Foreign body detection apparatus and foreign body detection method

Abstract

This foreign body detection apparatus comprises an acquisition unit, a determination unit, and a setting unit. The acquisition unit captures images of an inspection region of a substrate in accordance with the progress of mounting work by a component mounting machine that mounts components on the substrate to acquire a plurality of image data items by capturing images of the same inspection region. The determination unit determines whether or not a foreign body including a component that has accidentally dropped on the inspection area is present, on the basis of the difference between feature values of the inspection area acquired by performing image processing on a reference image data item, which is one image data item among the plurality of image data items, and inspection image data item, which is an image data item of an inspection target acquired after the reference image data item has been acquired. The setting unit sets an inspection algorithm at the time of determining whether or not a foreign body is present, on the basis of the external dimensions of a smallest component which is a component having the smallest external dimensions among the components to be mounted on the substrate, in a target machine which is a component mounting machine, and for which it is determined whether or not a foreign body is present.

Description

Foreign object detection device and foreign object detection method

[0001] This specification discloses a technique relating to a foreign object detection device and a foreign object detection method.

[0002] The determination circuit described in Patent Document 1 compares color information of a captured image with pre-stored color information, counts the number of pixels with mismatched color information, and if the determination circuit determines that the number of pixels with mismatched color information is greater than a preset number of pixels, issues a notification that a foreign object has been mixed in.

[0003] Japanese Patent Application Laid-Open No. 2003-141509

[0004] In component placement machines, there is a possibility that a component being placed may fall into an area on the board other than the intended placement area, and there is a demand for detecting such a component as a foreign object. For example, when comparing multiple image data of the same inspection area on a board and determining the presence or absence of a foreign object based on the difference in the feature values ​​of the inspection area, it is necessary to suppress erroneous determinations due to noise. Therefore, it is expected that the presence of a foreign object in the inspection area will be determined if the number of areas where the difference in the feature values ​​of the inspection area exceeds a predetermined threshold is equal to or greater than a predetermined area.

[0005] However, the smaller the external dimensions of the component to be detected as a foreign object, the smaller the predetermined area must be. Therefore, the component becomes more susceptible to the effects of, for example, changes in the bonding material, such as solder, over time. Specifically, if the area of ​​the bonding material that has changed over time is larger than the predetermined area, the bonding material that has changed over time may be erroneously detected as a foreign object.

[0006] In view of the above circumstances, this specification discloses a foreign object detection device and a foreign object detection method that can determine with appropriate accuracy the presence or absence of foreign objects, including parts that have accidentally dropped into an inspection area.

[0007] This specification discloses a foreign object detection device including an acquisition unit, a determination unit, and a setting unit. The acquisition unit captures images of an inspection area of ​​a board as a component mounting machine that mounts components on the board performs a mounting operation, and acquires multiple image data images of the same inspection area. The determination unit determines the presence or absence of foreign objects, including components that have accidentally dropped into the inspection area, based on differences in feature values ​​of the inspection area acquired by image processing reference image data, which is one of the multiple image data, and inspection image data, which is image data of the inspection target acquired after the reference image data. The setting unit sets an inspection algorithm for determining the presence or absence of foreign objects based on the outer dimensions of a smallest component, which is the component with the smallest outer dimensions among the components to be mounted on the board by the target component mounting machine that is the component mounting machine for which the presence or absence of the foreign object is to be determined.

[0008] This specification also discloses a foreign object detection method including an acquisition step, a determination step, and a setting step. The acquisition step involves capturing images of an inspection area of ​​a board as a component mounting machine that mounts components on the board performs a mounting operation, thereby acquiring multiple image data images of the same inspection area. The determination step involves determining the presence or absence of foreign objects, including components that have accidentally dropped into the inspection area, based on differences in feature values ​​of the inspection area acquired by image processing reference image data, which is one of the multiple image data, and inspection image data, which is image data of the inspection target acquired after the reference image data. The setting step involves setting an inspection algorithm for determining the presence or absence of foreign objects based on the outer dimensions of a smallest component, which is the component with the smallest outer dimensions among the components that will be mounted on the board by the target component mounting machine that is the component mounting machine for which the presence or absence of the foreign object is to be determined.

[0009] This specification discloses a technical idea in claim 5 of the claims originally attached to the application (hereinafter referred to as the "original claims"), where "the foreign object detection device according to claim 1" is changed to "the foreign object detection device according to any one of claims 1 to 4." This specification also discloses a technical idea in claim 8 of the original claims, where "the foreign object detection device according to claim 5" is changed to "the foreign object detection device according to any one of claims 5 to 7."

[0010] Furthermore, this specification discloses the technical idea of ​​changing "the foreign object detection device according to claim 1" in claim 9 originally claimed to "the foreign object detection device according to any one of claims 1 to 8." Also, this specification discloses the technical idea of ​​changing "the foreign object detection device according to claim 1" in claim 12 originally claimed to "the foreign object detection device according to any one of claims 1 to 11."

[0011] The above-described foreign matter detection device can set an inspection algorithm for determining the presence or absence of foreign matter based on the outer dimensions of the smallest component that can be mounted on a circuit board by a target machine, which is a component mounting machine for which the presence or absence of foreign matter is to be determined, thereby making it possible to determine the presence or absence of foreign matter with appropriate accuracy.What has been described above regarding the foreign matter detection device can also be applied to the foreign matter detection method.

