Characterization of the proportion of molten bale strands in a ply of fibrous material.

Abstract

To provide a method for characterizing a ply of fiber having a thermoplastic veil.SOLUTION: The system and the method include acquiring an image of a fiber material comprising strands of fiber and further comprising a veil of thermoplastic filaments, subdividing the image into a plurality of slices, determining an amount of melted filaments depicted within each of the slices, and determining an amount of unmelted filaments depicted within each of the slices.SELECTED DRAWING: None

Description

[Technical Field]

[0001] The present disclosure relates to the field of composite materials, and in particular to thermal plasticity The present invention relates to a fiber-reinforced composite material comprising a veil. [Background technology]

[0002] Dry carbon fiber materials typically contain a layer of carbon fiber strands. Melting The dry carbon fiber material is used as input for the manufacturing of composite parts. To ensure consistent manufacturing quality, the thermoplastic veil of dry carbon fiber material must be present in a specific amount among the carbon fiber strands. Melting However, inspection of dry carbon fiber material remains a manual and labor-intensive process that adds to the cost of manufacturing composite parts. This is particularly noteworthy because thousands of feet of dry carbon fiber material may be utilized in a single composite part (e.g., an aircraft wing skin).

[0003] It would therefore be desirable to have a method and apparatus that takes into account at least some of the above-mentioned challenges, as well as other potential challenges. Summary of the Invention

[0004] The embodiments described herein are directed to the formation of a thermoplastic veil within a fibrous material (e.g., a unidirectional dry carbon fiber material that is not impregnated with a thermosetting or thermoplastic resin, a fiberglass material, a material having metal fibers or even ceramic fibers, etc.). Melting A feature detection process is used to characterize the quantity. Melting The number of filaments in the veil (resulting in a change in color / brightness) Melting By comparing the number of unbound filaments, MeltingFor example, the machine learning process described herein can divide an image of a textile material into slices and utilize a trained convolutional neural network to characterize the amount of fiber in the bale. Melting The filament Melting Detect the unoccupied filaments and for each slice, Melting The filament Melting The ratio of the number of filaments to the number of unaffected filaments is then calculated for each slice. Melting An overall metric of the quantity may be determined.

[0005] One embodiment is a method for characterizing a fiber ply having a thermoplastic veil, the method comprising: acquiring an image of a fiber material including strands of fiber and further including a veil of thermoplastic filaments; subdividing the image into a plurality of slices; and characterizing a portion of the image shown in each slice. Melting The amount of filament that was present in each slice was determined. Melting and determining the amount of unspent filament.

[0006] A further embodiment is a non-transitory computer-readable medium embodying programmed instructions that, when executed by a processor, are operable to perform a method for characterizing a ply of fiber having a thermoplastic veil, the method including acquiring an image of a fiber material including strands of carbon fiber and further including a veil of thermoplastic filaments, subdividing the image into a plurality of slices, and characterizing a ply of fiber having a thermoplastic veil, the ply of fiber having a thermoplastic veil, the thermoplastic veil, and the carbon fiber strands. Melting The amount of filament that was present in each slice was determined. Melting and determining the amount of unspent filament.

[0007] A further embodiment is an apparatus for characterizing a ply of fiber having a thermoplastic veil, the apparatus comprising: an interface for receiving an image of a fiber material including strands of fiber and further including a veil of thermoplastic filaments; and segmenting the image into a plurality of slices, each slice including a plurality of segments of a fiber ply having a thermoplastic veil. Melting Determine the amount of filaments present in each slice. Melting The controller determines the amount of free filament.

[0008] The apparatus and methods of the present disclosure are also referred to in the following clauses, which should not be confused with the claims.

[0009] A1 1. A method for characterizing a ply of fiber having a thermoplastic veil, comprising: acquiring (202) an image of a textile material including strands of fiber and further including a veil of thermoplastic filaments; Segmenting the image into a plurality of slices (204); Shown in each of the slices Melting determining the amount of filament removed (206); Shown in each of the slices Melting Determining the amount of unfilled filament (208) A method comprising:

[0010] A2 In each slice Melting The number of filaments and Melting of the veil in each slice based on the number of unstripped filaments Melting Quantifying the amount (210) and The veil in each slice Melting of the veil in the image based on the amount Melting Quantifying the quantity (212) and There is further provided a method as set forth in paragraph A1, further comprising:

[0011] A3 The aforementioned Melting Determining the amount of filament removed Melting identifying a portion of each slice containing a selected filament; The aforementioned Melting The amount of unfilled filament can be determined by Melting Further provided is the method of paragraph A1, comprising identifying a portion of each slice that includes an unbound filament.

