System and method for manufacturing

Abstract

Provided is a system, method, and device for manufacturing. A manufacturing device includes at least one sensor, at least one end-effector member configured to add and / or subtract material to manufacture an object, and at least one computing device in communication with the at least one sensor, and a control system for the at least one end-effector member, the at least one computing device configured to scan each layer of a plurality of layers of an object manufactured by the end-effector member and modify at least one layer of the plurality of layers based on comparing at least one scan of the at least one layer or at least one previous layer to a 3D representation of the at least one layer or the at least one previous layer.

Description

Attorney Docket No.08993-2407108 SYSTEM AND METHOD FOR MANUFACTURING CROSS-REFERENCE TO REPLATED APPLICATION

[0001] This application claims the benefit of United States Provisional Patent Application No. 63 / 541,654 filed on September 29, 2023, the disclosure of which is hereby incorporated by reference in its entirety. BACKGROUND 1. Field

[0002] This disclosure relates generally to additive manufacturing and, in non-limiting embodiments, to systems and methods for manufacturing using at least one sensor. 2. Technical Considerations

[0003] Additive manufacturing processes involve manufacturing parts by building them layer-by-layer and have been widely used in various industries for rapid prototyping or to fabricate functional parts. However, current additive manufacturing processes are prone to stochastic failures and lack reliability, which significantly limit their use in engineering and critical applications.

[0004] Generally, parts manufactured using deposition-based additive manufacturing methods are considered mechanically weak due to inconsistency in material deposition. These deposition inconsistencies can also lead to deviation of the part from the intended design, causing geometric defects. Furthermore, deposition errors such as under-deposition will lead to mechanical failure, while over-deposition may pose a risk during manufacturing, as collision with a significant geometric defect can damage the equipment.

[0005] Currently, a majority of additive manufacturing methods rely upon a pre- programmed open-loop workflow and adhere to a set motion path without any sensory feedback to adjust the motion or process parameters. While this open-loop workflow is fast and cost-effective for manufacturing, it often results in lower product quality and inaccuracies. Recent studies address quality control of the parts made using additive manufacturing by coupling the fabrication process with post-inspection methods that utilize additional equipment such as coordinate measuring machines (CMM), computer vision, or expensive and bulky 3D scanners. Post-inspection methods provide significant benefits toward after-build quality assessment, but they are time-consuming and cannot reduce fabrication failures and defects due to the nature of post-inspection. 5Y94264.DOCX Page 1 of 27Attorney Docket No.08993-2407108

[0006] One approach for process monitoring involves applying a mechanical load to the workpiece and detecting acoustic waves emitted by internal defects. Another approach involves in-situ inspection and defect monitoring by using machine learning and computer vision. Yet another approach uses a closed-loop control method on machine parameters based on image analysis, relying on tuned proportional–integral–derivative (PID) controller parameters, which limits its generalizability to even different layers of the same part. Another closed-loop parameter tuning and re-slicing system ensures the printed part reaches a width and height within the desired tolerances, but relies on the heuristics of re-slicing software and cannot handle infill areas. The related art for monitoring and control strategies either lack approaches to address the detected defects during fabrication or are limited to control strategies that lack generalizability as they are specifically tuned for selective process parameters. Existing post-inspection and over-inspection approaches either fail to prevent fabrication failures or significantly increase the inspection cost. Therefore, a layer-wise inspection and repair framework that is adequate to identify and correct defects during fabrication could improve build quality and reduce the cost of inspection. SUMMARY

[0007] According to non-limiting embodiments or aspects, provided is a system comprising at least one processor configured to: (a) control a fabrication device to manufacture a layer of a plurality of layers of a 3D model by moving an end-effector member of the fabrication device; (b) scanning a surface of the layer with at least one sensor arranged to move with the end-effector member relative to the layer, resulting in a scanned 3D representation; (c) determining if the layer comprises a defect by comparing the scanned 3D representation to 3D data for a corresponding layer of the 3D model; (d) in response to determining the layer comprises the defect, determining whether the defect comprises a positive defect or a negative defect; (e) in response to determining that the defect comprises the positive defect, controlling the fabrication device to re-plan the layer; (f) in response to determining that the defect comprises the negative defect, controlling the fabrication device to repair the layer; (g) repeat steps (a)-(f) with at least one next layer of the plurality of layers.

[0008] In non-limiting embodiments or aspects, the at least one sensor comprises a laser projector and a camera, the at least one sensor configured to measure depth of a point. In non- limiting embodiments or aspects, the at least one processor is further configured to stich a plurality of depth measurements together to form point cloud data. In non-limiting embodiments or aspects, the end-effector member and the at least one sensor are co-located 5Y94264.DOCX Page 2 of 27Attorney Docket No.08993-2407108 on an end of a movable unit. In non-limiting embodiments or aspects, the at least one processor is further configured to: generate a 3D point cloud by combining the scanned 3D representations obtained for each layer of the plurality of layers. In non-limiting embodiments or aspects, a 3D point cloud is generated by transforming each scan of point cloud data into a fixed coordinate system relative to the fabrication device based on a pose of the end-effector member after each layer is manufactured. In non-limiting embodiments or aspects, the processor is further configured to adjust a rate of the end-effector member based on a detected defect classification.

[0009] According to non-limiting embodiments or aspects, provided is a method of manufacturing comprising: instructing, with at least one computing device, a manufacturing device to manufacture a layer of a plurality of layers with an end-effector member; scanning, with at least one computing device, the layer to produce a scanned 3D representation of the layer; calculating, with at least one computing device, a registration differential between the scanned 3D representation of the layer and a 3D representation of the layer; determining, with at least one computing device, a manufacturing protocol based on the registration differential; and executing, with at least one computing device, the manufacturing protocol.

[0010] In non-limiting embodiments or aspects, wherein, in response to the registration differential being substantially zero, the manufacturing protocol comprises instructing the manufacturing device to manufacture a next layer of the plurality of layers. In non-limiting embodiments or aspects, wherein, in response to the registration differential satisfying a threshold, the manufacturing protocol comprises a positive-defect protocol for a positive defect or a negative-defect protocol for a negative defect. In non-limiting embodiments or aspects, the positive-defect protocol comprises: generating a replan path for at least one next layer of the plurality of layers. In non-limiting embodiments or aspects, wherein executing the replan path comprises: projecting the scanned 3D representation of the layer with the positive defect onto a surface of the layer; computing an alpha shape of the positive defect to generate a polygon representation of the positive defect; projecting a planned trajectory onto the surface of the layer; determining where a planned trajectory of a next layer intersects with the polygon; modifying the planned trajectory for the next layer based on the intersection.

