Nonconformity management system and method for handling laminated panels having nonconformity

Abstract

The present disclosure relates to a nonconforming item management system and a method for processing a laminate with nonconforming items, and specifically to a method, device and system for processing nonconforming items in a laminate. The nonconforming item management system includes a sensor system and an analyzer in a computer system. The sensor records stacking information related to the layer stack on the workpiece platform and records inspection information related to the laminate located on the inspection platform, wherein the laminate is formed by curing the workpiece. The analyzer in the computer system uses the inspection information to identify laminate nonconforming items in the laminate, generates nonconforming item information related to the laminate nonconforming items, and displays the nonconforming item information related to the laminate nonconforming items on the laminate using a display system for augmented reality display.

Description

Technical Field

[0001] The present disclosure relates to the field of multilayer manufacturing, and in particular, to a laminate nonconformance management system. Background Art

[0002] A laminate is a structure manufactured in multiple layers. Through the selection of layers used to form the laminate, the laminate can have desired properties, such as improved strength, stability, sound insulation, appearance, or other properties.

[0003] The stack of raw materials can be laid up in layers. The stack can be laid up on a first metal backing plate. The stack can be, for example, a first polyvinyl fluoride (PVF) layer, an embossing resin (ER) layer and a second polyvinyl fluoride layer. The embossing resin layer is located between the first polyvinyl fluoride layer and the second polyvinyl fluoride layer. These layers form a workpiece or sandwich.

[0004] Multiple workpieces may be stacked from multiple layers. The layup is typically performed at a build station. A first workpiece is stacked on a pad on a platform at the build station. Subsequent workpieces may be formed by stacking layers to form additional workpieces on top of the first workpiece. These different workpieces may be separated from each other by peel sheets or multiple types of layers that provide the ability to maintain separate laminates formed by curing these workpieces. Additionally, a texture layer may be included to form a texture in the laminate.

[0005] When all the workpieces are stacked, a second metal backing plate is placed on top of the last workpiece to form a tray. The tray is placed in a press to process the workpieces. The press applies pressure to the layers of workpieces. Additionally, as part of the curing process, the temperature can be increased to heat the layers in the tray while the press applies pressure.

[0006] After the workpieces are cured to form the laminates, the pallets are returned to the build station for further processing. At the build station, a human operator inspects the laminates. Inspection is performed to determine if there are nonconforming items that would prevent the laminates from being used in manufacturing parts. Laminates that pass the inspection are prepared and routed for further processing to produce parts from the laminates.

[0007] Currently, this process results in more scrap from laminates with nonconformances than is desired. Detecting these nonconformances from visual inspection can be tedious, error-prone, and operator-reliant. It would be desirable to have methods and apparatus that take into account at least some of the issues discussed above, as well as other possible issues. For example, it would be desirable to have methods and apparatus that overcome the technical problem of accurately identifying nonconformances in laminates. Summary of the invention

[0008] The example described herein provides a nonconforming item management system, which includes a workpiece platform, an inspection platform, a sensor system, and an analyzer in a computer system. The workpiece platform supports a layer stack (layup of layer) stacked on the workpiece platform to form a workpiece. The inspection platform supports a laminate formed by the workpiece. The sensor system records the stacking information (layup information) of the layer stack on the workpiece platform, and records the inspection information related to the laminate located on the inspection platform, wherein the laminate is formed by curing the workpiece. The analyzer in the computer system uses the inspection information to identify laminate nonconforming items in the laminate, generates nonconforming item information about laminate nonconforming items, and displays the nonconforming item information about laminate nonconforming items on the laminate using a display system for augmented reality display.

[0009] Another example provides a nonconforming item management system including a sensor system and an analyzer in a computer system. The sensor system records stacking information related to a layer stack forming a workpiece. The analyzer in the computer system uses the stacking information to predict laminate nonconforming items in a laminate, wherein the laminate is formed by curing the layer stack. The analyzer generates change information indicating a change in the layer stack that reduces the probability that a laminate nonconforming item will exist when the layer stack is cured to form the laminate. The analyzer displays the change information indicating the change in the layer stack on a real-time view of the layer stack using a display system for augmented reality display.

[0010] Another example of the present disclosure provides a non - conforming item management system including a sensor system and an analyzer in a computer system. The sensor system detects laminates on an inspection platform. The laminates are formed by curing a workpiece including a layer stack. The analyzer in the computer system determines whether there are laminate non - conforming items in the laminates using the stack information recorded by the sensor system. When a laminate non - conforming item is detected, non - conforming item information about the laminate non - conforming item is generated, and the non - conforming item information about the laminate non - conforming item is displayed on the laminate using a display system for augmented reality display. The analyzer uses an artificial intelligence system to determine whether there are laminate non - conforming items in the laminates, and the artificial intelligence system is trained using the previous stack information recorded for previous workpieces, the previous inspection information about the previous laminates formed from the previous workpieces, and the previous user input about the previous non - conforming items in the previous laminates.

[0011] Another example provides a method for managing the manufacture of laminates. A sensor system records stack information about a layer stack on a workpiece platform, where the layer stack forms the workpiece. The sensor system records inspection information about a laminate on an inspection platform, where the laminate is formed by curing the workpiece. A user input system receives user input describing a laminate non - conforming item in the laminate on the inspection platform. A computer system uses the stack information, the inspection information, and the user input describing the laminate non - conforming item to train an artificial intelligence system.

[0012] These features and functions can be implemented independently in multiple embodiments of the present disclosure, or can be combined in other embodiments. In other embodiments, further details can be seen with reference to the following description and the drawings. Description of the Drawings

[0013] The novel features that are considered to be characteristics of the exemplary embodiments are set forth in the appended claims. However, the exemplary embodiments, their preferred usage patterns, their further purposes and features will be best understood when read in conjunction with the accompanying drawings, by reference to the following detailed description of the exemplary embodiments of the present disclosure, where:

[0014] Figure 1 is an illustration of a graphical representation of a network and a construction station of a data processing system capable of implementing the exemplary embodiments;

[0015] Figure 2 is an illustration of a block diagram of a laminate manufacturing environment according to the exemplary embodiments;

[0016] Figure 3 is an illustration of a data flow for predicting non - conforming items according to the exemplary embodiments;

[0017] Figure 4is an illustration of a data flow for managing nonconformities in a management pressure plate according to an illustrative embodiment;

[0018] Figure 5 is an illustration of a data flow for training an artificial intelligence system to manage laminate nonconformities in laminates according to an illustrative embodiment;

[0019] Figure 6 is an illustration of an augmented reality display of nonconforming item information on a laminate according to an exemplary embodiment;

[0020] Figure 7 is an illustration of the display of a pattern on a laminate according to an exemplary embodiment;

[0021] Figure 8 is an illustration of a display of change information for a material layer in a workpiece according to an exemplary embodiment;

[0022] Fig. 9 is an illustration of a flow chart of a process for managing the manufacture of a management plate according to an illustrative embodiment;

[0023] Fig.10 is an illustration of a flow chart of a process for identifying laminate nonconformities in laminates according to an illustrative embodiment;

[0024] Fig.11 is an illustration of a flow chart of a process for predicting laminate nonconformities in laminates according to an illustrative embodiment;

[0025] Fig.12 is an illustration of a flow chart of a process for processing a laminate having a laminate nonconformity according to an illustrative embodiment;

[0026] Fig.13 is an illustration of a block diagram of a data processing system according to an illustrative embodiment;

[0027] Fig.14 is an illustration of a block diagram of an aircraft manufacturing and service method according to an illustrative embodiment;

[0028] Fig.15 is an illustration of a block diagram of an aircraft in which an illustrative embodiment may be implemented; and

[0029] Fig.16 is an illustration of a block diagram of a product management system according to an illustrative embodiment. DETAILED DESCRIPTION

[0030] The illustrative embodiments recognize and take into account one or more different considerations. For example, the illustrative embodiments recognize and take into account that nonconformance in the analysis of laminates can affect the way in which the stacking of layers to form a workpiece occurs. For example, the illustrative embodiments recognize and take into account that at least one of wrinkles in the layers, foreign matter, debris, material handling, material problems, or other factors in the stacked layers can cause nonconformance in the laminate.

[0031] As used herein, when the phrase "at least one" is used with a list of items, it means that different combinations of one or more of the listed items can be used, and only one of the items in the list may be required. In other words, "at least one" means that any combination of items and numbers of items can be used from the list, but not all of the items in the list are required. The item can be a specific object, thing, or category.

[0032] For example, but not limited to, "at least one of item A, item B, or item C" may include item A, item A and item B, or item B. This example may also include item A, item B, and item C, or item B and item C. Of course, there may be any combination of these items. In some illustrative examples, "at least one" may be, for example (but not limited to), two of item A, one of item B; and ten of item C; four of item B and seven of item C; or other suitable combinations.