[0012] A4 Further provided is a method as set forth in paragraph A1, wherein the determining step is performed via a trained neural network.

[0013] A5 Further provided is the method of paragraph A4, wherein the neural network comprises a convolutional neural network.

[0014] A6 The veil in the image Melting comparing the quantity to the design tolerance; The veil in the image Melting sending a notification in response to determining that the quantity is not within said design tolerance; and There is further provided a method as set forth in paragraph A1, further comprising:

[0015] A7 based on differences in at least one of brightness or color, Melting The filament Melting Further provided is the method of paragraph A1, further comprising distinguishing the non-woven filaments from the non-woven filaments.

[0016] A8 Further provided is the method of paragraph A1, wherein the strands of fiber are selected from the group consisting of carbon fiber, glass fiber, metal fiber, and ceramic fiber.

[0017] A9 Further provided is the method of paragraph A8, wherein the strands of fiber are strands of carbon fiber.

[0018] A10 (c) any part of an aircraft assembled in accordance with the method set forth in paragraph A1;

[0019] According to a further aspect of the medium of the present disclosure, there is provided:

[0020] B1 1. A non-transitory computer-readable medium embodying programmed instructions, the instructions, when executed by a processor, operable to perform a method for characterizing a ply of fiber having a thermoplastic veil, the method comprising: acquiring (202) an image of a textile material including strands of fiber and further including a veil of thermoplastic filaments; Segmenting the image into a plurality of slices (204); Shown in each of the slices Melting determining the amount of filament removed (206); Shown in each of the slices Melting Determining the amount of unfilled filament (208) 1. A non-transitory computer-readable medium comprising:

[0021] B2 The method comprises: In each slice Melting The number of filaments and Melting of the veil in each slice based on the number of unstripped filaments Melting Quantifying the amount (210) and The veil in each slice Melting of the veil in the image based on the amount Melting Quantifying the quantity (212) and There is further provided a medium according to paragraph B1, further comprising:

[0022] B3 The aforementioned Melting Determining the amount of filament removed Melting identifying a portion of each slice containing a selected filament; The aforementioned Melting The amount of unfilled filament can be determined by Melting Further provided is the medium of paragraph B1, comprising identifying a portion of each slice that includes an unbound filament.

[0023] B4 Further provided is the medium of paragraph B1, wherein the determining step is performed via a trained neural network.

[0024] B5 Further provided is the medium of paragraph B2, wherein the neural network comprises a convolutional neural network.

[0025] B6 The veil in the image Melting comparing the quantity to the design tolerance; The veil in the image Melting sending a notification in response to determining that the quantity is not within said design tolerance; and There is further provided a medium according to paragraph B1, further comprising:

[0026] B7 The machine learning model, based on differences in at least one of brightness or color, Melting The filament Melting There is further provided a medium according to paragraph B1, which is distinguished from non-woven filaments.

[0027] B8 Further provided is the medium of paragraph B1, wherein the strands of fiber are selected from the group consisting of carbon fibers, glass fibers, metal fibers, and ceramic fibers.

[0028] B9 Further provided is the medium of paragraph B8, wherein the strands of fiber are strands of carbon fiber.

[0029] B10 a portion of an aircraft assembled by a method prescribed by said Directive stored on a computer-readable medium as described in paragraph B1.

[0030] According to further aspects of the apparatus of the present disclosure, there is provided:

[0031] C1 1. An apparatus for characterizing a ply of fiber having a thermoplastic veil, comprising: an interface (716) for receiving an image (742) of a fibrous material (750) comprising a strand (752) of fiber and further comprising a veil (754) of thermoplastic filaments (760); and The image is divided into a plurality of slices (744), and the image is displayed in each of the slices. Melting Determine the amount of filaments present in each slice. Melting A controller (712) for determining the amount of unfilled filament. A device comprising:

[0032] C2 The controller Melting The number of filaments and Melting of the veil in each slice based on the number of unstripped filaments Melting Quantify the amount of veil in each slice Melting of the veil in the image based on the amount Melting Further provided is a device according to paragraph C1 that quantifies the amount.

