Inspection system, inspection method, manufacturing method using inspection method, and inspection program

Abstract

The objective of the present invention is to improve the reliability of a detection result of abnormality detection. An inspection system (60) for a molded object formed by laminating a material on a substrate comprises: an acquisition unit (61) for acquiring a preceding image, which is an image of a preceding layer including at least one layer and formed precedingly among a plurality of laminated layers, and a succeeding image, which is an image of a succeeding layer including at least one layer and formed after the preceding layer; a calculation unit (62) for calculating a preceding luminance parameter relating to the luminance of the preceding image and a succeeding luminance parameter relating to the luminance of the succeeding image, and calculating a luminance change parameter relating to luminance change using the preceding luminance parameter and the succeeding luminance parameter; and a determination unit (63) for comparing the luminance change parameter with a predetermined threshold to determine whether or not the environment for molding the molded object is normal.

Description

Inspection system, inspection method, manufacturing method using the inspection method, and inspection program

[0001] The present disclosure relates to an inspection system, an inspection method, a manufacturing method using the inspection method, and an inspection program.

[0002] Additive manufacturing (AM) products are manufactured by laminating materials, and non-destructive testing such as X-ray testing is sometimes used to ensure the quality of AM products.

[0003] In particular, in powder bed fusion (PBF), inspections are sometimes performed during fabrication by checking the state of powder placement (see, for example, Patent Document 1). Layer fabrication is performed by laying powdered metal material on a bed such as a base plate, irradiating the metal material with a laser, and repeatedly melting and solidifying the material. During this process, heat generated by the laser irradiation generates metal vapor (fumes), which is part of the metal material laid on the bed.

[0004] Japanese Patent Application Laid-Open No. 2022-179347

[0005] Non-destructive testing, such as X-ray testing, used for quality assurance of AM products is expensive. Therefore, alternative, low-cost quality assurance methods are desired. Also, in the fabrication of AM products, there is a quality assurance method (see Patent Document 1) that checks for abnormalities in powder application using images that record the state of the applied powder and the state of laser irradiation, but this method does not sufficiently guarantee the quality of the fabricated product.

[0006] The present disclosure has been made in consideration of the above circumstances, and aims to provide an inspection system, an inspection method, a manufacturing method using the inspection method, and an inspection program that can improve the reliability of the detection results of abnormality detection.

[0007] An inspection system according to one aspect of some embodiments of the present disclosure is an inspection system for an object formed by stacking materials on a substrate, and includes: an acquisition unit that acquires a leading image, which is an image of a leading layer consisting of at least one layer formed earlier among the multiple stacked layers, and a trailing image, which is an image of a trailing layer consisting of at least one layer formed later than the leading layer; a calculation unit that calculates a leading brightness parameter related to the brightness of the leading image and a trailing brightness parameter related to the brightness of the trailing image, respectively, and calculates a brightness change parameter related to a brightness change using the leading brightness parameter and the trailing brightness parameter; and a determination unit that determines whether the environment in which the object is formed is normal by comparing the brightness change parameter with a predetermined threshold.

[0008] An inspection method according to one aspect of some embodiments of the present disclosure is a method for inspecting a shaped object formed by stacking materials on a substrate, and includes an acquisition step of acquiring a leading image, which is an image of a leading layer consisting of at least one layer formed earlier among a plurality of stacked layers, and a trailing image, which is an image of a trailing layer consisting of at least one layer formed later than the leading layer; a calculation step of calculating a leading brightness parameter, which is a parameter related to the brightness of the leading image, and a trailing brightness parameter, which is a parameter related to the brightness of the trailing image, and calculating a brightness change parameter using the leading brightness parameter and the trailing brightness parameter; and a determination step of determining whether an environment in which the shaped object is to be formed is normal by comparing the brightness change parameter with a predetermined threshold value.

[0009] A manufacturing method according to one aspect of some embodiments of the present disclosure includes a powder layer formation process in which a powder of the material is laid in the molding area of ​​the object to form a powder layer, a molding layer formation process in which a laser is irradiated onto the powder layer to melt and solidify the material to form a molding layer, and an inspection process in which the molding layer is inspected using the above-described inspection method.

[0010] An inspection program according to one aspect of some embodiments of the present disclosure is an inspection program for an object formed by stacking materials on a substrate, and causes a computer to execute an acquisition process for acquiring a leading image, which is an image of a leading layer consisting of at least one layer formed earlier among a plurality of stacked layers, and a trailing image, which is an image of a trailing layer consisting of at least one layer formed later than the leading layer; a calculation process for calculating a leading brightness parameter, which is a parameter related to the brightness of the leading image, and a trailing brightness parameter, which is a parameter related to the brightness of the trailing image, and calculating a brightness change parameter using the leading brightness parameter and the trailing brightness parameter; and a determination process for determining whether the environment in which the object is formed is normal by comparing the brightness change parameter with a predetermined threshold value.

[0011] According to the present disclosure, it is possible to achieve an effect of improving the reliability of the detection result of anomaly detection.

