Inspection device

Abstract

Provided is an inspection device capable of classifying the type of solder on the basis of the difference in shape (texture) of a solidification structure appearing on the solder surface of an object to be inspected. An inspection device (10) is provided with: an imaging means (20) for imaging a subject (12) to be inspected; and a control unit (30), in which the control unit (30): acquires image data by capturing an image of a solder portion on the object to be inspected (12) by means of the image capturing unit (20); extracting, from the image data, a feature amount of the shape of a solidification structure appearing on the surface of the solder portion; and classifying the type of solder used by the solder portion based on the feature quantity.

Description

Technical Field

[0001] The invention relates to an inspection device. Background Art

[0002] In an inspection device for inspecting the appearance of a substrate on which an electronic component or the like as an object to be inspected is mounted, the soldering state of the substrate is inspected (for example, see Patent Document 1). In addition, in recent years, many solders with low lead content have been developed. Therefore, solders with different performances depending on the difference in composition have been developed (for example, see Patent Document 2).

[0003] Prior art literature

[0004] Patent Literature

[0005] Patent Document 1: Japanese Patent Application Publication No. 2012-053015

[0006] Patent Document 2: Japanese Patent Application Publication No. 2019-206032 Summary of the invention

[0007] Problem that the invention aims to solve

[0008] As mentioned above, many solders with low lead content have been developed in recent years, but from the perspective of quality assurance, the type of solder used for each substrate is determined. However, sometimes a solder different from the determined solder is used due to errors, etc. In such a case, there is a problem that the current inspection device cannot classify the type of solder used for the substrate.

[0009] The present invention has been made in view of the above-mentioned problems, and an object of the present invention is to provide an inspection device capable of classifying the types of solder based on the difference in the shape (texture) of the solidified structure appearing on the solder surface of the inspection object.

[0010] Solutions for solving problems

[0011] In order to solve the above-mentioned problem, the inspection device involved in the present invention comprises: an imaging unit, which photographs an object to be inspected; and a control unit, wherein the control unit performs the following processing: acquiring image data by photographing a solder portion on the object to be inspected by the imaging unit; extracting characteristic quantities of the shape of a solidified structure appearing on the surface of the solder portion from the image data; and classifying the type of solder used for the solder portion based on the characteristic quantities.

[0012] Effects of the Invention

[0013] According to the inspection apparatus of the present invention, the type of solder can be classified based on the difference in the shape (texture) of the solidified structure appearing on the solder surface of the inspection object. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is an explanatory diagram for explaining the structure of the inspection device.

[0015] Figure 2 These are explanatory diagrams for explaining the projection angle of the lighting unit and the detection of its reflected light. (a) shows the projection angle of each illumination source of the lighting unit, and (b) shows an example of the state of the inspection surface of the inspection object.

[0016] Figure 3 This is an explanatory diagram for explaining the correspondence between the hue in the HSV color system and the projection angle of the illumination source of the illumination unit.

[0017] Figure 4 : is a flowchart showing the flow of image synthesis processing.

[0018] Figure 5 : is a flowchart showing the flow of solder type classification processing.

[0019] Figure 6 It is an explanatory diagram showing an example of a feature amount map.

[0020] Figure 7 : is a flowchart showing the flow of the first inspection method.

[0021] Figure 8 : is a flowchart showing the flow of the second inspection method.

[0022] Fig. 9 : is a flowchart showing the flow of the third inspection method.

[0023] Fig.10 : is a flowchart showing the flow of the fourth inspection method.

[0024] Fig.11 : is a flowchart showing the flow of the fifth inspection method. DETAILED DESCRIPTION

[0025] Hereinafter, a preferred embodiment of the present invention will be described with reference to the accompanying drawings. Figure 1The structure of the inspection device 10 involved in the present embodiment is explained. The inspection device 10 is a device that inspects the inspection object 12 using the inspection object image data obtained by photographing the inspection object 12. The inspection object 12 is, for example, an electronic circuit substrate on which many electronic components are installed. The inspection device 10 determines whether the installation state of the electronic components is good or not based on the inspection object image data. Usually, the inspection is performed on each component with respect to multiple inspection items. The inspection item is the item that needs to be determined whether it is good or not. The inspection items include, for example, inspection items about the configuration of the components, such as missing parts, positional offset, polarity inversion, etc., and inspection items about the connection between the components and the substrate, such as the welding state and floating pins of the components.

[0026] The inspection device 10 is configured to include: an inspection platform 14 for holding an inspection object 12; an imaging unit 20 for illuminating and photographing the inspection object 12; an XY table 16 for moving the imaging unit 20 relative to the inspection platform 14; and a control unit 30 for controlling the imaging unit 20 and the XY table 16. Figure 1 As shown, the inspection object arrangement surface of the inspection platform 14 is set as the XY plane, and the direction perpendicular to the arrangement surface (that is, the imaging direction of the imaging unit 20 (the optical axis direction of the optical system of the camera unit 21)) is set as the Z direction.

[0027] The camera unit 20 is mounted on a movable platform (not shown) of the XY table 16, and can be moved in the X direction and the Y direction by the XY table 16. The XY table 16 is, for example, a so-called H-type XY table. Therefore, the XY table 16 includes: a Y linear motor that moves the movable platform in the Y direction along a Y direction guide that extends in the Y direction; and two X direction guides and an X linear motor that are configured to support the Y direction guide at both ends and can move the movable platform and the Y direction guide in the X direction. In addition, the XY table 16 may also include a Z moving mechanism that moves the camera unit 20 in the Z direction, and may also include a rotating mechanism that rotates the camera unit 20. The inspection device 10 may also include an XY table that can move the inspection platform 14. In this case, the XY table 16 that moves the camera unit 20 may also be omitted.

[0028] The imaging unit 20 is configured to include a camera unit 21, a semi-transparent mirror 22, an illumination unit 23, and a projection unit 24. In the inspection device 10 involved in the present embodiment, the camera unit 21, the semi-transparent mirror 22, the illumination unit 23, and the projection unit 24 may also be configured as an integrated imaging unit 20. In the integrated imaging unit 20, the relative positions of the camera unit 21, the semi-transparent mirror 22, the illumination unit 23, and the projection unit 24 may be fixed, or each unit may be configured to be relatively movable. In addition, the camera unit 21, the semi-transparent mirror 22, the illumination unit 23, and the projection unit 24 may also be configured separately and be movable separately. In addition, in the following description, the case where the semi-transparent mirror 22 is used to illuminate the object to be inspected 12 is described, but the semi-transparent mirror 22 may not be present.

[0029] The camera unit 21 includes an imaging element that generates two-dimensional image data of an object and an optical system (e.g., a lens) for imaging the image on the imaging element. The camera unit 21 is, for example, a CCD camera. The maximum field of view of the camera unit 21 may also be smaller than the inspection object placement area of ​​the inspection platform 14. In this case, the camera unit 21 captures the entirety of the inspection object 12 in a manner divided into a plurality of partial images. The control unit 30 controls the XY worktable 16 so that each time the camera unit 21 captures a partial image and outputs partial image data, the camera unit 21 is moved to the next imaging position. The control unit 30 synthesizes the partial image data to generate overall image data of the inspection object 12.