[0033] C3 The controller: Melting by identifying the portion of each slice containing the affected filament. Melting A neural network (724) is run to determine the amount of the filament that has been removed. The controller: Melting by identifying the portion of each slice that contains undisturbed filaments. Melting Further provided is the apparatus of paragraph C1, which determines the amount of unspun filament.

[0034] C4 The controller, via a trained neural network, Melting The amount of filament and Melting Further provided is the apparatus of paragraph C1, which determines the amount of unspun filament.

[0035] C5 The method of paragraph C4, wherein the neural network comprises a convolutional neural network. Device is further provided.

[0036] C6 The veil in the image Melting comparing the quantity to the design tolerance; The veil in the image Melting sending a notification in response to determining that the quantity is not within said design tolerance; and There is further provided the apparatus of paragraph C1, further comprising:

[0037] C7 Further provided is the apparatus of paragraph C1, wherein the strands of fiber are selected from the group consisting of carbon fiber, glass fiber, metal fiber, and ceramic fiber.

[0038] C8 Further provided is the apparatus of paragraph C7, wherein the strands of fiber are strands of carbon fiber.

[0039] C9 The manufacture of a part of an aircraft using the equipment described in paragraph C1.

[0040] Other exemplary embodiments (e.g., methods and computer-readable media related to the above-described embodiments) may be described below. The above-described features, functions, and advantages may be realized alone in various embodiments or may be combined in yet other embodiments. Further details of these embodiments may be found by reference to the following description and accompanying drawings. [Brief explanation of the drawings]

[0041] Some embodiments of the present disclosure will now be described, by way of example only, with reference to the accompanying drawings, in which the same reference numerals represent the same elements or types of elements in all the drawings.

[0042] [Figure 1] FIG. 1 is a block diagram of a fiber characterization system according to an exemplary embodiment. [Figure 2] FIG. 1 is a flow diagram illustrating a method for evaluating a fibrous material according to an exemplary embodiment. [Figure 3] FIG. 10 illustrates an imaging of a fiber material according to an illustrative embodiment. [Figure 4] FIG. 10 illustrates a slice from an image according to an exemplary embodiment. [Figure 5] FIG. 10 illustrates a slice from an image according to an exemplary embodiment. [Figure 6] FIG. 10 illustrates a slice from an image according to an exemplary embodiment. [Figure 7] FIG. 1 is a block diagram of a fiber material characterization system in accordance with an illustrative embodiment; [Figure 8] FIG. 1 is a flowchart of an aircraft production and service method in accordance with an illustrative embodiment; [Figure 9] FIG. 1 is a block diagram of an aircraft in accordance with an illustrative embodiment; DETAILED DESCRIPTION OF THE INVENTION

[0043] The drawings and the following description illustrate specific exemplary embodiments of the present disclosure. Therefore, it should be understood that those skilled in the art can embody the principles of the present disclosure by devising various arrangements not explicitly described or shown herein, but which are within the scope of the present disclosure. Furthermore, it should be understood that any examples described herein are intended to aid in the understanding of the principles of the present disclosure and are not limited to the specifically described examples or conditions. Consequently, the present disclosure is not limited to the specific embodiments or examples below, but is limited by the scope of the claims and their equivalents.

[0044] Composite parts, such as carbon fiber reinforced polymer (CFRP) parts, are initially laid up as multiple layers that together form a laminate. Individual fibers within each layer of the laminate are aligned parallel to one another, but various layers may exhibit different fiber orientations to enhance the strength of the resulting composite along various directions. To solidify the laminate into a composite part (e.g., for use in an aircraft), the laminate may contain a viscous resin that solidifies. Carbon fibers impregnated with uncured thermosetting or thermoplastic resins are called "prepregs." Other types of carbon fibers include "dry fibers" that are not impregnated with thermosetting resins but may contain a tackifier or binder. Dry fibers may be infused with resin before curing. In thermosetting resins, hardening is a unidirectional process called curing, while in the case of thermoplastic resins, the resin may reach a viscous state upon reheating. The systems and methods described herein describe the evaluation of dry fiber materials containing binders in the form of a thermoplastic veil.