[0033] The illustrative embodiments also recognize and take into account that the ability of a human operator to consistently detect nonconformities is often not as great as desired. The illustrative embodiments recognize and take into account that nonconformities may be difficult to detect due to their size. Furthermore, the illustrative embodiments recognize and take into account that with repeated and large numbers of laminates for inspection and other duties, a human operator may not always correctly identify nonconformities in laminates.

[0034] Thus, illustrative embodiments provide methods, apparatus, and systems for managing nonconformities in manufacturing laminates. In an illustrative example, a sensor system records stacking information about a layer stack on a tool on a workpiece platform. The layer stack forms a workpiece. The sensor system records inspection information about a laminate on an inspection platform. The laminate is formed by curing the workpiece. A user input system receives user input describing nonconformities in a laminate on an inspection platform. A computer system trains an artificial intelligence system using the stacking information, the inspection information, and the user input describing the nonconformities in the laminate.

[0035] Referring now to the drawings, and in particular to Figure 1, depicts an example of a pictorial representation of a network and construction station of a data processing system in which the illustrative embodiments may be implemented. Network data processing system 100 is a network of computers in which the illustrative embodiments may be implemented. Network data processing system 100 includes network 102, which is a medium for providing communication links between multiple devices and computers connected together within network data processing system 100. Network 102 may include connections such as wires, wireless communication links, or fiber optic cables.

[0036] In the depicted example, server computer 104 and client computer 106 are connected to network 102. In the depicted example, server computer 104 provides information such as boot files, operating system images, and applications to client computer 106.

[0037] Program code located in network data processing system 100 may be stored on a computer recordable storage medium and downloaded to a data processing system or other device for use. For example, program code may be stored on a computer recordable storage medium on server computer 104 and downloaded to client computer 106 via network 102 for use on client computer 106.

[0038] In the depicted example, network data processing system 100 is the Internet with network 102 representing a global collection of networks and gateways that use the Transmission Control Protocol / Internet Protocol (TCP / IP) suite of protocols to communicate with one another. At the heart of the Internet is a backbone of high-speed data communication lines between host computers consisting of thousands of commercial, government, educational, and other computer systems that route data and messages. Of course, network data processing system 100 may also be implemented using multiple different types of networks. For example, network 102 may include at least one of the Internet, an intranet, a local area network (LAN), a metropolitan area network (MAN), or a wide area network (WAN). Figure 1 It is intended as an example and not as an architectural limitation to the different illustrative embodiments.

[0039] As used herein, when "plurality" is used with reference to an item, "plurality" means one or more items. For example, "plurality of different types of networks" is one or more different types of networks. In the depicted example, client computer 106 communicates with a sensor system including camera 108, camera 110, and camera 112 at build station 114. Using these components, client computer 106 can record stacking information 116 about a stack of layers to be formed into a workpiece on a tool (such as a metal backing plate on platform 118 in build platform 114). The formation of the workpiece can be performed by at least one of human operator 120 or human operator 122 at build station 114.

[0040] In addition, client computer 106 is also in communication with a display system at build station 114 that includes laser projector 124. Laser projector 124 can display information to human operator 120 and human operator 122. In this illustrative example, laser projector 124 uses one or more lasers that are directed to and scan platform 118 or an object on platform 118 to display information. The information may include text, graphics, video, or other information visible to at least one of human operator 120 or human operator 122. This type of display can provide an augmented reality display to display information on a real-time view of a real-world environment such as platform 118 or an object on platform 118. The display can cause information to be seamlessly woven so that the information is perceived as part of platform 118 or an object on platform 118.

[0041] During a build operation at build station 114, material layers are stacked on platform 118 to form one or more workpieces. During the build operation, human operator 120 may identify nonconforming items in the layers being stacked. Nonconforming items in the layers may include at least one of rips, tears, wrinkles, foreign debris, or other nonconforming items.

[0042] In addition to identifying nonconformances, human operator 120 may also indicate whether a particular nonconformance is acceptable or can be resolved. If the nonconformance cannot be resolved, the layer is discarded.

[0043] In this illustrative example, the client computer 106 projects a user interface directly onto the layer on the platform 118 to allow the human operator 120 to specify the precise location of the location in the layer where a nonconforming item may exist. Such a nonconforming item can be a nonconforming item that the human operator 120 believes will not cause a nonconforming item in the laminate. In this example, the specification is a user input in the form of a gesture that can be detected by at least one of the camera 108, the camera 110, or the camera 112. The user input can be considered as part of the stacking information 116. The stacking information 116 can also include a video of the stacking process or other information that can be detected by the camera (camper).

[0044] The stack information 116 is sent to the analyzer 126. The analyzer 126 can use the stack information 116 to train the artificial intelligence system 128. As the artificial intelligence system 128 learns potential problems, the artificial intelligence system 128 can communicate with the client computer 106 to highlight potential nonconformance areas directly on the layers stacked on the platform 118 using the laser projector 124 and allow the human operator 120 to verify the presence of nonconformances and other information about the nonconformances for that layer. This information forms additional information that can be used for further training of the artificial intelligence system 128.

[0045] After the layers are stacked to form the workpieces, another metal backing plate may be placed on the workpieces to form a tray. The tray is moved to a press where pressure and heat are applied to cure the workpieces, thereby forming a laminate. The laminates may be returned to the platform 118 in the build station 114 for inspection.

[0046] In this example, a human operator 122 inspects the laminate for nonconformities. The human operator 122 generates user input indicating the location of any nonconformities on the laminate. This information, along with the inspection video or image from the camera and other suitable information, forms inspection information 130. As shown, the inspection information 130 is sent to an analyzer 126 running on the server computer 104.

[0047] Using the inspection information 130 and the stacking information 116, the analyzer 126 can use the artificial intelligence system 128 to correlate the nonconformities identified in the workpiece with nonconformities in the laminate formed by curing the workpiece. In this way, a prediction of when a nonconformity is likely to occur can be made based on the nonconformities identified in the stacked layers for the workpiece. In addition, the verification of the prediction of nonconformities can be used in further training of the artificial intelligence system 128 by the analyzer 126.

[0048] As shown, computer vision and gesture recognition processing can be implemented in at least one of the analyzer 126 or the artificial intelligence system 128. The processing can enable the human operator 122 to generate user input detected by at least one of the camera 108, the camera 110, and the camera 112. The user input specifies where the non-conforming item is on the laminate, and the type of the non-conforming item is classified. These processes can also receive user input related to the arrangement and state of the laminate. The state can be, for example, one of useable, rework, or scrap.

[0049] In addition, the analyzer 126 can also use the laser projector 124 to project patterns of laminate cuts directly onto the laminate on the platform 118 in the build station 114. These patterns are potential patterns for cutting parts from the laminate. In the illustrative example, the analyzer 126 projects one pattern onto the laminate at a time.

[0050] Additionally, the analyzer 126 may also project a graphical indicator of the nonconforming item on the laminate using the laser projector 124. For example, the graphical indicator may be an outline of the nonconforming item, a border around the nonconforming item, or other types of graphical indicators that may draw attention to the location of the nonconforming item on the laminate. This display of information is an augmented reality display that allows the human operator 122 to visualize patterns associated with one or more nonconforming items in the laminate.

[0051] Additionally, the human operator 122 can also generate user input to reposition the pattern projected onto the laminate. Furthermore, the human operator 122 can view multiple patterns for the same or different parts to determine which pattern or patterns may be the most desirable pattern based on the nonconformities on the laminate. With the visualization of this information in the augmented reality display, the human operator 120 can accept, reject, and reorient patterns and visualize these patterns in the laminate, where the locations of the nonconformities are displayed on the laminate.

[0052] In addition, user input can be used with the inspection information 130 to train the artificial intelligence system 128 using machine learning techniques. The training can enable the artificial intelligence system 128 to identify non-conformities after curing. The inspection information 130 can include, for example, non-conformity classification, non-conformity location information, laminate part type, or pattern selection positioning.

[0053] Next, refer to Figure 2 , an illustration of a block diagram of a laminate manufacturing environment is depicted in accordance with an illustrative embodiment. In this illustrative example, laminate manufacturing environment 200 is an environment for manufacturing laminate material 202.

[0054] For example, the layer stack 204 is stacked to form the workpiece 206. The workpiece 206 exists when all of the material layers 228 for the laminate 208 are stacked on the workpiece platform 230. The workpiece 206 is cured to form the laminate 208 in the laminate material 202. The curing may be performed using at least one of pressure or heat applied to the workpiece 206.

[0055] In this illustrative example, material layers 228 in layer stack 204 include first outer layer 248, core layer 250, and second outer layer 252. Core layer 250 is located between first outer layer 248 and second outer layer 252.

