Methods and systems for detecting impurities in additive manufacturing materials

Abstract

Methods and systems for detecting impurities in additively manufactured materials are disclosed. An example method for detecting impurities in additively manufactured materials includes: irradiating a sample of the additively manufactured material with light by a light source; simultaneously irradiating the sample with light by a camera acquiring image data of the sample; and processing the image data to determine the amount of impurities in the sample of the additively manufactured material. An example system for detecting impurities in additively manufactured materials includes: a light source for irradiating a sample of the additively manufactured material with light; a camera for acquiring image data of the sample while irradiating the sample with light; and a computing device having one or more processors configured to execute instructions stored in a memory to process the image data, thereby determining the amount of impurities in the sample of the additively manufactured material.

Description

TECHNICAL FIELD

[0001] The present disclosure relates generally to methods and systems for detecting impurities in additive manufacturing materials, and more particularly to processing image data of an additive manufacturing material sample to determine an amount of impurities in the additive manufacturing material sample. BACKGROUND

[0002] The quality of powder used in additive manufacturing (AM) methods can affect the quality of parts manufactured therefrom. Particle size factors affect the flowability and thickness of each powder layer in the build box. For high performance applications, it can be important to identify additional factors such as the type, quantity, and size of particulate contaminants that can be present in the powder. Contaminants can be introduced during powder manufacturing, handling, or during the build process itself. When contaminants are mixed into a batch of powder, the contaminants contained in the batch of powder can be introduced into a part, and the contaminants can remain as discrete particles or as non-fused interfaces that act as stress concentrators.

[0003] The presence of contaminants can shorten the service life of a part due to the increased likelihood of fatigue cracking.

[0004] Currently, an operator uses a microscope to inspect an additive manufacturing powder sample for foreign object debris (FOD) or contaminants. The operator determines a quantitative count of FOD in the powder sample by judgment. This manual process is both time consuming and tedious, and is prone to underestimating the amount of FOD in the additive manufacturing powder sample. SUMMARY

[0005] In an example, a method for detecting impurities in an additive manufacturing material is described, the method comprising: illuminating a sample of the additive manufacturing material with light by a light source; causing a camera to acquire image data of the sample while the sample is illuminated with light; and processing the image data to determine an amount of impurities in the sample of the additive manufacturing material.

[0006] In another example, a system for detecting impurities in an additive manufacturing material is described, the system comprising: a light source to illuminate a sample of the additive manufacturing material with light; a camera to acquire image data of the sample while the sample is illuminated with light; and a computing device having one or more processors configured to execute instructions stored in a memory to process the image data to determine an amount of impurities in the sample of the additive manufacturing material.

[0007] In yet another example, an additive manufacturing system for detecting impurities in additive manufacturing material is described, the system comprising: an additive manufacturing machine to manufacture a part using a supply of additive manufacturing material; a collection receptacle to store remaining additive manufacturing material from the supply of additive manufacturing material after manufacturing the part; a light source to illuminate a sample of the remaining additive manufacturing material with light; a camera to acquire image data of the sample while the sample of the remaining additive manufacturing material is illuminated with light; and a computing device having one or more processors configured to execute instructions stored in memory to process the image data to determine an amount of impurities in the sample of the remaining additive manufacturing material.

[0008] The features, functions, and benefits can be achieved independently in various examples or can be combined in other examples, as desired. Other details BRIEF DESCRIPTION OF DRAWINGS

[0009] The novel features described herein are believed to be of particular value in the art. However, it should be understood that the illustrative examples, while having the best mode of practicing the application in accordance with the knowledge of those skilled in the art, and that various

[0010] Figure 1 A system for detecting impurities in additive manufacturing material is shown in accordance with an example implementation.

[0011] Figure 2 A conceptual image based on image data of a sample of additive manufacturing material acquired by a camera is shown in accordance with an example implementation.

[0012] Figure 3 Another conceptual image based on image data of a sample of additive manufacturing material acquired by a camera is shown in accordance with an example implementation.

[0013] Figure 4 Another conceptual image based on image data of a sample of additive manufacturing material acquired by a camera is shown in accordance with an example implementation.

[0014] Figure 5 Another conceptual image based on image data of a sample of additive manufacturing material acquired by a camera is shown in accordance with an example implementation.

[0015] Figure 6 Another conceptual image based on image data of a sample of additive manufacturing material acquired by a camera is shown in accordance with an example implementation.

[0016] Figure 7Another conceptual image based on image data of a sample of additive manufacturing material acquired by a camera is shown, according to an example embodiment.

[0017] Figure 8 Another example of an image acquired by a camera while illuminating a sample of additive manufacturing material with UV light is shown, according to an example embodiment.

[0018] Figure 9 An output of an image processing technique applied to an image of Figure 8 is shown, according to an example embodiment.

[0019] Figure 10 Another example of an image acquired by a camera while illuminating a sample of additive manufacturing material with UV light is shown, according to an example embodiment.