[0012] FIG. 1 is a diagram illustrating a schematic configuration of a modeling apparatus according to an embodiment of the present disclosure; FIG. 2 is a diagram illustrating an example of a modeling unit during formation of a modeling layer according to an embodiment of the present disclosure; FIG. 3 is a diagram illustrating an example of a hardware configuration of an inspection system according to an embodiment of the present disclosure; FIG. 4 is a functional block diagram illustrating functions of an inspection system according to an embodiment of the present disclosure; FIG. 5 is a diagram illustrating an example of an image of a first layer (initial layer) acquired by an acquisition unit according to an embodiment of the present disclosure; FIG. 6 is a diagram illustrating an example of an image of a second layer acquired by an acquisition unit according to an embodiment of the present disclosure; FIG. 7 is a diagram illustrating an example of an image of a fifth layer acquired by an acquisition unit according to an embodiment of the present disclosure; FIG. 8 is a diagram illustrating an example of an image of a final layer acquired by an acquisition unit according to an embodiment of the present disclosure; FIG. 9 is a diagram illustrating an example of image processing according to an embodiment of the present disclosure; FIG. 10 is a diagram illustrating an example of an abnormality that could become a defective portion according to an embodiment of the present disclosure, showing an example of an image in which an abnormality due to recoater interference appears as a defective portion; FIG. 11 is a diagram illustrating an example of an abnormality that could become a defective portion according to an embodiment of the present disclosure, showing an example of an image in which an abnormality due to powder fall appears as a defective portion; FIG. 12 is a diagram illustrating an example of an abnormality that could become a defective portion according to an embodiment of the present disclosure, showing an example of an image in which an abnormality due to powder short appears as a defective portion. FIG. 1 is a diagram showing an image of an example of an abnormality that becomes a defective portion according to an embodiment of the present disclosure, and is a diagram showing an example of an image in which an abnormality of a powder depression appears as a defective portion. FIG. 2 is a flowchart showing an example of a procedure for an abnormality determination process in a molding environment according to an embodiment of the present disclosure. FIG. 3 is a flowchart showing an example of a procedure for a defect determination process including an abnormality determination process according to an embodiment of the present disclosure. FIG. 4 is a flowchart showing an example of a procedure for a defect determination process including an abnormality determination process according to an embodiment of the present disclosure.

[0013] Hereinafter, an embodiment of an inspection system, an inspection method, a manufacturing method using the inspection method, and an inspection program according to the present disclosure will be described with reference to the drawings.

[0014] FIG. 1 is a diagram illustrating a schematic configuration of a molding apparatus 10 according to an embodiment of the present disclosure. A surface plate 22 and columns 26 are fixed to a base 21. The base 21 is installed so that its upper surface is horizontal. The upper surface of the surface plate 22 is also horizontal. The upper surface of the surface plate 22 serves as a stage, on which powder material is spread to form a molding layer. A flange-like convex portion 22a is formed around the entire periphery of the upper surface of the surface plate 22. The outer peripheral surface of the convex portion 22a contacts the inner surface of the molding tank 23, allowing the powder to be held in the space surrounded by the upper surface of the surface plate 22 and the inner surface of the molding tank 23. The powder material is, for example, a metal material or a ceramic material. In other words, the molding apparatus 10 forms a molded object by Powder Bed Fusion (PBF).

[0015] Powder is laid on the forming section 35 of the forming tank 23 to form a powder layer. Then, a laser 32 is irradiated onto the powder layer to melt and solidify the powder, thereby forming a forming layer. In this embodiment, the laser 32 is used as the heat source for solidifying the powder. The forming tank 23 is movable in the vertical direction (stacking direction) and is raised a certain amount to form and stack the forming layers. Specifically, the support section 24 supports the lower surface of the flange section 23a of the forming tank 23 so that the upper surface of the flange section 23a is horizontal. The support section 24 is connected to the drive section 25 and moves the forming tank 23 in the vertical direction. The drive section 25 is fixed to a column 26 and includes, for example, a motor.

[0016] The laser scanner 28 irradiates the powder layer formed in the modeling unit 35 with a laser 32. The laser scanner 28 is supported by the support unit 27 and can scan the laser 32 on a horizontal surface. In other words, it is possible to selectively heat and solidify the powder at any location on the horizontal surface. The laser 32 is generated by a laser oscillator and introduced into the laser scanner 28 via an optical fiber.

[0017] In the modeling unit 35, powder is supplied from the forming unit 41. For example, pipes 51 and 48 are connected to the supply unit 46 via branch 47, and a pressure reducer 49 reduces the pressure in the supply unit 46 via pipe 48, and powder is supplied from the storage unit 50 via pipe 51 to the supply unit 46. The powder is then supplied from the supply unit 46 via pipe 45 to the distributor 44. The distributor 44 measures the powder and supplies a predetermined amount of powder to the gap 42 in the modeling unit 41. The forming unit 41 then moves horizontally (orthogonal to the vertical direction) to form a powder layer in the modeling unit 35.

[0018] Specifically, when forming the object 37, the drive unit 25 moves the modeling tank 23 upward, thereby forming a step between the already formed modeling surface and the upper surface of the flange portion 23a of the modeling tank 23. Then, the forming unit 41 moves horizontally, forming a new powder layer on top of the previously formed, fixed modeling layer. At this time, the height of the uppermost powder layer becomes equal to the height of the upper surface of the flange portion 23a. Then, the laser 32 is irradiated to a predetermined area of ​​the powder layer, selectively heating and solidifying it. In this way, modeling layers are formed. By moving the modeling tank 23 upward and repeating the same operation, each modeling layer is stacked.

[0019] The modeling apparatus 10 is provided with a camera 55. The camera 55 is supported by, for example, the laser scanner 28 or the support unit 27 and is provided near the laser scanner 28. The camera 55 captures an image of the modeling unit 35 to generate an image of the formed modeling surface. The modeling surface is the surface of the layer to be modeled. The captured image is used in the inspection system 60, which will be described later. The specifications of the camera 55 are set based on the desired detection resolution for the defect D. The captured image is, for example, a black-and-white image. That is, for each pixel of the image, a brightness value ranging from 0 to an upper limit is set. The upper limit is 255 in 8-bit (256 gradations). The closer the brightness value is to 0, the darker the image is displayed, and the closer the brightness value is to the upper limit, the whiter the image is displayed. The defect D may appear white or black.

[0020] 2 is a diagram illustrating an example of the modeling unit 35 during the formation of a modeling layer according to an embodiment of the present disclosure. As shown in FIG. 2 , when a laser 32 is irradiated onto a predetermined region of the powder layer to form a model 37, heat generated by the laser irradiation vaporizes part of the material, generating fumes F. As shown in FIG. 2 , the generated fumes F flow both horizontally and upward, and the fumes F flowing horizontally are exhausted from the modeling unit 35 through an exhaust port 57. On the other hand, the fumes F flowing upward adhere as smut S to a protective layer provided on the output surface of the laser 32 of the laser scanner 28 located above the modeling unit 35 and to the lens of the camera 55.

