Monitoring systems and additive manufacturing systems
By collecting and processing information from additional manufacturing processes through a monitoring system, quality data is generated, solving the problem of difficulty in monitoring product quality in existing technologies. This enables timely judgment and correction of defects, improving the efficiency and quality of the manufacturing process.
Patent Information
- Application Number
- CN202210586812.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2021-05-28
- Filing Date
- 2022-05-26
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2042-05-26
AI Technical Summary
Existing technologies are insufficient to effectively monitor and assess the quality of items during the post-manufacturing process, especially the presence or absence of defects, which may lead to quality problems in the manufactured items.
A monitoring system is used to collect information from the additional manufacturing process through imaging devices and temperature sensors, generate quality data, and a processing device judges defects and generates data indicating whether defects exist.
This enables easier monitoring of the quality of additional manufactured items, reduces the time and cost of extra inspections, improves the transparency and reliability of the manufacturing process, allows for timely correction of defects, and improves the quality of the items.
Smart Images

Figure CN115401220B_ABST
Abstract
Description
Technical Field
[0001] Embodiments of the present invention relate to monitoring systems and additive manufacturing systems. Background Art
[0002] There is an additive manufacturing device that manufactures an object by additive manufacturing. In additive manufacturing, metal powder is repeatedly melted and solidified to add layers one by one. For additively manufactured objects, a technology that can more easily control the quality is required.
[0003] Prior art literature
[0004] Patent Literature
[0005] Patent Document 1: Japanese Patent Application Publication No. 2020-15944 Summary of the invention
[0006] Problems that the invention will solve
[0007] The problem to be solved by the present invention is to provide a monitoring system and an additive manufacturing system that can more easily grasp the quality of additively manufactured items.
[0008] Means for solving problems
[0009] The monitoring system of the embodiment includes a collecting device and a processing device. The collecting device collects information of a solidified solidified portion in additive manufacturing in which a plurality of layers are formed by repeatedly melting and solidifying metal powder. The processing device uses the information to determine whether there is a defect in the solidified portion and generates quality data indicating the presence or absence of the defect. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] Figure 1 is a schematic diagram showing an additive manufacturing system according to an embodiment.
[0011] Figure 2 This is a block diagram showing the configuration of a monitoring system according to an embodiment.
[0012] Figure 3 is a block diagram showing a control system of an additive manufacturing device.
[0013] Figure 4 is a schematic diagram showing a situation of additive manufacturing.
[0014] Figure 5 It is a schematic diagram showing an image obtained by a photographing device.
[0015] Figure 6 This is a schematic diagram for explaining the shooting area.
[0016] Figure 7It is a flowchart showing the operation of the monitoring system according to the embodiment.
[0017] Figure 8 It is a block diagram showing the configuration of an additive manufacturing system according to an embodiment.
[0018] Fig. 9 It is a flowchart showing the operation of the monitoring system according to the embodiment.
[0019] Fig.10 It is a flowchart showing the operation of the monitoring system according to the embodiment.
[0020] Fig.11 This is a schematic diagram showing the hardware configuration. DETAILED DESCRIPTION
[0021] Hereinafter, embodiments of the present invention will be described with reference to the drawings.
[0022] The accompanying drawings are schematic or conceptual drawings, and the relationship between the thickness and width of each part, the ratio of the size between the parts, etc. are not necessarily the same as the actual situation. Even when the same part is shown, there are cases where the mutual size and ratio are shown differently according to the drawings.
[0023] In the present specification and each drawing, the same reference numerals are given to the same elements as those already described, and the detailed description is appropriately omitted.
[0024] Figure 1 is a schematic diagram showing an additive manufacturing system according to an embodiment.
[0025] Figure 2 This is a block diagram showing the configuration of a monitoring system according to an embodiment.
[0026] Figure 3 is a block diagram showing a control system of an additive manufacturing device.
[0027] like Figure 1 As shown, the additive manufacturing system 2 includes a monitoring system 1 and an additive manufacturing device 100 .
[0028] like Figure 1 As shown, the additive manufacturing apparatus 100 includes a first container 110 , a first stage 111 , a second container 120 , a second stage 121 , a coater 130 , an irradiation device 140 , and an optical system 141 .
[0029] A powder bed 205 on which metal powder 201 is spread is provided inside the first container 110. The additive manufacturing apparatus 100 partially melts the metal powder 201 provided on the upper surface of the powder bed 205. The molten metal powder 201 solidifies to form a solidified layer. Another solidified layer is repeatedly added on the solidified layer and joined to form a solidified portion 210. Finally, an article consisting of the solidified portion 210 is manufactured.
[0030] The irradiation device 140 irradiates the metal powder 201 in the first container 110 with a laser 150. The irradiation device 140 may also emit an electron beam. The laser 150 is reflected by the optical system 141 and irradiates a portion of the powder bed 205. The laser 150 irradiates an arbitrary position of the powder bed 205 by driving the optical system 141.
[0031] The second container 120 stores the metal powder 201 supplied to the first container 110. A first workbench 111 is provided at the bottom of the first container 110. A second workbench 121 is provided at the bottom of the second container 120. The first workbench 111 and the second workbench 121 can be raised and lowered. If the first workbench 111 is raised or lowered, the height of the upper surface of the powder bed 205 and the height of the upper surface of the solidification part 210 change. If the second workbench 121 is raised or lowered, the height of the upper surface of the metal powder 201 stored in the second container 120 changes.