[0045] 1 is a block diagram of a fiber characterization system 100 according to an exemplary embodiment. Melting Thermoplastic filaments and MeltingThe fiber characterization system 100 may comprise any system, device, or component operable to automatically evaluate images of a fiber material (e.g., unidirectional CFRP, fiberglass material, material having metal fibers or even ceramic fibers, etc.) to determine (measure) the ratio of thermoplastic filaments to non-thermoplastic filaments. In this embodiment, the fiber characterization system 100 comprises a characterization unit 110 and an imaging system 130.

[0046] The imaging system 130 acquires images of a sheet 140 of fibrous material 142 (e.g., a ply of unidirectional CFRP, fiberglass material, material having metal fibers, or even ceramic fibers, etc.). These images may be acquired at various positions and / or orientations along the sheet 140. The images show not only strands 150 of fibers 152 (e.g., carbon fiber, fiberglass, metal fiber, ceramic fiber, etc.) within the sheet 140, but also a veil 160 of thermoplastic filaments 162 that act as a binder or tackifier for the strands 150. Each thermoplastic filament 162 may be, for example, 7000ths of an inch thick or even thinner. Each strand 150 may be even smaller, such as 12,000 to 40,000 strands in a single linear inch. The imaging system 130 may include a camera (e.g., a color camera, a stereo camera, etc.) or other non-destructive imaging component, such as an ultrasound or laser imager.

[0047] Images acquired via imaging system 130 are received at interface (I / F) 116. These images may be stored by controller 112 in memory 114 (e.g., hard disk, flash memory, etc.) for subsequent analysis. Controller 112 manages the operation of characterization unit 110 to facilitate the receipt, analysis, and reporting of images. For example, controller 112 may access neural network 124 in memory 114 when evaluating the images. Neural network 124 may analyze the characteristics of the images. Melting Untreated filaments and MeltingTo detect the broken filaments, the neural network may include, for example, a convolutional neural network trained based on training data 122.

[0048] The training data 122 may include a set of images or slices (e.g., thousands of images) and associated tags that indicate features found within these elements. For example, the training data 122 may include: Melting Completed or not Melting The training data 122 may include images with regions already classified as "good" or "bad." The training data 122 may further include images taken from dry carbon materials where the in-plane fiber angles are varied (e.g., 0 degrees, +45 degrees, -45 degrees, 90 degrees, etc.). This may be important for training the neural network 124 to examine the differences in brightness or contrast found at various fiber angles. Thus, the training data 122 may be used to train the neural network 124 to recognize the differences in brightness or contrast found at various fiber angles. Melting The filament and Melting The controller 112 may be implemented, for example, as a custom circuit, as a hardware processor executing programmed instructions, or as some combination of these.

[0049] Exemplary details of the operation of the fiber characterization system 100 are described in connection with FIG. Melting The filament Melting Suppose an engineer wishes to characterize a sheet 140 of fibrous material 142 to determine if the ratio of unwoven to woven filaments is within a desired tolerance.

[0050] 2 is a flow diagram illustrating a method 200 for characterizing a textile material, according to an exemplary embodiment. The steps of method 200 are described with reference to textile characterization system 100 of FIG. 1, but one skilled in the art will understand that method 200 may be implemented in other systems. The steps of the flow diagram described herein are not exhaustive and may include other steps not shown. The steps described herein may also be performed in a different order.

[0051] In step 202, imaging system 130 acquires an image of sheet 140 of fibrous material 142. Fiber material 142 includes strands 150 of fibers 152 and further includes a veil 160 of thermoplastic filaments 162 of thermoplastic material. The image may be generated in any suitable format, and a digital version of the image may be acquired by I / F 116 for storage in memory 114. In one embodiment, an image is acquired every few hundred meters of length of fibrous material 142. The image represents a small portion of fibrous material 142 (e.g., a 2 inch by 2 inch portion). However, the image may show any suitable area of ​​any suitable size desired.