[0021] If smut S adheres to the protective layer of the laser scanner 28, the output of the laser 32 is suppressed, increasing the possibility of defects D occurring. Furthermore, if smut S adheres to the lens of the camera 55, the brightness of the image of the modeling surface captured by the camera 55 becomes lower than when smut S is not attached to the lens. In such cases, the image of the model 37 captured by the inspection system 60 may be inappropriate for use in inspection due to the influence of fumes F, reducing the reliability of the inspection by the inspection system 60. For this reason, the inventors have diligently studied an inspection method that solves the above-mentioned problems. The inspection system proposed by the inventors is described below.

[0022] FIG. 3 is a diagram showing an example of the hardware configuration of an inspection system 60 according to this embodiment. As shown in FIG. 3 , the inspection system 60 is a computer system including, for example, a CPU 110, a ROM (Read Only Memory) 120 for storing programs executed by the CPU 110, a RAM (Random Access Memory) 130 that functions as a work area when each program is executed, a hard disk drive (HDD) 140 as a large-capacity storage device, and a communication unit 150 for connecting to a network or the like. A solid-state drive (SSD) may also be used as the large-capacity storage device. These units are connected via a bus 180.

[0023] The inspection system 60 may also include an input unit such as a keyboard and a mouse, and a display unit such as a liquid crystal display device for displaying data.

[0024] The storage medium for storing the programs executed by the CPU 110 is not limited to the ROM 120. For example, it may be other auxiliary storage devices such as a magnetic disk, a magneto-optical disk, or a semiconductor memory.

[0025] A series of processing steps for realizing the various functions described below are recorded in the form of a program on the hard disk drive 140 or the like, and the CPU 110 reads this program into the RAM 130 or the like and executes information processing and arithmetic operations to realize the various functions described below. The program may be pre-installed in the ROM 120 or other storage medium, provided in a state stored in a computer-readable storage medium, or distributed via wired or wireless communication means. Examples of computer-readable storage media include magnetic disks, magneto-optical disks, CD-ROMs, DVD-ROMs, and semiconductor memories.

[0026] 4 is a functional block diagram showing functions of the inspection system 60. As shown in FIG. 4, the inspection system 60 includes an acquisition unit 61, a calculation unit 62, and a determination unit 63.

[0027] The inspection system 60 may further include a processing unit 64 .

[0028] The inspection system 60 may further include an identification unit 65 .

[0029] The inspection system 60, for example, uses each component of the inspection system 60 to perform abnormality judgment, which determines whether an image of the surface of the forming layer being formed can be used for defect judgment, as described below, and defect judgment, which inspects the forming layer that constitutes the formed object for the presence or absence of defects.

[0030] The acquisition unit 61 acquires a leading image, which is an image of a leading layer consisting of at least one layer formed earlier among the multiple stacked layers, and a trailing image, which is an image of a trailing layer consisting of at least one layer formed after the leading layer. Specifically, the leading layer is a powder layer laid in the formation of a modeling layer at a predetermined, relatively early stage in the entire additive manufacturing process. The leading image is an image corresponding to the leading layer. Specifically, the trailing layer is a powder layer laid in the formation of a modeling layer at a predetermined, relatively late stage in the entire additive manufacturing process. The trailing image is an image corresponding to the trailing layer. For example, the acquisition unit 61 acquires images of the surface of the powder layer during the formation of the modeling layer, layer by layer. In other words, the powder layer that forms the model is inspected. In particular, the images record the state of powder application. It is preferable to capture the images after the powder has been laid but before it has solidified (i.e., before the beam is irradiated). This is because defects in recesses can be identified both before and after solidification, while defects in protrusions can be identified before solidification but may be difficult to identify after solidification because they are smoothed (to a uniform height) by beam irradiation. In other words, whether the defect is a recess or a protrusion, capturing an image before solidification (before beam irradiation) allows for effective defect determination. However, as long as the powder laying state is known, an image can be taken either before or after the powder is solidified by beam irradiation. The acquisition unit 61 may acquire an image of the surface of the modeling layer (modeling surface) in addition to an image of the surface of the powder bed. The acquisition unit 61 may be, for example, an imaging device such as a camera that captures an image of the surface of the powder bed.

[0031] The preceding layer and the following layer are defined, for example, as follows: A preceding layer is a layer located closer to the base than the intermediate layer among all layers forming the shaped object. A following layer is a layer located closer to the surface of the shaped object than the intermediate layer in the stacking direction. A preceding layer may consist of any one layer or multiple layers among all layers forming the shaped object that are located closer to the base than the intermediate layer. Similarly, a following layer is a layer after the intermediate layer among all layers forming the shaped object, and may consist of any one layer or multiple layers.

[0032] 5A to 5D are diagrams showing example images of each layer acquired by the acquisition unit 61. FIG. 5A is an example image of the first layer (initial layer). In the image of the first layer, the base 21 is not completely covered by the scattered powder. Therefore, as illustrated in FIG. 5A, the shape of the base 21 is reflected in the image of the first layer. FIG. 5B is an example image of the second layer. In the image of the second layer, the powder is applied to an extent that the shape of the base 21 is not recognizable, but the amount of powder applied is not yet uniform. Therefore, as illustrated in FIG. 5B, the image of the second layer reflects partial distortion due to the shape of the base 21 and the uneven thickness of the powder layer. As shown in FIGS. 5A and 5B, the brightness of the images of layers near the initial layer is unstable depending on the position in the image due to adjustments to the parallelism of the base 21 during modeling and tilting during setting for modeling.

[0033] FIG. 5C is an example of an image of the fifth layer, for example. In the image of the fifth layer, the base 21 is completely covered with powder. Therefore, as illustrated in FIG. 5C, the image of the fifth layer is an image of the layer surface without any installation abnormalities. FIG. 5D is an example of an image of the final layer. In the image of the final layer, the image of the layer surface is lower in brightness than the state illustrated in FIG. 5C. This is because, at the time the image of the final layer is acquired, fumes generated during modeling become smut S and adhere to the lens of the camera 55. Therefore, the image of the final layer is lower in brightness than the image of the fifth layer, depending on the amount of fume afterimage.