[0032] When the metal powder 201 is melted by the laser 150 and a new solidified layer is added to the solidified portion 210, the first workbench 111 descends. The upper surface of the powder bed 205 and the upper surface of the solidified portion 210 are located below the upper surface of the first container 110. Then, the second workbench 121 ascends. The upper surface of the metal powder 201 stored in the second container 120 is located above the upper surface of the second container 120. The coating machine 130 moves from the second container 120 toward the first container 110. The coating machine 130 transports the metal powder 201 located above the upper surface of the second container 120 toward the first container 110. A new layer of the metal powder 201 is supplied to the powder bed 205 and the solidified portion 210 by the coating machine 130.
[0033] The monitoring system 1 collects information on additive manufacturing by the additive manufacturing apparatus 100. The monitoring system 1 uses the information to determine whether there are defects in the solidified portion 210. In addition, the monitoring system 1 generates quality data indicating the presence or absence of defects based on the determination result. Figure 1 As shown, the monitoring system 1 includes a camera 21 , a temperature sensor 22 , and a lighting device 23 .
[0034] The imaging device 21 is, for example, a camera, and images the state of the first container 110 during additive manufacturing. The imaging device 21 images the powder bed 205, the solidified portion 210, the molten pool 220 generated by the melting of the metal powder 201, the laser 150 irradiated onto the surface of the powder bed 205, etc. Thus, images showing the state of additive manufacturing are collected as the information.
[0035] The temperature sensor 22 measures the temperature of the powder bed 205, the solidified part 210 or the molten pool 220. Thus, the temperature of each part in the additive manufacturing, the overall temperature distribution, etc. are collected as the information. The temperature sensor 22 measures the temperature of the object based on infrared rays radiated from the object, for example.
[0036] In order to enable the camera 21 to obtain a clearer image, the lighting device 23 illuminates the powder bed 205. An optical system for adjusting the photographing position of the camera 21 and the lighting position of the lighting device 23 may be appropriately provided.
[0037] Figure 2 It is a schematic diagram showing the configuration of a monitoring system according to an embodiment.
[0038] like Figure 2 As shown, the monitoring system 1 of the embodiment further includes a processing device 11 , an input device 12 , a display device 13 , and a storage device 14 .
[0039] The processing device 11 generates quality data based on information collected by the imaging device 21 and the temperature sensor 22. The input device 12 is used when the user inputs data into the processing device 11. The display device 13 displays the data output from the processing device 11 to the user. The storage device 14 stores data. For example, the imaging device 21 and the temperature sensor 22 store the acquired information in the storage device 14. The processing device 11 accesses the storage device 14 and acquires information.
[0040] The operations of the imaging device 21 , the temperature sensor 22 , and the lighting device 23 may be controlled by the processing device 11 or by other control devices.
[0041] Figure 3 is a schematic diagram showing a control system of an additive manufacturing device.
[0042] For example, Figure 3 As shown, the additive manufacturing apparatus 100 further includes a control device 101. The operations of the first workbench 111, the second workbench 121, the coating machine 130, the irradiation device 140, and the optical system 141 are controlled by the control device 101. The control device 101 refers to the preset additive manufacturing conditions and operates each component according to the conditions.
[0043] Figure 4 is a schematic diagram showing a situation of additive manufacturing.
[0044] exist Figure 4 In the embodiment, the laser 150 as a heat source is irradiated to a part of the powder bed 205, and the metal powder 201 is melted. The heat source may be an electron beam. The melted metal powder 201 forms a molten pool 220. In addition, the melted metal powder 201 solidifies to form a solidified portion 210.
[0045] The solidified portion 210 includes a plurality of beads 211. The beads 211 extend along a first direction D1 in which the laser beam 150 is scanned. The plurality of beads 211 are arranged in a second direction D2 that is perpendicular to the first direction D1.
[0046] If one or more weld beads 211 are formed with respect to a layer of metal powder 201 extending along the first direction D1 and the second direction D2, a new layer of metal powder 201 is supplied in the third direction D3. The third direction D3 is perpendicular to the first direction D1 and the second direction D2. Another weld bead is formed on the new layer of metal powder 201.
[0047] The imaging device 21 images one or more weld beads 211 and the molten pool 220 during the irradiation of the laser 150. The imaging device 21 may also image the powder bed 205 before the irradiation of the laser 150. The imaging device 21 may also image the powder bed 205 and the solidified portion 210 after the irradiation of the laser 150 and before the new metal powder 201 is supplied.
[0048] Figure 5 It is a schematic diagram showing an image obtained by a photographing device.
[0049] exist Figure 5 The image shown (first image) shows the laser 150, the metal powder 201, a plurality of weld beads 211a to 211c, and a molten pool 220. The weld bead 211b (second weld bead) is formed before the weld bead 211a (first weld bead). The weld bead 211c is formed before the weld bead 211b. The weld bead 211b is located between the weld beads 211a and 211c, and is adjacent to the weld beads 211a and 211c.
[0050] If the processing device 11 receives Figure 5The image shown in FIG. 1 is used to extract data that are features of the additive manufacturing process. For example, the processing device 11 extracts first data, which includes one or more data selected from the following data: the width W1 of the weld bead 211a immediately after solidification, the contour of the weld bead 211a, the surface shape of the weld bead 211a, the width W2 of the weld bead 211b, the contour of the weld bead 211b, the surface shape of the weld bead 211b, the width W3 of the weld bead 211c, the contour of the weld bead 211c, the surface shape of the weld bead 211c, the contour of the molten pool 220, and the size of the laser 150.