[0052] Once the image is acquired, the controller 112 then proceeds to subdivide the image into slices (step 204). As used herein, a "slice" may include any suitable portion of the image. For example, a slice may include a portion that occupies the entire width of the image but only a portion of the height of the image, may include a portion that occupies the entire height of the image but only a portion of the width of the image, may include a triangular section, etc. Ideally, the size (e.g., narrow dimension) of a slice is small enough so as not to show multiple filaments, yet still Melting filament or MeltingThe slices are large enough so that a convolutional neural network trained for region detection can operate effectively when attempting to classify the portions of the slices that represent undifferentiated filaments. For example, the size of a slice may be between 60 and 160 pixels (e.g., 100 pixels). Each slice may be expected to represent a number of individual filaments (e.g., 50 to 100 filaments).

[0053] In further embodiments, the slice size may be selected so that the height of the image is evenly divisible by the slice size, or the image may be pre-processed (e.g., cropped, scaled, filtered, etc.) to enhance image quality and / or slicing.

[0054] In step 206, for each slice, the controller 112 Melting As used herein, " Melting filament (e.g., Fig. 3 Melting The strand 150 is shown as a slit 324. Melting This may be performed by the controller 112 running a neural network 124, which Melting Features within the slice that indicate the presence of a filament are detected. For example, Melting The filaments may be associated with particular curvatures, brightnesses, colors, etc., and the neural network 124 may be trained via the training data 122 to recognize such characteristics. In one embodiment, the neural network 124 Melting Feature analysis is performed on the slice to detect the presence of one or more features associated with the selected filament. The size of each region examined by the neural network 124 may be equal to the dimension of the size of the slice being examined. If enough features are detected with sufficient confidence, the neural network 124 may detect a feature within the region of the slice being analyzed. MeltingIt can be shown that there are filaments that have been broken.

[0055] Additionally, for each slice, the controller 112 Melting The amount of unspent filament is determined (i.e., step 208). Melting filaments (e.g., Fig. 3 Melting The strand 150 is shown as a portion 326 that is not Melting This may be performed by the controller 112 running the neural network 124, which may Melting Features in the slice that indicate the presence of unstripped filaments are detected. For example, Melting Unclear filaments may be associated with particular curvatures, brightness, colors, etc., and the neural network 124 may be trained via training data 122 to recognize such features. Melting When making a determination regarding an unstained filament, neural network 124 may perform a feature recognition task similar to the task described above in connection with step 206.

[0056] Certain parts of the filament are partially Melting In this case, depending on how the neural network used by the controller 112 was trained, the controller 112 may appear to Melting Status or not Melting In a further embodiment, the specific region may be classified as one of: Melting The filament and Melting The controller 112 may identify such regions based on how the neural network used by the controller 112 was trained. Melting Status or not Melting It can be classified into one of the following states:

[0057] In steps 206 and 208, not all regions within the slice are necessarily filament (e.g., Melting filament or Melting These areas may be reported as void areas. Melting The size of the empty region can be important when determining whether it is within a non-ratio related tolerance range.

[0058] The quantities determined in steps 206 and 208 may indicate the size of the area where filaments of a given type are determined to be present (e.g., linear or flat area), may indicate the number of filaments of a given type, or may include other suitable indicators (e.g., the number of pixels representing filaments of a given type). Melting The filament Melting It is used to determine the ratio of unstained filaments to unstained filaments.

[0059] In step 210, the controller 112 determines, for each slice, the number of thermoplastic filaments 162 in the veil 160. Melting This can be done, for example, by quantifying the amount of Melting The filament Melting The amount of unspent filament is then added together. Melting In a further embodiment, this can be done by dividing the amount of filaments that have been spun by this sum. Melting The filament Melting This may include determining the ratio of unfilled filaments to unfilled filaments as desired by the design specifications. Melting The ratio may vary depending on the application. Melting An example percentage is between 30 and 50 percent.

[0060] Step 212 is to determine the number of veils 160 in each slice. Melting Based on the quantity of bales in the image, 160 Melting For example, the controller 112 may be configured to quantify the amount of the chromatic aberrations found in the image. MeltingTo determine the amount, for each slice, Melting The amounts may be averaged.