[0034] As illustrated in FIGS. 5A to 5D , the first few images (e.g., the first to fourth layers) formed may not show a complete coverage of the base 21 with powder. Images in which the base 21 is reflected have high image brightness and are therefore unsuitable for use in determining abnormalities. For this reason, the leading layer must be a layer in which the base 21 is completely covered. In the above example, the leading layer is the fifth layer, but this is not a limitation and may be changed as appropriate depending on the conditions of the inspection performed by the inspection system 60. Similarly, the trailing layer is not a limitation to the final layer and may be changed as appropriate depending on the conditions of the inspection performed by the inspection system 60.

[0035] As described above, the metal substrate is reflected in the image of the first layer, causing the image brightness to be higher than expected. If the above-mentioned determination is performed using an image with a brightness higher than expected, the reliability of the abnormality determination cannot be guaranteed. For this reason, it is preferable that the preceding layer is a layer corresponding to an image in which the brightness parameter, which is a parameter related to the brightness of the image, is equal to or lower than a predetermined upper limit. The predetermined upper limit is set, for example, based on a reference image obtained when the environment in which the object 37 is formed is normal.

[0036] In the environment in which the object is to be formed, the conditions around the printing area change each time depending on the amount of powder material dispersed. Therefore, if an image of the entire printing environment for the object is acquired and each brightness parameter is calculated, noise corresponding to the conditions around the printing area will be included in each brightness parameter. Therefore, it is preferable that the image used to calculate the brightness parameters is the printing area where the material is laid on the surface of the layer. In this way, by limiting the range of the image used to calculate the brightness parameters to the printing area on the surface of the layer, the calculation unit can accurately calculate the average brightness.

[0037] The leading layer and the following layer are not limited to one layer each, and may each consist of multiple layers. For example, the leading layer is a layer in the range from the fifth layer to the hundredth layer. The following layer may be a layer in the range from the layer ten layers before the final layer to the final layer. A layer in the range from the fifth layer to the layer at the midpoint of all layers may be the leading layer, and a layer in the range from the midpoint of all layers to the final layer may be the following layer.

[0038] The calculation unit 62 calculates a leading brightness parameter, which is a parameter related to the brightness of the leading image, and a trailing brightness parameter, which is a parameter related to the brightness of the trailing image, and calculates a brightness change parameter related to brightness change using the leading brightness parameter and the trailing brightness parameter. The leading brightness parameter is, for example, a leading average brightness, which is the average brightness of the leading image. The trailing brightness parameter is, for example, a trailing average brightness, which is the average brightness of the trailing image. By using the average brightness as the brightness parameter in this way, it is possible to suppress the influence of brightness variations that differ from position to position in the layer image (i.e., to improve the accuracy of abnormality determination). The brightness parameter is not limited to the average brightness. The brightness parameter may be a median or another value obtained by statistically processing brightness values. The brightness change parameter is, for example, a rate of change in average brightness calculated using the leading average brightness and the trailing average brightness. The brightness change parameter may be an amount of change or another value related to the change in brightness of the image.

[0039] When the acquisition unit 61 acquires an image of each layer, the calculation unit 62 may calculate a luminance parameter for each image and calculate a luminance change parameter using the calculated luminance parameter for each image. For example, the calculation unit 62 may calculate an average luminance using the image of each layer acquired by the acquisition unit 61 and calculate a change rate of the average luminance from the fifth layer to the final layer for every two consecutive layers or for every plurality of consecutive layers.

[0040] The determination unit 63 determines whether the environment in which the object 37 is to be formed is normal by comparing the brightness change parameter with a predetermined threshold. The predetermined threshold is, for example, a value set based on a reference image, which is an image of the forming surface in a normal environment in which the object 37 is to be formed. More specifically, the predetermined threshold is a rate of change in average brightness calculated in advance based on the reference image in a normal environment in which the object 37 is to be formed. The determination unit 63 determines that there is an abnormality in the environment in which the object 37 is to be formed, when the rate of change in average brightness calculated by the calculation unit 62 is equal to or greater than the rate of change in average brightness calculated using the reference image. The predetermined threshold may be stored in the ROM 120 in advance, or may be stored on a cloud server or the like external to the inspection system 60.

[0041] Furthermore, the determination unit 63 determines the tendency of the amount of fumes generated in the printing environment based on the luminance change parameter. Specifically, if the rate of change in average luminance calculated by the calculation unit 62 is equal to or greater than the rate of change in average luminance calculated using the reference image, the determination unit 63 determines that the amount of fumes generated in the current environment in which the object 37 is being printed is greater than the expected amount. If the amount of fumes generated is greater than the expected amount, a large amount of smut S will adhere to the lens of the camera 55, reducing the luminance of the subsequent image. In this way, it is possible to determine whether the amount of fumes generated is greater than in a normal environment, using the rate of change in average luminance in the current environment in which the object 37 is being printed.

[0042] The processing unit 64 performs image processing on the acquired image. Specifically, the processing unit 64 performs image processing (feature portion extraction) on the acquired image to emphasize the defect portion D. The image processing is at least one of trapezoidal correction, trimming, contrast adjustment, binarization, first differentiation, second differentiation, contour extraction, and noise removal. Other image processing may also be used as long as it emphasizes the defect portion D (makes the defect portion D easier to determine).

[0043] The inspection system 60 is not limited to the above configuration, and may include, for example, an imaging unit that captures images of the stacked layers.

