Method and system for in-process monitoring of additive manufacturing

Abstract

To provide a system and method for in-process monitoring of additive manufacturing.SOLUTION: A system and method for in-process monitoring of additive manufacturing are described. The system and method utilize a predictive model trained to identify anomalies within a component which have a likelihood of resulting in a manufacturing defect. The predictive model is trained at least by identifying one or more manufacturing anomalies relating to the additive manufacturing of a test coupon, identifying one or more manufacturing defects within the resulting test coupon, and performing positioning between the one or more manufacturing anomalies and the one or more manufacturing defects. The predictive model is used to monitor additive manufacturing processes and optionally inform the updating of process parameters.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to systems and methods for additive manufacturing. More particularly, the disclosed embodiments relate to methods and systems for monitoring additive manufacturing. [Background technology]

[0002] Traditional quality control methods utilized in additive manufacturing include post-manufacturing methods such as destructive testing of test coupons and non-destructive testing of final products, which may be used to identify anomalies and defects in the final product but are inadequate for in-process monitoring. Furthermore, testing final products for defects can result in unnecessary waste because defects are identified only after the manufacturing process has concluded and the material has been used. Therefore, improved monitoring of additive manufacturing would reduce defective components and wasted material. Summary of the Invention [Problem to be solved by the invention]

[0003] The present disclosure provides systems, devices, and methods for in-process monitoring of additive manufacturing. [Means for solving the problem]

[0004] In some examples, methods and systems for in-process monitoring of additive manufacturing include receiving and / or utilizing data related to additive manufacturing of test coupons; identifying one or more manufacturing anomalies in the test coupons based on the received data; identifying one or more manufacturing defects in the test coupons based on non-destructive testing; and using a machine learning model to align the one or more manufacturing anomalies with the one or more manufacturing defects to generate a predictive model, wherein the predictive model is configured to identify future manufacturing anomalies that will result in future manufacturing defects.

[0005] In some examples, methods and systems for in-process monitoring of an additive manufacturing process include monitoring the in-process additive manufacturing process using optical tomography; and utilizing a predictive model to analyze the optical tomography data, where the predictive model identifies one or more manufacturing anomalies that will result in one or more manufacturing defects in a component resulting from the additive manufacturing process, wherein the predictive model is trained by receiving historical optical tomography data for additive manufacturing of a test coupon; identifying one or more historical manufacturing anomalies in the test coupon in the historical optical tomography data; identifying one or more manufacturing defects in the test coupon; and performing an alignment between the one or more manufacturing anomalies and the one or more manufacturing defects, resulting in the predictive model.

[0006] The features, functions, and advantages may be achieved independently in various embodiments of the present disclosure or may be combined in yet further embodiments, further details of which can be understood with reference to the following description and drawings. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is a schematic diagram illustrating a system for in-process monitoring of an additive manufacturing process according to an aspect of the present disclosure. [Figure 2] FIG. 2 is a schematic diagram illustrating an additive manufacturing device monitored by the system of FIG. 1. [Figure 3] 1 is a flowchart illustrating steps of a method for in-process monitoring of an additive manufacturing process according to an aspect of the present disclosure. [Figure 4] 4 is a flow chart illustrating steps of a method for registration between optical tomography data and computed tomography data utilized in the method of FIG. 3; [Figure 5] FIG. 1 is a schematic diagram illustrating a data processing system according to an aspect of the present disclosure. [Figure 6] FIG. 1 is a schematic diagram illustrating a network data processing system according to an aspect of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0008] Various aspects and examples of methods and systems for in-process monitoring of additive manufacturing are described below and illustrated in the associated drawings. Unless otherwise specified, an in-process additive manufacturing system according to the present teachings, and / or its various components, may include at least one of the structures, components, functionality, and / or variations described, illustrated, and / or incorporated herein. Furthermore, unless specifically excluded, the process steps, structures, components, functionality, and / or variations described, illustrated, and / or incorporated herein in connection with the present teachings may be included in other similar apparatus and methods, including being interchangeable among the disclosed embodiments. The following description of various examples is merely exemplary in nature and does not limit the present disclosure, its application, or uses. Furthermore, the advantages provided by the examples and embodiments described below are exemplary in nature, and not all examples and embodiments provide the same advantages or the same degree of advantages.

[0009] This detailed description includes the following immediately following sections: (1) Definitions, (2) Overview, (3) Examples, Components, and Alternatives, (4) Advantages, Aspects, and Features, and (5) Conclusion. The Examples, Components, and Alternatives sections are further divided into subsections, each of which is labeled accordingly.

[0010] definition Unless otherwise indicated, the following definitions apply herein:

[0011] The terms "comprising," "including," and "having" (and their conjugations) are used interchangeably and mean inclusive but not necessarily exclusive, and are not intended to exclude additional, unrecited elements or method steps.

[0012] Terms such as "first," "second," and "third" are used to distinguish or identify various members of a group, etc., and are not intended to denote sequential or numerical limitations.

[0013] "AKA" means "also known as" and may be used to indicate alternative or corresponding terms for one or more given elements.

[0014] "Processing logic" describes any suitable device or hardware that processes data by performing one or more logical and / or arithmetic operations (e.g., executing coded instructions). For example, processing logic may include one or more processors (e.g., central processing units (CPUs) and / or graphics processing units (GPUs)), microprocessors, clusters of processing cores, FPGAs (field programmable gate arrays), artificial intelligence (AI) accelerators, digital signal processors (DSPs), and / or any other suitable combination of logic hardware.

[0015] A "controller" or "electronic controller" includes processing logic programmed with instructions to perform a control function with respect to a control element. For example, an electronic controller may be configured to receive an input signal, compare the input signal to a selected control value or set point, and determine an output signal to a control element (e.g., a motor or actuator) to take corrective action based on the comparison. In another example, an electronic controller may be configured to interface between a host device (e.g., a desktop computer, mainframe, etc.) and a peripheral device (e.g., a memory device, an input / output device, etc.) to control and / or monitor input / output signals to and from the peripheral device.

[0016] overview In general, methods and systems for in-process monitoring of additive manufacturing include receiving data related to the additive manufacturing of a test coupon, identifying anomalies (e.g., spatter, etc.) related to the additive manufacturing process in the test coupon based on the received data, identifying post-manufacture defects (e.g., cracks) in the test coupon, training a predictive model by performing alignment between the anomalies and the resulting defects, and utilizing the predictive model to monitor the manufacturing of additional components.

[0017] In some examples, the additive manufacturing process includes laser powder bed fusion. Additionally or alternatively, the additive manufacturing process may include directed energy deposition. Thus, the received data related to additive manufacturing of the test coupon may include data related to an additive manufacturing method utilizing a focused energy source, such as a laser, plasma arc, or electron beam. For example, the received data may include melt pool data (e.g., melt pool size, melt pool temperature, etc.), the power and / or beam diameter of the focused energy source, scan speed, and / or other process parameters utilized in the additive manufacturing process.

[0018] In some examples, the received data includes image data, such as optical tomography (OT) image data from an optical tomography imager. In some examples, the OT image data may be captured by the optical tomography imager continuously or at a predetermined sample rate. Additionally or alternatively, the OT image data may be captured by the optical tomography imager at a predetermined stage in the additive manufacturing process.

[0019] Identifying anomalies in the test coupon may include analyzing the received data (e.g., image data) to identify one or more anomalies, such as spatter, that occur at any stage of the additive manufacturing process. In some examples, the OT image data of the additive manufacturing process may be analyzed by one or more computer vision algorithms to determine the presence of one or more anomalies in the manufactured material. For example, one or more of the computer vision algorithms may include an edge detection algorithm and / or an image recognition algorithm to detect anomalies in the manufactured layers of the test coupon.

[0020] In some examples, identifying anomalies in the received data may include using an image classification model to classify portions of the OT image data into different classifications based on the presence of features corresponding to spatter and / or other manufacturing anomalies. For example, identifying anomalies may include classifying regions of the manufactured material as either normal or irregular.

[0021] In some examples, identifying anomalies may include segmenting the OT image data into two or more portions, such as segmenting a melt pool from surrounding material in the OT image data, in which case irregularity identification may be performed on one, some, and / or all of the segmented portions in the OT image data.

[0022] In some examples, identifying anomalies in the received data may include analyzing gradients in the OT image data to identify portions of the OT image data that include, for example, irregular gradients and / or regions of high contrast between adjacent pixels that may indicate anomalies in the material.