[0012] FIG. 1 is a configuration diagram showing an example of the configuration of a substrate-related work line. FIG. 2 is a plan view showing an example of the configuration of a component mounting machine. FIG. 3 is a schematic diagram showing an example of the relationship between a component detected as a foreign object and a bonding member. FIG. 4 is a schematic diagram showing another example of the relationship between a component detected as a foreign object and a bonding member. FIG. 5 is a side view showing an example of a dropped component. FIG. 6 is a block diagram showing an example of a control block of a foreign object detection device. FIG. 7 is a flowchart showing an example of a control procedure by the foreign object detection device. FIG. 7 is a schematic diagram showing an example of reference image data. FIG. 8 is a schematic diagram showing an example of inspection image data. FIG. 9 is a schematic diagram showing an example of the relationship between the time from acquisition of reference image data to acquisition of inspection image data and the limit time. FIG. 9 is a schematic diagram showing another example of the relationship between the time from acquisition of reference image data to acquisition of inspection image data and the limit time.

[0013] 1. Embodiment 1-1. Configuration Example of Substrate-related Work Line WL0 In the substrate-related work line WL0, predetermined substrate-related work is performed on the substrate 90. The type and number of substrate-related work machines WM0 that make up the substrate-related work line WL0 are not limited. As shown in Figure 1, the substrate-related work line WL0 of the embodiment is equipped with multiple substrate-related work machines WM0, including a printer WM1, a print inspection machine WM2, a component mounting machine WM3, a reflow oven WM4, and a visual inspection machine WM5, and the substrate 90 is transported in this order by a board transport device.

[0014] The printer WM1 prints solder at the mounting positions of multiple components 91 on the board 90. The print inspection machine WM2 inspects the printing condition of the solder printed by the printer WM1. As shown in FIG. 2, the component mounting machine WM3 mounts multiple components 91 on the board 90 on which solder has been printed by the printer WM1. There may be one or more component mounting machines WM3. As shown in FIG. 1, when multiple component mounting machines WM3 (three in the figure) are provided, the multiple (three) component mounting machines WM3 can share the mounting work of multiple components 91.

[0015] The reflow furnace WM4 heats the board 90 on which multiple components 91 have been mounted by the component mounting machine WM3, melting the solder and performing soldering. The visual inspection machine WM5 inspects the mounting state of the multiple components 91 mounted by the component mounting machine WM3. In this way, the board-related work line WL0 uses multiple board-related work machines WM0 to sequentially transport the boards 90 and perform production processes including inspection processes to produce the product board 900. Note that the board-related work line WL0 can also be equipped with board-related work machines WM0 such as a function inspection machine, a buffer device, a board supply device, a board inverting device, a shield mounting device, an adhesive application device, and an ultraviolet irradiation device as needed.

[0016] The substrate-related performing machines WM0 and the line management device LC0 that make up the substrate-related performing line WL0 are communicatively connected by a communication unit. The line management device LC0 and the management device HC0 are communicatively connected by the communication unit. The communication unit can communicatively connect them by wire or wirelessly, and various communication methods can be used.

[0017] In the embodiment, a local area network (LAN) is configured by the plurality of substrate-related performing machines WM0, the line management device LC0, and the management device HC0. Therefore, the plurality of substrate-related performing machines WM0 can communicate with each other via a communication unit. Furthermore, the plurality of substrate-related performing machines WM0 can communicate with the line management device LC0 via the communication unit. Furthermore, the line management device LC0 and the management device HC0 can communicate with each other via the communication unit.

[0018] The line management device LC0 controls the plurality of substrate-related performing machines WM0 that make up the substrate-related performing line WL0 and monitors the operating status of the substrate-related performing line WL0. The line management device LC0 stores various control data for controlling the plurality of substrate-related performing machines WM0. The line management device LC0 transmits the control data to each of the plurality of substrate-related performing machines WM0. Furthermore, each of the plurality of substrate-related performing machines WM0 transmits its operating status and production status to the line management device LC0.

[0019] The management device HC0 manages at least one line management device LC0. For example, the operating status and production status of the substrate-related performing machine WM0 acquired by the line management device LC0 are transmitted to the management device HC0 as needed. The management device HC0 is provided with a storage device. The storage device can store various acquired data acquired by the substrate-related performing machine WM0. For example, various image data captured by the substrate-related performing machine WM0 is included in the acquired data. Records of the operating status (log data) acquired by the substrate-related performing machine WM0 are also included in the acquired data. The storage device can also store various production information related to the production of the product substrates 900.

[0020] The substrate-related work line WL0 is equipped with an input / output device 80. A known input / output device can be used as the input / output device 80. The input / output device 80 is equipped with a display unit that visibly displays various data. The display unit is also configured with a touch panel, and functions as an input device that accepts various operations by workers.

[0021] 1-2. Example of the configuration of the component mounting machine WM3 The component mounting machine WM3 mounts a plurality of components 91 on a board 90. As shown in Figure 2, the component mounting machine WM3 includes a board transport device 11, a component supply device 12, a component transfer device 13, a component camera 14, a board camera 15, a control device 16, and a display device 17.

[0022] The board transport device 11 is configured, for example, by a belt conveyor or the like, and transports the board 90 in a transport direction (X-axis direction). The board 90 is a circuit board on which various circuits such as electronic circuits, electric circuits, and magnetic circuits are formed. The board transport device 11 transports the board 90 into the component mounting machine WM3 and positions the board 90 at a predetermined position within the machine. After the component mounting machine WM3 has completed the mounting process of the multiple components 91, the board transport device 11 transports the board 90 out of the component mounting machine WM3.

[0023] The component supply device 12 supplies a plurality of components 91 to be mounted on the board 90. The component supply device 12 includes a plurality of feeders 12a arranged along the conveyance direction (X-axis direction) of the board 90. Each of the plurality of feeders 12a is equipped with a reel. A carrier tape storing a plurality of components 91 is wound around the reel. The feeder 12a feeds the carrier tape at a pitch to supply the components 91 so that they can be picked up at a supply position located at the tip side of the feeder 12a. The component supply device 12 can also supply electronic components (e.g., lead components) that are relatively large compared to chip components and the like, arranged on a tray.