[0011] In non-limiting embodiments or aspects, the positive-defect protocol comprises: generating a repair path for the layer before a next layer of the plurality of layers is manufactured. In non-limiting embodiments or aspects, wherein executing the repair path comprises: projecting the scanned 3D representation of the layer with the negative defect onto a surface of the layer; computing an alpha shape of the positive defect to generate a 5Y94264.DOCX Page 3 of 27Attorney Docket No.08993-2407108 polygon representation of the negative defect; generating an infill path of the negative defect by offsetting a boundary of the polygon; calculating a repair path to fill the boundary of the negative defect by following the infill path; and modifying the manufacturing volume and / or rate of the manufacturing device according to a length of the repair path and / or volume of the negative defect. In non-limiting embodiments or aspects, the end-effector member and at least one sensor are co-located on an end of a robotic arm of the manufacturing device. In non-limiting embodiments or aspects, further comprising: instructing the manufacturing device to manufacture at least one next layer of the plurality of layers; generate a 3D point cloud by combining the scanned 3D representation obtained for each layer of the plurality of layers. In non-limiting embodiments or aspects, wherein scanning the layer comprises: projecting a laser with a laser projector over a surface of the layer; generating a 2D image of the layer comprising the laser with a camera; measuring 3D information of the layer by triangulating laser points from the 2D image; and stitching the 3D information together across time to construct a 3D point cloud of the layer.

[0012] According to non-limiting embodiments or aspects, provided is a manufacturing device comprising: at least one laser projector; at least one visual sensor; at least one end- effector member configured to add and / or subtract material to manufacture an object; and at least one computing device in communication with the at least one laser projector, the at least one visual sensor, and a control system for the at least one end-effector member, the at least one computing device configured to: scan each layer of a plurality of layers of an object manufactured by the end-effector member; and modify at least one layer of the plurality of layers based on comparing at least one scan of the at least one layer or at least one previous layer to a 3D representation of the at least one layer or the at least one previous layer.

[0013] In non-limiting embodiments or aspects, further comprising a robotic arm, the at least one laser projector and the at least one visual sensor are co-located with the at least one end-effector on a robotic arm. In non-limiting embodiments or aspects, the at least one computing device is further configured to: control the at least one end-effector to manufacture each layer of the plurality of layers, wherein each layer is scanned while the at least one end-effector is manufacturing the layer. In non-limiting embodiments or aspects, the at least one computing device is further configured to: detect at least one defect in the at least one layer or the at least one previous layer based on comparing the at least one scan of the at least one layer or the at least one previous layer to the 3D representation of the at least one layer or the at least one previous layer; determine a classification for the at least one defect, the at least one layer is modified based on the classification. In non-limiting embodiments or 5Y94264.DOCX Page 4 of 27Attorney Docket No.08993-2407108 aspects, wherein comparing the at least one scan of the at least one layer or the at least one previous layer to the 3D representation of the at least one layer or the at least one previous layer results in a differential, and the classification is determined based on comparing the differential to at least one threshold.

[0014] Other preferred and non-limiting embodiments or aspects of the present invention will be set forth in the following numbered clauses:

[0015] Clause 1: A system comprising at least one processor configured to: (a) control a fabrication device to manufacture a layer of a plurality of layers of a 3D model by moving an end-effector member of the fabrication device; (b) scanning a surface of the layer with at least one sensor arranged to move with the end-effector member relative to the layer, resulting in a scanned 3D representation; (c) determining if the layer comprises a defect by comparing the scanned 3D representation to 3D data for a corresponding layer of the 3D model; (d) in response to determining the layer comprises the defect, determining whether the defect comprises a positive defect or a negative defect; (e) in response to determining that the defect comprises the positive defect, controlling the fabrication device to re-plan the layer; (f) in response to determining that the defect comprises the negative defect, controlling the fabrication device to repair the layer; (g) repeat steps (a)-(f) with at least one next layer of the plurality of layers.

[0016] Clause 2: The system of clause 1, wherein the at least one sensor comprises a laser projector and a camera, the at least one sensor configured to measure depth of a point.

[0017] Clause 3: The system of any of any of clauses 1-2, wherein the at least one processor is further configured to stich a plurality of depth measurements together to form point cloud data.

[0018] Clause 4: The system of any of clauses 1-3, wherein the end-effector member and the at least one sensor are co-located on an end of a robotic arm.

[0019] Clause 5: The system of any of clauses 1-4, wherein the at least one processor is further configured to: generate a 3D point cloud by combining the 3D representations obtained for each layer of the plurality of layers.

[0020] Clause 6: The system of any of any of clauses 1-5, wherein the 3D point cloud is generated by transforming each scan into a fixed coordinate system relative to the fabrication device based on a pose of the end-effector member after each layer is manufactured.

[0021] Clause 7: The system of any of clauses 1-6, wherein the processor is further configured to adjust a rate of the end-effector member based on a detected defect classification. 5Y94264.DOCX Page 5 of 27Attorney Docket No.08993-2407108

[0022] Clause 8: A method of manufacturing comprising: instructing, with at least one computing device, a manufacturing device to manufacture a layer of a plurality of layers with an end-effector member; scanning, with at least one computing device, the layer to produce a scanned 3D representation of the layer; calculating, with at least one computing device, a registration differential between the scanned 3D representation of first layer and a reference of the layer; determining, with at least one computing device, a manufacturing protocol based on the registration differential; and executing, with at least one computing device, the manufacturing protocol.

[0023] Clause 9: The method clause 8, wherein, in response to the registration differential being substantially zero, the manufacturing protocol comprises instructing the manufacturing device to manufacture a next layer of the plurality of layers.

[0024] Clause 10: The method of any of clauses 8-9, wherein, in response to the registration differential satisfying a threshold, the manufacturing protocol comprises a positive-defect protocol for a positive defect or a negative-defect protocol for a negative defect.