[0030] The camera unit 21 may include an imaging element that generates a one-dimensional image instead of a two-dimensional imaging element. In this case, the entire image of the subject 12 can be acquired by scanning the subject 12 with the camera unit 21 .

[0031] The lighting unit 23 is configured to project illumination light for the camera unit 21 to the surface of the object to be inspected 12 for photographing. The lighting unit 23 includes one or more light sources that emit light of a wavelength or a wavelength range selected from a wavelength range that can be detected by the imaging element of the camera unit 21. The illumination light is not limited to visible light, and ultraviolet light, X-rays, etc. may also be used. When a plurality of light sources are provided, each light source is configured to project light of different wavelengths (for example, red, blue, and green) to the surface of the object to be inspected 12 at different projection angles.

[0032] In the inspection device 10 according to the present embodiment, the illumination unit 23 includes: an incident illumination source 23a that projects illumination light perpendicularly to the inspection surface of the inspection object 12 (i.e., the surface (XY plane) facing the camera unit 20); and a side illumination source (in the present embodiment, composed of an upper light source 23b, a middle light source 23c, and a lower light source 23d) that projects illumination light from an oblique direction to the inspection surface of the inspection object 12. In addition, a semi-transparent mirror 22 is arranged on the optical axis of the optical system of the camera unit 21, and a part of the illumination light radiated from the incident illumination source 23a is reflected by the semi-transparent mirror 22, passes through the optical axis, and is projected to the inspection object 12. Here, a half prism may be used instead of the semi-transparent mirror 22. In the inspection device 10 according to the present embodiment, the side illumination sources 23b, 23c, and 23d are respectively annular illumination sources, which are configured to surround the optical axis of the camera unit 21 and obliquely project illumination light onto the inspection surface of the inspection object 12. Each of these side illumination sources 23b, 23c, and 23d may be configured such that a plurality of light sources are arranged in an annular shape. In addition, the upper light source 23b, the middle light source 23c, and the lower light source 23d as the side illumination sources are respectively configured to project illumination light onto the inspection surface at different angles.

[0033] In addition, each of the upper light source 23b, the middle light source 23c, and the lower light source 23d as the side illumination source may be composed of one annular illumination source or may include a plurality of annular illumination sources. For example, the epi-illumination source 23a is installed on the side of the camera unit 21, the upper light source 23b of the side illumination source is composed of one annular illumination unit, and the middle light source 23c and the lower light source 23d can be composed of one integrated annular illumination unit. In addition, in the present embodiment, the epi-illumination source 23a is a red illumination source, the upper light source 23b and the lower light source 23d of the side illumination source are red illumination sources, and the middle light source 23c of the side illumination source is composed of a green illumination source, a blue illumination source, and a red illumination source.

[0034] As described above, in the description of this embodiment, the case where four light sources are used to irradiate illumination light to the inspection object 12 from different angles is described, but the type (number) of light sources is not limited to four, and only the incident illumination source 23a may be used, or a combination of any one of the side illumination sources 23b to 23d and the incident illumination source 23a may be used, or only the side illumination sources 23b to 23d or a plurality of them may be used. In addition, any one of the light sources 23a to 23d may be used, and in this case, a monochrome image generated by a monochrome light source may be obtained.

[0035] exist Figure 1In FIG. 1 , a light beam projected from the incident illumination source 23a and reflected on the inspection surface of the object 12 to be inspected and projected to the camera unit 21 is shown by a dotted arrow for reference. Here, the light reflected on the inspection surface of the object 12 is incident on the semi-transparent mirror 22, and a part of the light is incident on the camera unit 21 through the semi-transparent mirror 22. In addition, the projection from the side illumination sources 23b, 23c, 23d and the projection unit 24 is also shown by a dotted arrow. As an example, a light beam projected from the upper light source 23b and reflected on the inspection surface of the object 12 to be inspected and incident on the camera unit 21 is also shown. Here, for the sake of convenience of explanation, the surface of the object 12 to be inspected is shown as a plane, but in fact, it has an inclination and height depending on the part, like a general object to be inspected.

[0036] The projection unit 24 projects a pattern onto the inspection surface of the inspection object 12. The inspection object 12 on which the pattern is projected is photographed by the camera unit 21. In addition, in the illustrated embodiment, the projection unit 24 is provided between the upper light source 23b and the middle light source 23c, but the configuration of the projection unit 24 is not limited thereto, and for example, the projection unit 24 may be provided outside the lower light source 23d.

[0037] The inspection device 10 creates a height map of the inspection surface of the inspection object 12 based on the pattern image data of the inspection object 12 captured in a state where the pattern is projected from the projection unit 24. The control unit 30 detects the local inconsistency of the pattern image with respect to the projection pattern, and obtains the height of the portion based on the local inconsistency. That is, the change of the imaging pattern (the pattern projected onto the inspection object 12 and captured by the camera unit 21) with respect to the projection pattern (the pattern projected from the projection unit 24 to the inspection object 12) corresponds to the change in height on the inspection surface.

[0038] Here, the projection pattern is preferably a one-dimensional stripe pattern in which bright lines and dark lines are alternately and periodically repeated. The projection unit 24 is configured to project the stripe pattern onto the inspection surface of the inspection object 12 from an oblique direction. The discontinuity of the height of the inspection surface of the inspection object 12 appears as a shift of the pattern in the stripe pattern image. Therefore, the height difference can be calculated based on the shift of the pattern. In the inspection device 10 involved in the present embodiment, the control unit 30 creates a height map by using the PMP (Phase Measurement Profilometry) method of a stripe pattern whose brightness changes according to a sinusoidal curve. In the PMP method, the shift of the stripe pattern is equivalent to the phase difference of the sine curve.

[0039] The projection unit 24 is configured to include a pattern forming device, a light source for illuminating the pattern forming device, and an optical system for projecting a pattern onto the inspection surface of the inspection object 12. The pattern forming device can be, for example, a variable pattern forming device that can dynamically generate a desired pattern, such as a liquid crystal display, or a fixed pattern forming device that fixedly forms a pattern on a substrate such as a glass plate. In the case where the pattern forming device is a fixed pattern forming device, it is preferred to make the projection position of the pattern variable by providing a moving mechanism that moves the fixed pattern forming device, or by providing an adjustment mechanism in the optical system for pattern projection. In addition, the projection unit 24 can also be configured to be able to switch between a plurality of fixed pattern forming devices having different patterns.

[0040] A plurality of projection units 24 may be provided around the camera unit 21. The plurality of projection units 24 are arranged to project patterns from different projection directions onto the inspection object 12. This can reduce the area where the pattern cannot be projected due to shadows caused by height differences of the inspection surface.

[0041] Figure 1 The control unit 30 shown here uniformly controls the entire device, and is implemented as hardware by a CPU, memory, or other LSI of any computer, or as software by a program loaded into the memory, etc., and functional blocks implemented by their cooperation are drawn here. Therefore, it can be understood by those skilled in the art that these functional blocks can be implemented in various forms by hardware only, software only, or a combination of them.