[0023] In some instances, one or more mechanical fatigue testing steps (AKA stress testing) may be applied to the test coupons after fabrication. For example, the test coupons may be subjected to one or more compression tests, axial fatigue tests, torsional fatigue tests, etc.

[0024] After fabrication and / or stress testing of the test coupon, one or more manufacturing defects (e.g., cracks) may be identified. Identifying the one or more manufacturing defects may include utilizing one or more non-destructive testing processes, such as computed tomography (CT). In some examples, CT may utilize x-ray imaging to obtain CT image data.

[0025] In some examples, identifying manufacturing defects in the test coupon includes analyzing the CT image data to identify one or more defects, such as cracks, occurring in the test coupon. In some examples, the CT image data may be analyzed by one or more computer vision algorithms to determine the presence of one or more cracks in the manufactured material. For example, one or more of the computer vision algorithms may include an edge detection algorithm and / or an image recognition algorithm to detect cracks in the test coupon.

[0026] In some examples, similar to the irregularity identification described above, identifying manufacturing defects in the CT image data may include using an image classification model to classify portions of the CT image data into different classes based on the presence of features corresponding to the manufacturing defects.

[0027] In some examples, identifying manufacturing defects in the CT image data may include analyzing gradients in the CT image data to identify portions of the CT image data that include irregular gradients and / or regions of high contrast between adjacent pixels, which may be indicative of cracks in the material, for example.

[0028] Generally, a predictive model is trained on identified anomalies and manufacturing defects to predict whether a detected anomaly will result in a manufacturing defect during manufacturing. Thus, the predictive model is configured to generate a defect prediction for a given detected anomaly, i.e., a prediction of whether the anomaly will result in a manufacturing defect.

[0029] In some examples, the defect prediction may include a classification between two types or anomaly types (e.g., a benign anomaly type and a defect-causing anomaly type). In some examples, the defect prediction may include a percentage likelihood that the anomaly will develop into a manufacturing defect. In some examples, the defect prediction may include a rating measure of the anomaly type, e.g., the predictive model may rate the anomaly on a scale of potential defect severity.

[0030] Generally, a predictive model is trained by performing an alignment between one or more manufacturing anomalies and one or more manufacturing defects such that the predictive model is configured to identify manufacturing anomalies that result in manufacturing defects.

[0031] In some examples, aligning the anomaly and the defect may include utilizing a classification model that classifies the anomaly into two or more classifications based on a comparison with the resulting defect. For example, the predictive model may classify the anomaly as either a) an anomaly that does not result in a manufacturing defect, or b) an anomaly that does result in a manufacturing defect.

[0032] In some examples, performing registration between the anomaly and the defect may include utilizing feature extraction, e.g., edge detection, pixel density analysis, etc., on associated image data (e.g., OT image data and CT image data) for the detected anomaly and the detected defect to determine corresponding features of the anomaly and the defect. The extracted features may then be matched between the anomaly and the defect, e.g., by identifying correspondence between features in the OT image data and corresponding features in the CT image data.

[0033] After training, the predictive model is configured to receive in-process monitoring data related to the additive manufacturing of non-test components (e.g., production components) and identify anomalies that may result in defects in the final product, thereby enabling proactive adjustments to the manufacturing process.

[0034] For example, during production, an optical tomography imager may be used to monitor the manufacturing process and acquire in-process OT image data. The in-process OT image data may be processed by one or more computer vision algorithms to determine anomalies, as described above with respect to the test coupons. The detected anomalies may be analyzed by a predictive model to determine a respective defect prediction for each detected anomaly.

[0035] If the detected anomaly is predicted to result in a defect, the methods and systems described herein may be configured to alter the current manufacturing process by (i) modifying one or more process parameters of the in-process additive manufacturing, (ii) stopping the in-process additive manufacturing, and / or (iii) designating the component to be discarded.

[0036] In some examples, altering one or more process parameters of an in-process additive manufacturing process may include altering laser power (e.g., adjusting the intensity of the laser in laser powder bed fusion and / or directed energy deposition to ensure proper melting and solidification of the material), melt pool size, melt pool temperature, scan speed, thickness of the produced layer, atmospheric control of the production chamber, gas flow rate, gas composition, powder bed temperature, etc.

[0037] Disclosed herein is a technical solution for in-process monitoring of additive manufacturing. Specifically, the disclosed system and method address a technical problem related to quality control techniques that arise in the field of additive manufacturing, namely, ensuring that components are manufactured without defects or anomalies that compromise the structural integrity of the manufactured components. The disclosed system and method provide an improved solution to this technical problem by utilizing predictive models that identify anomalies in the manufacturing process that result in defects in the final product.

[0038] The disclosed systems and methods provide an integrated, practical application of the principles described herein. Specifically, the disclosed systems and methods describe specific methods for monitoring in-process additive manufacturing that offer specific improvements over conventional systems and result in improved manufactured components. Thus, the disclosed systems and methods apply (or use) the relevant principles in a meaningful, limited way.

[0039] Aspects of the systems and methods for in-process monitoring of additive manufacturing described herein may be embodied as a computer method, computer system, or computer program product. Accordingly, aspects of the systems and methods may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, microcode, etc.), or an embodiment combining software and hardware aspects, all of which may be referred to as a "circuit," "module," or "system." Furthermore, aspects of the systems and methods may take the form of a computer program product embodied in a computer-readable medium(s) having computer-readable program code / instructions embodied therein.

[0040] Any combination of computer-readable media may be utilized. The computer-readable medium may be a computer-readable signal medium and / or a computer-readable storage medium. The computer-readable storage medium may include an electronic, magnetic, optical, electromagnetic, infrared, and / or semiconductor system, apparatus, or device, or any suitable combination thereof. More specific examples of computer-readable storage media may include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, and / or any suitable combination thereof. In the context of the present disclosure, a computer-readable storage medium may include any suitable non-transitory tangible medium that can be used by or contain or store a program associated with an instruction execution system, apparatus, or device.

[0041] A computer-readable signal medium may include a propagated data signal containing computer-readable program code, for example, embodied in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including, but not limited to, electromagnetic, optical, and / or any suitable combination thereof. A computer-readable signal medium is not a computer-readable storage medium, but may include any computer-readable medium that can communicate, propagate, or transport a program used by or associated with an instruction execution system, apparatus, or device.

[0042] The program code embodied in a computer readable medium may be transmitted using any suitable medium, including, but not limited to, wireless, wired, fiber optic cable, radio frequency (RF), etc., and / or any suitable combination thereof.

[0043] Computer program code for performing operations for aspects of the systems and methods may be written in one or any combination of programming languages, including object-oriented programming languages ​​(e.g., Java, C++), traditional procedural programming languages ​​(e.g., C), and functional programming languages ​​(e.g., Haskell). Mobile applications may be developed using any suitable language, including the aforementioned languages, as well as Objective-C, Swift, C#, HTML5, etc. The program code may run entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), and / or may be connected to an external computer (e.g., via the Internet using an Internet Service Provider).

[0044] Aspects of the systems and methods may be described below with reference to flowchart illustrations and / or block diagrams of methods, apparatus, systems, and / or computer program products. Each block and / or combination of blocks in the flowchart and / or block diagrams may be implemented by computer program instructions. The computer program instructions may be programmed into or otherwise provided to processing logic (e.g., a general-purpose computer, a special-purpose computer, a processor of a field programmable gate array (FPGA) or other programmable data processing device) to produce a machine whose (e.g., machine-readable) instructions, which execute through the processing logic, create means for implementing the function(s) / act(s) specified in the block(s) of the flowchart and / or block diagram.

[0045] Alternatively or additionally, these computer program instructions may be stored on a computer-readable medium that can cause processing logic and / or other suitable devices to function in a particular manner to produce an article of manufacture comprising instructions that implement the function(s) / act(s) specified in the flowchart and / or block diagram block(s), where the instructions stored on the computer-readable medium.

[0046] Furthermore, the computer program instructions can be loaded into processing logic and / or any other suitable device to perform a series of operational steps on the device to generate computer-implemented processes, such that the executed instructions perform steps to implement the function(s) / operation(s) specified in the flowchart and / or block diagram block(s).