[0025] Clause 11: The method of any of clauses 8-10, wherein the positive-defect protocol comprises: generating a replan path for at least one next layer of the plurality of layers.

[0026] Clause 12: The method of any of clauses 8-11, wherein executing the replan path comprises: projecting the scanned 3D representation of the layer with the positive defect onto a surface of the layer; computing an alpha shape of the positive defect to generate a polygon representation of the positive defect; projecting a planned trajectory onto the surface of the layer; determining where a planned trajectory of a next layer intersects with the polygon; modifying the planned trajectory for the next layer based on the intersection.

[0027] Clause 13: The method of any of clauses 8-12, wherein the positive-defect protocol comprises: generating a repair path for the layer before a next layer of the plurality of layers is manufactured.

[0028] Clause 14: The method of any of clauses 8-13, wherein executing the repair path comprises: projecting the scanned 3D representation of the layer with the negative defect onto a surface of the layer; computing an alpha shape of the positive defect to generate a polygon representation of the negative defect; generating an infill path of the negative defect by offsetting a boundary of the polygon; calculating a repair path to fill the boundary of the negative defect by following the infill path; and modifying the manufacturing volume and / or 5Y94264.DOCX Page 6 of 27Attorney Docket No.08993-2407108 rate of the manufacturing device according to a length of the repair path and / or volume of the negative defect.

[0029] Clause 15: The method of any of claims 8-14, wherein the end-effector member and at least one sensor are co-located on an end of a robotic arm of the manufacturing device. 16. The method of any of claims 8-16, further comprising: instructing the manufacturing device to manufacture at least one next layer of the plurality of layers; generate a 3D point cloud by combining the scanned 3D representation obtained for each layer of the plurality of layers. 17. The method of any of claims 8-16, wherein scanning the layer comprises: projecting a laser with a laser projector over a surface of the layer; generating a 2D image of the layer comprising the laser with a camera; measuring 3D information of the layer by triangulating laser points from the 2D image; and stitching the 3D information together across time to construct a 3D point cloud of the layer.

[0030] Clause 18: A manufacturing device comprising: at least one sensor; at least one end-effector member configured to add and / or subtract material to manufacture an object; and at least one computing device in communication with the at least one sensor, and a control system for the at least one end-effector member, the at least one computing device configured to: scan each layer of a plurality of layers of an object manufactured by the end-effector member; and modify at least one layer of the plurality of layers based on comparing at least one scan of the at least one layer or at least one previous layer to a 3D representation of the at least one layer or the at least one previous layer.

[0031] Clause 19: The manufacturing device of clause 18, further comprising a movable unit, wherein the at least one laser projector and the at least one visual sensor are co-located with the at least one end-effector on the movable unit.

[0032] Clause 20: The manufacturing device of any of clauses 18-19, wherein the at least one computing device is further configured to: control the at least one end-effector to manufacture each layer of the plurality of layers, wherein each layer is scanned while the at least one end-effector is manufacturing the layer.

[0033] Clause 21: The manufacturing device of any of clauses 18-20, wherein the at least one computing device is further configured to: detect at least one defect in the at least one layer or the at least one previous layer based on comparing the at least one scan of the at least one layer or the at least one previous layer to the 3D representation of the at least one layer or the at least one previous layer; determine a classification for the at least one defect, wherein the at least one layer is modified based on the classification. 5Y94264.DOCX Page 7 of 27Attorney Docket No.08993-2407108

[0034] Clause 22: The manufacturing device of any of clauses 18-21, wherein comparing the at least one scan of the at least one layer or the at least one previous layer to the 3D representation of the at least one layer or the at least one previous layer results in a differential, and wherein the classification is determined based on comparing the differential to at least one threshold.

[0035] These and other features and characteristics of the present disclosure, as well as the methods of operation and functions of the related elements of structures and the combination of parts and economies of manufacture, will become more apparent upon consideration of the following description and the appended claims with reference to the accompanying drawings, all of which form a part of this specification, wherein like reference numerals designate corresponding parts in the various figures. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Additional advantages and details are explained in greater detail below with reference to the non-limiting, exemplary embodiments that are illustrated in the accompanying figures shown in the separate attachment, in which:

[0037] FIG. 1 is a schematic diagram of a manufacturing system according to non- limiting embodiments or aspects;

[0038] FIG.2 an illustration of a robot arm scanning an object allowing reconstruction of a 3D point cloud according to non-limiting embodiments or aspects;

[0039] FIGS. 3A-3D are illustrations of geometric defects and defect correction according to non-limiting embodiments or aspects;

[0040] FIGS.4A and 4B are illustrations of a re-planning strategy for handling a positive defect according to non-limiting embodiments or aspects;

[0041] FIGS. 5A and 5B are illustrations of a repair strategy of a negative defect according to non-limiting embodiments or aspects;

[0042] FIG. 6 is an illustration of a manufacturing device according to non-limiting embodiments or aspects; and

[0043] FIG. 7 illustrates example components of a computing device used in connection with non-limiting embodiments or aspects. 5Y94264.DOCX Page 8 of 27Attorney Docket No.08993-2407108 DETAILED DESCRIPTION

[0044] It is to be understood that the embodiments may assume various alternative variations and step sequences, except where expressly specified to the contrary. It is also to be understood that the specific devices and processes described in the following specification are simply exemplary embodiments or aspects of the disclosure. Hence, specific dimensions and other physical characteristics related to the embodiments or aspects disclosed herein are not to be considered as limiting. No aspect, component, element, structure, act, step, function, instruction, and / or the like used herein should be construed as critical or essential unless explicitly described as such. Also, as used herein, the articles “a” and “an” are intended to include one or more items and may be used interchangeably with “one or more” and “at least one.” Also, as used herein, the terms “has,” “have,” “having,” or the like are intended to be open-ended terms. Further, the phrase “based on” is intended to mean “based at least partially on” unless explicitly stated otherwise.

