7 instead of image entropy.

[0063] 10, an image IM1 showing a pad P1 on which solder, the volume of which is to be predicted, is printed and its surroundings may be input as board information C7. Alternatively, an image IM2 showing only an image of the pad P1 and silk Sk may be generated based on image IM1, and the image IM2 may be input as board information C7. Image IM2 may be generated by a machine learning model 19 that has been trained to use image IM1 as input and output image IM2, for example.

[0064] FIG. 11 is a schematic diagram illustrating the prediction performed by the result prediction device according to the embodiment. The example shown in FIG. 11 differs from the example described with reference to FIG. 4 in that unevenness information C70 is used as substrate information C7.

[0065] A plurality of protrusions Cp (see FIG. 12, etc.) are provided on the surface of the substrate S1. The unevenness information C70 is information relating to the protrusions Cp provided on the substrate S1. More specifically, the unevenness information includes at least one of thickness information C71 relating to the thickness of the protrusions Cp, distance information C72 corresponding to the distance between the protrusions Cp and the pads P1, and image entropy C73 calculated from an image including the protrusions Cp. The protrusions Cp include, for example, silk Sk. The following description will be given taking as an example a case where the protrusions Cp are silk Sk.

[0066] FIG. 12 is a schematic plan view illustrating a part of the substrate. As shown in FIG. 12, a plurality of protrusions Cp (silk Sk in this example) are provided around the pad P1. The distance information C72 is, for example, the shortest distance Dm between the center P1c of the pad P1 and the protrusions Cp. In other words, the distance information C72 is the distance between the center P1c and the protrusions Cp closest to the center P1c. The distance information C72 is not limited to the shortest distance Dm itself, but may be a distance corresponding to the shortest distance Dm, for example, the distance between the pad P1 and the protrusion Cp closest to the pad P1. For example, the distance information C72 may be the shortest distance between the edge of the pad P1 and the protrusions Cp.

[0067] The distance information C72 can be obtained from, for example, design information of the substrate S1. For example, the shortest distance Dm can be calculated based on the position and shape of the silk Sk (for example, a binarized image of the silk Sk on the substrate) based on the design information of the substrate S1 and the coordinates of the pad P1.

[0068] 13(a) and 13(b) are schematic plan views illustrating a portion of the substrate, and FIG. 13(c) is a graph illustrating the unevenness of the substrate. Although multiple pads, silk screens Sk, wiring, etc. are provided on the surface of the substrate S1, they are omitted in Fig. 13(a) for simplicity. Fig. 13(b) is an enlarged view of one of the multiple regions R1 shown in Fig. 13(a). On the substrate surface, unevenness due to protrusions Cp occurs along straight lines such as line L1 shown in Fig. 13(b). Fig. 13(c) is an example of unevenness along straight lines on the substrate surface measured by a coordinate measuring machine.

[0069] 13(c), the thickness information C71 is the thickness TCp of the protrusion Cp (height of the silk Sk). The thickness TCp of the protrusion Cp may be based on an actual measurement value or on design information of the substrate S1.

[0070] The thickness information C71 is not limited to the thickness of the protrusion Cp closest to the pad P1 itself, but may be a value corresponding to the thickness of the protrusions Cp provided around the pad P1. For example, each of the multiple regions R1 on the substrate S1 includes one or more protrusions Cp. The thickness information C71 may be the average value of the thicknesses (measured values) of the multiple protrusions Cp included in the multiple regions R1. In this example, the thickness information C71 is the average thickness of the multiple protrusions Cp in three regions R1. The size, position, and number of regions R1 may be determined appropriately and are not particularly limited.

[0071] The image entropy C73 may be the image entropy calculated based on an image of the substrate S1 in which the convex portion Cp is extracted by the same method as described above with reference to Fig. 7. For example, if the convex portion Cp is silk Sk, the image entropy C73 is the image entropy described with reference to Fig. 7.

[0072] FIG. 14 is a schematic view illustrating a substrate and a mask in a printing process. 14, when a mask M1 is placed on a substrate S1, the adhesion between the substrate S1 and the mask M1 changes depending on the unevenness of the protrusions Cp on the substrate S1. For example, the distance between the pads P1 and the mask M1 changes. Therefore, the volume of the printed solder changes depending on the unevenness information C70 regarding the protrusions Cp provided on the substrate S1.