[0056] In an illustrative example, first outer layer 248 is selected from one of a thermoplastic layer and a polyvinyl fluoride layer. Second outer layer 252 is selected from one of a thermoplastic layer and a polyvinyl fluoride layer. Core layer 250 is selected from one of a resin layer, a carbon layer, and a honeycomb layer. In addition, the layers in layer stack 204 may also include at least one of a release sheet, a texture blanket, or a coating. Layers such as release sheets and texture blankets do not become part of laminate 208, but are used in forming laminate 208. In this example, the coating does become part of laminate 208. The coating may have a design or decal.

[0057] Workpiece 206 may be associated with laminate 208 using identifier 254. As shown, identifier 254 is associated with workpiece 206. Identifier 254 is present in laminate 208 and identifies laminate 208 as being formed from workpiece 206. In this illustrative example, identifier 254 may be selected from at least one of a barcode, a radio frequency identifier, text, a visual code, or some other visual or machine-readable identifier.

[0058] As shown, nonconforming item management system 210 can be used to manage the distribution of pressed material 202. In this illustrative example, nonconforming item management system 210 includes a plurality of different components. As shown in this example, nonconforming item management system 210 includes sensor system 212, display system 214, input system 216 and analyzer 218. As shown, analyzer 218 is located in computer system 220 in nonconforming item management system 210.

[0059] As shown, the sensor system 212 is a physical hardware system that operates to detect operations, steps, and other actions performed on at least one of the stacked layers of material of the stack 204 used to form the workpiece 206 when the stack 204 is completed. The sensor system 212 can also detect the laminate 208 on the inspection platform 232. The laminate 208 is produced by curing the workpiece 206.

[0060] In this illustrative example, sensor system 212 includes a number of different components. For example, sensor system 212 may include at least one of a camera, a visible light camera, an infrared camera, a laser scanner, or other suitable types of sensors.

[0061] The display system 214 is a physical hardware system and includes one or more display devices that can display the graphical user interface 222. The display device may include at least one of a projector, a laser projector, smart glasses, a smart contact lens, a tablet computer, a mobile phone, a mobile computing device with a camera and a display device, or other suitable types of devices capable of displaying information on a surface. In addition, the display system 214 may also include other display devices, including at least one of a light emitting diode (LED) display, a liquid crystal display (LCD), an organic light emitting diode (OLED) display, a computer monitor, a flat panel display, a head-up display (HUD), or some other suitable device that can output information to present information.

[0062] Display system 214 is configured to display graphical user interface 222 to human operator 224. In this illustrative example, graphical user interface 222 may take the form of augmented reality display 226. In augmented reality display 226, information is displayed directly on the real-time view in a manner that augments the real-time view of one or more objects.

[0063] In this illustrative example, information can be displayed on a real-time view of at least one of layer stack 204, workpiece 206, laminate 208, workpiece platform 230, or inspection platform 232. In some illustrative examples, the real-time view can be seen through smart glasses, a tablet computer, or a mobile phone. In another illustrative example, the information can be displayed without a display device to view the object. For example, a projector such as a laser projector can be used to display the information directly on the physical object itself.

[0064] Human operator 224 is a person who can interact with graphical user interface 222 through user input 225 generated by input system 216. Input system 216 is a physical hardware system and can be selected from at least one of a mouse, a keyboard, a gesture detection device, a camera, a virtual reality glove, a microphone, a gaze tracker, a motion detector, or some other suitable type of input device. In this illustrative example, when there is a camera in input system 216, the camera can also act as a sensor in sensor system 212. In other words, there may be an overlap in the functionality of the devices.

[0065] In this illustrative example, human operator 224 places material layers 228 on workpiece platform 230 to create layer stack 204. The layers may be sheets cut from a roll of material. When completed, layer stack 204 forms workpiece 206.

[0066] The workpiece platform 230 is a physical structure that supports the layer stack 204, which is stacked on the workpiece platform 230 to form the workpiece 206. The layer stack 204 can be stacked on a tool on the workpiece platform 230. The tool can be, for example, a metal caul plate, an ontour layup tool, a fixture, a form, or other suitable tool.

[0067] After the workpiece 206 is cured to form the laminate 208, the laminate 208 may be placed on an inspection platform 232. As shown, the inspection platform 232 is a physical structure that supports the laminate 208 formed from the workpiece 206. The workpiece platform 230 may be the inspection platform 232. In other words, the same physical structure may be used to implement both functional blocks.

[0068] In this illustrative example, sensor system 212 records at least one of stacking information 234 related to one of layer stacks 204 on workpiece platform 230 or inspection information 236 related to laminate 208 located on inspection platform 232. In this depicted example, stacking information 234 and inspection information 236 may include at least one of video, images, or audio related to layer stacks 204 forming workpiece 206.

[0069] In some illustrative examples, stacked information 234 may also include user input 225. When input system 216 generates user input 225, user input 225 may be sent to sensor system 212 for use in generating stacked information 234. Furthermore, user input 225 may be considered separate from stacked information 234 and may be sent directly from input system 216 to analyzer 218. In other words, user input 225 may be part of stacked information 234 or may be separate from stacked information 234. Sensor system 212 sends stacked information 234 and inspection information 236 to analyzer 218.

[0070] As shown, the analyzer 218 in the computer system 220 identifies the laminate nonconformity 238. The analyzer 218 can be implemented as software, hardware, firmware, or a combination thereof. When software is used, the operations performed by the analyzer 218 can be implemented as program code, which is configured to run on hardware such as a processor unit. When firmware is used, the operations performed by the analyzer 218 can be implemented as program code and data and stored in a persistent memory to run on a processor unit. When hardware is used, the hardware can include circuits that operate to perform the operations in the analyzer 218.

[0071] In an illustrative example, the hardware can take the form of at least one of a circuit system, an integrated circuit, an application specific integrated circuit (ASIC), a programmable logic device, or some other suitable type of hardware configured to perform multiple operations. Using a programmable logic device, the device can be configured to perform multiple operations. The device can be reconfigured at a later time, or can be permanently configured to perform multiple operations. Programmable logic devices include, for example, programmable logic arrays, programmable array logic, field programmable logic arrays, field programmable gate arrays, and other suitable hardware devices. In addition, the process can be implemented as an organic component integrated with an inorganic component, and can be composed entirely of organic components other than humans. For example, the process can be implemented as a circuit in an organic semiconductor.

[0072] The computer system 220 is a physical hardware system and includes one or more data processing systems. When there are more than one data processing system in the computer system 220, these data processing systems communicate with each other using a communication medium. The communication medium may be a network. The data processing system may be selected from at least one of a computer, a server computer, a tablet computer, or some other suitable data processing system.

[0073] In this illustrative example, analyzer 218 may use inspection information 236 to identify laminate nonconformance 238 in laminate 208, and nonconformance information 240 related to laminate nonconformance 238. In some illustrative examples, analyzer 218 may use stackup information 234 and inspection information 236 to identify laminate nonconformance 238 in laminate 208. In this illustrative example, nonconformance information 240 describing laminate nonconformance 238 includes at least one of a location, a region containing the nonconformance, a nonconformance type, a laminate status, a laminate part number, a laminate component part, or other suitable information describing or related to laminate nonconformance 238.

[0074] As shown, the identification of laminate nonconformance 238 and the generation of nonconformance information 240 may be performed by an artificial intelligence system 242. Artificial intelligence system 242 is a system that has intelligent behavior and may be based on the functions of a human brain.

[0075] The artificial intelligence system includes at least one of an artificial neural network, a cognitive system, a Bayesian network, fuzzy logic, an expert system, a natural language system, a cognitive system, or some other suitable system. The artificial intelligence system is trained using machine learning. Machine learning involves inputting data into a processor and allowing the processor to adjust and improve the functionality of the artificial intelligence system.

[0076] A cognitive system is a computing system that mimics the functions of the human brain. A cognitive system may be, for example, IBM Watson, available from International Business Machines Corporation.

[0077] In the illustrative example, analyzer 218 displays nonconformance information 240 related to nonconformances in laminate 208 using display system 214 for augmented reality display 226. This display of nonconformance information 240 is on a real-time view of laminate 208. The real-time view can be used directly by human operator 224 without an intervening display device. This type of display can be performed using a projector such as a laser projector, a video projector, or a digital projector.

[0078] In another example, a camera may capture images of laminate 208. These images may be displayed on a display device with a real-time view of laminate 208 augmented with nonconforming item information 240.

[0079] As shown, the analyzer 218 can request user input 225 to verify that the identification of laminate nonconformances 238 in the laminates 208 identified by the analyzer 218 is correct based on a setting that indicates prompting a human operator for verification. The setting can be a default setting that always requests verification, or a user-selected setting. The setting can be, for example, based on an event such as requesting verification after every fifth laminate that is inspected.