[0045] As used herein, the terms “communication” and “communicate” refer to the receipt or transfer of one or more signals, messages, commands, or other type of data. For one unit (e.g., any device, system, or component thereof) to be in communication with another unit means that the one unit is able to directly or indirectly receive data from and / or transmit data to the other unit. This may refer to a direct or indirect connection that is wired and / or wireless in nature. Additionally, two units may be in communication with each other even though the data transmitted may be modified, processed, relayed, and / or routed between the first and second unit. For example, a first unit may be in communication with a second unit even though the first unit passively receives data and does not actively transmit data to the second unit. As another example, a first unit may be in communication with a second unit if an intermediary unit processes data from one unit and transmits processed data to the second unit. It will be appreciated that numerous other arrangements are possible.

[0046] As used herein, the terms “processor” or “computing device” may refer to one or more electronic devices configured to process data. A processor and / or computing device may include, for example, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a microprocessor, a controller, and / or any other computational device capable of executing logic. A “computer readable medium” may refer to one or more memory devices or other non-transitory storage mechanisms capable of storing compiled or non-compiled program instructions for execution by one or more processors. Reference to “a processor” or 5Y94264.DOCX Page 9 of 27Attorney Docket No.08993-2407108 “a computing device” as used herein, may refer to a previously-recited computing device and / or processor that is recited as performing a previous step or function, a different server and / or processor, and / or a combination of computing devices and / or processors. For example, as used in the specification and the claims, a first computing device and / or a first processor that is recited as performing a first step or function may refer to the same or different computing device and / or a processor recited as performing a second step or function.

[0047] In non-limiting embodiments, a manufacturing system is provided that overcomes technological deficiencies associated with existing devices and methods. A manufacturing system, as described herein, may include a manufacturing device (e.g., fabrication device), such as an additive manufacturing device, a subtractive manufacturing device, a hybrid manufacturing device, at least one sensor, and at least one computing device (e.g., such as a processor). The manufacturing device, sensor, and processor may act sequentially to detect geometric defects that may occur as the manufacturing device performs layer-wise fabrication, e.g., deposition and / or subtraction, formulate a plan to adjust fabrication based on the defects, and execute the plan to correct the defects. In non-limiting embodiments the manufacturing device may include hardware components such as, for example, an end- effector member (e.g., one or more tools such as a filament extruder, a deposition member, a nozzle, a blade, a drill, a print head, a material dispenser, a spray or jet nozzle, and / or the like) for manufacturing, an end-effector positioning system (e.g., using a robotic arm, movable frame, and / or any other type of movable unit), a heated print bed, an end-effector heater and cooler, and / or a controller. The sensor, for example, may include a sensor arrangement including a laser projector (e.g., configured to project a laser line) and a visual sensor (e.g., such as a monocular camera). In some non-limiting embodiments the laser projector and visual sensor may be collocated or separated (e.g., on the same robot arm or other movable unit, or a different robot arm or other movable unit). It will be appreciated that the sensor may be one or more of any type of sensor capable of sensing 3D information and / or 2D information that can be processed to determine or predict 3D information. For example, a single-dot distance / depth sensor may be used as the sensor in some non-limiting embodiments. As another example, in some non-limiting embodiments the sensor may include a 2D camera that captures frames used to predict 3D information (e.g., 3D error). Other variations are also possible to capture information that can be used to generate a 3D representation of the layer. 5Y94264.DOCX Page 10 of 27Attorney Docket No.08993-2407108

[0048] The sensor may measure 3D information by triangulating laser points from a 2D image of the laser points on a surface (e.g., the uppermost layer of deposition and / or subtraction). In non-limiting embodiments, the sensor may be more compact compared to commercial sensors and may have a form factor of, for example, 80 x 14.5 x 52mm, allowing it to fit in the limited space next to the end-effector member in a manufacturing device. The sensor may include one or more cameras with different resolutions and / or one or more laser line projectors with varying projection patterns. In some non-limiting embodiments, the sensor may be any type of depth sensor and / or sensor capable of measuring 2D and 3D properties of a manufactured object (e.g., workpiece) and / or feature. In such examples, the sensor may not use a camera and / or laser. Referring now to FIG. 1, shown is a schematic diagram of a manufacturing system 1000 according to non-limiting embodiments. The manufacturing system 1000 includes a fabrication subsystem 101, an inspection subsystem 103, and a correction subsystem 102. One or more computing devices (not shown in FIG. 1) may be included in the system 1000 and / or subsystems 101, 102, 103. For example, each subsystem 101, 102, 103 may have one or more separate computing devices. In other examples, one or more subsystems 101, 102, 103 may share a common computing device. The computing device may execute one or more software applications local and / or remote to the computing device. For example, the computing device may execute software applications that correspond to each of the subsystems 101, 102, 103.

[0049] With continued reference to FIG. 1, the fabrication subsystem 101 may include a parser 104, such as a GCode parser, that receives software code (e.g., such as GCode or the like) and inputs the code into an instruction queue 105. The instruction queue 105 maintains a sequence of software code and provides control commands to a positioning system 107 and end-effector member 106 of a manufacturing device. The inspection subsystem 103 performs layer-by-layer 3D scanning to detect geometric defects during fabrication with a sensor arrangement 108. The inspection subsystem 103 may scan each layer as it is being deposited and / or formed (e.g., subtracted). Additionally or alternatively, the inspection subsystem 103 may scan each layer after the layer has been completed. A 3D accumulator 109 may be software and / or hardware (e.g., such as a software application or routine executed by one or more computing devices) configured to compile the consecutive layer-wise scans captured by the scanning arrangement 108 to produce a 3D representation (e.g., such as a 3D point cloud) of the entire printed object. The inspection subsystem 103 may also include a defect detection 110 step to classify the detected geometric defects in categories, such as positive or negative defects. The correction subsystem 102 amends geometric defects encountered during 5Y94264.DOCX Page 11 of 27Attorney Docket No.08993-2407108 fabrication by associating each defect type with a replan strategy 111 or repair strategy 112. Positive defects may be corrected with a replan strategy 111 which modifies the subsequent layer to rectify the defect. For example, the re-plan strategy 111 may modify the trajectory of the end-effector member 106 by instructing the positioning system 107 to prevent the end- effector member 106 from depositing over a positive defect or creating additional positive defects.

[0050] In non-limiting embodiments, the sensor arrangement 108 may be controlled using techniques described in U.S. Patent Application No. 17 / 924,570 (U.S. Patent App. No. 2023 / 0186496), filed November 10, 2022, the entirety of which is incorporated herein by reference.