[0073] FIG. 15 is a graph illustrating the relationship between the distance between the protrusion and the pad and the rate of increase in the volume of the solder. In Fig. 15, the increase rate is the percentage increase in the volume of solder printed on pad P1, with the case where there is no protrusion Cp (or the protrusion Cp is sufficiently far from pad P1) as the reference. Fig. 15 shows data when the thickness of the protrusion Cp (silk Sk) is 21 μm and data when the thickness of the protrusion Cp (silk Sk) is 81 μm.

[0074] 15, when the distance between the protrusion Cp and the pad P1 is reduced, the volume of the printed solder increases. In particular, when the protrusion Cp is thicker, the rate of increase in volume is greater.

[0075] 11, the printing conditions 16 include board information C7 that includes concave-convex information C70. By taking the concave-convex information C70 into consideration when predicting the volume of the solder to be printed, the prediction accuracy can be further improved.

[0076] FIG. 16 is a schematic diagram illustrating another example of prediction performed by the result prediction device according to the embodiment. This example differs from the example described with reference to FIG. 11 in that the printing conditions 16, which are input to the prediction model 15, do not include the volume information C4 and the printing sequence C5.

[0077] In this example, the printing conditions 16 also include board information C7, which includes unevenness information C70. This improves prediction accuracy. Furthermore, if the printing conditions 16 do not include volume information C4, it is not necessary to obtain the previous print results when printing, making it possible to predict the solder volume with high accuracy, even for the first print, for example.

[0078] FIG. 17 is a graph illustrating the predicted error of the printed solder volume. "(A) Distance + Thickness", "(B) Distance", "(C) Thickness", and "(D) None" respectively indicate cases where the input to the prediction model 15 includes thickness information C71 and distance information C72, distance information C72, thickness information C71, and does not include unevenness information C70. Note that the input to each prediction model 15 includes mask information C1, solder information C2, and equipment parameters C3, but does not include volume information C4 or printing order C5.

[0079] In the case of "(A) distance + thickness", the prediction error is about 40% smaller than in the case of "(D) none". In the case of a model in which the prediction model 15 inputs printing conditions 16 including unevenness information C70, the prediction error can be made smaller than in the case of a model that does not include unevenness information C70 in its input.

[0080] FIG. 18 is a schematic plan view illustrating an enlarged example of a portion of the substrate. The substrate S1 may be provided with an outer layer circuit. As shown in Fig. 18, the outer layer circuit includes wiring Wa that protrudes upward from the surface of the substrate. In the above, the protrusions Cp are described as silk Sk, but the protrusions Cp are not necessarily limited to silk Sk. For example, the protrusions Cp may be wiring Wa provided on the surface of the substrate S1. Alternatively, the intersections of the silk Sk and the wiring Wa (the portions where the silk Sk and the wiring Wa overlap in the thickness direction perpendicular to the substrate surface) may be the protrusions Cp.

[0081] For example, both the silk Sk and the wiring Wa may be considered as the convex portion Cp. That is, the multiple convex portions Cp may include multiple first convex portions (e.g., silk Sk) and multiple second convex portions (e.g., wiring Wa). In this case, the thickness information C71 may include at least one of first thickness information regarding the thickness of the first convex portions and second thickness information regarding the thickness of the second convex portions. The distance information C72 may include at least one of first distance information corresponding to the distance between the pad and the first convex portion and second distance information corresponding to the distance between the pad and the second convex portion. The image entropy may be calculated from an image extracted from at least one of the first convex portion and the second convex portion. Alternatively, the unevenness information 70 may include a first image entropy calculated from an image of the first convex portion and a second image entropy calculated from an image of the second convex portion.

[0082] FIG. 19 is a schematic diagram illustrating the learning of a prediction model. The print result prediction device 100 may include a learning unit 17 that performs machine learning to generate the prediction model 15. The learning unit 17 generates the prediction model 15 in advance by machine learning, before predicting the volume of the solder.