[0080] In another example, a confidence level is assigned to the identification of the laminate nonconformance 238. The confidence level indicates the likelihood of believing that the laminate nonconformance 238 exists.

[0081] As shown, when the confidence level of the identification of the laminate nonconformance 238 in the laminate 208 identified by the analyzer 218 is less than a threshold value for proceeding without the user input 225, the analyzer 218 requests the user input 225 to verify whether the identification of the laminate nonconformance 238 in the laminate 208 identified by the analyzer 218 is correct. The threshold value may be, for example, 88%, 95%, 98%, or other levels. The threshold value may be selected, for example, using specifications or design rules.

[0082] In response to the analyzer 218 request for verification, the human operator 224 generates a user input 225 to verify whether the laminate nonconformance 238 in the laminate 208 identified by the analyzer 218 is present.

[0083] In addition, although the illustrative example is described with respect to processing layer stack 204 to form laminate 208, nonconforming item management system 210 can be used with layers of multiple workpieces stacked. For example, eight workpieces, ten workpieces, or twenty-six workpieces can be stacked on a first tool (such as a first metal pad) on workpiece platform 230. A second tool (such as a second metal pad) can be placed on top of the stack of workpieces. This data can be referred to as a tray. The tray can be moved to a press that applies pressure and heat to the tray to form a stack of laminates.

[0084] The pallet containing the laminates may then be moved to an inspection platform 232. Inspection of the laminates may be performed by an analyzer 218 using the sensor system 212 to generate inspection information 236 for each of the laminates in the pallet. The inspection information 236 may be analyzed using an artificial intelligence system 242 to determine if there are any inconsistencies in the stack of laminates.

[0085] Additionally, the analyzer 218 may use the stacking information 234 recorded during the process of forming the ply stack 204 to predict the occurrence of a laminate nonconformance 238 of the laminate 208 prior to curing the ply stack 204 to form the laminate 208. The prediction may be made by the analyzer 218 using the artificial intelligence system 242. As a result, the ply stack 204 may be reprocessed prior to curing to form the laminate 208. As a result, the laminate nonconformance 238 predicted by the analyzer 218 may be avoided. Thus, through the predictive identification of nonconformances by the artificial intelligence system 242, less frequent occurrences of inconsistencies in the laminate material 202 may occur.

[0086] Next, refer to Figure 3 , an example of a data flow for predicting nonconformities is depicted according to an exemplary embodiment. In the illustrative examples, the same reference numerals may be used in more than one figure. This repeated use of reference numerals in different figures represents the same element in different figures.

[0087] In this illustrative example, analyzer 218 in computer system 220 uses artificial intelligence system 242 to predict the presence of laminate nonconformance 238 in laminate 208. As shown, sensor system 212 records stacking information 234 from layers in stack 204 being stacked to form workpiece 206 (which in turn is cured to form laminate 208).

[0088] Analyzer 218 may generate prediction 300 for laminate nonconformance 238 occurring in laminate 208 based on stackup information 234 for ply stack 204. In this illustrative example, stackup information 234 may be continuously generated as the layers in ply stack 204 are placed to form workpiece 206. Stackup information 234 may be sent when it is generated, sent periodically, sent when ply stack 204 is completed, or some combination thereof.

[0089] In the illustrative example, stacking information 234 includes an image or video of the layers within ply stack 204. This information may be present for each layer that is placed to form ply stack 204. This information may be analyzed to identify stacking nonconformities 304 within ply stack 204 of workpiece 206 before workpiece 206 is cured to form laminate 208. Stacking nonconformities 304 may include at least one of wrinkles in a layer, foreign object debris, missing alignment of a layer, or some other nonconformity.

[0090] As shown, the prediction 300 is generated before the workpiece 206 is cured to form the laminate 208. The prediction 300 can include the likelihood of the laminate nonconformance 238 occurring in the laminate 208. In some cases, the presence of the stacking nonconformance 304 will not result in the laminate nonconformance 238 in the laminate 208.

[0091] Additionally, the analyzer 218 may also generate change information 302 indicating a change in the ply stack 204 that reduces the likelihood that the laminate nonconformance 238 will exist when the ply stack 204 is cured to form the laminate 208. In this example, the prediction 300 and the change information 302 are generated by the analyzer 218 using the artificial intelligence system 242.

[0092] Analyzer 218 uses display system 214 for augmented reality display 226 to display change information 302 indicating changes in ply stack 204 on the real-time view of ply stack 204. In this illustrative example, change information 302 may include instructions to resolve stack nonconformance 304 in ply stack 204 such that a likelihood that laminate nonconformance 238 will be present is reduced when ply stack 204 is cured to form laminate 208.

[0093] Additionally, the human operator 224 can use the identification of the stackup nonconformance 304 to make changes in the ply stack 204 to reduce the likelihood that the laminate nonconformance 238 will occur in the laminate 208. The change information 302 can include at least one of a stackup nonconformance type for the stackup nonconformance, a location of the ply stack containing the stackup nonconformance, or instructions to resolve the stackup nonconformance.

[0094] Now let’s refer to Figure 4 , an illustration of a data flow for managing nonconformities in laminates is depicted according to an illustrative embodiment. In this illustrative example, laminate 208 is placed on inspection platform 232. Sensor system 212 generates inspection information 236 related to laminate 208. Analyzer 218 uses inspection information 236 to identify laminate nonconformities 238 that have been identified as existing.

[0095] As shown, determine the state 400 of the laminate 208. In this particular example, the state 400 can be, for example, acceptable, reworked, or discarded. In addition, in this example, the state 400 can include laminate production (yield), which can be based on width, fixed length, and material type.

[0096] Part of determining the state 400 may be whether a laminate nonconformance 238 in the laminate 208 affects a set of parts 402 that may be formed from the laminate 208. The determination may be made by examining patterns 404. The set of parts 402 is identified using nonconformance information 240 related to the laminate nonconformance 238. As shown, the nonconformance information 240 describing the laminate nonconformance 238 includes at least one of a location, a region containing the nonconformance, a nonconformance type, a laminate state, a laminate part number, a laminate component part, or other suitable information describing or related to the laminate nonconformance 238.

[0097] In this illustrative example, part type for part 402 may be based on the material in laminate 208. The part type may be obtained from an identifier, such as identifier 254, which may take the form of a bar code, a radio frequency identifier (RFID) chip, a graphic, text, or some other suitable type of item that may be placed on or in workpiece 206 that remains in place when laminate 208 is formed.

[0098] In this example, the location of laminate nonconformance 238 and the area or extent of laminate nonconformance 238 may be used to determine whether laminate 208 may be used to make group of parts 402. In this illustrative example, analyzer 218 may display pattern 406 for group of parts 402 on laminate 208. Additionally, analyzer 218 may also display area 408 at the location of laminate nonconformance 238.

[0099] In one illustrative example, human operator 224 may view pattern 406 as part of augmented reality display 226 regarding area 408 encompassing laminate nonconformance 238. Human operator 224 may perform a visual inspection to determine whether laminate 208 may be used for group of parts 402 in pattern 406. If area 408 is within the cutout of pattern 406 for a portion of group of parts 402, human operator 224 may change the orientation of pattern 406 to determine whether the change in pattern results in laminate 208 being usable for making group of parts 402 using pattern 406.

[0100] If laminate 208 is not suitable for use in making set of parts 402 using pattern 406, another one of patterns 404 may be displayed on laminate 208. The different pattern may have at least one of a different orientation or a different spacing of parts for the same parts as pattern 406. The other pattern may have different types of parts that may be more suitable for making those parts.

[0101] This processing may also be performed by artificial intelligence system 242. The selected pattern and orientation in pattern 404 enables laminate 208 to be displayed to human operator 224 on laminate 208 in augmented reality display 226. Human operator 224 may generate user input 225 to verify that the selection is correct or to select a different pattern. In addition, if more than one pattern is identified in pattern 404 that can be used to form laminate 208, those options may also be displayed to human operator 224 to select an appropriate pattern for laminate 208.

[0102] Now refer to Figure 5 , an illustration of a data flow for training an artificial intelligence system to manage laminate nonconformities in laminates is depicted according to an illustrative embodiment. In this illustrative example, trainer 500 is operated to train artificial intelligence system 242.

[0103] As shown, the trainer 500 may implement machine learning techniques 502 to train the artificial intelligence system 242. The training of the artificial intelligence system 242 may be performed using previous stacking information 504 recorded for a previous layer stack 506 of a previous workpiece 508, previous inspection information 510 related to a previous laminate 512 formed from the previous workpiece 508, and previous user input 514 identifying a previous laminate nonconformity 515 in the previous laminate 512.