[0051] Referring now to FIG 2, shown is an illustration of the inspection subsystem according to non-limiting embodiments. The inspection subsystem may include a sensor arrangement 201 mounted to a movable unit 200 (e.g., robot arm or other device that can move an end-effector to manufacture an object or feature) to allow the sensor arrangement 201 to scan a 3D model to reconstruct a scanned 3D representation (e.g., scanned point cloud) by combining (e.g., concatenating, stitching, and / or the like) laser line scans 202 along a linear coverage scan. Although a robot arm is shown in the example in FIG. 2, it will be appreciated that different type of manufacturing devices may use different types of movable units to support an end-effector that deposits, adds, and / or subtracts. For example, a movable unit 200 may include a platform configured to move along two or three axes on a track, motion frame, and / or the like. The sensor arrangement 201 and / or moveable unit 200 may be in communication with one or more computing devices configured to control the sensor arrangement 201 and / or moveable unit 200, receive data from the sensor arrangement 201, and perform the calculations and steps described herein. The sensor arrangement 201 may include one or more cameras (not shown in FIG. 2) with different resolutions and one or more laser projectors (e.g., such as a laser profiler) to project the laser line scans 202 with varying projections to capture different minimum feature sizes ℓ^^^^ ^^^^ ^^^^by adjusting the variables of the camera sensor width ^^^^, distance to object ^^^^, effective focal length ^^^^^^^^, and camera resolution ^^^^^^^^:

[0052] With continued reference to FIG. 2, in non-limiting embodiments the sensor arrangement 201 may measure depth along the projected laser line. The measurements may then be stitched across time (e.g., across various timesteps corresponding with the deposition) 5Y94264.DOCX Page 12 of 27Attorney Docket No.08993-2407108 to reconstruct a 3D point cloud of the most-current layer. The sensor arrangement 201 may perform a linear coverage scan between each layer as the layer is added and / or formed. The pose of the robot arm 200 at each time step may then be used to transform each line scan into a fixed coordinate system of the base frame of the robot (e.g., a relative coordinate system), and the scans may be combined (e.g., concatenated and / or the like) into a single 3D point cloud of the manufactured part.

[0053] With continued reference to FIG.2, the sensor arrangement 201 and the projected laser lines 202 may be used to calculate a scanned point cloud ^^^^^^^^^^^^(or other 3D representation) of a most-current layer ^^^^. The scanned point cloud ^^^^^^^^^^^^may then be compared to a reference point cloud ^^^^^^^^(or other 3D representation) sliced at ^^^^^^^^^^^^to detect defects. For example, the defect detection process may be initialized by obtaining a dense point cloud ^^^^^^^^by performing volumetric sampling on a reference model, such as a 3D CAD model. After an initial layer ^^^^ is deposited and / or subtracted by the manufacturing device, the layer can be preprocessed by obtaining a scanned point cloud ^^^^^^^^^^^^0 from the scanning sensor. The scanned point cloud may be filtered by using a manually defined crop box followed by statistical outlier removal to obtain ^^^^^^^^^^^^. The reference cloud ^^^^^^^^^^^^0 for layer ^^^^ may then be extracted from ^^^^^^^^using the known z-level, e.g., the absolute z-height in robot coordinates, of layer ^^^^, ^^^^^^^^:^^^^^^^^^^^^← ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^( ^^^^^^^^, ^^^^^^^^^^^^0 )

[0054] After pre-processing, point cloud registration may be performed between ^^^^^^^^^^^^and ^^^^^^^^^^^^0. The workpiece transformation with respect to the robot base may be used as an initial alignment, which can be further refined, such as by using an iterative closest point (ICP) algorithm. The obtained transformation may then be used to transform ^^^^^^^^^^^^0onto ^^^^ ^^^^^^^^ to get ^^^^ ^^^^^^^^:( ^^^^0, ^^^^0) ← ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^ ^^^^^^^^^^^^^^^^← ^^^^^^^^^^^^^^^^^^^^ ^^^^0 + ^^^^^^^^ / / Apply transformation to ^^^^^^^^

[0055] For example, to detect a defect, the difference (e.g., differential) of point clouds ^^^^^^^^may be calculated by taking every point in ^^^^^^^^^^^^not near some point in ^^^^^^^^^^^^, where a measured distance to ^^^^^^^^^^^^may be defined as ^^^^^^^^ ^^^^^^^^. The difference of point clouds ^^^^^^^^may be computed using a K-Dimensional (KD) Tree on ^^^^^^^^^^^^, segmenting each point ^^^^^^^^∈ ^^^^^^^^^^^^with:5Y94264.DOCX Page 13 of 27Attorney Docket No.08993-2407108 where ^^^^ is a tunable threshold parameter, such as half the layer height where geometries outside a 1-layer band are detected as defects. Alternatively, the difference of point clouds ^^^^^^^^may be calculated with:The detected defects in ^^^^^^^^may be further categorized into positive ^^^^^^^^^^^^and negative ^^^^^^^^^^^^ defects based on the layer z-level ^^^^^^^^where defect points with ^^^^ ≥ ^^^^^^^^are positive defects and defect points with ^^^^ < ^^^^^^^^are negative defects: ^^^^^^^^^^^^ ^^^^(^^^^)= inf^^^^^^^^∈ ^^^^ ^^^^‖^^^^ − ^^^^ ^^^^‖^^^^

[0056] In non-limiting embodiments, the following software procedure and / or other like software procedures may be executed by a computing device in communication with the manufacturing device to detect defects: 5Y94264.DOCX Page 14 of 27Attorney Docket No.08993-2407108

[0057] In non-limiting embodiments, a differential (e.g., point cloud differential or any other differential between 3D representations) may be compared to one or more thresholds. For example, in response to satisfying a threshold (e.g., meeting or exceeding a predetermined threshold value), it may be determined that there is a defect. If the differential does not satisfy the threshold and / or is substantially zero, it may be determined that there is no defect.