[0061] In further embodiments, method 200 may be repeated on the same image by slicing the image differently (e.g., wide "slices," as well as "tall" slices, slices of various sizes, inverted or rotated slices, slices with adjusted color, brightness, or contrast, etc.). In yet another embodiment, method 200 may be repeated on multiple images to quantify the entire sheet 140. For example, in embodiments where an entire roll containing hundreds of feet of dry carbon fiber material 142 is to be characterized, it may be desirable to acquire and analyze a large number of images of the material.

[0062] Method 200 offers advantages over prior techniques and systems because it replaces manual inspection techniques with an automated process that is cheaper and more accurate, giving engineers more time to focus on other aspects of manufacturing and enhancing the process of producing composite parts from dry carbon fiber material.

[0063] The desired thickness of each ply is measured before layup begins. Melting To verify the ratio, the techniques of method 200 can be utilized to inspect the surfaces of a large number of plies. Melting If the ratio is known, any resulting preform made from the plies can also be Melting The ratio will be known, and this is also true for the plies placed inside the preform after inspection.

[0064] Example In the following examples, additional processes, systems, and methods are described in the context of characterizing dry carbon fiber materials. That is, while systems and methods for analyzing dry carbon fiber materials have been described above, the following figures provide examples showing how images can be sliced ​​and characterized.

[0065] FIG. 3 is a diagram illustrating a fibrous material, according to an exemplary embodiment. Specifically, FIG. 3 is a top view of a single ply of unidirectional dry fibrous material in the form of a CFRP. FIG. 3 shows one or more strands 310 of carbon fiber bonded together via a veil 320 of filaments 322. FIG. 3 shows minor non-uniformities in the distance between the carbon fiber strands 310. This is because the uniform distribution of the strands 310 in the bundle 300 is rough and not perfect. Some filaments Melting The other filaments have a portion 324 that is Melting The single filament has an unbonded portion 326. Melting and the area Melting It may have both a non-transferable portion and a non-transferable portion.

[0066] In this example, image 300 is subdivided at boundary 330 into multiple slices, resulting in slice 342, slice 344, and slice 346. Figure 4 shows slice 342 in detail. As indicated by bar 400 in Figure 4, portions of slice 342 have been classified with different identifiers based on analysis by the neural network. "E" indicates an area that is free of any type of filament, and "UM" indicates an area that is free of any type of filament. Melting "M" (melted) indicates the area occupied by unmelted filaments. Melting The area occupied by the interstitial filament is shown in slice 342. Melting To determine the amount of filament removed, the size of the portion of M (in this case, linear distance) may be compared to the size of the region UM.

[0067] Figure 5 shows slice 344, showing region M, region UM, and sky region through bar 500. In slice 344, the size of region M is substantially smaller than the size of region UM. Figure 6 shows slice 346, which has the highest ratio of region M to region UM, as indicated by bar 600.

[0068] 7 is a block diagram of a fiber material characterization system 700, according to an exemplary embodiment. According to FIG. 7, the system includes a carbon fiber material 750 made from a strand 752 of carbon fiber and a veil 754 of filaments 760. The filaments 760 are Melting Part 764 and Melting The image data 742 includes an unprocessed portion 766. The imaging system 730 generates images of the carbon fiber material 750, which are acquired (in digital form) by an interface (I / F) 716. The controller 712 may direct these images to a memory 714 for storage. The memory 714 stores a neural network 724, training data 722, and an objective function 726 used to score the output from the neural network 724 during training. The memory 714 further stores images 742, slices 744, and slice data 746. The slice data 746 may, for example, represent the amount of information detected in each slice. Melting The part and Melting The system described above focuses on dry fibrous materials, but in further embodiments, it may be utilized to perform a similar function for prepreg materials.