[0047] Any flowcharts and / or block diagrams in the drawings are intended to illustrate the architecture, functionality, and / or operation of possible implementations of the in-process monitoring system and method. In this regard, each block may represent a module, segment, or portion of code, including one or more executable instructions for implementing one or more specific logical functions. In some implementations, the functions described in the blocks may occur out of the order described in the drawings. For example, two blocks shown in succession may actually be executed substantially simultaneously, or the blocks may be executed in the reverse order depending on the relevant functionality. Each block and / or combination of blocks may be implemented by a dedicated hardware-based system (or a combination of dedicated hardware and computer instructions) that performs the specified function or operation.

[0048] Examples, Components and Alternatives The following sections describe selected aspects of exemplary systems and methods for in-process monitoring of additive manufacturing. The examples in these sections are intended to be illustrative and should not be construed as limiting the scope of the present disclosure. Each section may include one or more alternative embodiments or examples, and / or contextual or related information, functionality, and / or structure.

[0049] A. Exemplary System for In-Process Monitoring of Additive Manufacturing As illustrated, with reference to Figures 1 and 2, this section describes an exemplary system 100 for in-process monitoring of additive manufacturing. System 100 is an example of the systems described above.

[0050] System 100 is an in-process monitoring system for monitoring an additive manufacturing process 102. The additive manufacturing process 102 is an additive manufacturing process configured to produce structured components from raw material. In some examples, the additive manufacturing process includes utilizing a focused energy source to melt and / or fuse portions of the raw material in a predetermined manner such that a resulting component is produced. For example, the additive manufacturing process 102 may include a laser powder bed fusion process. Additionally or alternatively, the additive manufacturing process 102 may include a directed energy deposition process.

[0051] The additive manufacturing process 102 is utilized to manufacture test coupons 104. In some examples, the test coupons 104 are test components having a shape and / or structure specifically selected for mechanical testing of material properties of the test coupons 104. For example, the test coupons 104 may have a generally cylindrical shape, a generally planar shape, or other suitable shape for testing material properties. Additionally or alternatively, the test coupons 104 may have a shape and / or structure substantially similar to a non-test (e.g., production) component. For example, the test coupons 104 may have a shape that replicates a portion of the production component.

[0052] During manufacturing, the optical tomography device 106 is utilized to capture optical tomography (OT) image data related to the additive manufacturing of the test coupon 104. In some examples, the optical tomography device 106 is a single sensor device such that the OT image data is collected by a single source. In some examples, the optical tomography device 106 is a multi-sensor device such that the OT image data is collected by an array of OT imaging sources. In some examples, the OT image data may be captured by the optical tomography device 106 continuously or at a predetermined sample rate. In some examples, the OT image data may be captured by the optical tomography device 106 at a predetermined stage in the additive manufacturing process 102.

[0053] The OT image data is analyzed to identify anomalies, such as spatter in the test coupon, that occur during the additive manufacturing process. In some examples, the OT image data of the additive manufacturing process may be analyzed by one or more computer vision algorithms, such as edge detection algorithm(s) and / or image recognition algorithm(s), to determine the presence of one or more anomalies in the manufactured material.

[0054] The OT image data may be analyzed using an image classification model that classifies portions of the OT image data into different classes based on the presence of features corresponding to spatter and / or other manufacturing anomalies. For example, identifying anomalies may include classifying regions of the manufactured material as either normal or irregular.

[0055] The OT image data may be segmented into two or more portions, such as segmenting a melt pool of the additive manufacturing process 102 from surrounding material in the OT image data. In this manner, irregularity identification may be performed on one, some, and / or all of the segmented portions in the OT image data. Additionally or alternatively, identifying anomalies in the test coupon 104 may include analyzing gradients in the OT image data to identify portions of the OT image data that include, for example, irregular gradients and / or regions of high contrast between adjacent pixels that may indicate anomalies in the test coupon.

[0056] After fabrication, a mechanical test 108 may be applied to the test coupon 104. The mechanical test 108 is configured to subject the test coupon 104 to one or more processes that impart mechanical fatigue. Thus, the mechanical test 108 may include any mechanical testing process suitable for testing the mechanical and / or material properties of the test coupon 104. For example, the mechanical test 108 may include one or more of a compression test, an axial fatigue test, and / or a torsional fatigue test.

[0057] In some instances, such as instances where the test coupon 104 has a substantially similar form / shape to a production component, the mechanical testing 108 may include subjecting the test coupon 104 to conditions similar to those encountered by the production component. Similarly, in some instances, the mechanical testing 108 may include subjecting the test coupon 104 to worst-case conditions that the production component may encounter. For example, the mechanical testing 108 may include higher levels of stress, compression, and / or impact than those typically encountered by a production component.

[0058] After mechanical testing 108, fractography 110 is performed on the test coupon 104. Fractography 110 includes identifying one or more manufacturing defects, such as cracks / discontinuities, in the test coupon 104. Identifying the one or more manufacturing defects may include utilizing one or more non-destructive testing processes, such as computed tomography (CT) 112. In some examples, CT 112 may utilize x-ray imaging to obtain CT image data.

[0059] Thus, fractography 110 may include analyzing CT image data from CT 112 to identify and / or analyze defects occurring within the test coupon. In some examples, fractography 110 includes utilizing one or more computer vision algorithms (e.g., edge detection algorithms and / or image recognition algorithms) to determine the presence of one or more defects within the test coupon 104.

[0060] In some examples, the fracture surface analysis 110 may include using an image classification model to classify portions of the CT image data into different classifications based on the presence of features corresponding to cracks. For example, image classification may be used to classify portions of the CT image data into a) portions of material without defects and b) portions of material with defects.

[0061] In some examples, the fracture surface analysis 110 may include analyzing gradients within the CT image data to identify portions of the CT image data that contain irregular gradients and / or regions of high contrast between adjacent pixels, which may be indicative of crack defects within the material, for example.

[0062] An alignment process 114 is performed on the anomalies identified in the OT image data and the defects identified in the CT image data, resulting in a predictive model 116 that identifies manufacturing anomalies that result in manufacturing defects.

[0063] The alignment process 114 may include utilizing a classification model that classifies anomalies into two or more categories based on a comparison with the resulting defects. For example, the predictive model may classify anomalies as either a) anomalies that do not result in a manufacturing defect, or b) anomalies that result in a manufacturing defect.

[0064] The registration process 114 may involve using feature extraction, such as edge detection, pixel density analysis, etc., on the associated image data (e.g., OT image data and CT image data) for the detected anomaly and the detected defect to determine corresponding features of the anomaly and the defect. The extracted features may then be matched between the anomaly and the defect, for example, by identifying correspondence between features in the OT image data and corresponding features in the CT image data.

[0065] After the alignment step 114, the predictive model 116 is configured to predict whether a detected anomaly during manufacturing will result in a manufacturing defect. In other words, the predictive model 116 is configured to generate a defect prediction for a given detected anomaly, i.e., a prediction of whether the anomaly will result in a manufacturing defect. Thus, the predictive model can receive in-process monitoring data related to the additive manufacturing of non-test components (e.g., manufacturing components) and identify anomalies that may result in defects in the final product, thereby enabling proactive adjustments to the manufacturing process.

[0066] In some examples, the defect prediction may include a classification between two types or anomaly types (e.g., a benign anomaly type and a defect-causing anomaly type). In some examples, the defect prediction may include a percentage likelihood that the anomaly will develop into a manufacturing defect. In some examples, the defect prediction may include a rating measure of the anomaly type, e.g., the predictive model may rate the anomaly on a scale of potential defect severity.

[0067] If the detected anomaly is predicted to result in a defect, the system 100 may optionally generate updated manufacturing instructions 118 and provide them to the AM process 102 to modify the manufacturing process. The updated manufacturing instructions 118 may include at least one of: (i) modifying one or more process parameters for the AM process; (ii) canceling the AM process; and / or (iii) designating components to be discarded.

[0068] In some examples, altering one or more process parameters of an in-process additive manufacturing process may include altering laser power (e.g., adjusting the intensity of the laser in laser powder bed fusion and / or directed energy deposition to ensure proper melting and solidification of the material), melt pool size, melt pool temperature, scan speed, thickness of the produced layer, atmospheric control of the production chamber, gas flow rate, gas composition, powder bed temperature, etc.

[0069] 2 , an exemplary additive manufacturing device 200 is shown that may be used with predictive model 116 to perform additive manufacturing of a non-test component, such as manufactured component 202. In some examples, additive manufacturing device 200 is the same additive manufacturing device that performs additive manufacturing process 102. Alternatively, the additive manufacturing device may be a different additive manufacturing device that utilizes the same or a substantially similar additive manufacturing process 102.