[0083] The learning unit 17 is, for example, a computer equipped with a deep learning program. The prediction model 15 is, for example, a model trained using a neural network or a random forest. The prediction model 15 is trained so that it can input printing conditions and output a predicted value for the volume of the printed solder. Known techniques can be applied as appropriate to the machine learning.

[0084] Specifically, for example, multiple printing processes are performed in advance using one or more masks M2. That is, the printer 110 performs a printing process in which solder is printed on the pads P2 of the substrate S2 by filling the openings H2 of the mask M2 arranged on the substrate S2 with solder. Note that the substrate S2, mask M2, openings H2, and pads P2 are examples of the substrate S, mask M, openings H, and pads P described with reference to FIGS. 2(a) to 3(c), respectively. The mask M2 and substrate S2 used in the preliminary printing process may be the same (or have the same specifications) as the mask M1 and substrate S1 used in the printing process for which the printing result is predicted (the printing process for printing solder whose volume is predicted) described with reference to FIG. 4, or they may be different.

[0085] The learning unit 17 learns the relationship between the printing conditions in each previous printing process and the volume of each solder printed through each opening H2 of each mask M2 used in each previous printing process. That is, for example, the learning unit 17 learns, as training data, the printing conditions in the nth (n is an integer equal to or greater than 2) printing process using opening H2 of mask M2 and the volume Vn of solder printed through opening H2 of mask M2 in the nth printing process using mask M2.

[0086] The printing conditions for the nth printing process using mask M2 may include, for example, (1) mask information C1 regarding mask M2, (2) solder information C2 regarding the solder used in the nth printing process using mask M2, (3) device parameters C3 indicating the operation of printer 110 in the nth printing process using mask M2, (4) volume information C4 indicating the volume of solder printed by opening H2 of mask M2 in the n-1th printing process using mask M2, and (5) printing order C5 indicating the number of times mask M2 was used in the nth printing process using mask M2 (in other words, information indicating that the printing process using mask M2 is the nth printing process). Furthermore, the printing conditions for the nth printing process using mask M2 may include (6) environmental information C6 for the printing process and (7) substrate information C7 regarding the substrate S2 used in the printing process. For example, substrate information C7 may include concavo-convex information C70.

[0087] As described with reference to the example of FIG. 16 , the printing conditions 16 may not include the volume information C4 and the printing order C5, but may include substrate information C7 including the unevenness information C70. In this case, for example, the learning unit 17 learns the relationship between each printing condition in multiple prior printing processes and the volume of solder printed by each opening H2 of each mask M2 in the printing process under each printing condition. The printing conditions in the prior printing process may include, for example, (1) mask information C1 related to the mask M2 used in the printing process, (2) solder information C2 related to the solder used in the printing process, (3) device parameters C3 indicating the operation of the printer 110 in the printing process, and (4) substrate information C7 including the unevenness information C70 of the substrate S2 used in the printing process. If multiple printing processes are performed for one printing condition, the solder volume to be learned may be the average value for the multiple printing processes.

[0088] FIG. 20 is a schematic diagram illustrating the operation of the printing system according to the embodiment. As shown in FIG. 20, the acquisition unit 10 of the print result prediction device 100 (see FIG. 1) acquires inspection information Z from the inspection machine 120. The inspection information Z includes volume information C4 (see FIG. 4) on the volume of the solder printed in the previous printing process. The acquisition unit 10 of the print result prediction device 100 also acquires environmental information C6 such as temperature. Furthermore, information w is input to the print result prediction device 100. The information w includes mask information C1, solder information C2, and board information C7, which were described with reference to FIG. 4.

[0089] Furthermore, calculation unit 11 of print result prediction device 100 acquires device parameters C3 and printing order C5, as described with reference to Fig. 4. Based on information w, device parameters C3, volume information C4, and printing order C5, calculation unit 11 predicts the volume of solder to be printed in the next printing process using trained prediction model 15.