[0020] Figure 11 An output of an image processing technique applied to an image of Figure 10 is shown, according to an example embodiment.

[0021] Figure 12 An example image mask is shown, according to an example embodiment.

[0022] Figure 13A An example of an additive manufacturing system for detecting impurities in additive manufacturing material is shown, according to an example embodiment.

[0023] Figure 13B An example of an additive manufacturing machine is shown, according to an example embodiment.

[0024] Figure 14 A flowchart of an example of a method for detecting impurities in additive manufacturing material is shown, according to an example embodiment. DETAILED DESCRIPTION

[0025] The disclosed examples will now be described more fully below with reference to the accompanying drawings, in which some, but not all, disclosed examples are shown. Indeed, a variety of different examples can be described and should be understood as being within the scope of the present disclosure. Furthermore, the disclosed examples can be used in any number of contexts, including as examples of methods, systems, devices, components, and computer program products.

[0026] In an example, a method for detecting impurities in additive manufacturing material is described, the method comprising illuminating a sample of additive manufacturing material with light by a light source, and causing a camera to acquire image data of the sample while the sample of additive manufacturing material is illuminated with light. Next, the method comprises processing the image data to determine an amount of impurities in the sample of additive manufacturing material.

[0027] Using the methods described herein, automated detection of contaminants (e.g., impurities and / or foreign object debris) in additive manufacturing materials can be achieved through computer vision and image data processing techniques. A sample of the additive manufacturing material is illuminated with light of different wavelengths, and high resolution images of the additive manufacturing material can be acquired for processing.

[0028] The example methods and systems described herein can eliminate the need for an operator to inspect additive manufacturing powder for contaminants or foreign object debris and can enable more accurate identification and quantification of foreign object debris. The amount of foreign object debris in a sample of additive manufacturing material can affect the quality and mechanical properties (e.g., fatigue life and tensile strength) of a final additive manufactured part. Thus, determining the amount of contaminants can be useful in deciding whether to replace the additive manufacturing material.

[0029] For example, an example method for detecting impurities in additive manufacturing materials can be used in an additive manufacturing system. An example additive manufacturing system can include an additive manufacturing machine to manufacture parts using a supply of additive manufacturing material, a collection receptacle to store remaining additive manufacturing material from the supply of additive manufacturing material after manufacturing a part, a light source to illuminate a sample of the remaining additive manufacturing material with light, a camera to acquire image data of the sample while the sample is illuminated with light, and a computing device having one or more processors configured to execute instructions stored in memory to process the image data to determine an amount of impurities in the sample of the remaining additive manufacturing material. At least a portion of the remaining additive manufacturing material can be replaced, e.g., for further manufacturing of parts, when the amount of impurities in the sample of the remaining additive manufacturing material exceeds a threshold value.

[0030] Referring now to the drawings, Figure 1 A system 100 for detecting impurities in additive manufacturing materials is shown in accordance with an example implementation. The system 100 includes a light source 102 to illuminate a sample 104 of additive manufacturing material 106 with light 107, a camera 108 to acquire image data 109 of the sample 104 while the sample 104 is illuminated with light 107, and a computing device 110 having one or more processors 112 configured to execute instructions 114 stored in memory 116 to process the image data 109 to determine an amount of impurities in the sample 104 of additive manufacturing material 106.

[0031] The light source 102 and the camera 108 are communicatively coupled to the computing device 110. For example, the light source 102 and the camera 108 can be in wired or wireless communication with the computing device 110. The computing device 110 can send instructions to and control the operation of the light source 102 and the camera 108, and the light source 102 and the camera 108 can provide output to the computing device 110.

[0032] The light source 102 can include an ultraviolet (UV) light source for illuminating the sample 104 with light having wavelengths in the UV spectrum. As an example, the light source 102 can illuminate the sample 104 with light having wavelengths between about 100 nanometers (nm) and about 500 nm.

[0033] In an example, the system 100 can also include another light source 118. In this configuration, the light source 102 can be considered a first light source that illuminates the sample 104 of the additive manufacturing material 106 with light of a first wavelength, and the light source 118 can be considered a second light source for illuminating the sample 104 of the additive manufacturing material 106 with light of a second wavelength. For example, the first wavelength can be 100 nm, and the second wavelength can be 385 nm.

[0034] The additive manufacturing material 106 can be contained within a container, and can include many types of materials, such as polymers (e.g., polycarbonate, nylon, epoxy), ceramics (silicon dioxide or glass), and metals (steel, titanium alloy, aluminum alloy, etc.). The additive manufacturing material 106 can also have a variety of forms, such as a powder, a liquid, or a combination.

[0035] The sample 104 of the additive manufacturing material 106 can be a top layer of the additive manufacturing material 106, for example, such that the light source 102 illuminates the top layer, and the camera 108 acquires image data of the sample 104. The light source 102 and the camera 108 can be mounted to illuminate the sample 104 and acquire image data, and thus, the light source 102 and the camera 108 can be mounted above the container of the additive manufacturing material 106.