[0069] Referring more particularly to the drawings, embodiments of the present disclosure may be described with reference to an aircraft manufacturing and service method 800 shown in Figure 8 and an aircraft 802 shown in Figure 9. During pre-production, method 800 may include specification and design 804 and material procurement 806 of the aircraft 802. During production, component and subassembly manufacturing 808 and system integration 810 of the aircraft 802 occurs. The aircraft 802 may then undergo certification and delivery 812 and be placed into service 814. While in operation by a customer, the aircraft 802 is scheduled for periodic work in maintenance and service 816, which may include modification, reconfiguration, refurbishment, etc. Apparatus and methods embodied herein may be employed during any one or more suitable stages of manufacturing and service described in method 800 (e.g., specification and design 804, materials procurement 806, component and subassembly manufacturing 808, systems integration 810, certification and delivery 812, operation 814, maintenance and maintenance 816), and / or any suitable component of aircraft 802 (e.g., airframe 818, systems 820, interior 822, propulsion system 824, electrical system 826, hydraulic system 828, environmental system 830).

[0070] Each process of method 800 may be performed or carried out by a system integrator, a third party, and / or an operator (e.g., a customer). For purposes of this specification, a system integrator may include, but is not limited to, any number of aircraft manufacturers and major system subcontractors, a third party may include, but is not limited to, any number of vendors, subcontractors, and suppliers, and an operator may be an airline, a leasing company, a military entity, a service organization, etc.

[0071] 9 , aircraft 802 produced by method 800 may include an airframe 818 with a number of systems 820 and an interior 822. Examples of systems 820 include one or more of a propulsion system 824, an electrical system 826, a hydraulic system 828, and an environmental system 830. Any number of other systems may also be included. While an aerospace example is shown, the principles of the invention may be applied to other industries, such as the automotive industry.

[0072] As mentioned above, apparatus and methods embodied herein may be employed during any one or more stages of manufacturing and service described in method 800. For example, components or subassemblies corresponding to component and subassembly manufacturing 808 may be fabricated or manufactured in a manner similar to components or subassemblies manufactured while aircraft 802 is in service. Furthermore, one or more apparatus embodiments, method embodiments, or a combination thereof may be utilized during subassembly manufacturing 808 and system integration 810, e.g., by substantially streamlining the assembly of or reducing the cost of aircraft 802. Similarly, one or more apparatus embodiments, method embodiments, or a combination thereof may be utilized during the operational life of aircraft 802, such as, but not limited to, during maintenance and service 816. For example, the techniques and systems described herein may be used in material procurement 806, component and subassembly manufacturing 808, system integration 810, operation 814, and / or maintenance and service 816, and / or may be used in airframe 818 and / or interior 822. These techniques and systems may also be utilized for systems 820 including, for example, propulsion system 824 , electrical system 826 , hydraulic system 828 , and / or environmental system 830 .

[0073] In one embodiment, a part comprises a portion of the airframe 818 and is manufactured during component and subassembly manufacturing 808. The part is then incorporated into the aircraft in system integration 810, where it is then utilized in service 814 until wear renders the part unusable. The part may then be scrapped and replaced with a newly manufactured part in maintenance and service 816. Inventive components and methods may be utilized during component and subassembly manufacturing 808 to manufacture the new part.

[0074] Any of the various control elements (e.g., electrical or electronic components) shown in the figures or described herein may be implemented as hardware, software implemented by a processor, firmware implemented by a processor, or some combination thereof. For example, an element may be implemented as dedicated hardware. A dedicated hardware element may be referred to as a “processor,” “controller,” or some similar terminology. When performed by a processor, a function may be performed by a single dedicated processor, by a single shared processor, or by multiple individual processors (some of which may be shared). Furthermore, explicit use of the terms “processor” or “controller” should not be construed as referring only to hardware capable of executing software, but may implicitly include, without limitation, digital signal processor (DSP) hardware, network processors, application specific integrated circuits (ASICs) or other circuitry, field programmable gate arrays (FPGAs), read-only memory (ROM) for storing software, random access memory (RAM), non-volatile storage, logic, or any other physical hardware component or module.

[0075] Additionally, a control element may be implemented as instructions executable by a processor or computer, thereby performing the function of the element. Some examples of instructions are software, program code, and firmware. The instructions are operative when executed by a processor and direct the processor to perform the function of the element. The instructions may be stored in a processor-readable storage device. Some examples of storage devices are digital or solid-state memory, magnetic storage media such as magnetic disks or magnetic tapes, hard drives, or optically readable digital data storage media.

[0076] Although specific embodiments have been described herein, the scope of the disclosure is not limited to these specific embodiments. The scope of the disclosure is defined by the following claims and any equivalents thereof.