[0024] The component transfer device 13 includes a head driver 13a and a movable stage 13b. The head driver 13a is configured to move the movable stage 13b in the X-axis and Y-axis directions using a linear motion mechanism. A mounting head 20 is detachably (replaceably) attached to the movable stage 13b using a clamping member. The mounting head 20 uses at least one holding member 30 to pick up and hold components 91 supplied by the component supply device 12 and mount the components 91 on the board 90 positioned by the board transport device 11. The holding member 30 may be, for example, a suction nozzle or a chuck.

[0025] The component camera 14 and the board camera 15 may be any known imaging device. The component camera 14 is fixed to the base of the component mounting machine WM3 so that its optical axis faces upward in the vertical direction (Z-axis direction). The component camera 14 can capture images of components 91 and the like held by the holding member 30 from below. The board camera 15 is mounted on the movable stage 13b of the component transfer device 13 so that its optical axis faces downward in the vertical direction (Z-axis direction). The board camera 15 can capture images of the board 90 and the like from above. The component camera 14 and the board camera 15 capture images based on control signals sent from the control device 16. Image data of the images captured by the component camera 14 and the board camera 15 is sent to the control device 16.

[0026] The control device 16 includes a known arithmetic unit and a storage device, and functions as a control circuit. The control device 16 receives information, image data, and the like output from various sensors provided in the component mounting machine WM3. The control device 16 sends control signals to each device based on a control program and predetermined mounting conditions that have been set in advance.

[0027] For example, the control device 16 causes the board camera 15 to capture an image of the board 90 positioned by the board transport device 11. The control device 16 processes the image captured by the board camera 15 to recognize the positioning state of the board 90. The control device 16 also causes the holding member 30 to pick up and hold the component 91 supplied by the component supply device 12, and causes the component camera 14 to capture an image of the component 91 held by the holding member 30. The control device 16 processes the image captured by the component camera 14 to recognize the holding posture of the component 91.

[0028] The control device 16 moves the holding member 30 above the intended placement position that is set in advance by a control program or the like. The control device 16 also corrects the intended placement position based on the positioning state of the board 90, the holding posture of the component 91, and the like, and sets the placement position where the component 91 will actually be placed. The intended placement position and the placement position include a rotation angle in addition to the position (X-axis coordinate and Y-axis coordinate).

[0029] The control device 16 corrects the target position (X-axis coordinate and Y-axis coordinate) and rotation angle of the holding member 30 to match the placement position. The control device 16 lowers the holding member 30 at the corrected rotation angle in the corrected target position to place the component 91 on the board 90. The control device 16 repeats the above pick-and-place cycle to perform the placement process of placing multiple components 91 on the board 90.

[0030] A known display device can be used as the display device 17. The display device 17 has a display unit that visually displays various information such as the production status. The display unit is also configured with a touch panel, and functions as an input device that accepts various operations by the worker.

[0031] 1-3. Configuration Example of Foreign Object Detection Device 70 In component mounting machine WM3, there is a possibility that a component 91 to be mounted may fall into an area of ​​the board 90 other than the intended mounting area, and there is a demand to detect this component 91 as a foreign object 93. For example, when comparing multiple image data PD0 obtained by capturing images of the same inspection area CA0 of board 90 and determining the presence or absence of a foreign object 93 based on differences in the feature quantities of inspection area CA0, it is necessary to suppress erroneous determinations due to noise. Therefore, it is expected that if the number of areas where the difference in the feature quantities of inspection area CA0 exceeds a predetermined threshold is equal to or greater than a predetermined area, it will be determined that a foreign object 93 is present in inspection area CA0.

[0032] However, the smaller the external dimensions of the component 91 to be detected as a foreign object 93, the smaller the predetermined area must be. Therefore, the component 91 is more susceptible to the effects of, for example, changes in the bonding material 92, such as solder, over time. Specifically, if the area of ​​the bonding material 92 that has changed over time is equal to or larger than the predetermined area, the bonding material 92 that has changed over time may be erroneously detected as a foreign object 93. For example, FIGS. 3A and 3B show an example of the relationship (size relationship) between the component 91 and the bonding material 92 to be detected as a foreign object 93. Note that FIGS. 3A and 3B illustrate the electrode portion 91b of the component 91 that stands upright in the inspection area CA0, as shown in FIG. 3C. Also, FIGS. 3A and 3B illustrate the bonding material 92 in an area where the difference in feature amount exceeds a predetermined threshold due to changes over time.

[0033] The area of ​​the electrode portion 91b of the component 91 shown in FIG. 3A is larger than the area of ​​the bonding member 92 that has changed over time. Therefore, if the predetermined area is set larger than the area of ​​the bonding member 92 that has changed over time and smaller than the area of ​​the electrode portion 91b of the component 91 shown in FIG. 3A, the component 91 shown in FIG. 3A is detected as a foreign object 93, and the bonding member 92 that has changed over time is not detected as a foreign object 93. In contrast, the area of ​​the electrode portion 91b of the component 91 shown in FIG. 3B is smaller than the area of ​​the electrode portion 91b of the component 91 shown in FIG. 3A and smaller than the area of ​​the bonding member 92 that has changed over time. Therefore, when attempting to detect the component 91 shown in FIG. 3B as a foreign object 93, the predetermined area is set smaller than the area of ​​the bonding member 92 that has changed over time, and the bonding member 92 that has changed over time is erroneously detected as a foreign object 93.

[0034] Therefore, in this embodiment, a foreign object detection device 70 is provided. The foreign object detection device 70 determines with appropriate accuracy the presence or absence of foreign objects 93, including components 91 that have accidentally dropped into the inspection area CA0. Specifically, as shown in FIG. 4 , the foreign object detection device 70, when viewed as a control block, includes an acquisition unit 71, a determination unit 72, and a setting unit 73. The acquisition unit 71, the determination unit 72, and the setting unit 73 can be provided in various control devices, management devices, etc.