[0042] exist Figure 1 , an example of the structure of the control unit 30 is shown in FIG. The control unit 30 is configured to include an inspection control unit 31 and a memory 35 as a storage unit. The inspection control unit 31 is configured to include a height measuring unit 32, an inspection data processing unit 33, and an inspection unit 34. In addition, the inspection device 10 includes an input unit 36 ​​for accepting input from a user or other devices, and an output unit 37 for outputting information related to the inspection, and the input unit 36 ​​and the output unit 37 are respectively connected to the control unit 30. The input unit 36 ​​includes, for example, an input component such as a mouse and a keyboard for accepting input from a user, and a communication component for communicating with other devices. The output unit 37 includes a well-known output component such as a display and a printer.

[0043] The inspection control unit 31 is configured to perform various control processes for inspection based on the input from the input unit 36 ​​and the inspection-related information stored in the memory 35. The inspection-related information includes the two-dimensional image data of the object to be inspected 12, the height map of the object to be inspected 12, and the substrate inspection data (inspection data). Before the inspection, the inspection data processing unit 33 uses the two-dimensional image data and the height map of the object to be inspected 12 to ensure that all inspection items are qualified to create the substrate inspection data. The inspection unit 34 performs the inspection based on the created substrate inspection data, and the two-dimensional image data and the height map of the object to be inspected 12 to be inspected.

[0044] Substrate inspection data is inspection data produced for each type of substrate. Substrate inspection data can be said to be a collection of inspection data for each component mounted on the substrate. The inspection data for each component includes the inspection items necessary for the component, the inspection area on the image related to each inspection item, i.e., the inspection window, and the inspection benchmark as a benchmark for determining whether each inspection item is good or not. One or more inspection windows are set for each inspection item. For example, in an inspection item for determining whether the welding of a component is good or not, the same number of inspection windows as the number of welding areas of the component are usually set in a configuration corresponding to the configuration of the welding area. In addition, for inspection items that use image data obtained by performing prescribed image processing on the image data of the inspected object, the content of the image processing is also included in the inspection data.

[0045] As the substrate inspection data production process, the inspection data processing unit 33 sets each item of the inspection data to match the substrate. For example, the inspection data processing unit 33 automatically sets the position and size of each inspection window for each inspection item to be suitable for the component layout of the substrate. The inspection data processing unit 33 may also accept user input for a part of the items in the inspection data. For example, the inspection data processing unit 33 may also accept adjustment of the inspection benchmark by the user. The inspection benchmark may also be set using height information.

[0046] The inspection control unit 31 performs video processing on the object to be inspected 12 as a preprocessing for the production of substrate inspection data. For the object to be inspected 12, an object to be inspected that has passed all inspection items is used. As described above, while the object to be inspected 12 is illuminated by the lighting unit 23, the relative movement of the video unit 20 and the inspection platform 14 is controlled, and local images of the object to be inspected 12 are sequentially captured to obtain local image data, thereby performing video processing. A plurality of local image data are captured in a manner covering the entirety of the object to be inspected 12. The inspection control unit 31 synthesizes these multiple local image data to generate substrate whole-surface image data including the entire inspection surface of the object to be inspected 12. The inspection control unit 31 stores the substrate whole-surface image data in the memory 35.

[0047] In addition, as a preprocessing for making a height map, the inspection control unit 31 projects a pattern onto the inspected object 12 through the projection unit 24 while controlling the relative movement of the camera unit 20 and the inspection platform 14, so as to divide the pattern image of the inspected object 12 and photograph it in sequence to obtain the divided image data when the pattern is projected. The projected pattern is preferably a stripe pattern whose brightness changes according to a sine curve based on the PMP method. The inspection control unit 31 synthesizes the divided image data obtained by photographing to generate image data of the entire inspection surface of the inspected object 12, that is, pattern image data. The inspection control unit 31 stores the pattern image data in the memory 35. In addition, the pattern image data can be generated for a part of the inspection surface instead of the entire surface.

[0048] The height measuring unit 32 creates a height map of the entire inspection surface of the inspected object 12 based on the camera pattern of the pattern image data. The height measuring unit 32 first obtains the local phase difference between the pattern image data and the reference pattern image data for the entire image, thereby obtaining a phase difference map of the inspection surface of the inspected object 12. The reference pattern image data is a pattern image projected by the projection unit 24 (that is, image data generated by a pattern forming device built into the projection unit 24). The height measuring unit 32 creates a height map of the inspected object 12 based on a reference plane serving as a reference for height measurement and a phase difference map. The reference plane is, for example, the substrate surface of an electronic circuit substrate to be inspected. The reference plane does not have to be a plane, but may be a curved surface reflecting deformations such as warping of the substrate. The reference plane may be pre-specified by user input, or the reference plane may be obtained for each substrate by, for example, a substrate surface height measurement method described later.

[0049] Specifically, the height measuring unit 32 uses each pixel of the camera pattern image data and the pixel of the reference pattern image data corresponding to the pixel to obtain the phase difference of the stripe pattern. The height measuring unit 32 converts the phase difference into height. The local stripe width near the pixel is used for conversion to height. This is to interpolate the situation where the stripe width on the camera pattern image data is different depending on the position. This is because, since the distance from the projection unit 24 is different depending on the position on the inspection surface, even if the stripe width of the reference pattern is constant, the stripe width will change linearly from one end to the other end of the pattern projection area of ​​the inspection surface. The height measuring unit 32 obtains the height from the reference plane based on the converted height and the reference plane, and creates a height map of the inspected object 12.

[0050] The inspection control unit 31 may also create object image data having a height distribution by associating the height information of the height map of the object 12 with each pixel of the two-dimensional image of the object 12. In addition, the inspection control unit 31 may also perform a three-dimensional modeling display of the object 12 based on the object image data having the height distribution. In addition, the inspection control unit 31 may also display the height distribution on the output unit 37 in a manner superimposed on the two-dimensional object image data. For example, the object image data may also be displayed in color by the height distribution. In addition, in the inspection device 10 involved in the present embodiment, the projection unit 24 and the height measurement processing of the object 12 performed by the projection unit 24 may not be installed.

[0051] Next, a method for processing image data obtained by photographing using the lighting unit 23 will be described. As described above, in the inspection device 10 according to the present embodiment, the light sources (the incident illumination source 23a, and the upper light source 23b, the middle light source 23c, and the lower light source 23d as the side illumination sources) constituting the lighting unit 23 are as follows: Figure 2 As shown in (a) of FIG. 1 , the illumination light from the incident illumination source 23a is projected along the optical axis L of the optical system of the camera unit 21, that is, substantially perpendicular to the reference surface, and the upper light source 23b, the middle light source 23c, and the lower light source 23d project illumination light at projection angles close to the horizontal direction in this order.