[0090] The calculation unit 11 inputs a plurality of printing conditions 16 into the prediction model 15 and predicts the volume of solder that will be printed when the next printing process is performed under each of the input printing conditions 16. The plurality of printing conditions 16 input into the prediction model 15 are conditions in which the device parameter C3 is varied. In other words, for example, the plurality of printing conditions 16 used to predict the volume of solder that will be printed using the same opening H differ from each other in the device parameter C3 but are otherwise the same.

[0091] For example, the calculation unit 11 calculates the print quality y based on the prediction result, with the device parameter C3 as the variable x. The calculation unit 11 determines the device parameter C3 for the next printing process based on the change in print quality y when the device parameter C3 (variable x) is changed, and outputs the determined device parameter C3 to the printing machine 110.

[0092] In this way, the device parameter C3 for the next printing process is determined based on the predicted volume of solder. The printer 110 performs the next printing process using the operation indicated by the device parameter C3 for the next printing process determined by the calculation unit 11.

[0093] More specifically, the calculation unit 11 predicts the volume of solder to be printed on each of the pads P through each of the openings H provided in the mask M1. For example, the acquisition unit 10 acquires multiple pieces of volume information C4 indicating the volume of solder printed through each of the openings H in the mask M1 in a previous printing process using the mask M1. The calculation unit 11 inputs printing conditions 16 into the prediction model 15 for each of the openings H and predicts the volume of solder to be printed when the next printing process is performed under each of the input printing conditions 16. Note that the multiple printing conditions 16 (multiple device parameters C3) input into the prediction model 15 include multiple device parameters C3 common to the multiple openings H. Then, based on the prediction result, the calculation unit 11 determines, for example, the device parameter C3 included in one of the multiple printing conditions 16 as the device parameter C3 for the next printing process.

[0094] The print quality y is a parameter that represents, for example, the overall print quality of the solder printed on the multiple pads P present on the substrate S1. More specifically, for example, the "number of pads on which solder determined to be good is printed" can be used for print quality y. The determination of whether a product is good or bad is based on whether the volume of the printed solder meets a predetermined standard. The predetermined standard is, for example, a print transfer rate of 95% or more and 100% or less, but is not limited to this and can be set as appropriate. Alternatively, the print quality y can be the "total deviation of the print transfer rate from 100% for each pad on the substrate." In other words, the absolute value of the difference between the print transfer rate (%) for a pad and 100% can be used to determine the deviation of the print transfer rate for the pad, and the sum of the deviations of the print transfer rates for multiple pads can be used as print quality y.

[0095] Methods for determining the device parameters C3 to be used in the next printing process based on the print quality y include, for example, exhaustive search and steepest descent. In the exhaustive search, the print quality y is calculated for all device parameters C3 that can be set in the printing press 110, and the device parameters C3 that provide the best print quality y (e.g., the device parameters C3 that provide the best print quality y) are extracted. In the steepest descent method, the print quality y is first calculated using provisional device parameters C3 as input, and the provisional device parameters C3 are updated to improve the print quality y based on the gradient of the print quality y when the device parameters C3 are changed from their provisional values. By repeating this update, the device parameters C3 that provide a print quality y that is better than a predetermined reference value are calculated.

[0096] The above-described print quality y and the method for determining the device parameter C3 to be used in the next printing process based on the print quality y are merely examples, and are not necessarily limited to the above.

[0097] According to the printing system 200 of the embodiment, for example, during the production of a board on which solder is printed, the device parameters C3 can be updated as appropriate in response to changes in temperature or changes in the state of the side surfaces of the openings H in the mask M. For example, appropriate device parameters C3 can be automatically calculated from information about the object to be printed. By predicting print quality using the print result prediction device 100, appropriate device parameters C3 can be set without, for example, setting conditions by operating an actual line. Furthermore, for example, appropriate device parameters C3 can be set without relying on the experience of the user. For example, the time required to set the device parameters C3 can be reduced.

[0098] FIG. 21 is a schematic diagram illustrating the configuration of a print result prediction device according to an embodiment. The print result prediction device 100 according to the above-described embodiment is realized, for example, by a hardware configuration similar to that of a general computer (information processing device). The print result prediction device 100 includes a CPU (Central Processing Unit) 311, an input device 312, a display device 313, a ROM (Read Only Memory) 314, a RAM (Random Access Memory) 315, a storage device 316, a communication device 317, and a bus 318. The various components are connected via the bus 318.