[0104] For example, the trainer 500 can train the artificial intelligence system 242 using the sensor system 212 that records previous stacking information 504 of a previous workpiece 508 and previous inspection information 510 related to a previous laminate 512 formed from the previous workpiece 508. In addition, the training can also be performed using previous user input 514 received from the input system 216, which identifies a previous laminate nonconformity 515 in the previous laminate 512.

[0105] The training may be performed using machine learning techniques 502 to enable the artificial intelligence system 242 to identify the laminate nonconformities 238 in the laminates 208. This information forms the data or data set that the trainer 500 uses to train the artificial intelligence system 242.

[0106] With respect to using machine learning techniques 502 to train the artificial intelligence system 242, the trainer 500 may include one or more categories of machine learning techniques 502 for training artificial intelligence system models for the artificial intelligence system 242. The artificial intelligence system 242 includes one or more artificial intelligence system models that are trained to perform different tasks, such as detecting nonconformities, predicting nonconformities, determining whether a laminate can be used when nonconformities are present in the laminate, and other tasks.

[0107] In this illustrative example, these categories are: supervised learning algorithm 516, unsupervised learning algorithm 518, reinforcement learning algorithm 520, and transfer learning algorithm 521. As shown, at least one of supervised learning algorithm 516, unsupervised learning algorithm 518, reinforcement learning algorithm 520, or transfer learning algorithm 521 may be used to train artificial intelligence system 242.

[0108] In the illustrated example, the supervised learning algorithm 516 includes providing training data and the correct output values ​​for the data to the artificial intelligence system 242. During supervised learning, the values ​​for the output are provided to the model building process along with the training data (labeled into a data set). The algorithm deciphers the patterns that exist between the input training data and the known output values ​​through trial and error to create a model that can reproduce the same underlying rules with new data. The model is a component in the artificial intelligence system 242. Examples of supervised learning algorithms include regression analysis, decision trees, k-nearest neighbors, neural networks, and support vector machines.

[0109] If an unsupervised learning algorithm 518 is used, not all variables and data patterns are labeled, forcing the artificial intelligence machine model in the artificial intelligence system 242 to discover hidden patterns and create labels on its own by using the unsupervised learning algorithm 518. The advantage of the unsupervised learning algorithm 518 is that it discovers patterns in the data without the need for a labeled data set. Examples of unsupervised learning algorithms used in unsupervised machine learning for training the artificial intelligence system 242 include: k-means clustering, association analysis, and descending clustering.

[0110] Supervised learning algorithm 516 and unsupervised learning algorithm 518 cause the artificial intelligence model in artificial intelligence system 242 to learn from a data set, while reinforcement learning algorithm 520 causes the artificial intelligence model in artificial intelligence system 242 to learn from interactions with an environment. The environment may be detected by sensor system 212 and input system 216. Reinforcement learning algorithm 520 may be, for example, Q-learning, which is used to train the artificial intelligence model in artificial intelligence system 242 by interacting with the environment using measurable performance criteria.

[0111] In this illustrative example, transfer learning algorithm 521 is another machine learning technique that can be used to train artificial intelligence system 242. This particular machine learning technique can be used to use a pre-existing artificial intelligence system that has been pre-trained with a data set for a different purpose. In other words, artificial intelligence system 214 can be a pre-existing artificial intelligence system that has been trained for a different purpose to extract features from an image. For example, artificial intelligence system 242 may have been trained to extract features and classify those features to identify tools in an image. Using transfer learning algorithm 521, artificial intelligence system 242 can be modified or provided with new rules to perform classification to identify non-conforming items. In this way, the training enables artificial intelligence system 242 to extract features that have been performed before using transfer learning algorithm 521. Training using transfer learning algorithm 521 can take advantage of the fact that artificial intelligence system 242 can be trained to extract features. The focus of the training is classification to identify non-conforming items.

[0112] In addition, reinforcement or additional training can be performed even after artificial intelligence system 242 is operating to detect nonconformities, predict nonconformities, or determine whether a laminate with nonconformities can be used. For example, the process of stacking material layers of layer stack 204 to form workpiece 206 can be recorded in sensor system 212. In addition, identification of stacking nonconformities in layer stack 204 can also be identified in user input 225.

[0113] At this point in time, human operator 224 generates user input 225 to identify stacking nonconformities that human operator 224 saw during each of the ply stacks 204. The user input can also indicate whether a particular nonconformity will cause a laminate nonconformity in the laminate due to curing the ply stack. In addition, the identification of the laminate nonconformity can be in the user input 225 generated by human operator 224 when inspecting laminate 208. In other words, human operator 224, through gestures, can indicate where a particular laminate nonconformity exists.

[0114] The human operator 224 can also verify the extent of the laminate nonconformance, the type of nonconformance, and other information related to the laminate nonconformance. The sensor system 212 can record a video or image of the laminate inspected by the human operator 224. The artificial intelligence system 242 is trained using the user input 225 and the inspection information 236. The trainer 500 can use this verification of whether the laminate nonconformance 238 is present in the user input 225 and the inspection information 236 to further train the artificial intelligence system 242.

[0115] In some illustrative examples, this training may also include using stackup information 234. Stackup information 234 may be used in training artificial intelligence system 242 to identify when a particular stackup nonconformance of a layer in layer stack 204 results in laminate nonconformance 238 in laminate 208. This additional training may improve the accuracy of artificial intelligence system 242 in identifying laminate nonconformances.

[0116] Additionally, when training includes stackup information 234 in addition to inspection information 236, analyzer 218 using artificial intelligence system 242 may operate to predict when a laminate nonconformance is likely to occur.

[0117] Additionally, a root cause analysis may be performed on a previous layer stack 506 of a previous workpiece 508 that was cured to form a previous laminate 512. The analysis may be performed to generate a nonconformance map 522. The nonconformance map 522 is information that may be used by the trainer 500 to train the artificial intelligence system 242 to predict the occurrence of laminate nonconformances based on the stackup information.

[0118] The nonconforming item map 522 identifies the occurrence of laminate nonconforming items based on the stacking nonconforming items. The stacking nonconforming items in the nonconforming item map 522 can include at least one of wrinkles, creases, dents, washouts, incorrect layer stacking, contaminants, dirt, debris, or other nonconforming items that occur during the layer stacking of the workpiece.

[0119] In an illustrative example, one or more technical solutions are proposed to overcome the technical problem of using human operators to inspect laminates in the current technology to accurately identify non-conforming items in laminates. As a result, one or more technical solutions can provide the following technical effects, enabling a computer system to automatically inspect laminates for non-conforming items, predict the occurrence of non-conforming items during the stacking of layers of workpieces that are cured to form laminates, display change instructions during the stacking process to reduce non-conforming items in laminates, or reduce the discard of laminates through pattern selection for parts.

[0120] Thus, the illustrative examples provide methods, apparatus, and systems for managing the manufacture of laminates. The nonconformance management system 210 operates to reduce nonconformances in the laminates. In addition, the system can also operate to perform root cause analysis to identify the cause of nonconformances that occurred before the workpiece including the layer stack was cured to form the laminate. In addition, when nonconformances exist in the laminates, the nonconformance management system 210 can be used to perform part selection on the laminates.

[0121] The nonconformance management system 210 may employ a graphical user interface 222 in the form of an augmented reality display 226 displayed directly on the laminate 208. Additionally, the artificial intelligence system 242 and the nonconformance management system 210 may be trained to identify laminate nonconformances, which may be verified by a human operator 224. Furthermore, the artificial intelligence system 242 may be operable to predict the cause of a laminate nonconformance and display change information 302 that may be used to reduce the occurrence of laminate nonconformances prior to curing the workpiece.

[0122] The computer system 220 can be configured to perform at least one of the steps, operations, or actions described in the different illustrative examples using software, hardware, firmware, or a combination thereof. As a result, the computer system 220 operates as a special-purpose computer system, wherein the analyzer 218 in the computer system 220 implements at least one of: managing the manufacture of laminates during at least one of placing material layers to form a layer stack to form a workpiece, more accurately identifying non-conforming items during inspection of laminates, or selecting a pattern for a part when non-conforming items are present in the laminates. In particular, the analyzer 218 converts the computer system 220 into a special-purpose computer system compared to a general-purpose computer system that currently does not have the analyzer 218. In the illustrative example, the analyzer 218 includes a practical application of the artificial intelligence system 242.

[0123] In the illustrative example, the use of analyzer 218 in computer system 220 integrates processing into a practical application for managing the manufacture of laminates, which improves the performance of computer system 220. In other words, analyzer 218 in computer system 220 involves the practical application of processing integrated into analyzer 218 in computer system 220 to identify nonconformities in laminates from inspection information detected by a sensor system, wherein inspection information 242 is processed using artificial intelligence system. In this way, through training, analyzer 218 can use artificial intelligence system 242 in an improved manner compared to current techniques where human operators perform multiple operations.