[0052] The intensity of the light projected from the light sources 23a to 23d of the lighting unit 23 and reflected from the object to be inspected 12, except for the light reflected from the object to be inspected 12 and directly incident on the camera unit 21, is ideally 0. That is, the angle (inclination) of the inspection surface of the object to be inspected 12 relative to the reference surface, the intensity of the reflected light from the light sources 23a to 23d of the lighting unit 23, which are reflected from the inspection surface and directly incident on the camera unit 21, becomes larger, and the intensity of the reflected light from the other light sources is 0. For example, a Figure 2In the case of the cross-section of the solder shown in (b), the intensity of the reflected light of the illumination light emitted by each light source 23a to 23d of the illumination unit 23 detected by the imaging element of the camera unit 21 varies according to the angle of the surface of the solder relative to the reference plane. In the present embodiment, the intensity of the reflected light of the light from the incident illumination source 23a increases in the case of an inclined surface of 0° to 15° relative to the reference plane, the intensity of the reflected light of the light from the upper light source 23b increases in the case of an inclined surface of 15° to 45° relative to the reference plane, the intensity of the reflected light of the light from the middle light source 23c increases in the case of an inclined surface of 45° to 65° relative to the reference plane, and the intensity of the reflected light of the light from the lower light source 23d increases in the case of an inclined surface of 65° to 85° relative to the reference plane. In addition, the relationship between the angles of each light source 23a to 23d of the illumination unit 23 and the inclined surface of the object to be inspected 12 is an example and is not limited to this structure.

[0053] As described above, the intensity of each pixel of the image data obtained by lighting each of the light sources 23a to 23d of the lighting unit 23 and photographing with the camera unit 21 increases when the angle matches the above-mentioned inclined surface, and becomes a value close to 0 when the angle does not match the above-mentioned inclined surface.

[0054] Therefore, the inspection device 10 involved in this embodiment is constructed as follows: based on the image data obtained by projecting illumination light from each light source 23a~23d of the lighting unit 23 and photographing it by the camera unit 21, an image of R (red) component, G (green) component, and B (blue) component is generated, and an RGB image (color image) is generated by synthesizing these three images, thereby representing the tilted state of the inspection surface of the inspected object 12.

[0055] like Figure 3 As shown in FIG. 1 , when a color is expressed by hue H, chroma S, and lightness V (when expressed by the HSV color system), hue H is expressed by the angle of a circle, and chroma S and lightness V are expressed by the magnitudes of mutually orthogonal directions. In addition, on this hue H, R (red), G (green), and B (blue) are located at positions 120° apart. Therefore, the image data obtained by using the reflected light generated by projecting the light from the upper light source 23b, that is, the image data obtained by detecting the reflected light from the inclined surface of 15° to 45° in this embodiment (in Figure 3 The image data obtained by detecting the reflected light from the inclined surface of 45° to 65° (referred to as "Top") is assigned to R (red), and the ... Figure 3The image data obtained by detecting the reflected light from the inspection surface at an angle of 65° to 85° (referred to as "Side" in FIG. 1 ) is assigned to G (green), and the image data obtained by detecting the reflected light generated by projecting the light from the lower light source 23d, i.e., the ... Figure 3 In the example, the image data (referred to as "Low") is assigned to B (blue), and thus, based on the RGB image data (color image data) obtained by synthesizing these image data, image data expressed in RGB corresponding to the tilt state can be obtained, so the tilt state of the inspection surface of the inspection object 12 can be grasped based on the color of the image data. In addition, as described above, by making the projection angle of the side illumination sources 23b~23d of the illumination unit 23 correspond to the hue H, the image data (in the middle color (purple) between R (red) and B (blue) obtained by detecting the reflected light from the tilted surface of 0°~15° smaller than 15°~45° expressed by R (red) can be displayed. Figure 3 Therefore, even when four or more light sources with different projection angles are used as the lighting unit 23, the tilt state of the inspection surface of the inspection object 12 can be clearly expressed using the RGB image data (color image data). That is, it is possible to determine the tilt state of the inspection surface of the inspection object 12 based on the RGB image (color image). Figure 2 (b) shows the state of the solder.

[0056] In addition, since the color of the illumination light emitted from each light source 23a to 23d of the illumination unit 23 and the color (RGB) of the image data obtained by capturing the reflected light of the light emitted from each of these light sources 23a to 23d do not need to be consistent (since the hue H represents the tilt state (angle) of the inspection surface of the inspection object 12), the imaging element of the camera unit 21 does not need to be a color (as long as it can detect the intensity of light). In addition, in the generation of RGB image data (color image data), the difference in intensity is expressed by chroma S or brightness V.

[0057] In addition, the light sources 23a to 23d may be turned on sequentially and the camera unit 21 may take an image of the object to be inspected 12, or the camera unit 21 may be composed of a camera capable of acquiring color image data, and the light sources 23a to 23d may be turned on simultaneously to take an image of the object to be inspected 12 at once. In this case, image data of the R (red) component, image data of the G (green) component, and image data of the B (blue) component may be acquired from one color image data.

[0058] Then, use Figure 4The image synthesis processing of the inspection control unit 31 of the control unit 30 is described. In addition, as described above, the inspection control unit 31 controls the XY table 16 to obtain image data of the inspection surface of the inspection object 12 when illuminated by the epi-illumination source 23a (hereinafter referred to as "Coaxis image"), image data when illuminated by the upper light source 23b (hereinafter referred to as "Top image"), image data when illuminated by the middle light source 23c (hereinafter referred to as "Side image"), and image data when illuminated by the lower light source 23d (hereinafter referred to as "Low image"), and store the intensity of each pixel in the memory 35. In the following description, the image data (object image data) obtained by photographing the inspection surface of the object 12 to be inspected is assumed to be composed of M×N pixels (M and N are positive integers), and the storage area of ​​the image data (Coaxis image) of the incident illumination source 23a corresponding to the pixel (i, j) is assumed to be Ac(i, j), the storage area of ​​the image data (Top image) of the upper light source 23b is assumed to be At(i, j), the storage area of ​​the image data (Side image) of the middle light source 23c is assumed to be As(i, j), and the storage area of ​​the image data (Low image) of the lower light source 23d is assumed to be Al(i, j). In addition, the storage area of ​​the image data of the R (red) component generated by the following processing is assumed to be Br(i, j), the storage area of ​​the image data of the G (green) component is assumed to be Bg(i, j), and the storage area of ​​the image data of the B (blue) component is assumed to be Bb(i, j). Here, i=0···M-1 and j=0···N-1.

[0059] When the inspection control unit 31 of the control unit 30 captures image data of the inspection surface of the inspection object 12 based on the various light sources 23a~23d of the lighting unit 23 through the above-mentioned processing, the storage areas Br(i, j), Bg(i, j), and Bb(i, j) of the image data of the RGB components are cleared (step S100). Then, the variable i for counting the pixels of the image data in the column direction is set to 0 (step S102), and the variable j for counting the pixels of the image data in the row direction is set to 0 (step S104). First, the intensity (Ac(i, j)) of the Coaxis image at the pixel (i, j) is compared with the intensity (At(i, j)) of the Top image (step S106). When the intensity of the Coaxis image is greater than the intensity of the Top image, the intensity value of the Coaxis image is stored as the value of the pixel (i, j) of the image data of the R component (the value of Ac(i, j) is set for Br(i, j)) (step S108). When the intensity of the Top image is less than the intensity of the Coaxis image, the intensity value of the Top image is stored as the value of the pixel (i, j) of the image data of the R component (the value of At(i, j) is set for Br(i, j)) (step S110).