[0044] FIG. 6 is a diagram showing an example of image processing. In FIG. 6, image processing proceeds in the direction of the arrow. First, the input image is a captured image. When capturing an image of the printing surface with the camera 55, the shooting direction of the camera 55 may be tilted relative to the vertical direction. In such cases, the printing surface that appears in the image becomes a trapezoid as shown in FIG. 6. For this reason, trimming and keystone correction are performed as process P1. Trimming is a process of removing parts other than the printing surface from the image. Keystone correction corrects the printing surface that appears as a trapezoid to a square (as if it were captured from directly in front).

[0045] Next, contrast adjustment is performed in process P2, and binarization (which may be first or second derivative) is performed in process P3. This makes the defect D stand out, and then contour extraction is performed in process P4. Since noise is also contained in the image in this state, noise removal is performed in process P5. In noise removal, defect D that is smaller than a set size (for example, area) may also be removed. In this way, defect D is emphasized.

[0046] 7A to 7D show images of examples of abnormalities that become defect D. As shown in FIGS. 7A to 7D, each abnormality, such as recoater interference (FIG. 7A), powder falling (FIG. 7B), powder short (FIG. 7C), and powder depression (FIG. 7D), appears as defect D in the image.

[0047] The identifying unit 65 identifies defects D on the surface of the layer and the positions of the defects D based on the image (image that has been subjected to image processing). If defects D exist on the building surface whose image has been acquired by the acquiring unit 61, the defects D will appear in the image. Therefore, the identifying unit 65 identifies each defect D and the coordinates on the building surface that are the positions of each defect D based on the image. Since defects D have a range, it is preferable to identify coordinates that fall within this range.

[0048] In this embodiment, image processing is performed on the captured image, but if the defect D and its position can be identified without image processing, it is not necessary to perform image processing.

[0049] (Regarding Abnormality Determination) Next, an example of the abnormality determination process for the printing environment by the inspection system 60 will be described with reference to FIG. 8 . FIG. 8 is a flowchart showing an example of the procedure for the abnormality determination process for the printing environment according to this embodiment. The flow shown in FIG. 8 may be performed after printing, for example, by storing images corresponding to each printing layer.

[0050] In the abnormality determination process, first, an image is captured (S101). Next, the captured image is trimmed to the printing range (S102). Furthermore, various correction processes such as keystone correction may be performed on the trimmed image.

[0051] Next, a leading average luminance is calculated, which is the average luminance of the leading image, which is an image of a leading layer near the first layer, and a trailing average luminance is calculated, which is the average luminance of the trailing image, which is an image of a trailing layer near the final layer (S103). At this time, the average luminance may be calculated using images in which the contrast of each layer has been adjusted. Next, a change rate of the average luminance is calculated using the leading average luminance and the trailing average luminance (S104).

[0052] Next, the change rate of the average brightness is compared with a predetermined threshold, and whether or not there is an abnormality in the printing environment is determined based on whether or not the change rate of the average brightness is equal to or greater than the predetermined threshold (S105). If it is determined that the change rate of the average brightness is not equal to or greater than the predetermined threshold (NO in S105), it is determined that there is no abnormality and that the printing environment is normal (S106). If it is determined that the change rate of the average brightness is equal to or greater than the predetermined threshold (YES in S105), it is determined that there is an abnormality (S107).

[0053] In this way, by comparing the rate of change in the average brightness of the image of the printing surface with a predetermined threshold to determine whether there is an abnormality in the printing environment, it is possible to determine whether the current printing environment is an environment worthy of inspecting the object. For example, if the rate of change in average brightness calculated using the preceding average brightness and the following average brightness is equal to or greater than the rate of change in average brightness calculated using the reference image, it can be inferred that the amount of fume generated in the current printing environment is greater than the amount of fume generated in a normal printing environment. Then, it can be determined that it is not desirable to perform defect detection on the object using the image acquired in the current printing environment.

[0054] Furthermore, this processing makes it possible to determine whether or not there is an abnormality due to a change in the manufacturing environment over time, thereby improving the reliability of the detection results of the abnormality detection performed by the inspection system 60. Furthermore, by determining whether or not there is an abnormality due to a change in the manufacturing environment over time, the frequency of non-destructive testing can be reduced.

[0055] In the above-described anomaly determination process, the presence or absence of an anomaly is determined using the rate of change of the average luminance, but this is not limiting and the presence or absence of an anomaly may be determined using the amount of change of the average luminance. The preceding layer and the following layer may each be a single layer at a predetermined position, or multiple layers located in a predetermined range. When performing inspection during modeling, multiple following layers may be defined at different positions. In this case, multiple determinations are made during modeling.

[0056] When inspection is performed during modeling, the first layer of two consecutive layers may be designated as a leading layer and the next layer as a trailing layer, and abnormalities may be repeatedly determined based on the rate of change in the brightness parameters of these two layers.When inspection is performed during modeling, the layer at a predetermined initial position may be designated as a leading layer, and a layer spaced a predetermined distance from the leading layer may be designated as a trailing layer, and the leading layer and the trailing layer may be changed according to the progress of the modeling process while maintaining the predetermined distance, and abnormality determination processing may be performed.

[0057] (Regarding Defect Determination) Next, an example of the defect determination process by the inspection system 60 described above will be described with reference to FIGS. 9 and 10 . FIGS. 9 and 10 are flowcharts showing an example of the procedure of the defect determination process including the abnormality determination process according to this embodiment. The flow shown in FIGS. 9 and 10 is performed, for example, each time a modeling layer is formed and an image is acquired. The flow shown in FIGS. 9 and 10 may be performed, for example, after modeling, by accumulating images corresponding to each modeling layer, rather than each time an image is acquired. The defect determination process according to this embodiment is characterized by including an abnormality determination process that calculates the average brightness of the images of each layer as a brightness parameter, and determines that an abnormality exists in the image corresponding to the brightness parameter if each brightness parameter is greater than a predetermined upper limit value or less than a predetermined lower limit value.