[0035] For example, at least one of the acquisition unit 71, the determination unit 72, and the setting unit 73 may be provided in the control device 16 of the component mounting machine WM3. At least one of the acquisition unit 71, the determination unit 72, and the setting unit 73 may also be provided in the line management device LC0. At least one of the acquisition unit 71, the determination unit 72, and the setting unit 73 may also be provided in the management device HC0. At least one of the acquisition unit 71, the determination unit 72, and the setting unit 73 may also be formed on the cloud. As shown in FIG. 4 , in the foreign object detection device 70 of this embodiment, the acquisition unit 71, the determination unit 72, and the setting unit 73 are provided in the control device 16 of the component mounting machine WM3.

[0036] The acquisition unit 71, determination unit 72, and setting unit 73 may be provided in each control device 16 of multiple (three in the example shown in FIG. 1) component mounting machines WM3. Furthermore, the foreign object detection device 70 of this embodiment executes control in accordance with the flowchart shown in FIG. 5. The acquisition unit 71 performs the process shown in step S13. The determination unit 72 performs the process shown in step S14. The setting unit 73 performs the processes shown in steps S11 and S12. The matters described in this specification may be selected and applied as appropriate. The matters described in this specification may be combined as appropriate.

[0037] The acquisition unit 71 images the inspection area CA0 of the board 90 as the component mounting machine WM3 mounts the components 91 on the board 90 and acquires multiple image data PD0 of the same inspection area CA0 (step S13 shown in FIG. 5). The acquisition unit 71 may image the entire mounting area of ​​the board 90 as the inspection area CA0, or may image only a portion of the mounting area of ​​the board 90.

[0038] When capturing an image of a portion of a mounting area on the board 90, the acquisition unit 71 can capture an image of a mounting area of ​​a predetermined component 91 (such as a BGA (Ball Grid Array) component 91) that has a larger number of electrodes than a chip component and is more susceptible to the influence of foreign matter 93. Furthermore, the acquisition unit 71 can determine, based on past mounting records, mounting areas where poor mounting of the component 91 has occurred due to foreign matter 93, mounting areas where foreign matter 93 is likely to adhere, and the like, and can capture an image of these mounting areas as the inspection area CA0.

[0039] The acquisition unit 71 can also designate an area designated by a user of the component mounting machine WM3 as the inspection area CA0. The component mounting machine WM3 of this embodiment is equipped with a display device 17. The substrate-to-substrate work line WL0 is also equipped with an input / output device 80. Using these devices, for example, the user can designate any area (the entire mounting area of ​​the board 90 or a portion of the mounting area of ​​the board 90) as the inspection area CA0. In this case, the acquisition unit 71 can cause the display unit 17 or the input / output device 80 to display a schematic representation of the mounting area of ​​the components 91 on the board 90, allowing the user to select the desired mounting area.

[0040] The acquisition unit 71 can acquire image data PD0 using an imaging device capable of imaging the inspection area CA0. The imaging device is not limited as long as it is capable of imaging the inspection area CA0. For example, the imaging device includes a board camera 15 capable of imaging a portion of the mounting area of ​​the board 90 from above the board 90, and a ceiling camera capable of imaging the entire mounting area of ​​the board 90 from above the board 90. In this embodiment, the board camera 15 is used, and the acquisition unit 71 sets the mounting area of ​​a predetermined component 91 that is susceptible to the influence of foreign matter 93 as the inspection area CA0. Note that the acquisition unit 71 causes the imaging device to image the same inspection area CA0 under the same imaging conditions (e.g., exposure time, aperture, illumination time, etc.) that can be set by the imaging device.

[0041] The determination unit 72 determines the presence or absence of foreign matter 93, including a component 91 that has accidentally dropped into the inspection area CA0, based on the difference in the feature amounts of the inspection area CA0 obtained by image processing the reference image data PD1 and the inspection image data PD2 (step S14 shown in FIG. 5). The reference image data PD1 refers to one of the multiple image data PD0. As described above, the multiple image data PD0 are acquired by the acquisition unit 71. The inspection image data PD2 refers to the image data PD0 of the inspection target that is acquired after the reference image data PD1.

[0042] The feature amount may be any amount obtained by image processing of the image data PD0, and is not limited to this. For example, the feature amount includes the luminance, saturation, and brightness of each pixel in the reference image data PD1 and the inspection image data PD2. In this embodiment, the feature amount is the luminance of each pixel in the reference image data PD1 and the inspection image data PD2. In addition, to prevent erroneous determination due to noise, the determination unit 72 determines that a foreign substance 93 is present in the inspection area CA0 when the difference between the feature amount of the inspection area CA0 obtained from the reference image data PD1 and the feature amount of the inspection area CA0 obtained from the inspection image data PD2 exceeds a predetermined threshold value for a predetermined area or more. Details of determining the presence or absence of a foreign substance 93 will be described later.

[0043] As described above, the smaller the outer dimensions of the component 91 to be detected as a foreign object 93, the smaller the threshold value of the area (the above-mentioned predetermined area) for determining the presence or absence of the foreign object 93 must be, and the more susceptible the area becomes to the effects of, for example, changes over time in the joining material 92, such as solder. Furthermore, components 91 to be mounted on a board 90 by the target machine TG0, which is the component mounting machine WM3 that determines the presence or absence of the foreign object 93, often accidentally fall into the inspection area CA0. Considering these circumstances, it is sufficient to be able to detect, as a foreign object 93, a minimum component 91x, which is a component 91 with the smallest outer dimensions among the components 91 to be mounted on a board 90 by the target machine TG0. The need to detect, as a foreign object 93, components 91 smaller in outer dimensions than the minimum component 91x, is relatively low.