[0070] The additive manufacturing apparatus 200 includes an optical tomography (OT) imager 204. In some examples, the OT imager 204 is the OT imager 106. Alternatively, the OT imager 204 may be a different OT imager than the apparatus 106, but may be configured to utilize the same or a substantially similar OT process.

[0071] An optical tomography imager 204 is used to monitor the production of the manufactured components 202 and acquire in-process OT image data. The in-process OT image data for the manufactured components 202 may be processed by one or more computer vision algorithms substantially similar to those described above with respect to the test coupons 104 to determine in-process anomalies. The detected anomalies are analyzed by a predictive model 116 to determine a respective defect prediction for each detected anomaly.

[0072] Thus, if the detected anomaly is predicted to result in a defect, system 100 may optionally generate updated manufacturing instructions 118 and provide them to additive manufacturing device 200 to modify the manufacturing process. The updated manufacturing instructions 118 may include at least one of: (i) modifying one or more process parameters for the in-process additive manufacturing; (ii) canceling the in-process additive manufacturing; and / or (iii) designating components to be discarded.

[0073] Altering one or more process parameters of an in-process additive manufacturing process may include altering the laser power of the additive manufacturing apparatus 200 (e.g., adjusting the intensity of the laser in laser powder bed fusion and / or directed energy deposition to ensure proper melting and solidification of the material), melt pool size, melt pool temperature, scan speed, thickness of the produced layer, atmospheric control of the manufacturing chamber, gas flow rate, gas composition, powder bed temperature, etc.

[0074] B. Exemplary Methods for In-Process Monitoring of Additive Manufacturing 3 and 4, this section describes steps of an exemplary method 300 for in-process monitoring of additive manufacturing. Aspects of the systems and methods described above may be utilized in the method steps described below. Where appropriate, references are made to components and systems that may be used to perform each step. These references are for illustrative purposes and are not intended to limit possible ways of performing any particular step of the method.

[0075] 3 is a flowchart illustrating steps performed in an exemplary method and may not list the complete process or every step of the method. Although various steps of method 300 are described below and illustrated in FIG. 3, the steps do not necessarily have to be performed all together and may in some cases be performed simultaneously or in a different order than illustrated.

[0076] Step 302 of method 300 includes receiving data related to additive manufacturing of a test coupon, the received data including optical tomography (OT) image data from an optical tomography imaging device. The OT image data may include continuously captured image data and / or image data captured at a predetermined sample rate.

[0077] In some examples, the received data includes data regarding process parameters of the additive manufacturing method, such as melt pool data (e.g., melt pool size, melt pool temperature, etc.), power and / or beam diameter of the focused energy source, scan speed, and / or other process parameters utilized in the additive manufacturing process.

[0078] Step 304 of method 300 includes identifying one or more manufacturing anomalies in the test coupon. Identifying one or more manufacturing anomalies in the test coupon includes analyzing OT image data of the additive manufacturing process with one or more computer vision algorithms, such as edge detection algorithms and / or image recognition algorithms, to determine the presence of one or more anomalies in the manufactured material.

[0079] In some examples, the OT image data is analyzed using an image classification model that classifies portions of the OT image data into different classifications based on the presence of features corresponding to spatter and / or other manufacturing anomalies. For example, identifying anomalies may include classifying regions of the manufactured material as either normal or irregular.

[0080] In some examples, the OT image data may be segmented into two or more portions, such as segmenting a melt pool of an additive manufacturing process from surrounding material in the OT image data. In this manner, irregularity identification may be performed on one, some, and / or all of the segmented portions in the OT image data. Additionally or alternatively, identifying one or more anomalies may include analyzing pixel gradients in the OT image data to identify portions of the OT image data that include, for example, irregular gradients and / or regions of high contrast between adjacent pixels that may indicate anomalies in the test coupon.

[0081] Step 306 of method 300 includes identifying one or more manufacturing defects in the test coupon. Identifying the one or more manufacturing defects may include utilizing one or more non-destructive testing processes, such as computed tomography (CT). Accordingly, step 306 includes analyzing the CT image data using one or more computer vision algorithms (e.g., edge detection algorithms and / or image recognition algorithms) to identify defects occurring in the test coupon.

[0082] In some examples, step 306 includes utilizing an image classification model to classify portions of the CT image data into different classifications based on the presence of features corresponding to cracks. For example, image classification may be used to classify portions of the CT image data into a) portions of material without defects and b) portions of material with defects.

[0083] In some examples, step 306 may include analyzing gradients within the CT image data to identify portions of the CT image data that include irregular gradients and / or regions of high contrast between adjacent pixels, which may be indicative of crack defects within the material, for example.

[0084] Step 308 of method 300 includes using a machine learning model to perform alignment between one or more manufacturing anomalies and one or more manufacturing defects to generate a predictive model, where the predictive model is configured to identify future manufacturing anomalies that will result in future manufacturing defects. A further description of step 308 is provided below with reference to FIG. 4.

[0085] Step 310 of method 300 includes monitoring in-process additive manufacturing of a non-test component using optical tomography to obtain optical tomography data and analyzing the optical tomography data using a predictive model. As described in step 304 with respect to the test coupon, the optical tomography data is processed by one or more computer vision algorithms to determine in-process manufacturing anomalies. The detected anomalies are then analyzed by the predictive model to determine a respective defect prediction for each detected anomaly, where the defect prediction corresponds to the likelihood that the anomaly will result in a defect.

[0086] Optional step 312 of method 300 includes updating the manufacturing process based on the defect prediction. In some examples, updating the manufacturing process includes selecting one of the following update procedures: (i) modifying one or more process parameters for the in-process additive manufacturing; (ii) aborting the in-process additive manufacturing; and / or (iii) designating components to be discarded.

[0087] With reference to Figure 4, the alignment step 308 of the method 300 includes one or more subsequent steps. Although various subsequent steps of step 308 are described below and illustrated in Figure 4, the subsequent steps do not necessarily have to be performed all together and may even be performed simultaneously or in an order other than that illustrated.

[0088] Following step 308, step 308A involves extracting features of the anomalies identified in step 304. In some examples, this involves analyzing the optical tomography data using one or more computer vision algorithms, machine learning models, and / or statistical pattern recognition algorithms. For example, edge detection, pixel density analysis, etc. may be used in conjunction with models such as Bayesian classification, artificial neural network models, k-nearest neighbor models, and / or other classification / feature extraction models to extract features of the anomalies.

[0089] Following step 308, step 308B involves extracting features of the defects identified in step 306. In some examples, this involves analyzing the computed tomography data using one or more computer vision algorithms, machine learning models, and / or statistical pattern recognition algorithms. For example, edge detection, pixel density analysis, etc. may be used in conjunction with models such as Bayesian classification, artificial neural network models, k-nearest neighbor models, and / or other classification / feature extraction models to extract features of the defects.

[0090] Following step 308, step 308C includes performing registration between the anomaly and the defect based at least in part on the extracted features. In some examples, the extracted features may be compared and / or matched between the anomaly and the defect, for example, by identifying correspondences between features in the OT image data and corresponding features in the CT image data. For example, the matched features may include shape, size, position, orientation, depth, and / or other characteristics related to the shape and / or composition of the anomaly and / or defect.

[0091] In some examples, subsequent step 308C includes utilizing a classification model to classify the anomaly into two or more categories based on the comparison with the resulting defect. For example, the anomaly may be classified as either a) an anomaly that resulted in a manufacturing defect or b) an anomaly that did not result in a manufacturing defect.

[0092] C. Exemplary Data Processing System 5, this example illustrates a data processing system 500 (also referred to as a computer, computing system, and / or computer system) according to aspects of the present disclosure. In this example, data processing system 500 is an exemplary data processing system suitable for implementing aspects of systems and methods for in-process monitoring of additive manufacturing. More specifically, in some examples, devices that are embodiments of a data processing system (e.g., a smartphone, tablet, personal computer) may be utilized in training predictive models, running predictive models, analyzing optical tomography data, analyzing computed tomography data, and / or analyzing or utilizing data related to an additive manufacturing process.

[0093] In this illustrative example, data processing system 500 includes a system bus 502 (also referred to as a communications framework). System bus 502 may provide communications between a processor unit 504 (also referred to as one or more processors), memory 506, persistent storage 508, communications unit 510, input / output (I / O) unit 512, codec 530, and / or display 514. Memory 506, persistent storage 508, communications unit 510, input / output (I / O) unit 512, display 514, and codec 530 are examples of resources accessible by processor unit 504 via system bus 502.