[0099] The CPU 311 executes various processes in cooperation with various programs stored in advance in the ROM 314 or the storage device 316, and comprehensively controls the operation of each unit constituting the print result prediction device 100. In its processes, the CPU 311 uses a predetermined area of ​​the RAM 315 as a work area. The CPU 311 operates in cooperation with programs stored in advance in the ROM 314 or the storage device 316 to realize the input device 312, the display device 313, the communication device 317, and the like.

[0100] The input device 312 includes, for example, at least one of a keyboard, a mouse, and a touch panel. The input device 312 receives information input by a user as an instruction signal and outputs the instruction signal to the CPU 311. The display device 313 is, for example, a monitor. The display device 313 outputs various pieces of information in a visibly recognizable manner based on the signal output from the CPU 311.

[0101] The ROM 314 stores programs and various setting information used to control the print result prediction device 100 in a non-rewritable manner. The RAM 315 is a volatile storage medium such as an SDRAM (Synchronous Dynamic Random Access Memory). The RAM 315 functions as a work area for the CPU 311. Specifically, it functions as a buffer or the like that temporarily stores various variables, parameters, and the like used by the print result prediction device 100.

[0102] The storage device 316 is a rewritable storage device such as a semiconductor storage medium such as a flash memory, or a magnetically or optically recordable storage medium. The storage device 316 stores programs and various setting information used to control the print result prediction device 100, a database that records the model names and specifications of learned prediction models, masks, etc. The communication device 317 is used to communicate with external devices and send and receive information.

[0103] For example, the CPU 311, the ROM 314, and the RAM 315 function as the calculation unit 11 (see FIG. 1), the input device 312 and the communication device 317 function as the acquisition unit 10 (see FIG. 1), and the storage device 316 functions as the storage unit 13 (see FIG. 1).

[0104] The embodiment may include the following configurations (for example, technical solutions). (Configuration 1) 1. A printing result prediction device for predicting a volume of solder printed by a printer that prints solder on a substrate by filling openings of a mask arranged on the substrate with the solder, comprising: a calculation unit that inputs printing conditions into a prediction model that has been trained by machine learning, and predicts the volume of solder that will be printed through the opening in the mask when the next printing is performed under the input printing conditions; Equipped with The printing conditions are: mask information relating to the mask used in printing; solder information regarding the solder used in printing; substrate information including concavo-convex information relating to convex portions provided on the substrate used for printing; machine parameters indicative of the operation of the printing press in the printing process; A print result prediction device including: (Configuration 2) 2. The print result prediction device according to claim 1, wherein the prediction model is a model trained by a neural network or a random forest. (Configuration 3) the substrate used for printing has pads onto which solder is printed through the openings; The printing result prediction device according to configuration 1 or 2, wherein the unevenness information includes at least one of thickness information regarding the thickness of the convex portion, distance information corresponding to the distance between the convex portion and the pad, and image entropy calculated from an image including the convex portion. (Configuration 4) 4. The print result predicting device according to any one of configurations 1 to 3, wherein the convex portion includes silk. (Configuration 5) 5. The print result predicting device according to any one of configurations 1 to 4, wherein the convex portion includes wiring of an outer layer circuit. (Configuration 6) 6. The printing result predicting device according to any one of configurations 3 to 5, wherein the thickness information is an average of thicknesses of the plurality of convex portions provided in a plurality of regions on the substrate. (Configuration 7) 7. The print result predicting device according to any one of configurations 3 to 6, wherein the distance information is the shortest distance between the center of the pad and the convex portion. (Configuration 8) an acquisition unit that acquires volume information indicating a volume of solder printed through the openings in the mask in a previous printing operation using the mask; The printing conditions are: the volume information indicating the volume of the solder printed in the previous printing; a printing sequence indicating the number of times the mask is used in printing; 8. The print result prediction device according to any one of configurations 1 to 7, comprising: (Configuration 9) A print result prediction device according to any one of configurations 1 to 8; the printing press; an inspection machine that detects the volume of the printed solder; Equipped with the acquisition unit acquires, from the inspection machine, the volume information on the volume of the solder printed in the previous printing; the calculation unit determines the device parameters for the next printing based on the predicted volume of solder; A printing system in which the printing press performs the next printing in accordance with the operation indicated by the device parameters for the next printing determined by the calculation unit.