[0044] Therefore, the setting unit 73 sets an inspection algorithm for determining the presence or absence of the foreign matter 93 based on the external dimensions of the smallest component 91x (steps S11 and S12 shown in FIG. 5). This allows the determination unit 72 of the foreign matter detection device 70 to determine the presence or absence of the foreign matter 93 with appropriate accuracy. The setting unit 73 may take various forms as long as it is able to set the inspection algorithm as described above. For example, the setting unit 73 may acquire placement data MD0 used by the target machine TG0 when placing components 91 on the board 90, and identify the smallest component 91x from the acquired placement data MD0.

[0045] The placement data MD0 is included in the control data for controlling the component placement machine WM3 described above. For example, the component placement machine WM3 uses the placement data MD0 for placing the component 91 to place the component 91 on the board 90. The component placement machine WM3 can acquire the placement data MD0 from, for example, the line management device LC0. The placement data MD0 includes information about the component 91, such as the placement coordinates and placement angle of the component 91 to be placed, as well as information about the component 91, such as the external dimensions of the component 91. Thus, the setting unit 73 acquires the placement data MD0 for the target machine TG0, and searches for information about the component 91 to be placed on the board 90 by the target machine TG0 from the acquired placement data MD0, thereby identifying the smallest component 91x.

[0046] Note that a non-installed component 91r may occur. The non-installed component 91r refers to a component 91 that is no longer installed in the target machine TG0 after the placement data MD0 is acquired. If the smallest component 91x initially identified from the placement data MD0 is a non-installed component 91r, the actual smallest component 91x will be a component 91 that is larger in outer dimensions than the initially identified smallest component 91x. Therefore, the setting unit 73 may identify the smallest component 91x by excluding the non-installed component 91r, which is a component 91 that is no longer installed in the target machine TG0 after the placement data MD0 is acquired. This allows the setting unit 73 to identify the smallest component 91x more accurately than if the non-installed component 91r was not excluded.

[0047] For example, non-installed component 91r may occur when the installation of component 91 that was scheduled to be installed in test production is canceled. Also, non-installed component 91r may occur when the installation of component 91 is canceled due to a defect in component supply device 12 that supplies component 91 during the production of product board 900. As described above, component supply device 12 may include, for example, feeder 12a. A defect in feeder 12a may cause the supply of component 91 scheduled to be supplied from feeder 12a to be stopped, and the installation of that component 91 may be canceled.

[0048] Therefore, when the placement of a component 91 to be placed is canceled in test production or when the placement of a component 91 is canceled due to a defect in the component supply device 12 that supplies the component 91 in the production of the product board 900, the setting unit 73 may exclude the canceled component 91 as a non-placed component 91r. This allows the setting unit 73 to identify the non-placed component 91r and identify the minimum component 91x by excluding the non-placed component 91r. Note that the cancellation of the placement of the component 91 can be obtained, for example, from the control device 16 of the component placement machine WM3.

[0049] Furthermore, the inspection algorithm is not limited as long as it is one that is used by the determination unit 72 when determining the presence or absence of the foreign matter 93. Since the setting unit 73 sets the inspection algorithm based on the outer dimensions of the minimum component 91x, it is preferable that the inspection algorithm include a parameter that specifies the outer dimensions of the minimum component 91x.

[0050] Fig. 6 shows an example of reference image data PD1. Fig. 7 shows an example of inspection image data PD2. Note that, for the sake of convenience, Figs. 6 and 7 also show a plurality of pixels arranged in a grid pattern. In the reference image data PD1 shown in Fig. 6, no foreign matter 93 is present in the inspection area CA0, while in the inspection image data PD2 shown in Fig. 7, a foreign matter 93 is present in the inspection area CA0.

[0051] In an area in inspection area CA0 where foreign matter 93 is present, the difference in luminance between the pixel shown in FIG. 6 and the pixel shown in FIG. 7 for the pixel where foreign matter 93 is present exceeds a predetermined threshold. Conversely, in an area in inspection area CA0 where foreign matter 93 is not present, the difference in luminance between the pixel shown in FIG. 6 and the pixel shown in FIG. 7 does not exceed the predetermined threshold. The luminance comparison is performed for each corresponding pixel. For example, if the difference in luminance between several corresponding pixels exceeds the predetermined threshold, and the judgment unit 72 judges that foreign matter 93 is present, the possibility of an erroneous judgment due to noise increases.

[0052] Therefore, the determination unit 72 determines the presence or absence of a foreign substance 93 based on a specific area AR1 where the difference between the feature amount of the inspection area CA0 acquired from the reference image data PD1 and the feature amount of the inspection area CA0 acquired from the inspection image data PD2 exceeds a predetermined threshold. Also, as described above, it is sufficient if the smallest component 91x can be detected as a foreign substance 93, and there is relatively little need to detect a component 91 that is smaller in outer dimension than the smallest component 91x as a foreign substance 93.

[0053] Therefore, the judgment unit 72 may determine that a foreign substance 93 is present in the inspection area CA0 when the size of the specific area AR1 is equal to or larger than the area AR2 corresponding to the outer dimensions of the minimum component 91x. Furthermore, the judgment unit 72 may determine that a foreign substance 93 is not present in the inspection area CA0 when the size of the specific area AR1 is smaller than the area AR2 corresponding to the outer dimensions of the minimum component 91x. This allows the judgment unit 72 to determine with appropriate accuracy whether or not a foreign substance 93 is present. In the example shown in FIG. 7 , the size of the specific area AR1 is larger than the area AR2 corresponding to the outer dimensions of the minimum component 91x. Therefore, the judgment unit 72 determines that a foreign substance 93 is present in the inspection area CA0.

[0054] Furthermore, the parameters of the inspection algorithm are not limited as long as they specify the outer dimensions of the smallest component 91x. Similarly, the smallest component 91x can take various forms. As shown in FIG. 3C , for example, the smallest component 91x may be a chip component. The chip component includes a main body 91a and electrodes 91b provided on both ends of the main body 91a. In this form, the smallest outer dimensions of the smallest component 91x are obtained when the smallest component 91x is standing in the inspection area CA0 and viewed vertically (in the Z-axis direction).