[0036] The camera 108 can be a high-resolution camera for capturing images. In an example, the camera 108 acquires (or otherwise collects or obtains) image data including pixels or voxels. The camera 108 (or the computing device 110) can then generate or produce an image based on the acquired image data. The image then includes, for example, a representation of the sample 104 in the image.

[0037] The computing device 110 receives image data from the camera 108 and processes the image data to determine an amount of impurities in the sample 104 of the additive manufacturing material 106. To perform the above-mentioned functions, the computing device 110 includes a communication interface 120, an output interface 122, and each of the components of the computing device 110 is connected to a communication bus 124. The computing device 110 can also include hardware to enable communication within the computing device 110 and between the computing device 110 and other devices (not shown). This hardware can include, for example, a transmitter, a receiver, and an antenna.

[0038] The communication interface 120 can be a wireless interface and / or one or more wired interfaces that allow for short- and long-range communication to one or more networks or to one or more remote devices. Such a wireless interface can provide for communication under one or more wireless communication protocols, Bluetooth, WiFi (e.g., Institute of Electrical and Electronics Engineers (IEEE) 802.11 protocols), Long-Term Evolution (LTE), cellular communication, near-field communication (NFC), and / or other wireless communication protocols. Such a wired interface can include an Ethernet interface, a Universal Serial Bus (USB) interface, or a similar interface to communicate via a wire, twisted pair of wires, a coaxial cable, an optical link, a fiber-optic link, or other physical connection to a wired network. Thus, the communication interface 120 can be configured to receive input data from one or more devices and can also be configured to send output data to other devices.

[0039] The memory 116 can take the form of non-transitory computer-readable media, such as one or more computer-readable storage media that can be read or accessed by one or more processors 112. The computer-readable storage media can include volatile and / or non-volatile storage components, such as optical, magnetic, organic, or other storage or disk storage that can be integrated in whole or in part with one or more processors 112. In this regard, the memory 116 can be considered a computer-readable medium. In some examples, the memory 116 can be implemented using a single physical device (e.g., one optical, magnetic, organic, or other storage or disk storage unit), while in other examples, the memory 116 can be implemented using two or more physical devices.

[0040] Thus, the memory 116 is a computer-readable medium, and instructions 114 are stored thereon. The instructions 114 include computer-executable code.

[0041] The one or more processors 112 can be general-purpose processors or special-purpose processors (e.g., digital signal processors, application specific integrated circuits, etc.). The one or more processors 112 can receive inputs from the communication interface 120 and process them to generate outputs stored in the memory 116. The one or more processors 112 can be configured to execute instructions 114 (e.g., computer-readable program instructions) stored in the memory 116 and executable to provide the functionality of the computing device 110 described herein.

[0042] The output interface 122 outputs information for reporting or storage, thus, the output interface 122 can be similar to the communication interface 120 and can also be a wireless interface (e.g., a transmitter) or a wired interface.

[0043] The computing device 110 and / or the processor 112 can output data indicative of the amount of impurities in the sample 104 of the remaining additive manufacturing material 106 to the display 126.

[0044] In an example, in operation, when the instructions 114 are executed by the one or more processors 112 of the computing device 110, cause the one or more processors 112 to perform functions for receiving image data from the camera 108 and processing the image data to determine the amount of impurities in the sample 104 of the additive manufacturing material 106. The instructions 114 can also include a learning model 115, which is built by supervised learning using training images, which is executable to automatically perform the processing and identify the amount of impurities in the sample 104 of the additive manufacturing material 106, which is described below.

[0045] Figures 2 to 7 Conceptual images based on image data of a sample 104 of the additive manufacturing material 106 acquired by a camera are shown, according to example implementations. Figures 2 to 7 The images shown in FIGS. 1-3 are conceptual and the impurities are added in the additive manufacturing material 106 for illustrative purposes only. Thus, in practice, the images shown in FIGS. 1-3 can not be the same as the images acquired by the camera 108. Figures 2 to 7 In FIG. 3, an image of the additive manufacturing material is shown that is artificially modified. Figures 2 to 7 Each of the images shown in FIGS. 1-3 represents the same sample 104 of the additive manufacturing material 106, where the sample 104 is illuminated in each image using a different wavelength of light.

[0046] In Figure 2In some examples, some types of impurities can not be visible when illuminated by certain wavelengths of light, so multiple images can be acquired when illuminated with multiple different wavelengths of light. Thus, in examples, the camera 108 acquires first image data of the sample 104 of the additive manufacturing material 106 while the sample 104 of the additive manufacturing material 106 is illuminated with a first wavelength of light, and then the camera 108 acquires second image data of the sample 104 of the additive manufacturing material 106 while the sample 104 of the additive manufacturing material 106 is illuminated with a second wavelength of light.