[0058] In the defect determination process, first, an image is captured (S201). Next, trimming and keystone correction are performed (S202). Next, the average luminance of the image for each layer is calculated (S203). Next, it is determined whether the average luminance of all images falls within a threshold range. Specifically, if there is an average luminance that is greater than a predetermined upper limit value or less than a predetermined lower limit value, it is determined that there is an abnormality in the image corresponding to this average luminance (S204). The predetermined upper limit value and the predetermined lower limit value are values ​​that are set based on, for example, a reference image, which is an image of the printing surface when the environment in which the object 37 is printed is normal.

[0059] If the average brightness of any image is not within the threshold range (NO in S204), it is determined that some process abnormality has occurred and defect determination cannot be performed (S205). Process abnormalities may include, for example, the amount of fume generated in the printing environment being greater than expected, or the camera 55 being improperly calibrated. If the average brightness of all images is within the threshold range (YES in S204), contrast adjustment is performed (S206).

[0060] Next, the average brightness of the images of each layer after the contrast adjustment is calculated (S207). Next, it is determined whether the average brightness of all the images after the contrast adjustment falls within a threshold range. Specifically, if there is an average brightness that is greater than a predetermined upper limit or smaller than a predetermined lower limit, it is determined that there is an abnormality in the image corresponding to this average brightness (S208).

[0061] If the average brightness of any image is not within the threshold range (NO in S208), it is determined that some process abnormality has occurred and defect determination cannot be performed (S209).If the average brightness of all images is within the threshold range (YES in S208), the process proceeds to predetermined image processing (e.g., binarization, first derivative, second derivative, etc.) (S210).

[0062] Next, binarization (first or second differentiation may be performed) is performed (S210), and noise removal is performed (S211). That is, steps S202 to S211 constitute image processing.

[0063] Next, it is determined whether or not a defect D has been detected (S212). For example, if the area of ​​a region in the image that is assumed to be a defect D is equal to or larger than a threshold, this region is determined to be a defect D. Note that the determination method is not limited as long as it is possible to determine a defect D based on an image.

[0064] If no defect D is detected (NO in S212), it is determined to be normal (S213). If a defect D is detected (YES in S212), the coordinates of the defect D are recorded (S214).

[0065] Next, it is determined whether or not a defect D has occurred at the same coordinates for a predetermined number of consecutive layers (S215). In S215, the determination is made by referring to the record of the coordinates of the defect D for the lower modeling layer for which the determination has been made (processing of S214).

[0066] If no defect D occurs at the same coordinates for a predetermined number of consecutive layers (NO in S215), the determination of an abnormality is withheld (S216).

[0067] If a defect D occurs at the same coordinates for a predetermined number of consecutive layers (YES in S215), it is determined to be abnormal (S217).

[0068] By performing such processing, an abnormality determination process can be performed before the defect determination process, and it can be determined whether there are any abnormalities in the image used for defect determination, thereby ensuring the reliability of the determination results of the defect determination process.

[0069] In the above flow, only images determined as "NO" in S204 or S208 may be excluded from the inspection target, and the subsequent processing may be continued. In this case, if the determination in S204 or S208 is "NO," the defect determination processing is interrupted, and the administrator of the inspection system 60 is notified that a process abnormality has been confirmed.

[0070] The predetermined thresholds in S204 and S208, specifically, the predetermined upper limit and lower limit, may be values ​​that are set based on a reference image, which is an image of the printing surface captured when the environment in which the object is printed is normal. The processes from S207 to S209 may be omitted as appropriate depending on the printing conditions and inspection conditions of the object to be printed.

[0071] In the above description, the abnormality determination process and the defect determination process are performed separately, but this is not limiting. For example, the abnormality determination process and the defect determination process may be performed in parallel while performing modeling. Furthermore, the abnormality determination process and the defect determination process may be combined into one process, and the defect determination process may be performed after the abnormality determination process is completed, and each process may be repeatedly performed alternately.

[0072] The present disclosure is not limited to the above-described embodiments, and various modifications are possible within the scope of the invention. It is also possible to combine the various embodiments.

[0073] (Additional Notes) The inspection system, inspection method, manufacturing method, and inspection program using the inspection method described in each of the above-described embodiments may be understood, for example, as follows: An inspection system (60) according to a first aspect of the present disclosure is an inspection system for an object (37) formed by stacking materials on a substrate (21), and includes: an acquisition unit (61) that acquires a leading image that is an image of a leading layer consisting of at least one layer formed earlier among a plurality of stacked layers, and a following image that is an image of a following layer consisting of at least one layer formed later than the leading layer; a calculation unit (62) that calculates a leading brightness parameter related to the brightness of the leading image and a following brightness parameter related to the brightness of the following image, respectively, and calculates a brightness change parameter related to a brightness change using the leading brightness parameter and the following brightness parameter; and a determination unit (63) that determines whether an environment in which the object is to be formed is normal by comparing the brightness change parameter with a predetermined threshold.

[0074] According to the present disclosure, an inspection system for a model formed by stacking materials on a substrate includes an acquisition unit that acquires a leading image, which is an image of a leading layer consisting of at least one layer formed earlier among the multiple stacked layers, and a trailing image, which is an image of a trailing layer consisting of at least one layer formed later than the leading layer; a calculation unit that calculates a leading brightness parameter relating to the brightness of the leading image and a trailing brightness parameter relating to the brightness of the trailing image, respectively, and calculates a brightness change parameter relating to brightness change using the leading brightness parameter and the trailing brightness parameter; and a determination unit that determines whether the environment in which the model is to be formed is normal by comparing the brightness change parameter with a predetermined threshold. In this way, by acquiring images of layers at different stacking positions and using multiple brightness parameters calculated from the images of each layer to determine whether the printing environment is normal or not, it is possible to determine whether there is an abnormality due to changes in the printing environment over time. This improves the reliability of the detection results of anomaly detection performed by the inspection system. Furthermore, by determining whether there is an abnormality due to changes in the printing environment over time, the frequency of non-destructive testing can be reduced.

[0075] In the inspection system according to the second aspect of the present disclosure, in the first aspect, the preceding layer may be a layer located closer to the base than an intermediate layer among all layers forming the object, and the following layer may be a layer located closer to the surface of the object than the intermediate layer.