[0055] 7, the electrode portion 91b is visible, and the outer dimensions of the smallest component 91x are minimized. Therefore, if the smallest component 91x is a chip component, the parameters of the inspection algorithm should specify the outer dimensions of the electrode portion 91b of the smallest component 91x standing upright in the inspection area CA0. This allows the determination unit 72 to determine that the dropped chip component is a foreign object 93, regardless of the orientation of the chip component when it was dropped.

[0056] As is clear from FIG. 7 , the size of the specific area AR1 can be expressed by the area of ​​the smallest component 91x. In the example shown in FIG. 7 , the size of the specific area AR1 corresponds to the area of ​​a rectangular area. The size of the specific area AR1 can also be expressed by the perimeter of the smallest component 91x. In the example shown in FIG. 7 , the size of the specific area AR1 corresponds to the perimeter of the rectangle indicated by the dashed line. The same applies to the area AR2 corresponding to the outer dimensions of the smallest component 91x. Therefore, the parameter of the inspection algorithm may be the area or perimeter of the smallest component 91x. This allows the determination unit 72 to determine the size of the specific area AR1 and the size of the area AR2 corresponding to the outer dimensions of the smallest component 91x.

[0057] Furthermore, the inspection algorithm may include an image processing method for the reference image data PD1 and the inspection image data PD2. For example, an image processing method suitable for a component 91 having an outer dimension equal to or larger than that of the smallest component 91x may differ from an image processing method suitable for a component 91 having an outer dimension smaller than that of the smallest component 91x. For example, the outer shape of a component 91 smaller than that of the smallest component 91x is more difficult to recognize than that of a component 91 having an outer dimension equal to or larger than that of the smallest component 91x. Therefore, adjustments may be made in the image processing to make the outer shape of the component 91 easier to recognize.

[0058] In other words, the outer dimensions of a component 91 larger than or equal to the minimum component 91x are easier to recognize than those of a component 91 smaller than the minimum component 91x, so the above adjustment may not be necessary. As described above, the determination unit 72 only needs to be able to determine that a component 91 larger than or equal to the minimum component 91x is a foreign object 93. Therefore, the inspection algorithm preferably includes an image processing method for the reference image data PD1 and the inspection image data PD2 that is suitable for a component 91 larger than or equal to the minimum component 91x. This allows the foreign object detection device 70 to reduce the time required for image processing of the reference image data PD1 and the inspection image data PD2.

[0059] Furthermore, if the feature amount of inspection area CA0 acquired by image processing of image data PD0 fluctuates due to changes over time in bonding material 92 that is applied to inspection area CA0 of substrate 90 and bonds substrate 90 to component 91, the determination unit 72 may erroneously determine that bonding material 92 is foreign matter 93. Therefore, the acquisition unit 71 may specify the time TM0 from when the reference image data PD1 is acquired until when the inspection image data PD2 is acquired, so that the determination unit 72 does not erroneously determine that bonding material 92 is foreign matter 93 due to changes over time in the feature amount of inspection area CA0 that occur due to changes over time in bonding material 92 that is applied to inspection area CA0 and bonds substrate 90 to component 91.

[0060] The joining member 92 is not limited to any material as long as it joins the substrate 90 and the component 91. Examples of the joining member 92 include solder and adhesive. In this embodiment, the joining member 92 is solder. As the flux contained in the solder dries, the color of the solder changes from silver to gray. Therefore, the feature amount of the inspection area CA0 may change due to changes in the solder over time, which may lead to the determination unit 72 erroneously determining that the solder is foreign matter 93.

[0061] The time TM0 from when the reference image data PD1 is acquired to when the inspection image data PD2 is acquired can be acquired in advance, for example, by simulation, verification using an actual device, or the like. Furthermore, the time TM0 may differ depending on the type of joining member 92, and the setting unit 73 can also define the time TM0 depending on the type of joining member 92. For example, the setting unit 73 can define the time TM0 depending on the type of solder. Furthermore, the setting unit 73 can define the time TM0 depending on the type of adhesive.

[0062] Furthermore, the range in which the feature quantity of inspection area CA0 varies increases over time. For example, if the joining member 92 is solder, the contained flux gradually dries, and the range in which the feature quantity of inspection area CA0 varies increases over time. If the range in which the feature quantity of inspection area CA0 varies due to changes in the joining member 92 over time exceeds area AR2 corresponding to the outer dimensions of the smallest component 91x, the judgment unit 72 will erroneously judge the joining member 92 to be foreign matter 93.

[0063] Therefore, it is preferable that the acquisition unit 71 acquires the reference image data PD1 and the inspection image data PD2 within a limit time TM1. The limit time TM1 refers to the longest time during which the size of a specific area AR1, where the difference between the feature amount of the inspection area CA0 acquired from the reference image data PD1 and the feature amount of the inspection area CA0 acquired from the inspection image data PD2 exceeds a predetermined threshold, does not exceed an area AR2 corresponding to the outer dimensions of the smallest component 91x.

[0064] FIG. 8 shows an example of the relationship between the time TM0 from acquisition of reference image data PD1 to acquisition of inspection image data PD2 and the limit time TM1. FIG. 9 shows another example of the relationship between the time TM0 from acquisition of reference image data PD1 to acquisition of inspection image data PD2 and the limit time TM1. In these figures, the most upstream component mounting machine WM3 of the multiple (three) component mounting machines WM3 shown in FIG. 1 is indicated as component mounting machine M1. The central component mounting machine WM3 of the multiple (three) component mounting machines WM3 is indicated as component mounting machine M2 and corresponds to the target machine TG0, which is the component mounting machine WM3 that determines the presence or absence of foreign matter 93. The most downstream component mounting machine WM3 of the multiple (three) component mounting machines WM3 is indicated as component mounting machine M3.