[0094] Processor unit 504 is responsible for executing instructions that may be loaded into memory 506. Processor unit 504 may include several processors, multiple processor cores, and / or a particular type of processor (e.g., a central processing unit (CPU), a graphics processing unit (GPU), etc.), depending on the particular implementation. Furthermore, processor unit 504 may be implemented using some heterogeneous processor systems, in which a main processor resides on a single chip along with secondary processors. As another illustrative example, processor unit 504 may be a symmetric multiprocessor system that includes multiple processors of the same type.

[0095] Memory 506 and persistent storage 508 are examples of storage devices 516. A storage device may include any suitable hardware capable of temporarily or permanently storing information (e.g., digital information), such as data, program code in a functional form, and / or other suitable information.

[0096] The storage device 516 may also be referred to as a computer-readable storage device or a computer-readable medium. The memory 506 may include volatile memory 540 and non-volatile memory 542. In some examples, a basic input / output system (BIOS), containing the basic routines to transfer information between elements within data processing system 500, such as during start-up, may be stored in non-volatile memory 542. Persistent storage 508 may take various forms, depending on the particular implementation.

[0097] For example, persistent storage 508 may include one or more components or devices. For example, persistent storage 508 may include one or more devices such as a magnetic disk drive (also referred to as a hard disk drive or HDD), a solid-state disk (SSD), a floppy disk drive, a tape drive, a Jaz drive, a Zip drive, a flash memory card, a memory stick, or the like, or any combination thereof. One or more of these devices may be removable and / or portable, e.g., a removable hard drive. Persistent storage 508 may also include one or more storage media, separate from or in combination with other storage media, including optical disk drives such as compact disc ROM drives (CD-ROMs), CD recordable drives (CD-R drives), CD rewriteable drives (CD-RW drives), and / or digital versatile disc ROM drives (DVD-ROMs). A removable or non-removable interface, such as interface 528, is typically used to facilitate connection of persistent storage device 508 to system bus 502.

[0098] Input / output (I / O) unit 512 enables data to be input and output from other devices that may be connected to data processing system 500 (i.e., input and output devices). For example, input devices may include one or more pointing and / or information input devices, such as a keyboard, a mouse, a trackball, a stylus, a touchpad or touchscreen, a microphone, a joystick, a gamepad, a satellite dish, a scanner, a TV tuner card, a digital camera, a digital video camera, a webcam, etc. These and other input devices may be connected to processor unit 504 through system bus 502 via interface ports. Suitable interface ports may include, for example, a serial port, a parallel port, a game port, and / or a universal serial bus (USB).

[0099] One or more output devices may use several of the same type of ports, or even the same port, as input devices. For example, a USB port may be used to provide input to data processing system 500 and to output information from data processing system 500 to an output device. One or more output adapters may be provided for certain output devices (e.g., monitors, speakers, and printers, among others) that require special adapters. Suitable output adapters may include circuit cards (e.g., video cards and sound cards) that provide a means of connection between an output device and system bus 502. Other devices and / or systems of devices, such as remote computer 560, may provide both input and output capabilities. Display 514 may include any suitable human-machine interface or other mechanism for displaying information to a user, such as, for example, a cathode ray tube (CRT), light-emitting diode (LED), or liquid crystal display (LCD) monitor or screen.

[0100] Communications unit 510 refers to any suitable hardware and / or software used to provide communications with other data processing systems or devices. While communications unit 510 is shown internal to data processing system 500, in some examples, communications unit 510 may be at least partially external to data processing system 500. Communications unit 510 may include internal and external technologies, such as modems (including regular telephone-level modems, cable modems, and DSL modems), ISDN adapters, and / or wired and wireless Ethernet cards, hubs, routers, etc. Data processing system 500 may operate in a networked environment using logical connections to one or more remote computers 560. Remote computers 560 may include personal computers (PCs), servers, routers, network PCs, workstations, microprocessor-based devices, peer devices, smartphones, tablets, another network notebook, etc. Remote computers 560 typically include many of the elements described with respect to data processing system 500. Remote computers 560 may be logically connected to data processing system 500 via a network interface 562 connected to data processing system 500 via communications unit 510. Network interface 562 encompasses wired and / or wireless communication networks such as local area networks (LANs), wide area networks (WANs), and cellular networks. LAN technologies may include Fiber Distributed Data Interface (FDDI), Copper Distributed Data Interface (CDDI), Ethernet, Token Ring, etc. WAN technologies include point-to-point links, circuit-switched networks (e.g., Integrated Services Digital Networks (ISDN) and its variants), packet-switched networks, and Digital Subscriber Lines (DSL).

[0101] Codec 530 may include an encoder, a decoder, or both, including hardware, software, or a combination of hardware and software. Codec 530 may include any suitable device and / or software that encodes, compresses, and / or encrypts a data stream or signal for transmission and storage, and decodes a data stream or signal by decoding, decompressing, and / or decompressing the data stream or signal (e.g., for video playback or editing). Although codec 530 is shown as a separate component, codec 530 may be included in or implemented in memory, such as non-volatile memory 542.

[0102] Non-volatile memory 542 may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, etc., or any combination thereof. Volatile memory 540 may include random access memory (RAM), which may act as external cache memory. RAM may include static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), etc., or any combination thereof.

[0103] Instructions for the operating system, applications, and / or programs may be located in storage devices 516, which are in communication with processor unit 504 via system bus 502. In these illustrative examples, the instructions are in functional form in persistent storage 508. These instructions may be loaded into memory 506 for execution by processor unit 504. The processes of one or more embodiments of the present disclosure may be performed by processor unit 504 using computer-implemented instructions, which may be located in a memory, such as memory 506.

[0104] These instructions are referred to as program code, computer-usable program code, or computer-readable program code, which may be executed by a processor within processor unit 504. The program code in different embodiments may be embodied on different physical or computer-readable storage media, such as memory 506 or persistent storage 508. Program code 518 may be located in a functional form on selectively removable computer-readable medium 520 and loaded onto or transferred to data processing system 500 for execution by processor unit 504. Program code 518 and computer-readable medium 520 form computer program product 522 in these illustrative examples. In one example, computer-readable medium 520 may be computer-readable storage medium 524 or computer-readable signal medium 526.

[0105] Computer readable storage medium 524 may include, for example, an optical or magnetic disk that is inserted into or placed into a drive or other device that is part of persistent storage 508 for transfer onto a storage device, such as a hard drive that is part of persistent storage 508. Computer readable storage medium 524 may also take the form of persistent storage, such as a hard drive, thumb drive, or flash memory, connected to data processing system 500. In some cases, computer readable storage medium 524 may not be removable from data processing system 500.

[0106] In these examples, computer-readable storage medium 524 is not a medium that propagates or transmits program code 518, but rather a physical or tangible storage device used to store program code 518. Computer-readable storage medium 524 is also referred to as a computer-readable tangible storage device or a computer-readable physical storage device. In other words, computer-readable storage medium 524 is a medium that can be touched by a person.

[0107] Alternatively, program code 518 may be transferred to data processing system 500 remotely or over a network using computer readable signal media 526. Computer readable signal media 526 may be, for example, a propagated data signal containing program code 518. For example, computer readable signal media 526 may be an electromagnetic signal, an optical signal, and / or any other suitable type of signal. These signals may be transmitted over communications links, such as wireless communications links, fiber optic cable, coaxial cable, a wire, and / or any other suitable type of communications link. In other words, communications links and / or connections may be physical or wireless in illustrative examples.

[0108] In some demonstrative embodiments, program code 518 may be downloaded over a network to persistent storage 508 from another device or data processing system via computer readable signal medium 526 for use within data processing system 500. For example, program code stored on a computer readable storage medium in a server data processing system may be downloaded over a network from the server to data processing system 500. The computer providing program code 518 may be a server computer, a client computer, or some other device capable of storing and transmitting program code 518.

[0109] In some examples, program code 518 may include an operating system (OS) 550. The operating system 550, which may be stored on persistent storage 508, controls and allocates resources of the data processing system 500. One or more applications 552 utilize the operating system's resource management through program modules 554 and program data 556 stored on storage device 516. The OS 550 may include any suitable software system that manages and exposes the computer's 500's hardware resources for shared use by the applications 552. In some examples, the OS 550 provides an application programming interface (API) that facilitates the connection of different types of hardware and / or provides applications 552 access to hardware and OS services. In some examples, a particular application 552 may provide additional services for use by other applications 552, such as in the case of so-called "middleware." Aspects of the present disclosure may be implemented with respect to various operating systems or combinations of operating systems.