[0051] "Just after solidification" refers to the weld bead 211 on the line scanned by the laser 150. The weld bead 211 just after solidification is arranged in the molten pool 220 and the first direction D1. The width of the weld bead 211a, 211b or 211c corresponds to the length of the weld bead 211a, 211b or 211c in the second direction D2. As the surface shape, at least one selected from the size and position of the local depression (opening defect), surface roughness and gloss (brightness) is used. The size of the laser 150 is represented by the area of the region surrounded by the outline of the laser 150.
[0052] The storage device 14 may also store a first model for extracting first data from an image. The first model may include, for example, a neural network. The processing device 11 inputs an image into the first model and obtains first data output from the first model. For example, if the first model is input Figure 5 The image shown in FIG. 1 outputs line segments Li1 to Li3. Line segment Li1 is the boundary between weld bead 211a and metal powder 201 and the boundary between weld bead 211a and weld bead 211b, and represents the contour of weld bead 211a. Line segment Li2 represents the contour of laser 150. Line segment Li3 represents the contour of molten pool 220.
[0053] When the processing device 11 acquires the first data, it refers to the database stored in the storage device 14. The database includes conditions for determining the presence or absence of a defect based on the first data.
[0054] As an example, in a defective region, the width of any weld bead 211 changes locally. When the width is less than a preset threshold, it is determined that there is a defect in the region. As another example, when the size of the laser 150 is small, a sufficient amount of metal powder 201 is not melted, and defects are likely to occur. When the size is less than a preset threshold, it is determined that there is a defect in the region.
[0055] For example, the processing device 11 extracts a plurality of data consisting of the contour of the weld bead 211a, the contour of the molten pool 220, and the size of the laser 150 as the first data. The database includes conditions respectively corresponding to the contour of the weld bead 211a, the contour of the molten pool 220, and the size of the laser 150. The processing device 11 compares the plurality of data with the plurality of conditions respectively, and determines the presence or absence of a defect.
[0056] The database may also include information related to the type of defect. For example, the defect is an undercut where the solidified portion 210 is locally thin, an overlap where the solidified portion 210 is locally thick, or spatter formed by the scattering of molten metal. Multiple conditions corresponding to multiple types of defects are set for one data. The processing device 11 determines the presence or absence of defects and the type of defects based on the multiple conditions included in the database.
[0057] The existence of defects can also be expressed by probability. For example, one or more conditions are set for each data. The probability of the existence of defects is set for each condition. When the conditions are met, it is judged that the defect exists with the set probability. When multiple conditions are met, the probability of the existence of defects increases.
[0058] Figure 6 (a) and Figure 6 (b) is a schematic diagram for explaining the imaging area.
[0059] Figure 6 (a) shows the initial layer A of the metal powder 201 supplied to the first container 110 1 . Layer A 1 The first direction D1 and the second direction D2 include a plurality of regions B. 11 ~B xy In the example shown in the figure, x areas B are arranged in the first direction D1, and y areas B are arranged in the second direction D2. The imaged range C is set to be larger than one area B. The image capturing device 21 is in area B. 11 ~B xy When each layer is irradiated with the laser beam 150, the laser beam 150, the solidified portion 210, and the molten pool 220 are photographed. 1 , obtain x×y images.
[0060] The imaging device 21 repeatedly captures each layer in the same manner. Figure 6 (b) represents the zth layer A supplied to the first container 110 z The camera 21 is located on layer A. z In the middle, with layer A 1 Similarly, in area B 11 ~B xyThe images are taken when the laser beam 150 is irradiated.
[0061] A plurality of images with different shooting positions in the first direction D1, the second direction D2 or the third direction D3 are acquired by the imaging device 21. The processing device 11 determines the presence or absence of defects in each of the plurality of shooting areas based on the plurality of images.
[0062] The processing device 11 may also judge the presence or absence of defects based on the difference between the plurality of images. Typically, the number of regions judged to have defects is less than the number of regions judged to have no defects. The difference between the images of the regions judged to have no defects is relatively small. The difference between the images of the regions judged to have no defects and the images of the regions judged to have defects is relatively large.
[0063] For example, the processing device 11 inputs a new image and one or more past images into the first model, and obtains line segments Li1 to Li3 corresponding to the respective images. The processing device 11 calculates the difference in feature values between the plurality of images for the line segments Li1 to Li3. The processing device 11 compares the difference with a pre-set condition, and determines the presence or absence of defects in the region captured in the new image.
[0064] Alternatively, a reference image when there is no defect may be stored in advance in the storage device 14. The processing device 11 calculates the difference between the new image and the reference image. The processing device 11 determines the presence or absence of a defect in the area captured in the new image based on the difference.
[0065] The processing device 11 can also be in layer A 1 ~A z The difference between the images of the region B having the same position in the first direction D1 and the second direction D2 is calculated. z Area B 11 An image with layer A 1 ~A z-1 The difference of the image of area B11.
[0066] For example, the processing device 11 calculates one or both of the brightness difference and the contrast value difference as the difference. In the calculation of the difference, the processing device 11 may also perform calculations such as differentiating adjacent pixel areas to calculate the gradient of the contrast, quantitatively calculating the periodicity by Fourier transform, and simply obtaining the difference of the light and dark. A pixel area is an area composed of one or more pixels. As a condition for the difference, a threshold is pre-set. When the difference is larger than the threshold, the processing device 11 determines that the area captured in the new image has a defect.