[0047] Figures 3 to 7 An additional image acquired by the camera 108 while illuminating the sample 104 of the additive manufacturing material 106 with UV light is shown. Each additional image can be acquired by illuminating the sample 104 of the additive manufacturing material 106 with a different wavelength of UV light. As seen, using different wavelengths provides somewhat different results, and the impurities 130 can be detected by processing these images.

[0048] The amount of impurities in the sample 104 of the additive manufacturing material 106 can be assessed by calculating a fraction of an area of the image that includes impurities to an area of the image that does not include impurities.

[0049] In some examples, some types of impurities can not be visible when illuminated by certain wavelengths of light, so multiple images can be acquired when illuminated with multiple different wavelengths of light. Thus, in examples, the camera 108 acquires first image data of the sample 104 of the additive manufacturing material 106 while the sample 104 of the additive manufacturing material 106 is illuminated with a first wavelength of light, and then the camera 108 acquires second image data of the sample 104 of the additive manufacturing material 106 while the sample 104 of the additive manufacturing material 106 is illuminated with a second wavelength of light.

[0050] The computing device 110 processes the first image data and the second image data to determine the amount of impurities in the sample 104 of the additive manufacturing material 106. The computing device 110 can process the first image data and the second image data to determine the amount of impurities in the sample 104 of the additive manufacturing material 106 by determining a first amount of impurities based on processing the first image data, determining a second amount of impurities based on processing the second image data, and adding the first amount of impurities and the second amount of impurities.

[0051] In some examples, only one light source is used, and the sample 104 of the additive manufacturing material 106 can be illuminated with multiple different wavelengths of light by changing the wavelength of the light of the light source 102 to illuminate the sample 104 of the additive manufacturing material 106 with multiple different wavelengths of light. Then, the camera 108 can acquire multiple image data of the sample 104 while illuminated with each of the multiple different wavelengths of light, and the computing device 110 can process the multiple image data to determine the amount of impurities in the sample 104 of the additive manufacturing material 106.

[0052] Many different computer vision methods can be used to process the image data to identify the contaminant in the image data. Examples include edge detection, color extraction, and Laplacian operators to reliably distinguish the contaminant from the additive manufacturing material.

[0053] Figure 8 Another example of an image acquired by the camera 108 while the sample 104 of additive manufacturing material 106 is illuminated with UV light is shown, according to an example implementation. The contaminant 130 is circled in the image for illustrative purposes.

[0054] Figure 9 The output of the image processing techniques applied to the image of Figure 8 is shown, according to an example implementation. In one example, an edge detection image processing technique can be used to identify points in the image where the image intensity changes by a threshold amount or has a discontinuity. Points where the image intensity changes sharply are often organized as a set of curve segments called edges. When the sample 104 of additive manufacturing material 106 is illuminated with UV light, the contaminant 130 will fluoresce at a greater intensity than the additive manufacturing material 106, and the contaminant 130 can be detected in the image using edge detection and image intensity change techniques.

[0055] In Figure 9 , the outline of the contaminant 130 is derived by processing the image of Figure 8 using edge detection processing.

[0056] Figure 10 Another example of an image acquired by the camera 108 while the sample 104 of additive manufacturing material 106 is illuminated with UV light is shown, according to an example implementation. The contaminant 130 is circled in the image for illustrative purposes.

[0057] Figure 11 The output of the image processing techniques applied to the image of Figure 10 is shown, according to an example implementation. In Figure 11 , the outline of the contaminant 130 is derived by processing the image of Figure 10 using edge detection processing.

[0058] Figure 12 An example image mask is shown, according to an example implementation. This mask can be generated using image segmentation, i.e., assigning a label (debris, background, etc.) to each pixel of the image. Thus, a learning model constructed by supervised learning using training images of manually identified contaminants is implemented to process the image, and a neural network is then trained to output a pixel-wise mask of the image. The learning model can be stored in the memory 116 and, for example, take the form of a portion of the instructions 114.

[0059] For example,Figure 12 The example mask shown is obtained by processing Figure 9 and Figure 11 The image shown is obtained. Once the mask is generated, the percentage of additive manufacturing material 106, including impurities, in the sample 104 can be calculated using pixels associated with fibrous object debris. Using image segmentation, individual pixels in the image are either labeled as or not labeled as fibrous object debris. After creating the image training set, the classification of pixels can be determined by processing the edge-detected images.

[0060] Figure 13A An example of an additive manufacturing system 150 for detecting impurities in additive manufacturing material is shown according to an exemplary embodiment. The additive manufacturing system includes: an additive manufacturing machine 152 for manufacturing part 154 using a supply of additive manufacturing material 106; and a collection reservoir 156 for storing remaining additive manufacturing material from the supply of additive manufacturing material 106 after the part has been manufactured.