[0110] The different components illustrated for data processing system 500 are not meant to provide architectural limitations to the manner in which different embodiments may be implemented. One or more embodiments of the present disclosure may be implemented in a data processing system that includes fewer components or components in addition to and / or instead of those illustrated for computer 500. Other components illustrated in FIG. 5 may differ from the depicted example. Different embodiments may be implemented using any hardware device or system capable of executing program code. As an example, data processing system 500 may include organic components integrated with inorganic components and / or may be composed entirely of organic components (excluding humans). For example, a storage device may be composed of organic semiconductors.

[0111] In some examples, the processor unit 504 may take the form of a hardware unit having hardware circuits specially manufactured or configured for a particular application or to bring about a particular result or progression. This type of hardware may perform operations without requiring program code 518 to be loaded into memory from a storage device to configure the operations. For example, the processor unit 504 may be a circuit system, an application-specific integrated circuit (ASIC), a programmable logic device, or some other suitable type of hardware that performs certain operations (e.g., pre-configured or reconfigured). For example, in a programmable logic device, the device may be configured to perform certain operations and later reconfigured. Programmable logic devices include, for example, programmable logic arrays, field programmable logic arrays, field programmable gate arrays (FPGAs), and other suitable hardware devices. In this type of implementation, executable instructions (e.g., program code 518) may be implemented as hardware, for example, by specifying the FPGA configuration using a hardware description language (HDL) and then using the resulting binary file to (re)configure the FPGA.

[0112] In another example, data processing system 500 may be implemented as a set of dedicated FPGA-based (or possibly ASIC-based) state machines (e.g., finite state machines (FSMs)), allowing critical tasks to be isolated and performed on custom hardware. While a processor, such as a CPU, can be described as a shared-purpose, general-purpose state machine that executes instructions provided to it, an FPGA-based state machine may be purpose-built to execute hardware-coded logic without sharing resources. Such systems are often utilized for safety-related and mission-critical tasks.

[0113] In yet another illustrative example, processor unit 504 may be implemented using a combination of processors and hardware units found in a computer. Processor unit 504 may have several hardware units and several processors configured to execute program code 518. In this illustrated example, some processes may be performed in several hardware units, while other processes may be performed in several processors.

[0114] In another example, system bus 502 may be comprised of one or more buses, such as a system bus or an input / output bus. Of course, the bus system may be implemented using any suitable type of architecture that provides for a transfer of data between different components or devices attached to the bus system. The system bus 502 may include several types of bus structures (one or more), including a memory bus or memory controller, a peripheral or external bus, and / or a local bus using any of a variety of available bus architectures, including, for example, Industrial Standard Architecture (ISA), Micro-Channel Architecture (MSA), Extended ISA (EISA), Intelligent Drive Electronics (IDE), VESA Local Bus (VLB), Peripheral Component Interconnect (PCI), Universal Serial Bus (USB), Advanced Graphics Port (AGP), Personal Computer Memory Card International Association bus (PCMCIA), Firewire (IEEE 1394), and Small Computer Systems Interface (SCSI).

[0115] Additionally, communications unit 510 may include several devices that transmit data, receive data, or both transmit and receive data. Communications unit 510 may be, for example, a modem or a network adapter, two network adapters, or some combination thereof. Additionally, memory may be, for example, memory 506 or a cache such as found in an interface and memory controller hub that may be present in system bus 502.

[0116] D. Exemplary Distributed Data Processing System 6, this example illustrates a general network data processing system 600, interchangeably referred to as a computer network, network system, distributed data processing system, or distributed network, aspects of which may be included in one or more exemplary embodiments of the systems and methods for in-process monitoring of additive manufacturing described herein. For example, communication between modules utilized in the above-described systems and / or devices that perform steps of computer-implemented methods may be facilitated through the use of network data processing system 600.

[0117] It should be appreciated that Figure 6 is provided as an illustration of one implementation and is not intended to suggest any limitation with regard to the environments in which different embodiments may be implemented. Many modifications to the depicted environments may be made.

[0118] Network system 600 is a network of devices (e.g., computers), each of which may be an example of data processing system 500 and other components. Network data processing system 600 includes network 602, which is a medium that provides communications links between the various devices and computers connected to each other within network data processing system 600. Network 602 may include connections such as wired or wireless communications links, fiber optic cables, and / or any other suitable medium for transmitting and / or communicating data between network devices, or any combination thereof.

[0119] In the depicted example, a first network device 604 and a second network device 606 connect to a network 602, as well as one or more computer-readable memory or storage devices 608. Network devices 604 and 606 are each examples of data processing system 500 described above. In the depicted example, devices 604 and 606 are shown as server computers and communicate with one or more server data stores 622 that may be used, among other things, to store information local to server computers 604 and 606. However, network devices may also include, but are not limited to, one or more personal computers, personal digital assistants (PDAs), tablets and smartphones, handheld gaming devices, wearable devices, tablet computers, mobile computing devices such as routers, switches, voice gateways, servers, electronic storage devices, imaging devices, media players, and / or other network-enabled tools that may perform mechanical or other functions. These network devices may be interconnected via wired, wireless, optical, and other suitable communication links.

[0120] Additionally, client electronic devices 610 and 612 and / or client smart device 614 may connect to network 602. Each of these devices is an example of data processing system 500 described above with reference to FIG. 5. Client electronic devices 610, 612, and 614 may include, for example, one or more personal computers, network computers, and / or mobile computing devices such as personal digital assistants (PDAs), smartphones, handheld gaming devices, wearable devices, and / or tablet computers. In the illustrated example, server 604 provides information such as boot files, operating system images, and applications to one or more of client electronic devices 610, 612, and 614. Client electronic devices 610, 612, and 614 may be referred to as “clients” in the context of their relationship to a server, such as server computer 604. Client devices may communicate with one or more client data stores 620, which may be used to store information local to the client (e.g., cookie and / or associated contextual information). Network data processing system 600 may include more or fewer servers and / or clients (or no servers or clients), as well as other devices not shown.

[0121] In some examples, the first client electronic device 610 may transfer the encoded file to the server 604. The server 604 may store the file, decode the file, and / or transmit the file to the second client electronic device 612. In some examples, the first client electronic device 610 may transfer the uncompressed file to the server 604, and the server 604 may compress the file. In some examples, the server 604 may encode text, audio, and / or video information and transmit the information to one or more clients over the network 602.

[0122] The client smart device 614 may include any suitable portable electronic device capable of wireless communication and software execution, such as a smartphone or tablet. Generally speaking, the term "smartphone" may refer to any suitable portable electronic device that performs the functions of a computer, typically having a touchscreen interface, Internet access, and an operating system capable of running downloaded applications. In addition to making phone calls (e.g., via a cellular network), a smartphone may be capable of sending and receiving email, text, and multimedia messages, accessing the Internet, and / or functioning as a web browser. A smart device (e.g., a smartphone) may also include the functionality of other known electronic devices, such as a media player, personal digital assistant, digital camera, video camera, and / or global positioning system. A smart device (e.g., a smartphone) may be capable of wirelessly connecting with other smart devices, computers, or electronic devices via near-field communication (NFC), BLUETOOTH, Wi-Fi, or a mobile broadband network, etc. Wireless connections may be established between smart devices, smartphones, computers, and / or other devices to form a mobile network over which information can be exchanged.

[0123] The data and program code located in the system 600 may be stored in or on a computer-readable storage medium, such as the network-attached storage device 608 and / or the persistent storage portion 508 of one of the network computers, as described above, or may be downloaded to a data processing system or other device for use. For example, the program code may be stored in a computer-readable storage medium on the server computer 604 and downloaded to the client 610 over the network 602 for use on the client 610. In some examples, the client data store 620 and the server data store 622 reside on one or more storage devices 608 and / or 508.