[0067] The photographing device 21 may also photograph the powder bed 205 and obtain an image (a second image) after a new layer of metal powder 201 is supplied and before the laser 150 is irradiated. For example, the processing device 11 calculates the position of each point of the powder bed 205 in the third direction D3 and the average position of these from the obtained image. "Point" is a part of "area". The processing device 11 calculates the distance (difference) between the position of each point and the average position. The condition (threshold) for the distance is set in advance. When the distance exceeds the threshold, it means that the surface of the solidified portion 210 formed at the point is locally concave or convex. The processing device 11 determines that there is a defect in the solidified portion 210 directly below the point where the distance exceeds the threshold. In addition, if the metal powder 201 at the point where the distance exceeds the threshold solidifies, the possibility of defects is high. Therefore, it can also be regarded as a defect (occurrence) at the point where the distance exceeds the threshold. In order to obtain the position in the third direction D3 with higher accuracy, the photographing device 21 may also include a depth sensor.
[0068] For example, the photographing device 21 photographs the powder bed 205 at multiple positions in the first direction D1 and the second direction D2. The processing device 11 arranges and joins the obtained images in the first direction D1 and the second direction D2 to obtain an overall image. The processing device 11 calculates the distance between the position of each point and the average position in the overall image.
[0069] The photographing device 21 may also photograph the solidified portion 210 after irradiation with the laser 150 and before supplying a new layer of the metal powder 201 to obtain an image (third image). For example, the processing device 11 joins the images of the various regions of the solidified portion 210 together to obtain an overall image. The processing device 11 calculates the position of each point in the solidified portion 210 in the third direction D3 and the average position of these from the obtained image. The processing device 11 calculates the distance (difference) between the position of each point and the average position. The condition (threshold) for the distance is pre-set. The processing device 11 determines that there is a defect at a point where the distance exceeds the threshold.
[0070] The processing device 11 may also detect splashes existing above the solidified portion 210 from the overall image. For example, an area where the position on the third direction D3 is higher than a predetermined threshold value compared to the average position is counted as splashes. The processing device 11 determines the area where the splashes are detected as a defective area. The processing device 11 may also determine an area where there are more splashes than a predetermined number within a predetermined area as a defective area. In addition, if the metal powder 201 solidifies above an area where splashes exist, the possibility of defects occurring is high. Therefore, it may also be considered that there are defects (occurrence) in an area located above an area where splashes exist.
[0071] A plurality of imaging devices 21 may be provided. For example, an imaging device 21 that images each region during irradiation with the laser 150 and another imaging device 21 that images the powder bed 205 or the solidified portion 210 before or after irradiation with the laser 150 may be provided.
[0072] The temperature sensor 22 measures the temperature of each part during the additive manufacturing process. Figure 5 The temperature of the weld bead 211a, the temperature of the weld bead 211b, the temperature of the weld bead 211c, or the temperature of the molten pool 220 immediately after solidification is measured to generate second data indicating the temperature.
[0073] When the processing device 11 obtains the second data, it refers to the database stored in the storage device 14. The database includes conditions for judging the presence or absence of defects based on the second data. For example, the database includes conditions (threshold values) for the temperature of the weld bead 211a, the temperature of the weld bead 211b, the temperature of the weld bead 211c, and the temperature of the molten pool 220. The processing device 11 compares the multiple temperatures included in the second data with the multiple conditions, respectively, to judge the presence or absence of defects. As an example, when the temperature of the weld bead 211a or the temperature of the molten pool 220 just after solidification is lower than the threshold value, it is judged that there is a defect.
[0074] For example, when the temperature of any one of the weld beads 211a, 211b, and 211c is lower than the threshold value, the temperature difference between the weld beads 211a, 211b, and 211c may cause cracks or thermal strains in the solidified portion 210. In addition, if the width of any one of the weld beads changes, the pattern density changes. If the pattern density changes greatly, poor welding or voids related to poor welding will occur, which will cause defects.
[0075] The database may also include information related to the types of defects. For example, multiple conditions corresponding to multiple types of defects are set for the temperature of the weld bead 211a, the weld bead 211b, or the molten pool 220. The processing device 11 determines the presence and type of defects based on the multiple conditions contained in the database. The existence of defects can also be represented by probability. For example, multiple conditions are set for multiple data respectively. The probability of the existence of defects is pre-set for each condition. When the conditions are met, it is judged that the defect exists with the set probability. When multiple conditions are met, the probability of the existence of defects increases.
[0076] The temperature sensor 22 follows the irradiation of the laser beam 150 similarly to the imaging device 21, and measures the temperature of each region of each layer. Figure 6 (a) shows the area B 11 ~B xyWhen the laser beam 150 is irradiated on each of the weld beads 211 a and 211 b , and the molten pool 220 , the temperature sensor 22 measures the temperatures of the weld beads 211 a and 211 b .
[0077] The temperature sensor 22 may also measure the temperature of each region of the powder bed 205 after a new layer of the metal powder 201 is supplied and before the laser 150 is irradiated. For example, the processing device 11 generates a temperature distribution of the powder bed 205 based on a plurality of measurement results. The processing device 11 calculates an average temperature, a temperature deviation, etc. based on the temperature distribution. The processing device 11 compares the calculated value with a pre-set condition (threshold value) to determine the presence or absence of a defect.
[0078] The temperature sensor 22 may also measure the temperature of each region after irradiation with the laser 150 and before supplying a new layer of the metal powder 201. The processing device 11 generates the temperature distribution of the powder bed 205 and the solidified portion 210 from the plurality of measurement results.
[0079] For example, if the temperature distribution is large, a deviation of residual stress, uneven shape, etc. may occur in the layer. When the temperature distribution is above a preset threshold, there is a high possibility that the layer and the upper and lower adjacent layers will have a defect in the shape. The processing device 11 determines that there are defects in the layer and the adjacent layers.