[0065] 8, the limit time TM1 is the time from when a board 90 is loaded into one component mounting machine WM3 until a predetermined component 91 is mounted in that component mounting machine WM3 without an error stop, and when the board 90 is loaded out of that component mounting machine WM3. Therefore, when the board 90 is loaded into the component mounting machine M1, the reference image data PD1 is acquired, and components 91 other than the target component, which is the component 91 to be mounted in the target machine TG0, are mounted. Then, the inspection image data PD2 is acquired, and the determination unit 72 determines whether or not a foreign object 93 is present. If the determination unit 72 determines that no foreign object 93 is present, the board 90 is transported from the component mounting machine M1 to the component mounting machine M2.

[0066] Furthermore, when the board 90 is carried into the component mounting machine M2, the reference image data PD1 is acquired, and components 91 other than the target component are mounted. Then, the inspection image data PD2 is acquired, and the determination unit 72 determines whether or not there is a foreign substance 93. If the determination unit 72 determines that there is no foreign substance 93, the target component is mounted. Then, the board 90 is carried out from the component mounting machine M2. Note that the component mounting machine M3 mounts components 91 other than the target component.

[0067] 9, the limit time TM1 is the time from when a board 90 is loaded into one component mounting machine WM3 until predetermined components 91 are mounted in one component mounting machine WM3 and another adjacent component mounting machine WM3 without an error stop, and when the board 90 is unloaded from that other component mounting machine WM3. Thus, when the board 90 is loaded into the component mounting machine M1, the reference image data PD1 is acquired, and components 91 other than the target components, which are the components 91 to be mounted in the target machine TG0, are mounted. Then, the board 90 is unloaded from the component mounting machine M1 without acquiring the inspection image data PD2.

[0068] Furthermore, when the board 90 is carried into the component mounting machine M2, the mounting of components 91 other than the target component is performed without acquiring the reference image data PD1. Then, the inspection image data PD2 is acquired, and the determination unit 72 determines whether or not there is a foreign substance 93. If the determination unit 72 determines that there is no foreign substance 93, the mounting of the target component is performed. Then, the board 90 is carried out from the component mounting machine M2. Note that the mounting of components 91 other than the target component is performed in the component mounting machine M3.

[0069] For example, when the determination unit 72 determines the presence or absence of foreign matter 93 for components 91 that are smaller than the minimum component 91x in outer dimensions, the area corresponding to the outer dimensions of the component 91 is smaller than the area AR2 corresponding to the minimum component 91x in outer dimensions. Therefore, the limit time TM1 is shorter than when the determination unit 72 determines the presence or absence of foreign matter 93 for components 91 that are larger than or equal to the minimum component 91x in outer dimensions. Therefore, for example, as shown in the example of FIG. 8 , the acquisition unit 71 needs to acquire reference image data PD1 and inspection image data PD2 for each component mounting machine WM3.

[0070] In other words, when the determination unit 72 determines whether or not a foreign object 93 exists for components 91 with dimensions equal to or larger than the minimum component 91x, the limit time TM1 is longer than when the determination unit 72 determines whether or not a foreign object 93 exists for components 91 with dimensions smaller than the minimum component 91x. Therefore, for example, as shown in FIG. 9 , the acquisition unit 71 can acquire reference image data PD1 and inspection image data PD2 for each of two component mounters WM3. In this case, the acquisition unit 71 can reduce the number of times an image is captured, thereby shortening the travel time of an image capture device (e.g., board camera 15) and the image capture time of the image capture device. As a result, the foreign object detection device 70 can improve the cycle time while maintaining the required detection accuracy.

[0071] Note that, like the time TM0 from when the reference image data PD1 is acquired to when the inspection image data PD2 is acquired, the limit time TM1 may also vary depending on the type of joining material 92. Therefore, the setting unit 73 can increase or decrease the limit time TM1 depending on the type of joining material 92. For example, when the joining material 92 is solder, the setting unit 73 can shorten the limit time TM1 for a type of solder that contains flux that dries more easily. In other words, when the joining material 92 is solder, the setting unit 73 can lengthen the limit time TM1 for a type of solder that contains flux that dries more slowly. What has been described above for the case where the joining material 92 is solder also applies to the case where the joining material 92 is adhesive.

[0072] There may also be cases where it is desired to determine the presence or absence of foreign matter 93, including objects smaller than the outer dimensions of the minimum component 91x (for example, dust, etc.). Therefore, the determination unit 72 can switch between determining the presence or absence of foreign matter 93, which is an object to be inspected that is equal to or larger than the outer dimensions of the minimum component 91x, and determining the presence or absence of foreign matter 93, which is an object to be inspected that is smaller than the outer dimensions of the minimum component 91x, as needed by the user of the target machine TG0. The user can issue an instruction to switch between the above determinations using, for example, the display device 17 or the input / output device 80 of the component mounting machine WM3.

[0073] Furthermore, in determining the presence or absence of foreign matter 93, which includes an object smaller than the external dimensions of minimum component 91x, the determination unit 72 determines that foreign matter 93 is present in inspection area CA0 when the size of specific area AR1 is equal to or larger than the area corresponding to the external dimensions of an object smaller than the external dimensions of minimum component 91x. Furthermore, the determination unit 72 determines that foreign matter 93 is not present in inspection area CA0 when the size of specific area AR1 is smaller than the area corresponding to the external dimensions of an object smaller than the external dimensions of minimum component 91x.

[0074] In either configuration, if the determination unit 72 determines that there is no foreign object 93 in the inspection area CA0, the component mounting machine WM3 transports the board 90 to the next component mounting machine WM3 located downstream. On the other hand, if the determination unit 72 determines that there is a foreign object 93 in the inspection area CA0, the component mounting machine WM3 stops transporting the board 90. The foreign object detection device 70 can also notify the user that there is a foreign object 93 in the inspection area CA0. In this case, the user can remove the board 90 and check for the presence or absence of the foreign object 93. If the foreign object 93 can be removed, the user can also remove the foreign object 93.