[0058] Referring now to FIGS.3A-3D, shown are illustrations of an end-effector member 300 encountering a positive defect 302 and a negative defect 303 before and after a correction strategy is performed by the correction subsystem (not shown in FIGS. 3A-3D) according to non-limiting embodiments. The manufacturing device shown in FIGS. 3A-3D is an additive manufacturing device, although it will be appreciated that such processes may also be performed with a subtractive and / or hybrid manufacturing device. FIG. 3A shows an end- effector member 300 (e.g., a deposit head in this example) depositing a layer 301 of material 5Y94264.DOCX Page 15 of 27Attorney Docket No.08993-2407108 with a positive defect 302 obstructing the path of the end-effector member 300. Positive defects may include over-depositions that lie above the deposition z-height and may obstruct the path of the deposition member and / or may affect the geometric tolerances of the manufactured part.

[0059] FIG. 3B shows an example of a re-plan strategy used when the inspection subsystem detects a positive defect blocking the path of the end-effector member 300 according to non-limiting embodiments. The path of the end-effector member 300 may be replanned to avoid the obstructing positive defect and the deposition (or subtraction in other embodiments) is adjusted so that the end-effector member 300 may deposit a layer 301 or modify a layer 301 without being obstructed by the positive defect. It will be appreciated that, in non-limiting embodiments using a subtractive and / or hybrid manufacturing device, detecting a positive defect may result in a repair strategy to remove the positive defect and / or reduce the positive defect with a subtraction layer or set of layers.

[0060] FIG. 3C shows an end-effector member 300 depositing a layer 301 of material with a negative defect 303 according to non-limiting embodiments. Negative defects may include, for example, under-depositions that cause the part surface to lie below the expected z-height, such as under-deposited or over-subtracted voids that affect the bonding strength between layers, reducing the strength and integrity of the manufactured part.

[0061] FIG. 3D shows an example of a repair strategy used when the system detects a negative defect in the path of the end-effector member 300. The end-effector member 300 may be instructed to fill in the negative defect so that it may deposit a layer 301 that remains flat. It will be appreciated that, in non-limiting embodiments using a subtractive and / or hybrid manufacturing device, detecting a negative defect may result in a re-plan strategy to avoid subtracting some or all of the negative defect region on the next layer or set of layers.

[0062] Referring now to FIGS. 4A and 4B, shown are illustrations of a projection of a manufacturing device with a positive defect 400 in the path of the end-effector member and a re-plan strategy according to non-limiting embodiments. The manufacturing device shown in FIGS. 4A and 4B is an additive manufacturing device, although it will be appreciated that such processes may also be performed with a subtractive and / or hybrid manufacturing device. The manufacturing device may encounter a positive defect 400 when depositing a layer and execute a re-plan strategy to modify the deposition and motion trajectory of the end-effector member to prevent the end-effector member from colliding with the positive defect and from over-depositing. For example, when a positive defect is detected in the layer, a scanned point cloud of the layer with a defect may be projected from 3D representation onto the 2D print 5Y94264.DOCX Page 16 of 27Attorney Docket No.08993-2407108 surface and the projection may be used to compute an alpha shape, e.g., planar representation, of the defect points.

[0063] It will be appreciated that, in non-limiting embodiments using a subtractive and / or hybrid manufacturing device, detecting a positive defect may result in a repair strategy to remove the positive defect and / or reduce the positive defect with a subtraction layer or set of layers.

[0064] FIG. 4A shows a projection of the positive defect 400 intersecting the path of the end-effector member. A planned trajectory of coordinates of a subsequent layer may then be projected from 3D representation onto the print surface to check for potential collisions. If the trajectory of the subsequent layer intersects with the representation of the positive defect 400 (e.g., a 2D defect polygon), the path of the end-effector member may be re-planned by splitting the trajectory across the positive defect. For example, FIG. 4B shows modification of the path of the end-effector member when encountering a positive defect 400 by removing the line segments intersecting with the positive defect and joining them with the skip paths, shown in dashed lines, to avoid deposition onto the positive defect. The re-planned deposition member path is then adjusted with a z-hop, e.g., a vertical lift, to pass above the positive defect and, while lifted, the deposition member travels along the skip paths. Deposition may be paused during the lifted motion to ensure no additional material is deposited to the defect.

[0065] Referring now to FIGS. 5A and 5B, shown are illustrations of a manufacturing device with a negative defect and a repair strategy according to non-limiting embodiments. The manufacturing device shown in FIGS. 5A and 5B is an additive manufacturing device, although it will be appreciated that such processes may also be performed with a subtractive and / or hybrid manufacturing device. The manufacturing device may encounter a negative defect such as, for example, an under-deposited void, when depositing a layer and execute a repair strategy to fill in the negative defect to ensure that the subsequent layer lies evenly on top of the previous layer, minimizing the chances of further defects. For example, when a negative defect is detected, a scanned point cloud of the layer with a defect may be projected from 3D representation onto the 2D print surface and the projection may be used to compute an alpha shape, e.g., a planar representation, of the defect points.

[0066] It will be appreciated that, in non-limiting embodiments using a subtractive and / or hybrid manufacturing device, detecting a negative defect may result in a re-plan strategy to avoid subtracting some or all of the negative defect region on the next layer or set of layers. Further, it will be appreciated that, in non-limiting embodiments, the path for the next layer and / or set of layers may be shifted or replanned even for non-major defects. 5Y94264.DOCX Page 17 of 27Attorney Docket No.08993-2407108

[0067] FIG. 5A shows a 2D representation of the negative defect 500. The 2D planar representation of the negative defect may then be offset inwards by the end-effector member radius which may be used as a tool path to fill the boundary of the negative defect. The interior tool path may be calculated by following an infill pattern over the 2D planar representation of the negative defect and the target deposition volume and deposition rate may be calculated using the repair path length and defect volume. For example, the interior of the negative defect may be filled in with an infill path, such as a zig-zag or other like pattern 501 shown in FIG. 5B. After the manufacturing device executes the repair strategy, an additional 3D scan may be performed on the layer to ensure the negative defect has been corrected and if any negative defect remains, the repair strategy may be re-executed until no negative defects remain.

[0068] Referring now to FIG.6, shown is an illustration of a manufacturing device 600 of the fabrication subsystem according to non-limiting embodiments. The manufacturing device includes an arm 601, an end-effector member 602, a sensor arrangement 603, and a surface, e.g., print bed, where a fabricated object 604 is manufactured (e.g., deposited and / or subtracted). Additive manufacturing devices may include, for example, binder jetting, directed energy deposition, material extrusion, material jetting, powder bed fusion, sheet lamination, wire-arc additive manufacturing, vat photopolymerization, and / or the like. Subtractive manufacturing devices may include, for example, CNC milling machines, laser cutters, water jet cutters, plasma cutters, router tables, and / or the like.