[0061] The additive manufacturing system 150 further includes Figure 1 The system 100 shown is for detecting impurities in additive manufacturing material 106. Therefore, the additive manufacturing system 150 includes: a light source 102 for illuminating a sample 104 of remaining additive manufacturing material; a camera 108 for acquiring image data of the sample 104 while illuminating the sample of remaining additive manufacturing material; and a computing device 110 having one or more processors 112 configured to execute instructions 114 stored in a memory 116 to process the image data, thereby determining the amount of impurities in the sample 104 of remaining additive manufacturing material.

[0062] After the part is completed, any remaining additive manufacturing material can be collected. For example, the bed of additive manufacturing machine 152 can be raised, and a vacuum can be used to collect all loose powder into a collection reservoir 156. In this example, a light source 102 and a camera 108 can be mounted above the collection reservoir 156 to illuminate the sample and acquire image data.

[0063] Additive manufacturing machine 152 operates by manufacturing parts in a layer-by-layer manner using multi-layered materials. Additive manufacturing can involve applying liquid or powder material to a work area and then performing a combination of sintering, curing, melting, and / or cutting to produce layers. This process can be repeated thousands of times to construct the desired final part. Depending on the type of manufacturing used, additive manufacturing machine 152 may include components such as printheads or printer nozzles, control mechanisms (e.g., computing devices), molds, etc. A range of processes that find industrial applications for additive manufacturing include direct metal deposition, electron beam melting, polymer processes such as fused filament fabrication (FFF), fused deposition modeling (FDM), solid-phase liquid chromatography (SGC), layered solid fabrication (LOM), and selective laser sintering (SLS) or selective laser melting (SLM), etc. Additive manufacturing machine 152 may include components of any of these processes, or in some examples, additive manufacturing machine 152 may include hybrid machine tools to combine additive manufacturing with subtractive processing.

[0064] Part 154, produced using additive manufacturing machine 152, is constructed by laying material layers one by one on a build platform. This process provides properties comparable to casting.

[0065] The additive manufacturing system 150 can utilize the methods described herein in many useful ways. As an example, based on the amount of impurities in sample 104 of remaining additive manufacturing material, computing device 110 can determine whether the remaining additive manufacturing material should be recycled for use in manufacturing subsequent parts. For example, light source 102 illuminates the top layer of remaining additive manufacturing material in collection reservoir 156, and if the impurities are below a threshold, it is determined that the remaining additive manufacturing material in collection reservoir 156 can be reused for subsequent parts. In this example, the remaining additive manufacturing material can be added back to the storage container comprising additive manufacturing material 106.

[0066] For example, powder of additive manufacturing material 106 is collected in a collection reservoir 156, and the top layer of the collection reservoir 156 is irradiated with UV light (e.g., at 385 nm) to identify impurities. Ideally, the powder will remain clean, but impurities may be introduced during the build process. The additive manufacturing system 150 may therefore include a computing device 110 incorporated therein to automatically analyze the remaining additive manufacturing material. An example output of this analysis is a count of impurities (e.g., possibly 100 parts per million of contaminants), and if the threshold is 200 ppm, the sample of remaining additive manufacturing material is deemed suitable for further use.

[0067] In other examples, based on the amount and location of impurities in the top layer of remaining additive manufacturing material, computing device 110 can determine to remove the top layer of remaining additive manufacturing material and provide a new layer of additive manufacturing material. As an example, a new layer of additive manufacturing material can be recoated onto an area on the build platform. In this example, the removal of the top layer can be performed manually or via a machine component, and additional additive manufacturing material 106 can be added as needed.

[0068] Figure 13B An example of an additive manufacturing machine 152 according to an exemplary embodiment is shown. In this example, the additive manufacturing machine 152 includes a storage container 159 for storing additive manufacturing material 106; a build platform 161 on which a part 154 is built; and a container reservoir 156 for vacuum-drawing remaining additive manufacturing material into the container using a vacuum mechanism 163. When impurities are detected in the remaining manufacturing material, for example, new manufacturing material from the storage container 159 can be provided to the build platform 161.

[0069] In these examples, computing device 110 determines whether the remaining additive manufacturing material has the quality to allow for a successful build.

[0070] Figure 14 A flowchart of an example of a method 200 for detecting impurities in additive manufacturing materials according to an exemplary embodiment is shown. Figure 14 The method 200 shown presents a method that can be used with, for example... Figure 1 The system 100 shown Figure 13A The additive manufacturing system 150 shown Figure 1 and Figure 13A An example of a method used with the computing device 110 shown. Furthermore, the device or system can be used or configured to perform... Figure 14 The logical functions provided herein. In some cases, components of a device and / or system may be configured to perform functions such that these components are actually configured and constructed (with hardware and / or software) to enable such performance. In other examples, components of a device and / or system may be arranged to be suitable for, able to, or adapted to perform these functions, for example, when operated in a particular manner. Method 200 may include one or more operations, functions, or actions shown in one or more of blocks 202-206. Although the blocks are shown in a sequential order, these blocks may also be performed in parallel and / or in an order different from that described herein. Moreover, the individual blocks may be combined into fewer blocks, divided into additional blocks, and / or removed, depending on the desired implementation.