[0124] exist Figures 2 to 4 The illustration of laminate manufacturing environment 200 in different components in the illustrative embodiments is not meant to imply physical or architectural limitations on the manner in which the illustrative embodiments may be implemented. Other components in addition to or in place of the components shown may be used. Some components may not be necessary. Likewise, blocks are provided to illustrate some functional components. When implemented in the illustrative embodiments, one or more of the blocks in these blocks may be combined, divided, or combined and divided into different blocks.

[0125] For example, in some illustrative examples, the workpiece platform 230 and the inspection platform 232 may also be considered part of the nonconformance management system 210. In another illustrative example, the artificial intelligence system 242 may be part of the analyzer 218, rather than a separate component. In yet another illustrative example, a video in the stacking information 234 containing the correct process for reducing the occurrence of stacking nonconformances that lead to laminate nonconformances may be presented to a human operator. When a stacking nonconformance is identified in a material layer stacked in a layer stack that forms a workpiece, these videos may be presented as part of the change information 302. In another illustrative example, these videos may be used as part of a separate training processor class for a human operator.

[0126] Next, refer to Figure 6 , depicts an example of an augmented reality display of nonconforming item information on a laminate according to an exemplary embodiment. As depicted in this example, laminate 600 is located on inspection platform 602. Laminate 600 is Figure 2 An example of a physical implementation of the laminate 208 is shown in block form in FIG. Figure 2 An example of a physical implementation of the inspection platform 232 is shown in block form in FIG.

[0127] In this illustrative example, laminate nonconformance 604 is present in laminate 600. In this example, laminate nonconformance 604 is a wrinkle in laminate 600. Laminate nonconformance 604 is Figure 2 An example of a laminate nonconformance 238 is shown in box form in FIG.

[0128] As shown, an area 606 is displayed on the laminate 600 around the laminate nonconformance 604. The display of the area 606 is performed using a laser projector. In addition, nonconformance information 608 is displayed on the laminate 600. The nonconformance information 608 is Figure 2 An example of non-conforming item information 240 is shown in box form in FIG.

[0129] As shown, the nonconformance information 608 may include at least one of a nonconformance type, relevant information identifying the location of the laminate nonconformance 604 , a laminate part number, a laminate material, or other suitable information related to the laminate nonconformance 604 .

[0130] In this illustrative example, laminate materials, laminate part numbers, and other suitable information may be identified in a number of different ways. For example, in this example, barcode 611 is located on laminate 600. Barcode 611 may be used to identify layers, layer materials (such as raw materials used to form layers), and other information related to the layer stack used to form a workpiece that is cured to form laminate 600.

[0131] Additionally, a verification prompt 610 is also displayed on the laminate 600. The prompt requests user input to indicate whether the identification of the laminate nonconformance 604 is correct. As shown, the display is performed by overlaying the information on the real-time view of the laminate 600 to provide an augmented reality display to the human operator. In this example, the user can request that the analyzer correct / classify and verify the identified nonconformance, part layout selection, or some combination thereof.

[0132] Additionally, a list of nonconformities 612 can be displayed on the laminate 600. The list of nonconformities 612 is nonconformities that are identified as potential candidates for laminate nonconformities 604. The list can be displayed as part of training the artificial intelligence system. For example, if the artificial intelligence system is unsure whether a particular nonconformity exists, the artificial intelligence system can display those options in the list of nonconformities 612. The list can be displayed instead of or in addition to the verification prompt 610.

[0133] Next, refer to Figure 7 , depicts an example of displaying a pattern on a laminate according to an exemplary embodiment. In this depicted example, a pattern 700 is displayed on a laminate 600 by a laser projector. The pattern 700 is Figure 4 An example of pattern 406 is shown in box form in FIG.

[0134] As shown, pattern 700 identifies cuts of a part. In this example, the cuts include: cut 702, cut 704, cut 706, cut 708, cut 710, and cut 712. A cut is a portion of laminate 600 that is removed from laminate 600 to form a part.

[0135] As shown, laminate nonconformance 604 does not interfere with cutting laminate 600 to obtain cutouts of parts, as shown by the overlay of pattern 700 onto laminate 600. If laminate nonconformance 604 is located within a cutout part, pattern 700 may be reoriented, or another pattern for another type of part may be selected and displayed on laminate 600 to determine whether laminate 600 is usable. When laminate nonconformance 604 is located within one or more cutouts of pattern 700, laminate 600 may be used to make parts, but fewer parts may be made from laminate 600.

[0136] Next, refer to Figure 8 , an illustration of display of change information of a material layer in a workpiece is depicted in accordance with an illustrative embodiment. In this illustrative example, material layer 800 is stacked on inspection platform 802 .

[0137] In this example, there is a stacking nonconformance 804 in the material layer 800. In this example, the stacking nonconformance 804 is a wrinkle in the material layer 800. As shown, the stacking nonconformance 804 is predicted to cause a nonconformance in the laminate produced by the material layer 800. In this example, the change information 806 is displayed directly on the material layer 800 using a laser projector.

[0138] As shown, the change information 806 includes a graphical indicator 808 that identifies the outline of the stacking nonconformity 804. In addition, the change information 806 also includes instructions 810. In this example, the instructions 810 are to smooth the wrinkles using a rod, and also see the video showing the technique of smoothing wrinkles.

[0139] Next go to Fig. 9 , depicts an illustration of a flow chart of a process for managing the manufacture of a pressure plate according to an exemplary embodiment. It can be implemented in hardware, software, or both Fig. 9 When implemented in software, the process may take the form of program code executed by one of a plurality of processor units in one or more hardware devices in one or more computer systems. For example, Figure 2 The processing is implemented in the analyzer 218 in the computer system 220 in.

[0140] The process begins by recording stacking information about a layer stack on a workpiece platform, wherein the layer stack forms a workpiece (operation 900). The stacking information is recorded by a sensor system, such as, Figure 2 9. The process records inspection information about a laminate on an inspection platform, wherein the laminate is formed by curing a workpiece (operation 902). In operation 902, the inspection information is also reported by the sensor system 212. The stacking information and the inspection information may include at least one of video, image, audio, user input, or other suitable information.

[0141] The process receives user input describing a laminate nonconformity in a laminate on an inspection platform (operation 904). The user input is received from a user input system. The description of the laminate nonconformity in the user input may include at least one of the location of the laminate nonconformity, the area containing the laminate nonconformity, the type of nonconformity, the laminate status, or other suitable information that may be input by a human operator inspecting the laminate.

[0142] In operation 904, user input may be provided by a gesture detected by a camera, a keyboard, a virtual reality glove, a microphone, or other suitable type of input device. For example, the location of the laminate nonconformity may be determined by a user using a gesture pointing to the location of the laminate nonconformity. In a similar manner, the user input may be a gesture that outlines or defines an area in which the laminate nonconformity exists.

[0143] The process trains the artificial intelligence system using the stacking information, the inspection information, and the user input describing laminate nonconformities in the laminates present in the inspection information (operation 906). The process terminates thereafter. Figure 5 A trainer 500 of one or more machine learning techniques 502 may be used to perform the training of the artificial intelligence system in operation 906.

[0144] The training may generate one or more artificial intelligence system models for the artificial intelligence system. The models may continue to be trained to improve at least one of the speed and accuracy of identifying or predicting non-conformities.

[0145] Now refer to Fig.10 , depicts an illustration of a flow chart of a process for identifying laminate nonconformities in laminates according to an exemplary embodiment. The invention may be implemented in hardware, software, or both. Fig.10 When implemented in software, the process may take the form of program code executed by one or more processor units in one or more hardware devices in one or more computer systems. Figure 2 The processing is implemented in at least one of the analyzer 218 in the computer system 220 or the artificial intelligence system 242.

[0146] The process begins by detecting the presence of a laminate for inspection (operation 1000). The process receives inspection information from a sensor system (operation 1002). The inspection information includes at least one of video, images, or audio associated with the laminate being inspected.

[0147] The process determines whether there are laminate nonconformities using the inspection information (operation 1004). In the illustrative example, operation 1004 is performed using an artificial intelligence system. In this example, the artificial intelligence system has been trained using previous stacking information recorded for previous layer stacks of previous workpieces, previous inspection information related to previous laminates formed from previous workpieces, and previous user input identifying previous nonconformities in previous laminates. The process terminates thereafter.

[0148] Now refer to Fig.11, depicts an illustration of a flow chart of a process for predicting laminate nonconformities in laminates according to an exemplary embodiment. The process may be implemented in hardware, software, or both. Fig.11 When implemented in software, the process may take the form of program code executed by one or more processor units in one or more hardware devices in one or more computer systems. For example, Figure 2 The processing is implemented in at least one of the analyzer 218 in the computer system 220 or the artificial intelligence system 242.