[0069] Referring now to FIG. 8, shown is a flow diagram for a method of manufacturing according to some non-limiting embodiments or aspects. The steps shown in FIG. 8 are for example purposes only. It will be appreciated that additional, fewer, different, and / or a different order of steps may be used in some non-limiting embodiments or aspects. In some non-limiting embodiments or aspects, a step may be automatically performed in response to performance and / or completion of a prior step. One or more steps may be performed by the same or different computing devices. At step 800 a manufacturing device is instructed to manufacture (e.g., deposit and / or subtract) a layer of a plurality of layers. At step 802 the layer is scanned as described herein to generate a 3D representation of the later, such as but not limited to a point cloud. Step 802 may occur concurrently with and / or after step 800. At step 804 a differential (e.g., such as a point cloud differential or any other differential between 3D representations) is calculated as described herein. At step 806 it is determined if a defect is detected based on the differential as described herein. If no defect is detected the method proceeds back to step 800 to manufacture the next layer until all layers are 5Y94264.DOCX Page 18 of 27Attorney Docket No.08993-2407108 completed. If there is a defect, the method proceeds to step 808 where the defect is classified as a positive or negative defect. In an additive manufacturing embodiment, a negative defect classification may proceed to step 812 where a repair strategy is generated and / or executed as described herein, and a positive defect classification may proceed to step 810 where a replan strategy is generated and / or executed as described herein. In a subtractive manufacturing embodiment, negative defects may result in a replan strategy and positive defects may result in a repair strategy. In a hybrid manufacturing embodiment, more than one strategy may be applied. The method may loop back to 806 (not shown in FIG.8) after steps 810 and 812 for a next defect in the current layer, if there are multiple defects in the layer detected at step 806, until all defects are processed and addressed with a repair and / or replan strategy. After all defects in a layer are addressed, the method may proceed back to step 800 to manufacture the next layer until all layers are completed.

[0070] Referring now to FIG. 7, shown is a diagram of example components of a computing device 900 for implementing and performing the systems and methods described herein according to non-limiting embodiments. For example, the computing device 900 may correspond to the computing device(s) described herein. In some non-limiting embodiments, device 900 may include additional components, fewer components, different components, or differently arranged components than those shown in FIG. 7. Device 900 may include a bus 902, a processor 904, memory 906, a storage component 908, an input component 910, an output component 912, and a communication interface 914. Bus 902 may include a component that permits communication among the components of device 900. In some non- limiting embodiments, processor 904 may be implemented in hardware, firmware, or a combination of hardware and software. For example, processor 904 may include a processor (e.g., a central processing unit (CPU), a graphics processing unit (GPU), an accelerated processing unit (APU), etc.), a microprocessor, a digital signal processor (DSP), and / or any processing component (e.g., a field-programmable gate array (FPGA), an application-specific integrated circuit (ASIC), etc.) that can be programmed to perform a function. Memory 906 may include random access memory (RAM), read only memory (ROM), and / or another type of dynamic or static storage device (e.g., flash memory, magnetic memory, optical memory, etc.) that stores information and / or instructions for use by processor 904.

[0071] With continued reference to FIG.7, storage component 908 may store information and / or software related to the operation and use of device 900. For example, storage component 908 may include a hard disk (e.g., a magnetic disk, an optical disk, a magneto- optic disk, a solid state disk, etc.) and / or another type of computer-readable medium. Input 5Y94264.DOCX Page 19 of 27Attorney Docket No.08993-2407108 component 910 may include a component that permits device 900 to receive information, such as via user input (e.g., a touch screen display, a keyboard, a keypad, a mouse, a button, a switch, a microphone, etc.). Additionally, or alternatively, input component 910 may include a sensor for sensing information (e.g., a photo-sensor, a thermal sensor, an electromagnetic field sensor, a global positioning system (GPS) component, an accelerometer, a gyroscope, an actuator, etc.). Output component 912 may include a component that provides output information from device 900 (e.g., a display, a speaker, one or more light-emitting diodes (LEDs), etc.). Communication interface 914 may include a transceiver-like component (e.g., a transceiver, a separate receiver and transmitter, etc.) that enables device 900 to communicate with other devices, such as via a wired connection, a wireless connection, or a combination of wired and wireless connections. Communication interface 914 may permit device 900 to receive information from another device and / or provide information to another device. For example, communication interface 914 may include an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, a radio frequency (RF) interface, a universal serial bus (USB) interface, a Wi-Fi® interface, a cellular network interface, and / or the like.

[0072] Device 900 may perform one or more processes described herein. Device 900 may perform these processes based on processor 904 executing software instructions stored by a computer-readable medium, such as memory 906 and / or storage component 908. A computer-readable medium may include any non-transitory memory device. A memory device includes memory space located inside of a single physical storage device or memory space spread across multiple physical storage devices. Software instructions may be read into memory 906 and / or storage component 908 from another computer-readable medium or from another device via communication interface 914. When executed, software instructions stored in memory 906 and / or storage component 908 may cause processor 904 to perform one or more processes described herein. Additionally, or alternatively, hardwired circuitry may be used in place of or in combination with software instructions to perform one or more processes described herein. Thus, embodiments described herein are not limited to any specific combination of hardware circuitry and software. The term “programmed or configured,” as used herein, refers to an arrangement of software, hardware circuitry, or any combination thereof on one or more devices.