[0076] According to the inspection system of the present disclosure, the preceding layer is a layer that is located closer to the base than a layer at an intermediate position in the formation of all layers that form the object, and the following layer is a layer that is located closer to the surface of the object than a layer at an intermediate position in the stacking direction. This makes it possible to grasp trends in the rate of change of average brightness over a wider range by using images of layers formed in the first half of the formation of the object and images of layers formed in the second half of the formation of the object, and to grasp trends in changes in the environment in which the object is formed over a wider range.

[0077] In the inspection system according to the third aspect of the present disclosure, in the second aspect, the preceding layer may be a layer corresponding to an image in which the preceding brightness parameter is equal to or less than a predetermined upper limit value.

[0078] According to the inspection system of the present disclosure, the preceding layer is a layer corresponding to an image in which the preceding brightness parameter is equal to or less than a predetermined upper brightness limit. For example, if the preceding layer is the first layer, a metal substrate may be reflected in the preceding image, increasing the brightness of the preceding image. Therefore, by determining the layer in which the preceding brightness parameter is equal to or less than a predetermined upper brightness limit as the preceding layer, it is possible to more accurately determine whether the environment in which the object is to be formed is normal.

[0079] In the inspection system according to the fourth aspect of the present disclosure, in any one of the first to third aspects, the determination unit may determine the trend in the amount of fume (F) generated in the environment based on the brightness change parameter.

[0080] According to the inspection system of the present disclosure, the determination unit determines the tendency of the amount of fumes generated in the environment in which the object is to be formed, based on the luminance change parameter obtained by using the preceding luminance parameter and the following luminance parameter, thereby making it possible to determine whether the amount of fumes generated in the environment in which the object is to be formed is within a normal range.

[0081] An inspection system according to a fifth aspect of the present disclosure may be configured such that, in any one of the first to fourth aspects, the leading brightness parameter is an average brightness of the leading image, the following brightness parameter is an average brightness of the following image, and the brightness change parameter is a rate of change between the average brightness of the leading image and the average brightness of the following image.

[0082] According to the inspection system of the present disclosure, the leading luminance parameter is the average luminance of the leading image, the trailing luminance parameter is the average luminance of the trailing image, and the luminance change parameter is the rate of change between the average luminance of the leading image and the average luminance of the trailing image. That is, the inspection system calculates the rate of change of the average luminance using the average luminance of each layer formed at a different position in the stacking direction, and compares the average rate of change of luminance with a predetermined threshold to determine whether the environment in which the object is to be formed is normal. This makes it possible to grasp the brightness of the environment in which the object is to be formed over time, and to determine whether images acquired in the current forming environment can be used to detect an abnormality in the object.

[0083] In the inspection system according to a sixth aspect of the present disclosure, in any of the first to fifth aspects, the predetermined threshold value may be a value set based on a reference image, which is an image of the printing surface when the environment in which the object is printed is normal.

[0084] According to the inspection system of the present disclosure, the predetermined threshold is a value that is set based on a reference image obtained when the environment in which the object is to be formed is normal. By setting the predetermined threshold based on the reference image in this manner, it is possible to more accurately determine whether the environment in which the object is to be formed is normal.

[0085] In the inspection system according to a seventh aspect of the present disclosure, in any one of the first to sixth aspects, the image may be an image of a build area in which the material is laid on the surface of a layer.

[0086] According to the inspection system of the present disclosure, the image is an image of a build area where material is laid on the surface of the layer. The environment in which the object is built changes depending on the amount of powder material dispersed, resulting in changes in the surroundings of the build area. Therefore, if an image of the entire build environment for the object is acquired and each brightness parameter is calculated, noise corresponding to the surroundings of the build area may be included in each brightness parameter. Therefore, by limiting the image range to the build area on the surface of the layer, the average brightness can be accurately calculated.

[0087] In an inspection system according to an eighth aspect of the present disclosure, in any one of the first to seventh aspects, the calculation unit calculates a brightness parameter related to the brightness of the image of each layer, and the determination unit determines that there is an abnormality in the image corresponding to the brightness parameter if any of the brightness parameters is greater than a predetermined upper limit value or smaller than a predetermined lower limit value.

[0088] In the inspection system according to the present disclosure, the calculation unit calculates a brightness parameter relating to the brightness of the image of each layer, and the determination unit determines that an abnormality exists in the image corresponding to the brightness parameter if the brightness parameter is greater than a predetermined upper limit or less than a predetermined lower limit. For example, if the brightness parameter of each image is not within the predetermined upper or lower limit range, it is possible that the amount of fume generated in the printing environment is greater than expected, or that the camera calibration has not been performed correctly. Therefore, by determining whether the brightness parameter of each image is within the predetermined upper or lower limit range, it is possible to improve the reliability of the laying abnormality inspection, which inspects for the presence or absence of laying abnormalities in the laying of materials during layer formation.

[0089] In the inspection system according to the ninth aspect of the present disclosure, in the eighth aspect, the upper limit value and the lower limit value are values ​​that are set based on a reference image, which is an image of the printing surface when the environment in which the object is printed is normal.

[0090] According to the inspection system of the present disclosure, the upper and lower limits are set based on a reference image, which is an image of the printing surface captured when the environment in which the object is printed is normal. In this way, the reference values ​​for determining an abnormality in the image inspection are set based on the reference image captured when the environment in which the object is printed is normal, thereby making it possible to more accurately determine whether the environment in which the object is printed is normal.

[0091] An inspection method according to a tenth aspect of the present disclosure is a method for inspecting a molded object (37) formed by stacking materials on a substrate (21), and includes an acquisition step of acquiring a leading image, which is an image of a leading layer consisting of at least one layer formed earlier among the multiple stacked layers, and a trailing image, which is an image of a trailing layer consisting of at least one layer formed later than the leading layer; a calculation step of calculating a leading brightness parameter, which is a parameter related to the brightness of the leading image, and a trailing brightness parameter, which is a parameter related to the brightness of the trailing image, and calculating a brightness change parameter using the leading brightness parameter and the trailing brightness parameter; and a determination step of determining whether the environment in which the molded object is formed is normal by comparing the brightness change parameter with a predetermined threshold.