[0080] The processing device 11 stores the judgment result in the storage device 14. If it is judged that there is a defect, the processing device 11 stores the position of the defect in the storage device 14. When it is judged that there is a defect, the processing device 11 may also associate the image used for the judgment with the judgment result and the position of the defect. For example, the quality data for the manufactured article includes the judgment result of the presence or absence of a defect, the position of the defect, and the image used for judging the presence of the defect.
[0081] Figure 7 It is a flowchart showing the operation of the monitoring system according to the embodiment.
[0082] The collecting device collects information in additive manufacturing (step S1). The processing device 11 obtains the collected information (step S2). The processing device 11 uses the information to determine whether there is a defect at the location where the information is collected (step S3). In the determination, each data contained in the collected information is compared with a pre-set condition. The processing device 11 generates quality data indicating the presence or absence of a defect (step S4).
[0083] Advantages of the embodiment will be described.
[0084] Sometimes, there are defects in items manufactured by additive manufacturing. An example of a defect in an item is a void. The presence or absence of a defect and the number of defects are related to the quality of the item. If there is a defect or the number of defects is large, it is considered to be of poor quality. The quality affects, for example, the price of the item, the application object of the item, etc. Alternatively, items of poor quality are removed from the transaction object. In other words, in order to determine the price of the item, the application object, the feasibility of the transaction, etc., it is preferable to be able to grasp the quality of the manufactured item.
[0085] There is also a method of conducting non-destructive inspection on manufactured products to investigate the presence and number of defects. However, this method requires time and money for inspection. Therefore, a technology that can more easily grasp the quality of products is desired.
[0086] According to the monitoring system 1 of the embodiment, the collecting device collects information in the additive manufacturing. The collecting device is the imaging device 21 or the temperature sensor 22. The processing device 11 uses the collected information to determine whether there is a defect. In addition, the processing device 11 generates quality data including the determination result.
[0087] By collecting information in additive manufacturing, there is no need to set up an additional inspection process after the manufacture of the item. In addition, by confirming the quality data, the user can understand the possibility of defects in the manufactured item. For example, the user can understand the possibility of defects, the number of defects that may exist, etc. According to the embodiment, the quality of the additively manufactured item can be more easily understood.
[0088] Furthermore, the monitoring system 1 of the embodiment can be added later to an existing additional manufacturing apparatus 100. By adding the monitoring system 1 to an existing additional manufacturing apparatus 100, the cost required to build an additional manufacturing apparatus with a defect determination function can be reduced compared to a newly purchased additional manufacturing apparatus.
[0089] The quality data preferably includes the position of the defect for the manufactured article. The user can easily understand where the defect may exist in the article. In addition, the quality data preferably includes an image used for defect determination. The user can easily confirm the reliability of the determination result obtained by the processing device 11. In order for the user to easily understand the position of the defect in the image, the position of the defect may also be marked in the image.
[0090] The processing device 11 may also use a second model for judging the presence or absence of a defect instead of the judgment based on a preset condition. The second model includes, for example, a neural network. If the processing device 11 obtains the first data or the second data, the first data or the second data is input into the second model. The second model outputs data indicating the presence or absence of a defect. The processing device 11 obtains the output of the second model as a judgment result. The second model is learned using a plurality of learning data. The learning data includes the first data, the second data, and labels for these data. The labels indicate the presence or absence of a defect and the type of defect.
[0091] The processing device 11 can combine the judgment based on the preset conditions with the judgment based on the second model to obtain the final judgment result. For example, when the processing device 11 judges that there is a defect based on the preset conditions, it judges that there is a defect in the area. Even if the processing device 11 judges that there is no defect based on the preset conditions, the first data or the second data is input into the second model. If the existence of a defect is shown by the second model, the processing device 11 judges that there is a defect in the area. By combining the second model, the existence of a defect that is difficult to judge only by the conditions can be judged with higher accuracy.
[0092] Figure 8 It is a block diagram showing the configuration of an additive manufacturing system according to an embodiment.
[0093] In the additive manufacturing system 2, the processing conditions of the additive manufacturing device 100 may also be changed according to the judgment result obtained by the monitoring system 1. Specifically, when it is judged that there is a defect, the processing device 11 changes the processing conditions of the additive manufacturing. The processing device 11 stores the changed processing conditions in the storage device 14. The control device 101 controls each component of the additive manufacturing device 100 according to the changed processing conditions.
[0094] For example, it is determined that a defect exists in a region of a portion of the weld bead 211. When irradiating the laser 150 to another region adjacent to the region, the processing conditions are changed. There is a possibility that the defect can be corrected. As an example, when it is determined that there is an undercut based on the first data, when irradiating the adjacent region with the laser 150, the irradiation time is extended or the irradiation energy is increased. Thereby, a portion of the metal powder 201 melted in another region can flow to the region with the undercut, and the undercut can be corrected.
[0095] The database includes information related to the processing conditions of additive manufacturing. The database includes the correspondence between the value of the first data and the processing conditions. If it is determined that there is a defect, the processing device 11 accesses the database. The processing device 11 obtains the processing conditions corresponding to the first data used for judgment. The processing device 11 saves the obtained processing conditions in the storage device 14. As a result, the pre-set processing conditions are changed to processing conditions for correcting the defects. The control device 101 controls the additive manufacturing device 100 according to the changed processing conditions.