[0124] Network data processing system 600 may be implemented as one or more of different types of networks. For example, system 600 may include an intranet, a local area network (LAN), a wide area network (WAN), or a personal area network (PAN). In some examples, network data processing system 600 includes the Internet with network 602, which represents a worldwide collection of networks and gateways that use the Transmission Control Protocol / Internet Protocol (TCP / IP) suite of protocols to communicate with each other. At the heart of the Internet is a backbone of high-speed data communication lines between major nodes or host computers. Thousands of commercial, government, educational, and other computer systems may be utilized to route data and messages. In some examples, network 602 may be referred to as a "cloud." In these examples, each server 604 may be referred to as a cloud computing node, client electronic devices may be referred to as cloud consumers, etc. FIG. 6 is intended as an example and not as an architectural limitation for any illustrative embodiment.

[0125] E. Illustrative Combinations and Additional Examples This section describes additional aspects and features of systems and methods for in-process monitoring of additive manufacturing, presented without limitation in a series of appended clauses, some or all of which may be presented in alphanumeric order for clarity and efficiency. Each of these appended clauses may be combined in any appropriate manner with one or more other appended clauses and / or with disclosure elsewhere in this application. Some of the appended clauses below explicitly refer to and further qualify other appended clauses, providing, without limitation, examples of some suitable combinations.

[0126] A0. A computer-implemented method, comprising: receiving data related to additive manufacturing of the test coupon; identifying one or more manufacturing anomalies in the test coupon based on the received data; identifying one or more manufacturing defects in the test coupon based on the non-destructive testing; performing an alignment between the one or more manufacturing anomalies and the one or more manufacturing defects using a machine learning model to generate a predictive model, the predictive model configured to identify future manufacturing anomalies that will result in future manufacturing defects; 11. A computer-implemented method comprising:

[0127] A1. The computer-implemented method of clause A0, wherein the additive manufacturing process includes laser powder bed fusion.

[0128] A1.1 The computer-implemented method of clause A0, wherein the additive manufacturing process comprises directed energy deposition.

[0129] A2. The computer-implemented method of claim A1, wherein the data related to additive manufacturing of the test coupon includes melt pool data.

[0130] A3. The computer-implemented method of clause A2, wherein the melt pool data includes a size of the melt pool.

[0131] A4. The computer-implemented method of any one of claims A2 and / or A3, wherein the data related to additive manufacturing of the test coupon further includes the power of a laser utilized in laser powder bed fusion.

[0132] A5.1 The computer-implemented method according to any one of appendixes A2 to A4, wherein the manufacturing abnormality includes a sputter abnormality.

[0133] A6. The computer-implemented method of any of clauses A0-A5, wherein the non-destructive testing includes computed tomography (CT).

[0134] A6.1 The computer-implemented method of clause A6, wherein the CT utilizes x-ray image data.

[0135] A7. The computer-implemented method of any of appendices A0-A6, wherein the machine learning model includes a classification model.

[0136] A8. The received data includes image data. The computer-implemented method of any of appendixes A0 to A7, wherein the step of identifying one or more manufacturing defects in the test coupon includes a step of utilizing a computer vision algorithm to identify one or more defects in the image data.

[0137] A9. The computer-implemented method of Clause A8, wherein the computer vision algorithm includes an edge detection algorithm.

[0138] A10. The computer-implemented method of any of claims A0-A9, wherein the received data includes optical tomography data.

[0139] A11. The computer-implemented method of any of Clauses A0-A10, wherein identifying one or more manufacturing defects includes identifying one or more cracks resulting from stress testing of the test coupon.

[0140] A12. Monitoring in-process additive manufacturing of a component using optical tomography to obtain optical tomography data; analyzing the optical tomography data using the predictive model; The computer-implemented method according to any one of appendices A0 to A11, further comprising:

[0141] A12.1. Based on the analyzing step, (i) modifying one or more process parameters of the in-process additive manufacturing, (ii) halting the in-process additive manufacturing, and / or (iii) designating components to be discarded. The computer-implemented method of claim A12, further comprising:

[0142] B0. A data processing system for in-process monitoring of an additive manufacturing process, comprising: one or more processors; Memory and a plurality of instructions stored in a memory; Including, Multiple instructions are receiving data related to the additive manufacturing of the test coupon; identifying one or more manufacturing anomalies in the test coupon based on the received data; identifying one or more manufacturing defects in the test coupon based on non-destructive testing; To perform an alignment between one or more manufacturing anomalies and one or more manufacturing defects using a machine learning model to generate a predictive model. executable by one or more processors; A data processing system, wherein the predictive model is configured to identify future manufacturing anomalies that will result in future manufacturing defects.

[0143] B1. The data processing system of clause B0, wherein the additive manufacturing process includes laser powder bed fusion.

[0144] B1.1 The data processing system of clause B0, wherein the additive manufacturing process comprises directed energy deposition.

[0145] B2. The data processing system of clause B1, wherein the data related to additive manufacturing of the test coupon includes melt pool data.

[0146] B3. The data processing system of Clause B2, wherein the melt pool data includes a size of the melt pool.

[0147] B4. The data processing system of clauses B2 and / or B3, wherein the data relating to the additive manufacturing of the test coupon further includes the power of the laser utilized in the laser powder bed fusion.

[0148] B5. The data processing system according to any one of appendix B2 to B4, wherein the one or more manufacturing abnormalities include a sputter abnormality.

[0149] B6. The data processing system of any one of appendices B0-B5, wherein the non-destructive testing includes computed tomography (CT).

[0150] B6.1 The data processing system of B6, wherein the CT utilizes X-ray image data.

[0151] B7. The data processing system of any one of appendices B0 to B6, wherein the machine learning model includes a classification model.

[0152] B8. The received data includes image data, The data processing system of any of appended clauses B0-B7, wherein the instructions are further executable by the one or more processors to utilize a computer vision algorithm to identify one or more manufacturing defects.

[0153] B8.1. The data processing system of Clause B8, wherein the computer vision algorithm includes an edge detection algorithm.

[0154] B9. The data processing system of any one of appendices B0 to B8.1, wherein the received data includes optical tomography data.

[0155] B10. A data processing system described in any of appendix B0 to B19, wherein the instructions are further executable by one or more processors to identify one or more cracks resulting from stress testing of the test coupon and identify one or more manufacturing defects.

[0156] B11. Multiple instructions are monitoring in-process additive manufacturing of the component using optical tomography to obtain optical tomography data; and analyzing the optical tomography data using a predictive model; The data processing system according to any one of appendixes B0 to B10, further executable by one or more processors.

[0157] B11.1. Multiple instructions Modifying one or more process parameters of the in-process additive manufacturing; and / or Stopping in-process additive manufacturing, and / or To specify the components to be discarded, The data processing system of clause B11, further executable by one or more processors.

[0158] C0. A computer-implemented method for in-process monitoring of an additive manufacturing process, comprising: monitoring the additive manufacturing process using optical tomography; utilizing a predictive model to analyze the optical tomography data, the predictive model identifying one or more manufacturing anomalies that will result in one or more manufacturing defects in the component resulting from the additive manufacturing process; Including, The predictive model is developed by the following steps: receiving historical optical tomography data for additive manufacturing of the test coupon; one or more historical manufacturing anomalies in the test coupon are identified in the historical optical tomography data; One or more manufacturing defects are identified in the test coupon; Alignment between one or more manufacturing anomalies and one or more manufacturing defects is performed, resulting in a predictive model. Trained by,computer-implemented methods.

[0159] C1. The computer-implemented method of Clause C0, wherein one or more historical manufacturing defects in the test coupon are identified by computed tomography (CT).

[0160] C2. The computer-implemented method of claim C0, wherein the CT utilizes x-ray image data.

[0161] C3. The computer-implemented method of any of clauses C0-C2, wherein the additive manufacturing process includes laser powder bed fusion.

[0162] C3.1 The computer-implemented method of any of clauses C0-C2, wherein the additive manufacturing process includes directed energy deposition.

[0163] C3.2. Monitoring a melt pool of an additive manufacturing process to obtain melt pool data; A step of utilizing a predictive model and melt pool data to modify one or more process parameters of an additive manufacturing process. The computer-implemented method of any one of clauses C3 and C3.1, further comprising:

[0164] C3.2.1. The computer-implemented method of Clause C3.2, wherein the melt pool data includes a size of the melt pool.

[0165] C3.3. Monitoring the power of a laser utilized in the additive manufacturing process to obtain laser power data; One step is to use a predictive model and laser power data to modify one or more process parameters. The computer-implemented method of any one of clauses C3 and C3.1, further comprising:

[0166] C3.4 The computer-implemented method of any of clauses C3.2-C3.3, wherein the one or more process parameters include at least one of melt pool size, melt pool temperature, and / or laser power.