[0075] 2. Foreign Object Detection Method What has already been described about the foreign object detection device 70 also applies to the foreign object detection method. Specifically, the foreign object detection method includes an acquisition step, a determination step, and a setting step. The acquisition step corresponds to control performed by the acquisition unit 71. The determination step corresponds to control performed by the determination unit 72. The setting step corresponds to control performed by the setting unit 73. Note that duplicated explanations will be omitted in this specification.

[0076] 3. Example of Effect of the Embodiment The foreign matter detection device 70 can set an inspection algorithm for determining the presence or absence of a foreign matter 93 based on the outer dimensions of the smallest component 91x, which is the component 91 with the smallest outer dimensions among the components 91 to be mounted on the board 90 in the target machine TG0, which is the component mounting machine WM3 that is used to determine the presence or absence of the foreign matter 93, and can determine the presence or absence of the foreign matter 93 with appropriate accuracy. What has been described above about the foreign matter detection device 70 also applies to the foreign matter detection method.

[0077] 12: component supply device, 70: foreign object detection device, 71: acquisition unit, 72: judgment unit, 73: setting unit, 90: board, 91: component, 91b: electrode unit, 91r: non-mounted component, 91x: smallest component, 92: joining member, 93: foreign object, 900: product board, MD0: mounting data, CA0: inspection area, AR1: specific area, AR2: area, PD0: image data, PD1: reference image data, PD2: inspection image data, TG0: target machine, TM0: time, TM1: limit time, WM3: component mounting machine.

Claims

1. A foreign object detection device comprising: an acquisition unit that images an inspection area of ​​a board as a component mounting machine that mounts components on the board performs a mounting operation, and acquires multiple image data images of the same inspection area; a determination unit that determines the presence or absence of foreign objects, including components that have accidentally fallen into the inspection area, based on differences in feature amounts of the inspection area obtained by image processing reference image data, which is one of the multiple image data, and inspection image data, which is image data of the object to be inspected that is acquired after the reference image data; and a setting unit that sets an inspection algorithm for determining the presence or absence of foreign objects, based on the external dimensions of a smallest component, which is the component with the smallest external dimensions among the components to be mounted on the board by the target machine that is the component mounting machine that is used to determine the presence or absence of foreign objects.

2. The foreign object detection device according to claim 1, wherein the setting unit acquires mounting data used by the target machine when mounting the component on the board, and identifies the smallest component from the acquired mounting data.

3. The foreign object detection device according to claim 2, wherein the setting unit identifies the smallest components by excluding non-installed components, which are components that are no longer installed on the target machine after the installation data is acquired.

4. A foreign object detection device as described in claim 3, wherein the setting unit excludes the component whose installation has been stopped as a non-installed component when the installation of the component that was scheduled to be installed is stopped in test production or when the installation of the component is stopped due to a defect in a component supply device that supplies the component in the production of a product board.

5. The foreign matter detection device according to claim 1, wherein the inspection algorithm includes a parameter for specifying the outer dimensions of the smallest component, and the judgment unit judges that the foreign matter is present in the inspection area when the size of a specific area in which the difference between the feature amount of the inspection area acquired from the reference image data and the feature amount of the inspection area acquired from the inspection image data exceeds a predetermined threshold is equal to or larger than the area corresponding to the outer dimensions of the smallest component, and judges that the foreign matter is not present in the inspection area when the size of the specific area is smaller than the area corresponding to the outer dimensions of the smallest component.

6. The foreign object detecting device according to claim 5, wherein the smallest component is a chip component, and the parameter specifies the outer dimensions of an electrode portion of the smallest component standing in the inspection area.

7. A foreign object detection device according to claim 5 or 6, wherein the parameter is the area or perimeter of the smallest part.

8. A foreign object detection device according to claim 5, wherein the inspection algorithm includes an image processing method for the reference image data and the inspection image data that is suitable for components having dimensions equal to or larger than the outer dimensions of the smallest component.

9. The foreign matter detection device of claim 1, wherein the acquisition unit specifies the time from acquisition of the reference image data to acquisition of the inspection image data so that the judgment unit does not mistakenly judge the joining material to be the foreign matter due to fluctuations in the feature amount of the inspection area caused by changes over time in the joining material that joins the substrate and the component that is applied to the inspection area.

10. A foreign object detection device as described in claim 9, wherein the acquisition unit acquires the reference image data and the inspection image data within a limit time during which the size of a specific area in which the difference between the feature amount of the inspection area acquired from the reference image data and the feature amount of the inspection area acquired from the inspection image data exceeds a predetermined threshold does not exceed an area corresponding to the external dimensions of the smallest component.

11. The foreign object detecting device according to claim 10, wherein the setting unit increases or decreases the limit time depending on the type of the joining material.

12. A foreign object detection device as described in claim 1, wherein the judgment unit switches between judging the presence or absence of foreign objects that are objects larger than the external dimensions of the smallest part and judging the presence or absence of foreign objects that are objects that are smaller than the external dimensions of the smallest part, depending on the needs of the user of the target machine.

13. A foreign matter detection method comprising: an acquisition step of capturing an image of an inspection area of ​​a board as a component mounting machine that mounts components on a board performs a mounting operation, and acquiring multiple image data images of the same inspection area; a determination step of determining the presence or absence of a foreign matter, including a component that has accidentally dropped into the inspection area, based on differences in feature amounts of the inspection area acquired by image processing reference image data, which is one of the multiple image data, and inspection image data, which is image data of the object to be inspected that is acquired after the reference image data; and a setting step of setting an inspection algorithm for determining the presence or absence of the foreign matter, based on the external dimensions of a smallest component, which is the component that has the smallest external dimensions of the components to be mounted on the board by the target machine that is the component mounting machine that is used to determine the presence or absence of the foreign matter.

Images