[0096] The processing conditions can also be changed according to the type and degree of the defect. For example, when the undercut is large, the irradiation time is further extended or the irradiation energy is further increased when irradiating the laser 150 to another area. As a result, the amount of melted metal powder 201 increases, and the molten metal becomes easier to flow to the undercut. The possibility of defect correction can be increased.
[0097] The possibility of correction may also be set according to the type of each first data. If the processing device 11 determines that there is a defect, it accesses the database and refers to the possibility of correction for the first data that serves as the basis for the judgment. If the correction can be made, the processing device 11 obtains the changed processing conditions for correcting the defect from the database. If the correction cannot be made, the processing device 11 does not change the processing conditions.
[0098] The additive manufacturing device 100 may also repeatedly manufacture the same article. It may also change the processing conditions when manufacturing the next article based on the judgment result when manufacturing the previous article. For example, if the processing device 11 judges that there is a defect when manufacturing the previous article, the processing conditions at the position judged to be a defect are changed when manufacturing the next article. In this way, the occurrence of defects is suppressed when manufacturing the next article.
[0099] Fig. 9 It is a flowchart showing the operation of the monitoring system according to the embodiment.
[0100] Reference Fig. 9 , the operation of the monitoring system 1 when the processing conditions are changed will be described. Figure 7Similarly to the flowchart shown, the collecting device collects information in the additive manufacturing (step S1). The processing device 11 obtains the information (step S2) and determines whether there is a defect (step S3). The processing device 11 determines whether a defect exists (step S11). When it is determined that a defect exists, the processing device 11 refers to the database to determine whether the defect can be corrected (step S12). When the defect can be corrected, the processing device 11 changes the processing conditions (step S13). In this way, the generated defect can be corrected. Alternatively, with respect to the next item, the generation of the defect can be suppressed.
[0101] After determining that the defect does not exist in step S11, after determining that correction is not possible in step S12, or after step S13, the processing device 11 saves the result in the storage device 14 (step S14). Specifically, the processing device 11 saves the judgment result, the feasibility of correction of the defect, the changed processing conditions, etc. for the area where the presence or absence of the defect is judged. The processing device 11 determines whether the additive manufacturing is completed (step S15). If not completed, step S1 is executed again. Alternatively, the steps after step S2 may be executed after the information of each area in the additive manufacturing is collected. In this case, steps S2 to S12 are repeated until the processing based on each information is completed. If the judgment of each area is completed, the processing device 11 generates quality data (step S4).
[0102] The processing device 11 may also determine the quality of the article based on the determination results of each area. For example, the quality data may also include information related to the quality of the article.
[0103] Fig.10 It is a flowchart showing the operation of the monitoring system according to the embodiment.
[0104] The processing device 11 may also be Figure 7 or Fig. 9 In step S4 of the flowchart shown in FIG. Fig.10 The processing device 11 accesses the storage device 14 and refers to the judgment result of each area (step S41). The processing device 11 judges whether a defect is judged to exist in any area (step S42). If a defect is not judged to exist in any area, the processing device 11 judges the quality of the article to be excellent (step S43).
[0105] For example, the database contains information about defects and the correspondence between defect patterns. When it is determined that there are defects in any area, the processing device 11 accesses the database and compares the number of defects, the location of defects, the type of defects and other information with the defect pattern (step S44). For example, the database contains data indicating whether each defect pattern is allowable. The processing device 11 determines whether the obtained defect pattern is allowable (step S45). When the defect pattern is allowable, the processing device 11 determines the quality as allowable (step S46). When the defect pattern is not allowable, the processing device 11 determines the quality as poor (step S47).
[0106] Excellent means better than acceptable. Acceptable means better than unacceptable. Here, an example of classifying quality into three grades is described. Quality may also be classified into four or more grades based on the presence or absence of defects, defect mode, etc.
[0107] The processing device 11 generates a report as quality data (step S48). For example, the report includes the presence or absence of defects, the number of defects, the type of defects, the changed processing conditions, the defect mode, the image of the area judged to be defective, and the quality. The processing device 11 displays the report on the display device 13 (step S49). Alternatively, the processing device 11 outputs the report in a specified format such as "Comma Separated Value (CSV)", and can also write it to a recording medium such as an SD card. The processing device 11 can use File Transfer Protocol (FTP) to send data to an external server, and can also perform database communication and use Open Database Connectivity (ODBC) to insert data into an external database server.
[0108] Fig.11 This is a schematic diagram showing the hardware configuration.
[0109] For example, the processing device 11 of the monitoring system 1 according to the embodiment is a computer, and includes a ROM (Read Only Memory) 11 a , a RAM (Random Access Memory) 11 b , a CPU (Central Processing Unit) 11 c , and a HDD (Hard Disk Drive) 11 d .
[0110] The ROM 11 a stores a program for controlling the operation of the computer. The ROM 11 a stores a program necessary for realizing the above-mentioned processing in the computer.
[0111] RAM11b functions as a storage area where the program stored in ROM11a is expanded. CPU11c includes a processing circuit. CPU11c reads the control program stored in ROM11a and controls the operation of the computer according to the control program. In addition, CPU11c expands various data obtained by the operation of the computer in RAM11b. HDD11d stores data required for reading and data obtained during reading. HDD11d can be used as Figure 2 The storage device 14 shown functions.
[0112] The processing device 11 may include eMMC (embedded Multi Media Card), SSD (Solid State Drive), SSHD (Solid State Hybrid Drive), etc. instead of the HDD 11d. The processing and functions of each processing device 11 may also be realized by the cooperation of more computers.
[0113] The input device 12 includes at least one of a mouse, a keyboard, and a touch panel. The display device 13 includes at least one of a monitor and a projector. A device that functions as both the input device 12 and the display device 13, such as a touch panel, may be used.