[0167] C3.5. The computer-implemented method of any of Clauses C3-C3.4, wherein the one or more manufacturing anomalies and / or one or more past manufacturing anomalies includes a sputter anomaly.

[0168] C4. The computer-implemented method of any of Clauses C0 to C3.3, wherein the predictive model comprises a classification model.

[0169] C5. The computer-implemented method of any of Clauses C0-C4, wherein one or more historical manufacturing anomalies in the test coupon are identified in the historical optical tomography data using a computer vision algorithm.

[0170] C5.1. The computer-implemented method of Clause C5, wherein the computer vision algorithm includes an edge detection algorithm.

[0171] C6. The computer-implemented method of any of Clauses C0-C5.1, wherein identifying one or more manufacturing defects in the test coupon includes identifying one or more cracks resulting from stress testing of the test coupon.

[0172] C7. An additive manufacturing apparatus that uses the computer-implemented method of any of clauses C0-C6 to monitor the production of the resulting components.

[0173] Advantages, Forms, and Benefits The different embodiments and examples of methods and systems for in-process monitoring of additive manufacturing described herein offer several advantages over known solutions for monitoring additive manufacturing processes. For example, the exemplary embodiments and examples described herein can enable real-time detection and correction of manufacturing anomalies, reducing the incidence of defects in the final product.

[0174] Additionally, among other advantages, the exemplary embodiments and examples described herein enable a reduction in material waste and associated costs by enabling proactive adjustments to the manufacturing process rather than relying on post-process testing.

[0175] Additionally, among other advantages, the exemplary embodiments and examples described herein allow for fine tuning of process parameters such as laser power, melt pool size, and scan speed, thereby improving the quality of the manufactured components.

[0176] Additionally, among other benefits, the exemplary embodiments and examples described herein allow for improved quality control, reduced waste, and increased overall efficiency in the manufacturing process.

[0177] There are no known systems or devices that can perform these functions, but not all embodiments and examples described herein offer the same advantages or to the same degree.

[0178] conclusion The above disclosure may encompass multiple separate examples having independent utility. While each of these examples is disclosed in its preferred form(s), the specific embodiments disclosed and illustrated herein are not to be construed in a limiting sense, as numerous variations are possible. Where headings are used within this disclosure, such headings are for organizational purposes only. The subject matter of this disclosure includes all novel and unobvious combinations and subcombinations of the various elements, forms, functions, and / or properties disclosed herein. The following claims particularly point out certain combinations and subcombinations that are deemed novel and unobvious. Other combinations and subcombinations of forms, functions, elements, and / or properties may be claimed in applications claiming priority from this or a related application. Such claims, whether broader, narrower, equivalent, or different in scope from the original claims, are considered to be within the subject matter of this disclosure. [Explanation of symbols]

[0179] 100 system, 102 additive manufacturing process, 104 test coupon, 106 optical tomography device, 108 mechanical testing, 110 fracture analysis, 112 computed tomography, 114 alignment process, 116 predictive model, 118 updated manufacturing instructions, 200 additive manufacturing device, 202 manufactured component, 204 optical tomography imaging device, 300 method, 302 steps, 304 steps, 306 steps, 308 steps, 308A, 308B, 308C subsequent steps, 500 data processing system, 502 system bus, 504 processor unit, 506 memory, 508 persistent storage, 510 communication unit, 512 input / output (I / O) unit, 514 display, 516 storage device, 518 program code, 520 computer readable medium, 522 computer program product, 524 Computer-readable storage medium, 526; Computer-readable signal medium, 528; Interface, 530; Codec, 540; Volatile storage memory, 542; Non-volatile memory, 550; Operating system, 552; Application, 554; Program module, 556; Program data, 560; Remote computer, 562; Network interface, 600; Network data processing system, 602; Network, 604; First network device, server, 606; Second network device, server, 608; Storage device, 610; First client electronic device, 612; Second client electronic device, 614; Client smart device, 620; Client data store, 622; Server data store

Claims

1. receiving (302) data related to additive manufacturing of a test coupon (104); identifying (304) one or more manufacturing anomalies in the test coupon (104) based on the received data; identifying (306) one or more manufacturing defects in the test coupon (104) based on non-destructive testing; performing (308) an alignment between one or more of the manufacturing anomalies and one or more of the manufacturing defects using a machine learning model to generate a predictive model (116), the predictive model (116) being configured to identify future manufacturing anomalies that will result in future manufacturing defects; 11. A computer-implemented method comprising:

2. The computer-implemented method of claim 1 , wherein the additive manufacturing process (102) comprises laser powder bed fusion.

3. The computer-implemented method of claim 1 , wherein the one or more manufacturing anomalies include a sputter anomaly.

4. The computer-implemented method of claim 1 , wherein the non-destructive testing comprises computed tomography (CT) (112).

5. The computer-implemented method of claim 4 , wherein the CT (112) utilizes X-ray image data.

6. the received data includes image data; 2. The computer-implemented method of claim 1, wherein identifying (304) one or more manufacturing anomalies in the test coupon (104) comprises utilizing a computer vision algorithm to identify the one or more manufacturing anomalies in the image data.

7. The computer-implemented method of claim 6 , wherein the computer vision algorithm comprises an edge detection algorithm.

8. A data processing system (500) for in-process monitoring (102) of an additive manufacturing process, comprising: one or more processors (504); A memory (506); a plurality of instructions stored in said memory (506); Including, A plurality of said instructions: receiving data related to additive manufacturing of the test coupon (104); Identifying one or more manufacturing anomalies in the test coupon (104) based on the received data; Identifying one or more manufacturing defects in the test coupon (104) based on non-destructive testing; using a machine learning model to perform an alignment between one or more of the manufacturing anomalies and one or more of the manufacturing defects to generate a predictive model (116); Executable by one or more of said processors (504), The data processing system, wherein the predictive model (116) is configured to identify future manufacturing anomalies that will result in future manufacturing defects.

9. The data processing system of claim 8 , wherein the machine learning model comprises a classification model.

10. 9. The data processing system of claim 8, wherein the received data comprises optical tomography data.

11. 9. The data processing system of claim 8, wherein the non-destructive testing includes computed tomography (CT) (112).

12. 9. The data processing system of claim 8, wherein the instructions are further executable by one or more of the processors to identify one or more cracks resulting from stress testing of the test coupon to identify one or more of the manufacturing defects.

13. A plurality of said instructions: monitoring in-process additive manufacturing of the component using optical tomography to obtain optical tomography data; and to analyze the optical tomography data using the predictive model (116), 9. The data processing system of claim 8, further executable by one or more of said processors (504).

14. A plurality of said instructions: Varying one or more process parameters of the in-process additive manufacturing; and / or Stopping the in-process additive manufacturing; and / or To specify the components to be discarded, 14. The data processing system of claim 13, further executable by one or more of said processors (504).

15. 1. A computer-implemented method (300) for in-process monitoring of an additive manufacturing process (102), the method (300) comprising: monitoring (310) the additive manufacturing process (102) using optical tomography to obtain optical tomography data; utilizing a predictive model (116) to analyze the optical tomography data, wherein the predictive model (116) identifies one or more manufacturing anomalies that will result in one or more manufacturing defects in a component resulting from the additive manufacturing process (102); Including, The predictive model (116) receiving historical optical tomography data relating to additive manufacturing of the test coupon (104); one or more historical manufacturing anomalies in the test coupon (104) are identified in the historical optical tomography data; Identifying one or more manufacturing defects in the test coupon (104); The alignment between the one or more manufacturing anomalies and the one or more manufacturing defects results in the predictive model (116). Trained by,computer-implemented methods.

16. The method (300) monitoring the output of a laser utilized in the additive manufacturing process (102) to obtain laser output data; utilizing the predictive model (116) and the laser output data to modify one or more process parameters; The computer-implemented method of claim 15 further comprising:

17. 17. The computer-implemented method of claim 16, wherein the one or more process parameters comprise at least one of melt pool size, melt pool temperature, and / or laser power.

18. 16. The computer-implemented method of claim 15, wherein the one or more historical manufacturing anomalies in the test coupon (104) are identified in the historical optical tomography data using a computer vision algorithm.

19. 16. The computer-implemented method of claim 15, wherein identifying one or more manufacturing defects in the test coupon comprises identifying one or more cracks resulting from stress testing of the test coupon.

20. 16. An additive manufacturing apparatus using the computer-implemented method (300) of claim 15 to monitor the production of the resulting component.

Images