[0105] According to the embodiments, it is possible to provide a print result prediction device and a printing system that can improve the prediction accuracy of the volume of printed solder.

[0106] Although several embodiments of the present invention have been described above, these embodiments are presented by way of example only and are not intended to limit the scope of the invention. These novel embodiments can be embodied in various other forms, and various omissions, substitutions, modifications, etc. can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, as well as within the scope of the invention and its equivalents as set forth in the claims. Furthermore, the above-described embodiments can be implemented in combination with each other. [Explanation of symbols]

[0107] 10: Acquisition part 11: Arithmetic section 13: Storage part 15: Predictive model 16: Printing conditions 17: Learning Department 19: Machine learning model 20:Solder 20a~20g: Part of the solder 25: Squeegee 100: Print result prediction device 110:Printing machine 111: Thermometer 112: Equipment 115: Pin 120: Inspection machine 200: Printing system 311:CPU 312: Input device 313:Display device 314:ROM 315:RAM 316: Storage device 317:Communication equipment 318: Bus B: Base material C1: Mask information C2: Solder Information C3: Equipment parameters C4: Volume information C5:Printing order C6:Environmental information C7: Board information C70: Concave / convex information C71: Thickness information C72: Distance information C73: Image Entropy Cp: ​​Convex part Dm: Shortest distance H, H1, H2: Opening IM1, IM2, IM3: Images M, M1, M2: Mask P, P1, P2: Pads P1c: Center of the pad R1: area S, S1, S2: Substrate Sk: Silk TCP: Thickness Vn: volume W, W1: Side Wa: Wiring Z: Test information w:information

Claims

1. 1. A printing result prediction device for predicting a volume of solder printed by a printer that prints solder on a substrate by filling openings of a mask arranged on the substrate with the solder, comprising: a calculation unit that inputs printing conditions into a prediction model that has been trained by machine learning, and predicts the volume of solder that will be printed through the opening in the mask when the next printing is performed under the input printing conditions; Equipped with The printing conditions are: mask information relating to the mask used in printing; solder information regarding the solder used in printing; substrate information including concavo-convex information relating to convex portions provided on the substrate used for printing; machine parameters indicative of the operation of the printing press in printing; A print result prediction device including:

2. The print result prediction device according to claim 1 , wherein the prediction model is a model trained by a neural network or a random forest.

3. the substrate used for printing has pads onto which solder is printed through the openings; 2. The printing result prediction device according to claim 1, wherein the unevenness information includes at least one of thickness information relating to the thickness of the convex portion, distance information corresponding to the distance between the convex portion and the pad, and image entropy calculated from an image including the convex portion.

4. 4. The printing result predicting device according to claim 1, wherein the convex portion includes silk.

5. 4. The printing result predicting device according to claim 1, wherein the convex portion includes wiring of an outer layer circuit.

6. The printing result predicting device according to claim 3 , wherein the thickness information is an average of thicknesses of the plurality of convex portions provided in a plurality of regions on the substrate.

7. The printing result predicting device according to claim 3 , wherein the distance information is the shortest distance between the center of the pad and the convex portion.

8. an acquisition unit that acquires volume information indicating a volume of solder printed through the openings in the mask in a previous printing operation using the mask; The printing conditions are: the volume information indicating the volume of the solder printed in the previous printing; a printing sequence indicating the number of times the mask is used in printing; 4. The printing result prediction device according to claim 1, further comprising:

9. The print result prediction device according to claim 8 ; the printing press; an inspection machine that detects the volume of the printed solder; Equipped with the acquisition unit acquires, from the inspection machine, the volume information on the volume of the solder printed in the previous printing; the calculation unit determines the device parameters for the next printing based on the predicted volume of solder; A printing system in which the printing press performs the next printing in accordance with the operation indicated by the device parameters for the next printing determined by the calculation unit.

Images