[0114] According to the monitoring system, processing device or monitoring method described above, the quality of additively manufactured products can be more easily grasped. In addition, the same effect can be obtained by using a program for operating a computer as a processing device.
[0115] The above-mentioned various data processing can be recorded on a disk (floppy disk and hard disk, etc.), an optical disk (CD-ROM, CD-R, CD-RW, DVD-ROM, DVD±R, DVD±RW, etc.), a semiconductor memory or other recording media as a program that can be executed by a computer.
[0116] For example, data recorded in a recording medium can be read out by a computer (or incorporated into a system). In the recording medium, the recording format (storage format) is arbitrary. For example, a computer reads a program from a recording medium and causes a CPU to execute instructions recorded in the program based on the program. In a computer, a program can also be obtained (or read out) through a network.
[0117] Implementations may include the following features.
[0118] (Feature 1)
[0119] A monitoring system, comprising:
[0120] A collecting device for collecting information of a solidified portion that has solidified in additive manufacturing in which a plurality of layers are formed by repeating melting and solidification of metal powder; and
[0121] The processing device determines the presence or absence of a defect in the solidified portion using the information, and generates quality data indicating the presence or absence of the defect.
[0122] (Feature 2)
[0123] The monitoring system according to feature 1, wherein:
[0124] The collecting device includes a photographing device,
[0125] The information includes images,
[0126] The processing device determines the presence or absence of the defect in the solidified portion based on the image.
[0127] (Feature 3)
[0128] The monitoring system according to feature 2, wherein:
[0129] The information includes a first image, wherein the first image captures a first weld bead and a second weld bead included in the solidified portion, a molten pool in the process of melting, and a heat source.
[0130] The processing device acquires first data from the first image, the first data including one or more data selected from the width of the first weld bead immediately after solidification, the contour of the first weld bead, the surface shape of the first weld bead, the width of the second weld bead adjacent to the first weld bead, the contour of the second weld bead, the width of the second weld bead, the contour of the molten pool, and the size of the heat source,
[0131] The processing device determines the presence or absence of the defect in the solidified portion based on the first data.
[0132] (Feature 4)
[0133] The monitoring system according to feature 3, wherein:
[0134] The processing device refers to a condition preset for the first data, and determines the presence or absence of the defect by comparing the first data with the condition.
[0135] (Feature 5)
[0136] The monitoring system according to feature 3 or 4, wherein:
[0137] The processing device acquires the first data including the contour of the first weld bead, the contour of the molten pool, and the contour of the heat source by inputting the first image into the first model.
[0138] (Feature 6)
[0139] The monitoring system according to feature 3, wherein:
[0140] The processing device extracts differences between the plurality of first images, and determines the presence or absence of the defect in the solidified portion based on the differences.
[0141] (Feature 7)
[0142] The monitoring system according to feature 2, wherein:
[0143] The information further comprises a second image, which captures the powder bed on which the metal powder is applied after a new layer of the metal powder has been supplied and before the metal powder has melted.
[0144] The processing device acquires the surface shape of the powder bed from the second image, and determines the presence or absence of the defect in the solidified portion based on the surface shape.
[0145] (Feature 8)
[0146] The monitoring system according to feature 2, wherein:
[0147] The information further includes a third image, the third image photographing the solidified portion after the metal powder is melted and solidified and before a new layer of the metal powder is supplied,
[0148] The processing device acquires the surface shape of the solidified portion from the third image, and determines the presence or absence of the defect in the solidified portion based on the surface shape.
[0149] (Feature 9)
[0150] The monitoring system according to any one of features 2 to 8, wherein:
[0151] When the processing device determines that the defect exists, the image used for the determination is added to the quality data.
[0152] (Feature 10)
[0153] A monitoring system according to any one of features 1 to 9, wherein:
[0154] The invention further comprises an illumination device for irradiating the coagulation part.
[0155] (Feature 11)
[0156] The monitoring system according to any one of features 1 to 10, wherein:
[0157] The collecting device comprises a temperature sensor,
[0158] The information includes second data indicating the temperature of the molten pool during melting and the temperature of the solidified portion.
[0159] The processing device determines the presence or absence of the defect in the solidified portion based on the second data.
[0160] (Feature 12)
[0161] The monitoring system according to any one of features 1 to 11, wherein:
[0162] The collecting device collects the information of the solidified portion when each of the plurality of layers is formed.
[0163] (Feature 13)
[0164] The monitoring system according to any one of features 1 to 12, wherein
[0165] The collecting device collects a plurality of the information in the additive manufacturing.
[0166] The processing device determines whether or not the defects exist in a plurality of regions of the solidified portion.
[0167] The quality data includes the presence or absence of the defect and the position of the region including the defect.
[0168] (Feature 14)
[0169] A monitoring system according to any one of features 1 to 13, wherein:
[0170] The processing device changes processing conditions during additive manufacturing based on the determination result of the presence or absence of the defect.
[0171] (Feature 15)
[0172] An additive manufacturing system, comprising:
[0173] A monitoring system according to any one of features 1 to 14, and an additive manufacturing device that performs additive manufacturing.
[0174] Several embodiments of the present invention are illustrated above, but these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other ways, and various omissions, substitutions, changes, etc. can be made without departing from the scope of the subject matter of the invention. These embodiments and their variations are included in the scope and subject matter of the invention, and are included in the scope of the invention described in the claims and their equivalents. In addition, the aforementioned embodiments can be implemented in combination with each other.