[0060] Next, the intensity (Ac(i, j)) of the Coaxis image at pixel (i, j) is compared with the intensity (Al(i, j)) of the Low image (step S112). When the intensity of the Coaxis image is greater than the intensity of the Low image, the intensity value of the Coaxis image is stored as the value of the pixel (i, j) of the image data of the B component (the value of Ac(i, j) is set for Bb(i, j)) (step S114). When the intensity of the Low image is lower than the intensity of the Coaxis image, the intensity value of the Low image is stored as the value of the pixel (i, j) of the image data of the B component (the value of Al(i, j) is set for Bb(i, j)) (step S116).

[0061] Then, the intensity (As(i, j)) of the Side image at the pixel (i, j) is stored as the value of the pixel (i, j) of the G component image data (the value of As(i, j) is set for Bg(i, j)) (step S118).

[0062] Then, 1 is added to the variable j (step S120), and it is determined whether the value of the variable j is less than N (step S122). If it is less than N, the process returns to step S106 and the above process is repeated. In addition, if it is determined in step S122 that the value of the variable j is greater than N, 1 is added to the variable i (step S124), and it is determined whether the value of the variable i is less than M (step S126). If it is less than M, the process returns to step S104 and the above process is repeated.

[0063] Finally, using the R component image data Br(i, j), B component image data Bb(i, j), and G component image data Bg(i, j) (i=0...M-1, j=0...N-1) generated for all M×N pixels as described above, for each pixel (i, j), the value of the red component is determined according to the value of Br(i, j), the value of the blue component is determined according to the value of Bb(i, j), and the value of the green component is determined according to Bg(i, j), and the color image data (RGB image data) is synthesized and stored in the memory 35 (step S128).

[0064] Basically, unless the projection angles of the light sources 23a to 23d of the lighting unit 23 and the tilt state of the inspection surface of the object 12 are directly input to the camera unit 21, the intensity of the reflected light cannot be detected. However, there is a case where the light reflected on the inspection surface is reflected at other parts of the inspection surface of the object 12 (based on double reflections) and is incident on the camera unit 21 for detection. In addition, if the camera unit 21 is used Figure 3 As described, in the present embodiment, R (red) in the hue H of the finally generated RGB image data is assigned to Top (indicating an inclination of 15° to 45°), and B (blue) is assigned to Low (indicating an inclination of 65° to 85°). Therefore, at pixel (i, j), when the intensity (Ac(i, j)) of the Coaxis image is greater than the intensity (At(i, j)) of the Top image and the intensity (Al(i, j)) of the Low image, by setting the intensity of the Coaxis image to the values ​​(Br(i, j) and Bb(i, j)) of the R image data and the B image data at the pixel (i, j), it is possible to determine that the light is the angle of incidence of the reflected light from the incident illumination source 23a to the camera unit 21 (in a state of inclination of 0° to 15°), and the hue H can be expressed as purple. In addition, the structure is as follows: when the intensity of the Top image is greater than the intensity of the Coaxis image, it can be determined that the inspection surface corresponding to the pixel is the angle at which the reflected light from the upper light source 23b directly enters the camera unit 21 (it is an inclined state of 15° to 45°), and the hue H is displayed as red; when the intensity of the Low image is greater than the intensity of the Coaxis image, it can be determined that the inspection surface corresponding to the pixel is the angle at which the reflected light from the lower light source 23d directly enters the camera unit 21 (it is an inclined state of 65° to 85°), and the hue H is displayed as blue.

[0065] Furthermore, if the hue H of the Coaxis is assigned to yellow, for example, the angle of the inspection surface is yellow when the angle is in the tilt state near the boundary between the tilt state corresponding to Side (45° to 65°) and the tilt state corresponding to Low (65° to 85°), so the tilt state cannot be determined. However, by setting the hue H corresponding to the Coaxis to purple, which is between R (red) and B (blue) with the farthest tilt angle range, the tilt state can be clearly determined. Similarly, by setting it to purple, the influence caused by secondary reflection can also be eliminated.

[0066] As described above, by making the inclination state (angle) of the inspection surface of the inspection object 12 and the angle of the hue H in the HSV color system (refer to Figure 3 ) is represented as RGB image data accordingly, so that the change in the angle of the hue H (i.e., the change in color) corresponds to the change in the angle of the inspection surface (for example, if the angle of the inspection surface changes from 0°→30°→55°→75°, the color of the pixel at the corresponding part of the RGB image changes from purple→red→green→blue), so the inclination state of the inspection surface can be understood sensorily. In addition, in the above description, the case where the Top, Side, and Low states are assigned to R (red), G (green), and B (blue), respectively (as a result, the Coaxis state is purple), but for example, in the case where the Top state is assigned to yellow, Figure 3 In the example, the problem is dealt with by allocating colors whose hue H is shifted 120° from yellow to the Side state and the Low state, and setting the state of the Coaxis to the hue H between the Top state and the Low state.

[0067] In addition, by using the RGB image data as described above, when the tilt state of the inspection surface of the inspection object 12 changes smoothly, it changes according to the angle of the hue H as described above, so when the change of the hue H is discontinuous or changes sharply, the possibility of abnormality of the inspection surface (abnormality of the height of the inspection surface) can be expressed. In addition, by estimating the tilt state (angle) of the inspection surface based on the change of the hue H in the RGB image data, it can also be handled as a material for measuring the height of the inspection surface.

[0068] In addition, the inspection object based on such RGB image data is not limited to the above-mentioned solder surface, and can also be applied to the shape of the tip of an IC lead or the shape of a chip electrode.

[0069] Next, when the object to be inspected 12 is an electronic circuit board or the like, types of solder used to mount electronic components on the electronic circuit board and a method of classifying the same will be described.

[0070] Conventional solder is an alloy with lead and tin as main components. When the heated and melted solder solidifies, a fine layered eutectic structure of lead and tin is formed, and the surface is flat and the concavoconvexity becomes smaller. On the other hand, in order to reduce the content of lead, in the case of the so-called "lead-free solder" in which silver, copper and other metals are mixed instead of lead, primary crystals of coarse dendrites (dendrites) appear first during solidification, and a eutectic structure is formed in the gaps between them. Therefore, many concavoconvexities of the order of tens of micrometers (μm) are formed on the surface of the solidified solder, but their shape, size and number vary depending on the metals mixed in the solder and their ratio. According to the above, the type of solder used can be classified according to the shape, size and number of concavoconvexities when the shape of the solidified structure appearing on the solder surface (the shape (texture) of the surface of the solder after solidification) is smooth, rough, and rough.

[0071] In the inspection device of this embodiment, as described above, by irradiating the surface of the inspected object 12 with illumination light radiated from different angles, RGB image data (color image data) expressing the angle of the inspection surface by the difference in color information can be obtained, and therefore, the type of solder used can be classified based on the image data of the surface of the solder obtained using the RGB image data. Next, the classification method of the type of solder is described.

[0072] First, use Figure 5 To illustrate the method of classifying the types of solder. When the solder type classification process starts, the control unit 30 reads out the RGB image data containing the solder part from the memory 35 (step S200). As described above, the substrate inspection data contains information about the inspection area, i.e., the inspection window, on the image related to each inspection item, and the position of the solder part on the inspected object 12 can be determined based on the information. Alternatively, the position of the solder can also be determined based on the design data of the inspected object 12. In addition, the control unit 30 performs HSV conversion on the read RGB image data to obtain the values ​​of the three axes of H (chroma), S (saturation) and V (brightness) (step S202).