[0092] The manufacturing method according to the eleventh aspect of the present disclosure includes a powder layer formation process in which a powder of the material is laid in the molding area of ​​the molded object to form a powder layer, a molding layer formation process in which a laser (32) is irradiated onto the powder layer to melt and solidify the material to form a molding layer, and an inspection process in which the molding layer is inspected using the inspection method of the tenth aspect.

[0093] An inspection program according to a twelfth aspect of the present disclosure is an inspection program for an object (37) formed by stacking materials on a substrate (21), and causes a computer to execute an acquisition process for acquiring a leading image, which is an image of a leading layer consisting of at least one layer formed earlier among the multiple stacked layers, and a trailing image, which is an image of a trailing layer consisting of at least one layer formed later than the leading layer; a calculation process for calculating a leading brightness parameter, which is a parameter related to the brightness of the leading image, and a trailing brightness parameter, which is a parameter related to the brightness of the trailing image, and calculating a brightness change parameter using the leading brightness parameter and the trailing brightness parameter; and a determination process for determining whether the environment in which the object is to be formed is normal by comparing the brightness change parameter with a predetermined threshold value.

[0094] DESCRIPTION OF SYMBOLS 10: Modeling device 21: Base 22: Surface plate 22a: Convex portion 23: Modeling tank 23a: Flange portion 24: Support portion 25: Drive portion 26: Pillar 27: Support portion 28: Laser scanner 32: Laser (heat source) 35: Modeling portion 37: Modeled object 41: Forming portion 42: Gap 44: Distributor 45: Piping 46: Supply portion 47: Branch 48: Piping 49: Pressure reducer 50: Storage portion 51: Piping 55: Camera 57: Exhaust port 60: Inspection system 61: Acquisition portion 62: Calculation portion 63: Determination portion 64: Processing portion 65: Identification portion 110: CPU 120: ROM 130 : RAM 140 : Hard disk drive 150 : Communication unit 180 : Bus D : Defective part F : Fume (metal vapor) S : Smut

Claims

1. An inspection system for an object formed by stacking materials on a substrate, comprising: an acquisition unit that acquires a leading image, which is an image of a leading layer consisting of at least one layer formed first among multiple stacked layers, and a trailing image, which is an image of a trailing layer consisting of at least one layer formed after the leading layer; a calculation unit that calculates a leading brightness parameter related to the brightness of the leading image and a trailing brightness parameter related to the brightness of the trailing image, and calculates a brightness change parameter related to brightness change using the leading brightness parameter and the trailing brightness parameter; and a determination unit that determines whether the environment in which the object is formed is normal by comparing the brightness change parameter with a predetermined threshold.

2. The inspection system according to claim 1, wherein the preceding layer is a layer located closer to the base than an intermediate layer among all layers forming the object, and the following layer is a layer located closer to the surface of the object than the intermediate layer.

3. The inspection system of claim 2, wherein the preceding layer is a layer corresponding to an image in which the preceding brightness parameter is equal to or less than a predetermined upper limit.

4. The inspection system according to claim 1, wherein the determining unit determines the tendency of the amount of fume generated in the environment based on the brightness change parameter.

5. The inspection system of claim 1, wherein the preceding brightness parameter is the average brightness of the preceding image, the following brightness parameter is the average brightness of the following image, and the brightness change parameter is the rate of change between the average brightness of the preceding image and the average brightness of the following image.

6. The inspection system according to claim 1, wherein the predetermined threshold value is a value set based on a reference image, which is an image of the object being formed when the environment in which the object is formed is normal.

7. The inspection system of claim 1, wherein the image is an image of a build area in which the material is laid down at the surface of a layer.

8. The inspection system of claim 1, wherein the calculation unit calculates a brightness parameter related to the brightness of the image of each of the layers, and the determination unit determines that an abnormality exists in the image corresponding to the brightness parameter if any of the brightness parameters is greater than a predetermined upper limit value or less than a predetermined lower limit value.

9. An inspection system according to claim 8, wherein the upper limit value and the lower limit value are values ​​set based on a reference image, which is an image of the object being formed when the environment in which the object is formed is normal.

10. A method for inspecting a molded object formed by stacking materials on a substrate, comprising: an acquisition step of acquiring a leading image, which is an image of a leading layer consisting of at least one layer formed first among a plurality of stacked layers, and a trailing image, which is an image of a trailing layer consisting of at least one layer formed after the leading layer; a calculation step of calculating a leading brightness parameter, which is a parameter related to the brightness of the leading image, and a trailing brightness parameter, which is a parameter related to the brightness of the trailing image, and calculating a brightness change parameter using the leading brightness parameter and the trailing brightness parameter; and a determination step of determining whether the environment in which the molded object is molded is normal by comparing the brightness change parameter with a predetermined threshold.

11. A method for manufacturing a molded object, comprising: a powder layer forming step of laying the powder material in a molding area of ​​the molded object to form a powder layer; a molding layer forming step of irradiating the powder layer with a laser to melt and solidify the material to form a molding layer; and an inspection step of inspecting the molding layer using the inspection method described in claim 10.

12. An inspection program for an object formed by stacking materials on a base, the inspection program causing a computer to execute the following steps: an acquisition process for acquiring a leading image, which is an image of a leading layer consisting of at least one layer formed first among the multiple stacked layers, and a trailing image, which is an image of a trailing layer consisting of at least one layer formed after the leading layer; a calculation process for calculating a leading brightness parameter, which is a parameter related to the brightness of the leading image, and a trailing brightness parameter, which is a parameter related to the brightness of the trailing image, and calculating a brightness change parameter using the leading brightness parameter and the trailing brightness parameter; and a judgment process for judging whether the environment in which the object is formed is normal by comparing the brightness change parameter with a predetermined threshold.

Images