[0071] It should be understood that, for the processes and other processes and methods disclosed herein, the flowchart illustrates the function and operation of one possible implementation of the present example. In this regard, each block or portion of each block may represent a module, segment, or portion of program code, which includes one or more instructions executable by a processor to implement a specific logical function or step in the process. The program code may be stored on any type of computer-readable medium or data storage device (e.g., storage devices including disks or hard disk drives). Furthermore, the program code may be encoded in a machine-readable format on a computer-readable storage medium or on other non-transitory media or articles of art. Computer-readable media may include non-transitory computer-readable media or memory, for example, computer-readable media that store data for a short period of time, such as register memory, processor cache, and random access memory (RAM). Computer-readable media may also include non-transitory media, such as auxiliary or permanent long-term storage devices, such as read-only memory (ROM), optical disks or magnetic disks, and compact disk read-only memory (CD-ROM). Computer-readable media may also be any other volatile or non-volatile storage system. For example, a computer-readable medium may be considered a tangible computer-readable storage medium.

[0072] in addition, Figure 14 Each box or portion of each box in the present disclosure, as well as each box or portion of each box in other processes and methods disclosed herein, may represent a circuit connected by lines to perform a specific logical function of that process. As will be understood by those skilled in the art, alternative implementations are included within the scope of the examples of this disclosure, and depending on the function involved, the functions of these examples of this disclosure may be performed in a different order than that shown or discussed, including substantially simultaneously or in reverse order.

[0073] At box 202, method 200 includes irradiating a sample 104 of additive manufacturing material 106 with light by means of light source 102. In an example, this includes irradiating the sample 104 with light having a wavelength in the ultraviolet spectrum, or with light having a wavelength between about 100 nanometers (nm) and about 500 nm.

[0074] In other examples, the function at box 202 includes changing the wavelength of the light from light source 102 to illuminate the sample 104 of additive manufacturing material 106 with multiple different wavelengths of light.

[0075] At frame 204, method 200 includes having camera 108 acquire image data of sample 104 of additive manufacturing material 106 while illuminating sample 104 of additive manufacturing material 106 with light.

[0076] In some examples, box 204 includes enabling camera 108 to acquire multiple image data of sample 104 while illuminating it with light of each of multiple different wavelengths.

[0077] At box 206, method 200 includes processing image data to determine the amount of impurities in a sample of additively manufactured material. In this example, box 206 includes calculating a fraction of the image data containing the impurities.

[0078] In some examples, when using light of multiple different wavelengths, box 206 may include processing multiple image data acquired with light of multiple different wavelengths to determine the amount of impurities in sample 104 of additive manufacturing material 106.

[0079] In other examples, box 206 may include the use of a learning model that is built using supervised learning based on training images of manually identified impurities.

[0080] In another example, method 200 may include: illuminating a sample 104 of additive manufacturing material 106 with a first light source of a first wavelength and having a camera 108 acquire first image data of the sample; illuminating the sample 104 of additive manufacturing material 106 with a second light source of a second wavelength and having the camera 108 acquire second image data of the sample; and processing the first image data and the second image data to determine the amount of impurities in the sample 104 of additive manufacturing material 106. The processing may include: determining a first impurity quantity based on the processed first image data, determining a second impurity quantity based on the processed second image data, and adding the first impurity quantity and the second impurity quantity together.

[0081] In another example, method 200 may include applying dye 155 to a sample 104 of the additive manufacturing material 106 prior to irradiating the sample 104 of the additive manufacturing material 106. For example, dye 155 may facilitate bonding to fiber particles rather than metal, and may, for example, make certain wavelengths of light more readily reflected and / or fluoresce. Figure 13A Dye 155 is shown as an optional ingredient added to sample 104.

[0082] The exemplary methods and systems described herein eliminate the need for operators to analyze impurities in a batch of additive manufacturing materials; instead, computer vision is used to identify impurities and FOD (FOD). Computer vision technology can also quantify the amount of impurities (per million powder particles). Because computer vision technology can perform this task faster and without human judgment, it increases the likelihood of more accurate impurity counting.

[0083] Furthermore, manufacturers employing powder-based additive manufacturing can utilize the example methods and systems described herein to define a stable and repeatable process for determining whether additive manufacturing powders contain impurities above a threshold.

[0084] In addition, this disclosure includes the following examples:

[0085] Example 1. A method for detecting impurities in additively manufactured materials, the method comprising: illuminating a sample of the additively manufactured material with light by means of a light source; simultaneously illuminating the sample of the additively manufactured material with light and causing a camera to acquire image data of the sample; and processing the image data to determine the amount of impurities in the sample of the additively manufactured material.