[0073] As described above, the chromaticity information represents the amount of inclination of the solder portion, which reflects the macroscopic concave-convex surface shape of the solder portion. Therefore, the control unit 30 uses the values ​​of the three axes obtained from the RGB image data to label the distribution of the chromaticity, thereby obtaining the characteristic quantity of granularity (the size, shape, number, etc. of the concave-convex (particles)) (step S204). In addition, the chromaticity information is a continuous quantity corresponding to the diffuse reflectivity of the surface of the solder portion, reflecting the microscopic surface roughness of the solder portion. Specifically, the chromaticity is close to 0 when there is more diffuse reflection, and the chromaticity is 100% when there is more total reflection and specular reflection, reflecting the microscopic surface roughness. Therefore, the control unit 30 uses the values ​​of the three axes obtained from the RGB image data to obtain the characteristic quantity of surface smoothness (smooth or rough) according to the chromaticity (step S206).

[0074] Finally, the control unit 30 compares the feature quantities obtained in steps S204 and S206 with, for example, Figure 6 The solder type is classified by comparing with the characteristic diagram shown in the figure (step S208), and the solder type classification process is ended. Figure 6 , the classification of solder types according to the number of particles, particle size, and surface smoothness is shown as feature quantities.

[0075] As a method for classifying the types of solder, an algorithm for inspecting specific areas within an image, namely contour matching, can be used. The contour matching is a method of inspecting by surrounding the contours of continuous pixels (areas) that meet the conditions and measuring their number, area, and contour length. In the case of binarizing the image to obtain the area of ​​the concave and convex, the object pixels are the same value regardless of whether they are scattered or concentrated. In contrast, the contour matching can capture the area as a pixel block, so the shape (texture) of the solder surface can be accurately expressed. As described above, in the solder type classification process involved in the present embodiment, the RGB image data is used after being converted to HSV, so the accuracy of the above-mentioned feature quantity can be improved. In addition, the original RGB image data that has not been converted to HSV can also be used to classify the solder.

[0076] When the concavity and convexity of the solidified tissue is finer than the resolution of the camera unit 21 and is in a state similar to the surface of pear skin, diffuse reflected light is captured. In this case, the RGB value corresponding to the lighting angle cannot be clearly known as in the case of mirror reflection, and an image in which various lightings are mixed is captured. In this case, it is difficult to extract the granular contour itself, but it is possible to obtain a feature that the concavity and convexity are finer than the resolution of the camera unit 21.

[0077] Alternatively, as a method for classifying the types of solder, classification can be performed through machine learning such as deep learning. Specifically, the RGB image data obtained by HSV conversion of each type of solder in a pre-selected image area is learned to create an AI model, so that during inspection, the types of solder can be classified based on the image data of the solder part (image data obtained by HSV conversion of the RGB image data) based on the AI ​​model. By using the AI ​​model, there is no need to adjust parameters for classification processing. In addition, classification can also be performed using the original RGB image data that has not been HSV converted.

[0078] In addition, regarding the classification of the type of solder used in the inspected object 12, not only one solder part is used for judgment, but the above-mentioned classification processing can also be performed on multiple solder parts of the inspected object 12, and the most classified type of solder can be classified as the type of solder used in the inspected object 12.

[0079] Furthermore, when obtaining RGB image data that has been HSV converted from image data obtained by irradiating the object to be inspected 12 with illumination light from different angles (specifically, image data obtained by making the colors correspond to the angles of the solder portions), in the classification of the types of solder, it is desirable to configure the camera unit 21 so that the optical axis of the lens of the camera unit 21 is as close to perpendicular as possible to the solder surface. Therefore, it is also possible to configure, in addition to the above-mentioned camera unit 21 (which will be referred to as the "main camera"), a sub-camera that photographs the object to be inspected 12 from an angle different from that of the main camera, and to use the main camera and the sub-camera to respectively obtain RGB image data corresponding to the angles of the solder portions. The sub-camera can be configured, for example, at Figure 1 When generating the RGB image data converted by the HSV conversion based on the image data obtained by the sub-camera, it is desirable to have the same relationship between the color and the angle of the solder part as that of the RGB image data obtained by the main camera. That is, it is desirable that both the RGB image data obtained by the main camera and the RGB image data obtained by the sub-camera have the same color when the angle of the solder part is the same.

[0080] In this way, when the RGB image data is acquired using the main camera and the sub-camera, the main camera may capture an image of solder without components mounted thereon, and the sub-camera may capture an image of qualified solder at an angle.

[0081] In the inspection device 10 according to the present embodiment, a certain degree of field of view is required to inspect the state of welding and the installation state of components, so the resolution of the camera unit 21 becomes low. However, as described above, the inspection object 12 is irradiated with illumination light from different angles to obtain image data, and RGB image data corresponding to the color and the angle of the solder part is generated based on these image data and used for classification of the types of solder. Thus, even if the resolution of the camera unit 21 is low, the types of solder can be classified with high accuracy. In other words, in the classification method of the types of solder, it is not necessary to capture the shape of the solidified structure in detail, as long as the camera unit 21 has the resolution required to capture a certain degree of global features. For example, in order to capture a 20μm structure, a resolution of 1 / 10, that is, 2μm, is generally required, but according to the method of the present application, a resolution of 5μm to 30μm that can be captured globally is sufficient. In addition, by expanding the field of view of the camera unit 21, the inspection speed of the inspection object 12 can be increased.

[0082] Next, the process of inspecting the solder portion of the inspected object 12 performed in the inspection device 10 according to the present embodiment will be described. In addition, the inspection of the inspected object 12 in the inspection device 10 is not only performed on the solder portion, but also on whether the mounting state of the electronic components is good or not. However, in the following description, only the inspection of the solder portion will be described.

[0083] - First inspection method -

[0084] First, use Figure 7 The first inspection method of solder is described. When the inspection starts, the control unit 30 of the inspection device 10 moves the inspection object 12 delivered from the upstream process of the inspection device 10 into the inspection area (step S300). In addition, the control unit 30 moves the camera unit 20 by the XY table 16 to capture the identification mark on the inspection object 12 (step S301). The identification mark can be used to accurately grasp the position of the substrate, so that the position of the solder can be accurately determined in subsequent processing.

[0085] Next, the control unit 30 moves the imaging unit 20 by the XY stage 16 to capture the solder portion to be used for classifying the type of solder on the inspection object 12 (step S302). As described above, the position of the solder can be determined based on the design data of the inspection object 12 and the substrate inspection data, and the image of the solder portion can be efficiently acquired based on this information.

[0086] When the image data of the solder part is obtained in step S302, the control unit 30 uses the image data to perform the above-mentioned solder type classification process, and classifies the type of solder used by the inspected object 12 currently being inspected (step S303). The control unit 30 compares the type of solder classified in step S303 with the type of solder specified by the design data and the substrate inspection data (step S304). Then, when the control unit 30 determines that the type of solder used is correct (the same as the type of solder specified by the design data and the substrate inspection data) (step S304: "Yes"), the control unit 30 photographs other areas on the inspected object 12 (step S305), and inspects the welding state in each area (step S306). When the inspection of all solder parts is completed, the inspected object 12 is moved out to the next process (step S307), and returns to step S300 to inspect the next inspected object 12.