[0149] The process begins by predicting laminate failures in a laminate using stack information, wherein the laminate is formed by curing a layer stack (operation 1100). The stack information is about the layer stack that forms the workpiece. The stack information may include at least one of video, image, or audio.

[0150] For example, after the layers in the layer stack are placed to form a workpiece, an image of the layers can be generated. In other illustrative examples, a video of the entire process can be generated, showing how a human operator stacks or places the layers. The video can also include instructions from the human operator on how to place layers in different layers or remove non-conforming items.

[0151] The prediction may be made at a number of different times. For example, the prediction may be made after the individual layers of material in the layer stack are stacked or after the layer stack is completed to form a workpiece.

[0152] The process generates change information indicating a change in the layer stack that reduces the likelihood that laminate nonconformities will exist when the layer stack is cured to form a laminate (operation 1102). The process displays the change information indicating the change in the layer stack on a real-time view of the layer stack using a display system for augmented reality display (operation 1104). The process terminates thereafter. Using the change information, a workpiece or a layer in a layer stack in a workpiece can be adjusted, reworked, or discarded to reduce the production of laminates with laminate nonconformities.

[0153] Next, refer to Fig.12 , depicts an illustration of a flow chart of a process for processing a laminate having laminate nonconformities according to an exemplary embodiment. The process may be implemented in hardware, software, or both. Fig.12 When implemented in software, the process may take the form of program code executed by one or more processor units in one or more hardware devices in one or more computer systems. For example, Figure 2 The processing is implemented in at least one of the analyzer 218 in the computer system 220 or the artificial intelligence system 242.

[0154] The process receives inspection information for a laminate (operation 1200). In this example, the process receives information from a plurality of laminates, such as Figure 2 The sensor system 212 in the embodiment of the present invention receives inspection information. The process uses the inspection information to identify laminate nonconformities in the laminate (operation 1202).

[0155] The process displays an identification of the laminate nonconformance as an augmented reality display on the real-time view of the laminate (operation 1204). The identification can be a graphical indicator displayed in the laminate nonconformance. The graphical indicator can overlay or cover the laminate nonconformance. The identification can also include other information, such as, nonconformance type.

[0156] The process displays the pattern of the set of parts as part of an augmented reality display on the real-time view of the laminate (operation 1206). The process terminates thereafter.

[0157] The identification of the laminate nonconformance and the display of the pattern can be reviewed by a human operator to determine whether the laminate can be used to make the set of parts. In one example, if the laminate cannot be used with the current pattern, a different pattern can be selected for review by the human operator. In some cases, the laminate nonconformance falls outside of a set of cutouts for the set of parts. In other cases, when there are multiple parts in the set of parts, the laminate nonconformance may be within only one of the cutouts, making the laminate usable to make some of the parts.

[0158] The flow charts and block diagrams in the different depicted embodiments illustrate the architecture, function and operation of some possible implementations of the equipment and methods in the illustrative embodiments. In this regard, each frame in the flow chart or block diagram can represent at least one of a module, segment, function or operation or a part of a step. For example, one or more frames in the frame can be implemented as a combination of program code, hardware or program code and hardware. When implemented in hardware, the hardware can, for example, take the form of an integrated circuit, which is manufactured or configured to perform one or more operations in the flow chart or block diagram. When implemented as a combination of program code and hardware, the implementation can take the form of firmware. Each frame in the flow chart or block diagram can be implemented using a combination of a dedicated hardware system or dedicated hardware that performs different operations and a program code run by dedicated hardware.

[0159] In some alternative implementations of the illustrative embodiments, the functions marked in the blocks may not occur in the order marked in the figure. For example, in some cases, two blocks shown in succession may be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order, depending on the functions involved. Moreover, in a flow chart or block diagram, other blocks may be added in addition to the blocks illustrated.

[0160] Now go to Fig.13 , depicts an example of a block diagram of a data processing system according to an exemplary embodiment. Data processing system 1300 may be used to implement Figure 1 The data processing system 1300 can also be used to implement the server computer 104 and the client computer 106 in the embodiment of the present invention. Figure 2 The computer system 220 in FIG.

[0161] In this illustrative example, data processing system 1300 includes communications framework 1302, which provides communications between processor unit 1304, memory 1306, persistent storage 1308, communications unit 1310, input / output (I / O) unit 1312, and display 1314. In this example, communications framework 1302 takes the form of a bus system.

[0162] Processor unit 1304 is used to execute instructions of software that can be loaded into memory 1306. Processor unit 1304 includes one or more processors. For example, processor unit 1304 can be selected from at least one of a multi-core processor, a central processing unit (CPU), a graphics processing unit (GPU), a physical processing unit (PPU), a digital signal processor (DSP), a network processor, or some other suitable type of processor.

[0163] Memory 1306 and persistent storage 1308 are examples of storage 1316. A storage device is any hardware capable of storing information such as, for example, but not limited to, at least one of data, program code in functional form, or other suitable information temporarily, permanently, or temporarily and permanently. In these illustrative examples, storage 1316 may also be referred to as computer-readable storage. In these examples, memory 1306 may be, for example, a random access memory or any other suitable volatile or non-volatile storage. Persistent storage 1308 may take various forms depending on the particular implementation.

[0164] For example, persistent storage 1308 may include one or more components or devices. For example, persistent storage 1308 may be a hard drive, a solid state drive (SSD), flash memory, a rewritable optical disk, a rewritable magnetic tape, or some combination thereof. The media used by persistent storage 1308 may also be removable. For example, a removable hard drive may be used for persistent storage 1308.

[0165] In these illustrative examples, communications unit 1310 provides for communications with other data processing systems or devices. In these illustrative examples, communications unit 1310 is a network interface card.

[0166] Input / output unit 1312 allows data input and output with other devices that may be connected to data processing system 1300. For example, input / output unit 1312 may provide a connection for user input through at least one of a keyboard, a mouse, or some other suitable input device. In addition, input / output unit 1312 may send output to a printer. Display 1314 provides a mechanism for displaying information to a user.

[0167] Instructions for at least one of the operating system, applications, and programs may be located in storage devices 1316, which are in communication with processor unit 1304 through communications framework 1302. The processes of the different embodiments may be performed by processor unit 1304 using computer-implemented instructions that may be located in a memory, such as memory 1306.

[0168] These instructions are referred to as program code, computer usable program code, or computer readable program code, which can be read and executed by a processor in processor unit 1304. The program code in different embodiments may be implemented on different physical or computer readable storage media, such as memory 1306 or persistent storage 1308.

[0169] Program code 1318 is located in functional form on optionally removable computer readable media 1320 and can be loaded into or transferred to data processing system 1300 for execution by processor unit 1304. In these illustrative examples, program code 1318 and computer readable media 1320 form computer program product 1322. In the illustrative examples, computer readable media 1320 is computer readable storage media 1324.

[0170] In these illustrative examples, computer readable storage media 1324 is a physical or tangible storage device used to store program code 1318 rather than a medium that propagates or transmits program code 1318 .

[0171] Alternatively, program code 1318 may be transmitted to data processing system 1300 using a computer readable signal medium. Computer readable signal media may be, for example, a propagated data signal containing program code 1318. For example, a computer readable signal medium may be at least one of an electromagnetic signal, an optical signal, and any other suitable type of signal. These signals may be sent, for example, via a wireless connection, an optical fiber cable, a coaxial cable, a wire, or any other suitable type of connection.

[0172] The different components illustrated for data processing system 1300 are not intended to provide architectural limitations to the manner in which different embodiments may be implemented. In some illustrative examples, one or more components may be included in or form part of another component. For example, in some illustrative examples, memory 1306 or portions thereof may be included in processor unit 1304. The different illustrative embodiments may be implemented in a data processing system including components in addition to or in place of those illustrated for data processing system 1300. Fig.13 Other components shown may be varied from the illustrative examples shown. The different embodiments may be implemented using any hardware device or system capable of running program code 1318 .

[0173] You can Fig.14 Aircraft manufacturing and service method 1400 is shown and Fig.15 Exemplary embodiments of the present disclosure are described in the context of aircraft 1500 as shown. Fig.14 , an illustration of a block diagram of an aircraft manufacturing and service method is depicted according to an illustrative embodiment. During pre-production, aircraft manufacturing and service method 1400 may include Fig.15 Specification and design 1402 of aircraft 1500 and material procurement 1404 .

[0174] During production, Fig.15 Component and subassembly manufacturing 1406 and system integration 1408 of the aircraft 1500 in FIG. Fig.15 The aircraft 1500 in may undergo certification and delivery 1410 to be placed in service 1412. When placed in service 1412 by a customer, Fig.15 Aircraft 1500 is scheduled for routine maintenance and overhaul 1414, which may include modification, reconfiguration, refurbishment, and other maintenance or overhaul.