[0086] Example 2. According to the method of Example 1, wherein irradiating a sample of additively manufactured material with light comprises irradiating the sample with light having a wavelength in the ultraviolet spectrum.

[0087] Example 3. The method according to Example 1 or 2, wherein irradiating a sample of additively manufactured material with light comprises irradiating the sample with light having a wavelength between about 100 nanometers (nm) and about 500 nm.

[0088] Example 4. The method according to any one of Examples 1 to 3 further includes: irradiating a sample of additive manufacturing material with a first light source of a first wavelength and causing a camera to acquire first image data of the sample; irradiating the sample of additive manufacturing material with a second light source of a second wavelength and causing a camera to acquire second image data of the sample; and processing the first image data and the second image data to determine the amount of impurities in the sample of additive manufacturing material.

[0089] Example 5. According to the method of Example 4, wherein processing the first image data and the second image data to determine the impurity content in a sample of additive manufacturing material includes: determining a first impurity mass based on processing the first image data; determining a second impurity mass based on processing the second image data; and adding the first impurity mass and the second impurity mass together.

[0090] Example 6. The method according to any one of Examples 1 to 5, wherein irradiating a sample of additively manufactured material with light comprises changing the wavelength of the light source to irradiate the sample of additively manufactured material with a plurality of different wavelengths of light.

[0091] Example 7. The method according to Example 6 further includes: acquiring multiple image data of the sample while irradiating it with light of each of a plurality of different wavelengths; and processing the multiple image data to determine the amount of impurities in the sample of the additively manufactured material.

[0092] Example 8. The method according to any one of Examples 1 to 7, wherein processing image data to determine the amount of impurities in a sample of additively manufactured material includes calculating the fraction of impurities contained in the image data.

[0093] Example 9. The method according to any one of Examples 1 to 8, wherein processing image data to determine the amount of impurities in a sample of additively manufactured material includes using a learning model constructed by supervised learning using training images based on manually identified impurities.

[0094] Example 10. The method according to any one of Examples 1 to 9 further includes: applying dye to the sample of the additive manufacturing material before irradiating the sample of the additive manufacturing material.

[0095] Example 11. A system for detecting impurities in additively manufactured materials, the system comprising: a light source for illuminating a sample of the additively manufactured material with light; a camera for acquiring image data of the sample while illuminating the sample of the additively manufactured material with light; and a computing device having one or more processors configured to execute instructions stored in a memory to process the image data, thereby determining the amount of impurities in the sample of the additively manufactured material.

[0096] Example 12. The system according to Example 11, wherein the light source is an ultraviolet (UV) light source for irradiating the sample with light having wavelengths in the UV spectrum.

[0097] Example 13. A system according to Example 11 or 12, wherein the light source is a first light source that irradiates a sample of additive manufacturing material with light of a first wavelength, and a camera acquires first image data of the sample while the sample of additive manufacturing material is irradiated with light of the first wavelength, and the system further includes a second light source for irradiating the sample of additive manufacturing material with light of a second wavelength, wherein a camera acquires second image data of the sample while the sample of additive manufacturing material is irradiated with light of the second wavelength, wherein a computing device processes the first image data and the second image data to determine the amount of impurities in the sample of additive manufacturing material.

[0098] Example 14. The system according to Example 13, wherein the computing device processes first image data and second image data in such a way as to determine the amount of impurities in a sample of additive manufacturing material by: determining a first impurity mass based on processing the first image data; determining a second impurity mass based on processing the second image data; and adding the first impurity mass and the second impurity mass together.

[0099] Example 15. An additive manufacturing system for detecting impurities in additive manufacturing material, the system comprising: an additive manufacturing machine for manufacturing a part using a supply of additive manufacturing material; a collection reservoir for storing residual additive manufacturing material from the supply of additive manufacturing material after the part has been manufactured; a light source for illuminating a sample of the residual additive manufacturing material; a camera for acquiring image data of the sample while illuminating the sample of the residual additive manufacturing material; and a computing device having one or more processors configured to execute instructions stored in a memory to process the image data, thereby determining the amount of impurities in the sample of the residual additive manufacturing material.

[0100] Example 16. An additive manufacturing system according to Example 15, wherein, based on the amount of impurities in a sample of remaining additive manufacturing material, a computing device determines that the remaining additive manufacturing material should be recycled for use in manufacturing subsequent parts.

[0101] Example 17. An additive manufacturing system according to Example 15 or 16, wherein a light source illuminates the top layer of remaining additive manufacturing material in a collection reservoir.

[0102] Example 18. An additive manufacturing system according to any one of Examples 15 to 17, wherein, based on the amount and location of impurities in the top layer of the remaining additive manufacturing material, a computing device determines to remove the top layer of the remaining additive manufacturing material and provide a new layer of additive manufacturing material.

[0103] Example 19. An additive manufacturing system according to any one of Examples 15 to 18, wherein irradiating a sample of additive manufacturing material with light by a light source includes changing the wavelength of the light to irradiate the sample of additive manufacturing material with a plurality of different wavelengths of light.