[0175] Description of Reference Numerals
[0176] 1: monitoring system, 2: additive manufacturing system, 11: processing device, 12: input device, 13: display device, 14: storage device, 21: shooting device, 22: temperature sensor, 23: lighting device, 100: additive manufacturing device, 101: control device, 110: first container, 111: first workbench, 120: second container, 121: second workbench, 130: coating machine, 140: irradiation device, 141: optical system, 150: laser, 201: metal powder, 205: powder bed, 210: solidification part, 211, 211a~211c: weld bead, 220: molten pool, D1: first direction, D2: second direction, D3: third direction, Li1~Li3: line segment.
Claims
1. A monitoring system, wherein: The invention comprises: a collecting device for collecting information of a solidified solidified portion in an additive manufacturing process in which a plurality of layers are formed by repeatedly melting and solidifying metal powder; and a processing device for using the information to judge whether there is a defect in the solidified portion and generate quality data indicating whether there is a defect, wherein the collecting device comprises a photographing device, the information comprises an image, the processing device judges whether there is the defect in the solidified portion based on the image, the information comprises a first image, the first image photographs a first weld bead and a second weld bead contained in the solidified portion, a molten pool in melting, and a heat source, and the processing device uses the information to judge whether there is a defect in the solidified portion and generate quality data indicating whether there is a defect, wherein the collecting device comprises a photographing device, the information comprises an image, the processing device judges whether there is the defect in the solidified portion based on the image, the information comprises a first image, the first image photographs a first weld bead and a second weld bead contained in the solidified portion, a molten pool in melting, and a heat source, and the processing device The first image obtains first data, and the first data includes one or more data selected from the width of the first weld bead just after solidification, the contour of the first weld bead, the surface shape of the first weld bead, the width of the second weld bead adjacent to the first weld bead, the contour of the second weld bead, the width of the second weld bead, the contour of the molten pool, and the size of the heat source. The processing device determines the presence or absence of the defect in the solidified portion based on the first data. The processing device extracts the difference between the multiple first images, and determines the presence or absence of the defect in the solidified portion based on the difference.
2. The monitoring system according to claim 1, wherein: The processing device refers to a condition preset for the first data, and determines the presence or absence of the defect by comparing the first data with the condition.
3. The monitoring system according to claim 1 or 2, wherein: The processing device acquires the first data including the contour of the first weld bead, the contour of the molten pool, and the contour of the heat source by inputting the first image into the first model.
4. The monitoring system according to claim 1 or 2, wherein: When the processing device determines that the defect exists, the image used for the determination is added to the quality data.
5. The monitoring system according to claim 1 or 2, wherein: The invention further comprises a lighting device for irradiating the coagulation part.
6. The monitoring system according to claim 1 or 2, wherein: The collecting device includes a temperature sensor, the information includes second data, the second data indicates the temperature of a molten pool during melting and the temperature of the solidified portion, and the processing device determines the presence or absence of the defect in the solidified portion based on the second data.
7. The monitoring system according to claim 1 or 2, wherein: The collecting device collects the information of the solidified portion when each of the plurality of layers is formed.
8. The monitoring system according to claim 1 or 2, wherein: The collecting device collects a plurality of the information in additive manufacturing, the processing device determines whether the defects exist in a plurality of regions of the solidified portion, and the quality data includes the presence or absence of the defects and the positions of the regions containing the defects.
9. The monitoring system according to claim 1 or 2, wherein: The processing device changes processing conditions during additive manufacturing based on the determination result of the presence or absence of the defect.
10. An additive manufacturing system, wherein: It comprises: the monitoring system according to claim 1 or 2; and an additive manufacturing device for performing additive manufacturing.
11. A monitoring system, wherein: The invention comprises: a collecting device for collecting information of a solidified solidified portion in additive manufacturing in which a plurality of layers are formed by repeatedly melting and solidifying metal powder; and a processing device for using the information to judge whether or not there are defects in the solidified portion and generate quality data indicating whether or not there are defects, wherein the collecting device comprises a photographing device, the information comprises an image, the processing device judges whether or not there are defects in the solidified portion based on the image, the information further comprises a second image, the second image photographs a powder bed covered with the metal powder after a new layer of the metal powder is supplied and before the metal powder is melted, the processing device obtains a surface shape of the powder bed from the second image, judges whether or not there are defects in the solidified portion based on the surface shape, and the processing device extracts differences between a plurality of the second images, and judges whether or not there are defects in the solidified portion based on the differences.
12. The monitoring system according to claim 11, wherein: The processing device changes processing conditions during additive manufacturing based on the determination result of the presence or absence of the defect.
13. A monitoring system, wherein: The invention comprises: a collecting device for collecting information of a solidified solidified portion in additive manufacturing that forms a plurality of layers by repeating the melting and solidification of metal powder; and a processing device for using the information to judge the presence or absence of defects in the solidified portion and generate quality data indicating the presence or absence of the defects, wherein the collecting device comprises a photographing device, the information comprises an image, the processing device judges the presence or absence of the defects in the solidified portion based on the image, the information further comprises a third image, the third image photographs the solidified portion after the metal powder is melted and solidified and before a new layer of the metal powder is supplied, the processing device obtains a surface shape of the solidified portion from the third image, judges the presence or absence of the defects in the solidified portion based on the surface shape, and the processing device extracts differences between a plurality of the third images, and judges the presence or absence of the defects in the solidified portion based on the differences.
14. The monitoring system according to claim 13, wherein: The processing device changes processing conditions during additive manufacturing based on the determination result of the presence or absence of the defect.