[0087] On the other hand, when the control unit 30 determines in step S304 that the type of solder used is wrong (different from the type of solder specified by the design data or the substrate inspection data) (step S304: "No"), the control unit 30 outputs a warning (step S308) using the output unit 37, etc., and temporarily terminates the inspection process. When the warning is output, the operator or the like takes out the object to be inspected 12 from the inspection device 10 and confirms the type of solder, etc.

[0088] In this way, according to the first inspection method, the type of solder used in the inspected object 12 can be classified based on the image of the solder part, and a warning can be issued when the type of solder is different from that specified by the design data and substrate inspection data, thereby managing the type of solder used in the inspected object 12.

[0089] - Second inspection method -

[0090] Next, use Figure 8 The second inspection method for solder is described below. The second inspection method is a method of classifying the types of solder, reading inspection parameters set according to the types of solder used, switching substrate inspection data based on the inspection parameters, and inspecting the soldered state.

[0091] When the inspection starts, the control unit 30 moves the inspection object 12 delivered from the upstream process of the inspection device 10 into the inspection area (step S320). In addition, the control unit 30 moves the imaging unit 20 by the XY stage 16 to capture the identification mark on the inspection object 12 (step S321). The identification mark can be used to accurately grasp the position of the substrate, so that the position of the solder can be accurately determined in subsequent processing.

[0092] Next, the control unit 30 moves the imaging unit 20 by the XY stage 16 to capture the solder portion used in the classification of the type of solder on the inspection object 12 (step S322). As in the first inspection method, the position of the solder can be determined based on the design data of the inspection object 12 and the substrate inspection data, and the image of the solder portion can be efficiently acquired based on this information.

[0093] When the image data of the solder portion is acquired in step S322, the control unit 30 uses the image data to perform the above-mentioned solder type classification process, and classifies the type of solder used in the inspected object 12 currently being inspected (step S323). Then, the control unit 30 reads the inspection parameters corresponding to the type of solder according to the type of solder obtained by classification (step S324). Here, the case of using either solder A or B is specifically described (the type of solder is not limited to two). When the control unit 30 determines that the type of solder is "A" (step S324: "Type A"), the inspection parameters for solder type A are read from the memory 35, etc. (step S325). In addition, when the control unit 30 determines that the type of solder is "B" (step S324: "Type B"), the inspection parameters for solder type B are read from the memory 35, etc. (step S326).

[0094] When the control unit 30 reads the inspection parameters, it photographs other areas on the inspected object 12 (step S327), and uses the inspection parameters read in the above step S325 or step S326 to inspect the welding status in each area (step S328). When the inspection of all solder parts is completed, the inspected object 12 is moved to the next process (step S329), and returns to step S320 to inspect the next inspected object 12.

[0095] In this way, according to the second inspection method, the type of solder used for the inspected object 12 can be classified according to the image of the solder part, the inspection parameters of the welding state can be read according to the classified type of solder, and the substrate inspection data can be switched using the inspection parameters, so that appropriate inspection can be performed according to the type of solder used.

[0096] - The third inspection method -

[0097] Next, use Fig. 9 The third inspection method of solder is described below. The third inspection method is a method of classifying the types of solder and generating substrate inspection data according to the type of solder used to perform inspection.

[0098] When the inspection starts, the control unit 30 reads the design data of the object to be inspected 12 to be inspected later from the memory 35 (step S340). In addition, the control unit 30 moves the object to be inspected 12 delivered from the upstream process of the inspection device 10 into the inspection area (step S341). In addition, the control unit 30 moves the camera unit 20 by the XY table 16 to capture the identification mark on the object to be inspected 12 (step S342). The position of the substrate can be accurately grasped by using the identification mark, so that the position of the solder can be accurately determined in the subsequent processing.

[0099] Next, the control unit 30 moves the imaging unit 20 by the XY stage 16 to capture the solder portion to be used in classifying the type of solder on the inspection object 12 (step S343). As in the first inspection method and the second inspection method, the position of the solder can be determined based on the design data of the inspection object 12 and the substrate inspection data, and the image of the solder portion can be efficiently acquired based on this information.

[0100] When the image data of the solder part is acquired in step S343, the control unit 30 uses the image data to perform the above-mentioned solder type classification process, and classifies the type of solder used in the inspected object 12 currently being inspected (step S344). Then, the control unit 30 reads the inspection library corresponding to the type of solder according to the type of solder obtained by classification (step S345). Here, the case of using either solder A or B is specifically described (the type of solder is not limited to two). When the control unit 30 determines that the type of solder is "A" (step S345: "Type A"), the inspection library for solder type A is read from the memory 35, etc. (step S346). In addition, when the control unit 30 determines that the type of solder is "B" (step S345: "Type B"), the inspection library for solder type B is read from the memory 35, etc. (step S347).

[0101] When the control unit 30 reads the inspection library, it photographs other areas on the object to be inspected 12 (step S348), and uses the design data read in the above step S340 and the inspection library read in step S346 or step S347 to expand the inspection library for each mounting component based on the design data (step S349). Then, the control unit 30 uses the expanded inspection library to inspect the soldering state in each area (step S350), and when the inspection of all solder parts is completed, the object to be inspected 12 is moved to the next process (step S351), and the process returns to step S340 to inspect the next object to be inspected 12.

[0102] As described above, according to the third inspection method, the type of solder used in the inspected object 12 can be classified based on the image of the solder portion, and an inspection library can be developed based on the classified type of solder, and the soldering state and the mounting state of the electronic components can be inspected based on the inspection library. Therefore, inspection data can be generated based on the type of solder used in the inspected object 12, so that appropriate inspection can be performed based on the type of solder used.

[0103] - The fourth inspection method -

[0104] Next, use Fig.10 The fourth inspection method for solder is described below. In the third inspection method, the inspection library is developed according to the type of solder used, but the fourth inspection method is combined with the first inspection method to interrupt the inspection process when the solder is classified as a type not planned to be used.

[0105] When the inspection starts, the control unit 30 reads the design data of the object to be inspected 12 to be inspected later from the memory 35 (step S360). In addition, the control unit 30 moves the object to be inspected 12 delivered from the upstream process of the inspection device 10 into the inspection area (step S361). Then, the control unit 30 moves the camera unit 20 by the XY table 16 to capture the identification mark on the object to be inspected 12 (step S362). The identification mark can be used to accurately grasp the position of the substrate, so that the position of the solder can be accurately determined in the subsequent processing.

[0106] Next, the control unit 30 moves the imaging unit 20 by the XY stage 16 to capture an image of a solder portion to be used in classifying the type of solder on the inspection object 12 (step S363). As described in the first inspection method, the position of the solder can be determined based on the design data of the inspection object 12 and the substrate inspection data, and an image of the solder portion can be efficiently acquired based on this information.