[0104] Example 20. An additive manufacturing system according to Example 19, wherein a camera acquires multiple image data of a sample while irradiating it with light of each of a plurality of different wavelengths, and wherein a computing device processes the plurality of image data to determine the amount of impurities in the sample of additive manufacturing material.

[0105] As used herein, the terms “substantially” and “about” mean that the stated characteristic, parameter, or value is not required to be precisely achieved, but rather that deviations or variations may occur in the quantity of the effect that the characteristic is intended to provide, including, for example, tolerances, measurement errors, measurement accuracy limitations, and other factors known to those skilled in the art.

[0106] The various examples of systems, devices, and methods disclosed herein include a wide range of components, features, and functions. It should be understood that the various examples of systems, devices, and methods disclosed herein may include any components, features, and functions of any other example of the systems, devices, and methods disclosed herein, in any combination or sub-combination, and all such possibilities are intended to be within the scope of this disclosure.

[0107] Various advantageous arrangements have been described for purposes of illustration and description, and are not intended to be exhaustive or limited to the examples disclosed. Many modifications and variations will be apparent to those skilled in the art. Furthermore, different advantageous examples may describe different advantages compared to other advantageous examples. The selection and description of one or more examples are for the purpose of best explaining the principles of the examples, their practical application, and enabling others skilled in the art to understand the disclosure of various examples with various modifications suitable for the particular intended use.

Claims

1. A method (200) for detecting impurities in an additive manufacturing material, the method comprising: illuminating (202) a top layer of an additive manufacturing material (106) with light (107) by a light source (102); acquiring (204) image data (109) of the top layer by a camera (108) while the top layer of the additive manufacturing material (106) is illuminated with the light (107); and processing (206) the image data (109) to determine an amount of impurities (130) in the top layer of the additive manufacturing material (106), wherein the illuminating (202) comprises: illuminating the top layer of the additive manufacturing material with a first light source (102) of a first wavelength and acquiring first image data of the top layer by the camera; illuminating the top layer of the additive manufacturing material with a second light source (118) of a second wavelength and acquiring second image data of the top layer by the camera; and wherein the processing (206) comprises: processing the first image data and the second image data to determine an amount of impurities in the top layer of the additive manufacturing material; wherein processing the first image data and the second image data to determine an amount of impurities in the top layer of the additive manufacturing material comprises: determining a first amount of impurities based on processing the first image data; determining a second amount of impurities based on processing the second image data; and adding the first amount of impurities and the second amount of impurities.

2. The method of claim 1, wherein, Illuminating the top layer of the additive manufacturing material with light comprises illuminating the top layer with light having a wavelength in the ultraviolet spectrum.

3. The method of any one of claims 1-2, wherein, Processing the image data to determine an amount of impurities in the top layer of the additive manufacturing material comprises calculating a fraction of the image data containing impurities.

4. A system (100) for detecting impurities (130) in an additive manufacturing material (106), the system comprising: a first light source (102) for illuminating a top layer of the additive manufacturing material (106) with light (107) of a first wavelength; a second light source (118) for illuminating the top layer of the additive manufacturing material (106) with light of a second wavelength; a camera (108) for acquiring first image data of the top layer while the top layer of the additive manufacturing material (106) is illuminated by the first light source and for acquiring second image data of the top layer while the top layer of the additive manufacturing material (106) is illuminated by the second light source; and a computing device (110) having one or more processors (112) configured to execute instructions (114) stored in a memory (116) to process the first image data and the second image data to determine an amount of impurities (130) in the top layer of the additive manufacturing material (106), wherein the computing device (110) is further configured to: process the first image data and the second image data; determine a first amount of impurities based on processing the first image data; determine a second amount of impurities based on processing the second image data; and add the first amount of impurities and the second amount of impurities. adding the first amount of impurities and the second amount of impurities to determine an amount of impurities (130) in the top layer of the additive manufacturing material (106).

5. An additive manufacturing system (150) for detecting impurities (130) in an additive manufacturing material (106), the additive manufacturing system comprising: an additive manufacturing machine (152) for manufacturing a part (154) using a supply of the additive manufacturing material (106); a collection reservoir (156) for storing remaining additive manufacturing material from the supply of the additive manufacturing material after manufacturing the part; and and the system (100) for detecting impurities (130) according to claim 4.

6. The system of claim 4 or the additive manufacturing system of claim 5, wherein, based on the amount of impurities in the top layer of the remaining additive manufacturing material, the computing device determines to recycle the remaining additive manufacturing material for use in manufacturing a subsequent part.

7. The system of claim 4 or the additive manufacturing system of claim 5, wherein, based on the amount of impurities in the top layer of the remaining additive manufacturing material and the location of the impurities, the computing device determines to remove the top layer of the remaining additive manufacturing material and provide a new layer of additive manufacturing material.

Images