[0073] Although embodiments have been described in detail for the purpose of illustration, it is to be understood that such detail is solely for that purpose and that the disclosure is not limited to the disclosed embodiments, but, on the contrary, is intended to 5Y94264.DOCX Page 20 of 27Attorney Docket No.08993-2407108 cover modifications and equivalent arrangements that are within the spirit and scope of the appended claims. For example, it is to be understood that the present disclosure contemplates that, to the extent possible, one or more features of any embodiment can be combined with one or more features of any other embodiment. 5Y94264.DOCX Page 21 of 27

Claims

Attorney Docket No.08993-2407108 WHAT IS CLAIMED IS 1. A system comprising at least one processor configured to: (a) control a fabrication device to manufacture a layer of a plurality of layers of a 3D model by moving an end-effector member of the fabrication device; (b) scanning a surface of the layer with at least one sensor arranged to move with the end-effector member relative to the layer, resulting in a scanned 3D representation; (c) determining if the layer comprises a defect by comparing the scanned 3D representation to 3D data for a corresponding layer of the 3D model; (d) in response to determining the layer comprises the defect, determining whether the defect comprises a positive defect or a negative defect; (e) in response to determining that the defect comprises the positive defect, controlling the fabrication device to re-plan the layer; (f) in response to determining that the defect comprises the negative defect, controlling the fabrication device to repair the layer; (g) repeat steps (a)-(f) with at least one next layer of the plurality of layers.

2. The system of claim 1, wherein the at least one sensor comprises a laser projector and a camera, the at least one sensor configured to measure depth of a point.

3. The system of any of claim 2, wherein the at least one processor is further configured to stitch a plurality of depth measurements together to form the 3D data.

4. The system of any of claims 1-3, wherein the end-effector member and the at least one sensor are co-located on an end of a movable unit.

5. The system of any of claims 1-4, wherein the at least one processor is further configured to: generate a 3D point cloud by combining the 3D data obtained for each layer of the plurality of layers.

6. The system of claim 5, wherein the 3D point cloud is generated by transforming each scan into a fixed coordinate system relative to the fabrication device based on a pose of the end-effector member after each layer is manufactured. 5Y94264.DOCX Page 22 of 27Attorney Docket No.08993-2407108 7. The system of any of claims 1-6, wherein the processor is further configured to adjust a rate of the end-effector member based on a detected defect classification.

8. A method of manufacturing comprising: instructing, with at least one computing device, a manufacturing device to manufacture a layer of a plurality of layers with an end-effector member; scanning, with at least one computing device, the layer to produce a scanned 3D representation of the layer; calculating, with at least one computing device, a differential between the scanned 3D representation of the layer and a reference 3D representation of the layer; determining, with at least one computing device, a manufacturing protocol based on the differential; and executing, with at least one computing device, the manufacturing protocol.

9. The method of claim 8, wherein, in response to the differential being substantially zero, the manufacturing protocol comprises instructing the manufacturing device to manufacture a next layer of the plurality of layers.

10. The method of any of claim 8, wherein, in response to the differential satisfying a threshold, the manufacturing protocol comprises a positive-defect protocol for a positive defect or a negative-defect protocol for a negative defect.

11. The method of claim 10, wherein the positive-defect protocol comprises: generating a replan path for at least one next layer of the plurality of layers.

12. The method of claim 11, wherein executing the replan path comprises: projecting the scanned 3D representation of the layer with the positive defect onto a surface of the layer; computing an alpha shape of the positive defect to generate a polygon representation of the positive defect; projecting a planned trajectory onto the surface of the layer; 5Y94264.DOCX Page 23 of 27Attorney Docket No.08993-2407108 determining where a planned trajectory of a next layer intersects with the polygon; modifying the planned trajectory for the next layer based on the intersection.

13. The method of claim 10, wherein the positive-defect protocol comprises: generating a repair path for the layer before a next layer of the plurality of layers is manufactured.

14. The method of claim 13, wherein executing the repair path comprises: projecting the scanned 3D representation of the layer with the negative defect onto a surface of the layer; computing an alpha shape of the positive defect to generate a polygon representation of the negative defect; generating an infill path of the negative defect by offsetting a boundary of the polygon; calculating a repair path to fill the boundary of the negative defect by following the infill path; and modifying the manufacturing volume and / or rate of the manufacturing device according to a length of the repair path and / or volume of the negative defect.

15. The method of any of claims 8-15, wherein the end-effector member and at least one sensor are co-located on an end of a movable unit of the manufacturing device.

16. The method of any of claims 8-16, further comprising: instructing the manufacturing device to manufacture at least one next layer of the plurality of layers; generate a 3D point cloud by combining the scanned 3D representation obtained for each layer of the plurality of layers.

17. The method of any of claims 8-16, wherein scanning the layer comprises: projecting a laser with a laser projector over a surface of the layer; 5Y94264.DOCX Page 24 of 27Attorney Docket No.08993-2407108 generating a 2D image of the layer comprising the laser with a camera; measuring 3D information of the layer by triangulating laser points from the 2D image; and stitching the 3D information together across time to construct a 3D representation of the layer.

18. A manufacturing device comprising: at least one sensor; at least one end-effector member configured to add and / or subtract material to manufacture an object; and at least one computing device in communication with the at least one sensor and a control system for the at least one end-effector member, the at least one computing device configured to: scan each layer of a plurality of layers of an object manufactured by the end-effector member; and modify at least one layer of the plurality of layers based on comparing at least one scan of the at least one layer or at least one previous layer to a 3D representation of the at least one layer or the at least one previous layer.

19. The manufacturing device of claim 18, further comprising a movable unit, wherein the at least one laser projector and the at least one visual sensor are co-located with the at least one end-effector on the movable unit.

20. The manufacturing device of claim 18, wherein the at least one computing device is further configured to: control the at least one end-effector to manufacture each layer of the plurality of layers, wherein each layer is scanned while the at least one end-effector is manufacturing the layer.

21. The manufacturing device of claim 18, wherein the at least one computing device is further configured to: detect at least one defect in the at least one layer or the at least one previous layer based on comparing the at least one scan of the at least one layer or the at least one 5Y94264.DOCX Page 25 of 27Attorney Docket No.08993-2407108 previous layer to the 3D representation of the at least one layer or the at least one previous layer; determine a classification for the at least one defect, wherein the at least one layer is modified based on the classification.

22. The manufacturing device of claim 21, wherein comparing the at least one scan of the at least one layer or the at least one previous layer to the 3D representation of the at least one layer or the at least one previous layer results in a differential, and wherein the classification is determined based on comparing the differential to at least one threshold.

23. The manufacturing device of claim 18, wherein the at least one sensor comprises: a camera, a laser projector, a depth sensor, or any combination thereof. 5Y94264.DOCX Page 26 of 27

Images