[0107] When the image data of the solder part is obtained in step S363, the control unit 30 uses the image data to perform the above-mentioned solder type classification processing, and classifies the type of solder used by the inspected object 12 currently being inspected (step S364). In addition, the control unit 30 determines whether the type of solder classified in step S364 is a known type of solder (the type of solder that may be set in the design data or substrate inspection data) (step S365). Specifically, when the control unit 30 determines that the type of solder used is known (step S365: "Yes"), the control unit 30 reads the inspection library corresponding to the type of solder classified from the memory 35 (step S366), photographs other areas on the inspected object 12 (step S367), and uses the design data read in step S360 and the inspection library read in step S366 to expand the inspection library for each mounting component based on the design data (step S368). Then, the control unit 30 inspects the welding status in each area based on the expanded inspection library (step S369). When the inspection of all solder parts is completed, the inspected object 12 is moved to the next process (step S370), and returns to step S360 to inspect the next inspected object 12.

[0108] On the other hand, when the control unit 30 determines that the type of solder used is unknown in step S365 (step S365: No), the control unit 30 outputs a warning (step S371) using the output unit 37, etc., and temporarily terminates the inspection process. When the warning is output, the operator or the like takes out the object to be inspected 12 from the inspection device 10 and confirms the type of solder, etc.

[0109] As described above, according to the fourth inspection method, the type of solder used in the inspected object 12 can be classified based on the image of the solder portion, and a warning can be issued when the solder is not of a known type, so that the type of solder used in the inspected object 12 can be managed. In addition, since the inspection library can be set according to the type of solder, appropriate inspection can be performed according to the type of solder used.

[0110] -Fifth inspection method-

[0111] Finally, use Fig.11 The fifth inspection method for solder is described. In the second inspection method, inspection parameters are read in according to the type of solder used, and the substrate data is switched based on the parameters to inspect the soldering state, but the fifth inspection method is combined with the first inspection method and is configured to interrupt the inspection process when the type of solder is classified as not planned to be used.

[0112] When the inspection starts, the control unit 30 moves the inspection object 12 delivered from the upstream process of the inspection device 10 into the inspection area (step S380). In addition, the control unit 30 moves the imaging unit 20 by the XY stage 16 to capture the identification mark on the inspection object 12 (step S381). The identification mark can be used to accurately grasp the position of the substrate, so that the position of the solder can be accurately determined in subsequent processing.

[0113] Next, the control unit 30 moves the imaging unit 20 by the XY stage 16 to capture a solder portion to be used in classifying the type of solder on the inspection object 12 (step S382). As in the first inspection method, the position of the solder can be determined based on the design data of the inspection object 12 and the substrate inspection data, and an image of the solder portion can be efficiently acquired based on this information.

[0114] When the image data of the solder portion is acquired in step S382, the control unit 30 uses the image data to perform the above-mentioned solder type classification process to classify the type of solder used by the inspected object 12 currently being inspected (step S383). When the type of solder is classified, the control unit 30 determines whether the type of solder classified in step S383 is a known type of solder (the type of solder that may be set in the design data or substrate inspection data) (step S384). Specifically, when the control unit 30 determines that the type of solder used is known (step S384: "Yes"), the control unit 30 reads the inspection parameter corresponding to the type of solder according to the type of solder classified (step S385). Here, the case of using either of the two types of solder A and B is specifically described (the type of solder is not limited to two). When the control unit 30 determines that the type of solder is "A" (step S385: "Type A"), the inspection parameter for solder type A is read from the memory 35 or the like (step S386). When the control unit 30 determines that the type of solder is "B" (step S385: "Type B"), the control unit 30 reads the inspection parameters for solder type B from the memory 35 or the like (step S387).

[0115] When the control unit 30 reads the inspection parameters, it photographs other areas on the inspected object 12 (step S388), and uses the inspection parameters read in the above-mentioned step S386 or step S387 to inspect the welding status in each area (step S389). When the inspection of all solder parts is completed, the inspected object 12 is moved to the next process (step S390), and the process returns to step S380 to inspect the next inspected object 12.

[0116] On the other hand, when the control unit 30 determines that the type of solder used is unknown in step S384 (step S384: No), the control unit 30 outputs a warning (step S391) using the output unit 37, etc., and temporarily ends the inspection process. When the warning is output, the operator or the like takes out the object to be inspected 12 from the inspection device 10 to confirm the type of solder, etc.

[0117] As described above, according to the fifth inspection method, the type of solder used in the inspected object 12 can be classified based on the image of the solder portion, and a warning can be issued when the solder is not of a known type, so that the type of solder used in the inspected object 12 can be managed. In addition, the inspection parameter of the soldering state can be read according to the type of solder classified, and the substrate inspection data can be switched using the inspection parameter, so that appropriate inspection can be performed according to the type of solder used.

[0118] Description of Reference Numerals

[0119] 10: Inspection device; 12: Inspection object; 20: Imaging unit (imaging section); 21: Camera unit; 23: Illumination unit (light source); 30: Control unit (control section).

Claims

1. An inspection device comprising: an imaging unit that images an image of the subject; and Control Department, in, The control unit performs the following processing: The imaging unit captures the solder portion on the object to be inspected to obtain image data; extracting a feature quantity of a shape of a solidified structure appearing on a surface of the solder portion from the image data; as well as The solder used in the solder portion is classified based on the characteristic amount.

2. The inspection device according to claim 1, wherein: The inspection device includes a light source for irradiating illumination light to the inspection object. The control unit performs the following processing: acquiring image data of the solder portion; generating RGB image data by associating the angle of the solder portion with color information based on the image data; as well as Solder used in the solder portion is classified based on the RGB image data.

3. The inspection device according to claim 2, wherein: The inspection device includes a plurality of light sources that irradiate the illumination light from different angles.

4. The inspection device according to claim 3, wherein: The color information corresponds to a color in the HSV color system.

5. The inspection device according to any one of claims 1 to 4, wherein: The control section determines a position on the inspection object of a solder portion for acquiring image data for classifying the solder, based on design data or inspection data of the inspection object.

6. The inspection device according to any one of claims 1 to 4, wherein: The control unit inspects the inspection object based on the classified solder.

7. The inspection device according to any one of claims 1 to 4, wherein: The control unit selects inspection data according to the classified solder, and inspects the inspection object based on the selected inspection data.

8. The inspection device according to any one of claims 1 to 4, wherein: The control unit generates inspection data based on the classified solder, and inspects the inspection object based on the generated inspection data.

9. The inspection device according to any one of claims 1 to 4, wherein: The characteristic amount is the size or number of irregularities on the surface of the solder portion.

10. The inspection device according to any one of claims 1 to 4, wherein: The control unit classifies the solder according to the feature amount and the solder based on an AI model generated by machine learning.

11. The inspection device according to any one of claims 1 to 4, wherein: The imaging unit includes a plurality of camera units having different imaging angles relative to the subject. The control unit classifies the solder using each image data of the inspection object captured by the plurality of camera units.

12. The inspection device according to any one of claims 1 to 4, wherein: The control unit acquires image data of a plurality of solder portions, and classifies solder of the solder portion corresponding to the image data according to each image data. The control unit classifies the largest amount of solder among the classified solders as solder used for the inspection object.

13. The inspection device according to any one of claims 1 to 4, wherein: The control unit inspects the soldering state of the solder portion on the inspection object in addition to classifying the solder.

14. The inspection device according to any one of claims 1 to 4, wherein: The control unit stops the inspection based on the classified solder.

Images