Claims

1. 1. A method for characterizing a ply of fiber having a thermoplastic veil, comprising: acquiring (202) an image of a textile material comprising strands of textile and further comprising a veil of filaments of thermoplastic material; Segmenting the image into a plurality of slices (204); determining (206) the amount of molten filament represented in each said slice; determining (208) the amount of unmelted filaments represented in each said slice; distinguishing molten filaments from unmelted filaments based on differences in at least one of brightness, color, or curvature; Including, The method, wherein determining the amount of melted filament and determining the amount of unmelted filament are performed via a trained neural network.

2. Quantifying (210) the amount of melting of the veil in each slice based on the number of melted filaments and the number of unmelted filaments in each slice; Quantifying (212) the amount of melting of the veil in the image based on the amount of melting of the veil in each slice; The method of claim 1 further comprising:

3. determining the amount of melted filaments includes identifying a portion of each slice that includes melted filaments; 3. The method of claim 1 or 2, wherein determining the amount of unmelted filaments comprises identifying a portion of each slice that includes unmelted filaments.

4. A method according to any one of claims 1 to 3, wherein the neural network comprises a convolutional neural network.

5. comparing the amount of melting of the veil in the image to a design tolerance; sending a notification in response to determining that the amount of melting of the veil in the image is not within the design tolerance; and The method of claim 1 , further comprising:

6. A method according to any one of claims 1 to 5, wherein each portion of each slice is classified with various identifiers based on analysis by a neural network, a first identifier indicating an area where no filaments of any kind are present, a second identifier indicating an area occupied by unmelted filaments, and a third identifier indicating an area occupied by melted filaments.

7. 7. The method of any one of claims 1 to 6, wherein the strands of fibers are selected from the group consisting of carbon fibers, glass fibers, metal fibers, and ceramic fibers.

8. The method of claim 7, wherein the fiber strands are carbon fiber strands.

9. 1. A non-transitory computer-readable medium embodying programmed instructions, the instructions, when executed by a processor, operable to perform a method for characterizing a ply of fiber having a thermoplastic veil, the method comprising: acquiring (202) an image of a textile material comprising strands of textile and further comprising a veil of filaments of thermoplastic material; Segmenting the image into a plurality of slices (204); determining (206) the amount of molten filament represented in each said slice; determining (208) the amount of unmelted filaments represented in each said slice; distinguishing molten filaments from unmelted filaments based on differences in at least one of brightness, color, or curvature; Including, a non-transitory computer-readable medium, wherein determining the amount of melted filament and determining the amount of unmelted filament are performed via a trained neural network.

10. 1. An apparatus for characterizing a ply of fiber having a thermoplastic veil, comprising: an interface (716) for receiving an image (742) of a fibrous material (750) comprising a strand of fiber (752) and further comprising a veil (754) of thermoplastic filaments (760); and a controller (712) for dividing the image into a plurality of slices (744), determining an amount of melted filament represented in each of the slices, and determining an amount of unmelted filament represented in each of the slices. Equipped with the controller distinguishes molten filament from unmelted filament based on differences in at least one of brightness, color, or curvature, and the controller determines an amount of the molten filament and an amount of the unmelted filament via a trained neural network.

11. 11. The apparatus of claim 10, wherein the controller quantifies an amount of melting of the veil in each slice based on the number of melted filaments and the number of unmelted filaments in each slice, and quantifies an amount of melting of the veil in the image based on the amount of melting of the veil in each slice.

12. the controller operating the neural network (724) to determine the amount of molten filament by identifying a portion of each slice that contains molten filament; 12. The apparatus of claim 10 or 11, wherein the controller determines the amount of unmelted filament by identifying a portion of each slice that includes the unmelted filament.

13. The apparatus of claim 10, wherein the neural network comprises a convolutional neural network.

14. comparing the amount of melting of the veil in the image to a design tolerance; sending a notification in response to determining that the amount of melting of the veil in the image is not within the design tolerance; and 14. The apparatus of claim 10, further comprising:

15. 14. The apparatus of any one of claims 10 to 13, wherein the strands of fibers are selected from the group consisting of carbon fibers, glass fibers, metal fibers, and ceramic fibers.

Images