[0175] Each of the processes of the aircraft manufacturing and service method 1400 may be performed or carried out by a system integrator, a third party, an operator, or some combination thereof. In these examples, the operator may be a customer. For purposes of this description, 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 contractors, subcontractors, and suppliers; and an operator may be an airline, a leasing company, a military entity, a service organization, etc.

[0176] Now refer to Fig.15 , depicts an illustration of a block diagram of an aircraft in which an illustrative embodiment may be implemented. In this example, aircraft 1500 is Fig.141400 is an aircraft manufacturing and service method, and may include fuselage 1502 having multiple systems 1504 and interior 1506. Examples of systems 1504 include one or more of propulsion system 1508, electrical system 1510, hydraulic system 1512, and environmental system 1514. Any number of other systems may be included. Although an aviation example is shown, different illustrative embodiments may be applied to other industries, such as the automotive industry.

[0177] Can be Fig.14 Apparatuses and methods embodied herein may be employed during at least one of the stages of aircraft manufacturing and service method 1400 .

[0178] In one illustrative example, aircraft 1500 may be operated in a manner similar to Fig.14 1412. Parts or subassemblies produced when put into service are made or manufactured in a manner Fig.14 Components or subassemblies produced in the component and subassembly manufacturing 1406. As another example, a component or subassembly can be produced in a production stage (such as, Fig.14 During component and subassembly manufacturing 1406 and system integration 1408 in the flight 1500, one or more apparatus embodiments, method embodiments, or a combination thereof are utilized. Fig.14 One or more apparatus embodiments, method embodiments, or a combination thereof may be utilized during or both maintenance and overhaul 1412 in the process.

[0179] For example, analyzer 218 may be used to manufacture a part from laminates during at least one of component and subassembly manufacturing 1406 or maintenance and overhaul 1414. By employing nonconformance management system 210 to reduce nonconformances in laminates used for a part, efficiency may be increased and costs may be reduced in manufacturing the part. Using a number of different illustrative embodiments may substantially speed up assembly of aircraft 1500, reduce the cost of aircraft 1500, or speed up assembly of aircraft 1500 and reduce the cost of aircraft 1500.

[0180] Now go to Fig.16 , depicts an illustration of a block diagram of a product management system according to an illustrative embodiment. Product management system 1600 is a physical hardware system. In this illustrative example, product management system 1600 includes at least one of manufacturing system 1602 or maintenance system 1604.

[0181] Manufacturing system 1602 is configured to manufacture products, such as, Fig.15 16. As shown, manufacturing system 1602 includes manufacturing equipment 1606. Manufacturing equipment 1606 includes at least one of fabrication equipment 1608 or assembly equipment 1610.

[0182] The manufacturing equipment 1608 is used to manufacture Fig.15 Fabrication equipment 1608 may include equipment for fabricating components of parts for aircraft 1500. For example, fabrication equipment 1608 may include machines and tools. These machines and tools may be at least one of a drill, a hydraulic press, a furnace, a mold, a composite tape laying machine, a vacuum system, a lathe, or other suitable types of equipment. Fabrication equipment 1608 may be used to fabricate at least one of a metal part, a composite part, a semiconductor, a circuit, a fastener, a rib, a skin panel, a wing spar, an antenna, or other suitable types of parts.

[0183] Assembly equipment 1610 is used to assemble parts to form Fig.15 In particular, assembly equipment 1610 is used to assemble components and parts to form Fig.15 The assembly equipment 1610 may also include machines and tools. These machines and tools may be at least one of a robotic arm, a crawler, a rapid installation system, a track-based drilling system, or a robot. The assembly equipment 1610 may be used to assemble parts such as seats, horizontal stabilizers, wings, engines, engine housings, landing gear systems, and Fig.15 Other parts of the aircraft 1500.

[0184] In this illustrative example, maintenance system 1604 includes maintenance equipment 1612. Maintenance equipment 1612 may include Fig.15 Maintenance equipment 1612 may include any equipment required to perform maintenance on aircraft 1500. Fig.15 The tools used to perform various operations on parts of aircraft 1500 in FIG. These operations may include disassembling a part, refurbishing a part, inspecting a part, reworking a part, manufacturing a replacement part, or performing other operations on a part. Fig.15 At least one of other operations of performing maintenance on the aircraft 1500 in the embodiment of the present invention. These operations can be used for routine maintenance, inspection, upgrade, refurbishment or other types of maintenance operations.

[0185] In the illustrative example, maintenance equipment 1612 may include ultrasonic inspection devices, X-ray imaging systems, visual systems, drills, crawlers, and other suitable devices. In some cases, maintenance equipment 1612 may include fabrication equipment 1608, assembly equipment 1610, or both to produce and assemble parts required for maintenance.

[0186] Product management system 1600 also includes control system 1614. Control system 1614 is a hardware system and may also include software or other types of components. Control system 1614 is configured to control the operation of at least one of manufacturing system 1602 or maintenance system 1604. In particular, control system 1614 may control the operation of at least one of fabrication equipment 1608, assembly equipment 1610, or maintenance equipment 1612.

[0187] The hardware in control system 1614 may be implemented using hardware that may include computers, circuits, networks, and other types of equipment. Control may take the form of direct control of manufacturing equipment 1606. For example, robots, computer-controlled machines, and other equipment may be controlled by control system 1614. In other illustrative examples, control system 1614 may manage operations performed by human operators 1616 in manufacturing or performing maintenance on aircraft 1500. For example, control system 1614 may assign tasks, provide instructions, display models, or perform other operations to manage operations performed by human operators 1616. In these illustrative examples, the hardware in control system 1614 may be implemented from human operators 1616. Figure 2 Non-conformity management system 210 to manage Fig.15 At least one of the manufacturing or maintenance of the aircraft 1500 in the process. For example, the analyzer 218 may be operable to help identify and reduce manufacturing failures in producing Fig.15 A nonconforming item in a laminate used in a part of at least one of manufacturing or performing maintenance for aircraft 1500.

[0188] In different illustrative examples, human operator 1616 may operate or interact with at least one of manufacturing equipment 1606, maintenance equipment 1612, or control system 1614. Such interaction may occur to manufacture Fig.15 The aircraft in 1500.

[0189] Of course, product management system 1600 can be configured to manage Fig.15 Although product management system 1600 has been described with respect to manufacturing in the aerospace industry, product management system 1600 can be configured to manage products for other industries. For example, product management system 1600 can be configured to manufacture products for the automotive industry and any other suitable industry.

[0190] Therefore, illustrative examples provide methods, devices, and systems for managing nonconformities in laminates. In an illustrative example, the nonconformity management system includes a sensor system and an analyzer in a computer system. A workpiece platform supports a stack of layers stacked on the workpiece platform to form a workpiece. An inspection platform supports a laminate formed by the workpiece. The sensor records stacking information about the stack of layers on the workpiece platform and records inspection information about the laminate located on the inspection platform, wherein the laminate is formed by curing the workpiece. The analyzer in the computer system uses the inspection information to identify laminate nonconformities in the laminate; generates nonconformity information about the laminate nonconformities, and displays the nonconformity information about the laminate nonconformities on the laminate using a display system for augmented reality display.

[0191] The nonconformance management system operates to reduce nonconformances that occur in laminates. For example, the system may also operate to perform a root cause analysis to identify the cause of a nonconformance that occurs before a workpiece including a layer stack is cured to form a laminate. Identification of the cause may be used to make changes to at least one of the techniques used to stack the layers, the materials of the layers, the suppliers, or the layers, or to make other changes. In addition, when nonconformances exist in the laminate, the system may be used to perform part selection for the laminate.

[0192] The description of different illustrative embodiments has been presented for the purpose of illustration and description and is not intended to be exhaustive or limited to the embodiments of the disclosed forms. The different illustrative examples describe components that perform actions or operations. In the illustrative embodiments, the components can be configured to perform the described actions or operations. For example, the components can have a configuration or design for a structure that provides the components with the ability to perform the actions or operations described as being performed by the components in the illustrative examples.

[0193] Furthermore, the present disclosure includes implementations according to the following clauses:

[0194] 1. A non-conforming item management system (210), the non-conforming item management system (210) comprising:

[0195] a workpiece platform (230), the workpiece platform (230) supporting a layer stack (204), the layer stack (204) being stacked on the workpiece platform (230) to form a workpiece (206);

[0196] an inspection platform (232) supporting a laminate formed from the workpiece (206);

[0197] a sensor system (212) that records stacking information (234) associated with the layer stack (204) on the workpiece platform (230) and records inspection information (236) associated with a laminate (208) located on the inspection platform (232), wherein the laminate (208) is formed by curing the workpiece (206); and

[0198] An analyzer (218), wherein the analyzer (218) is in a computer system (220), wherein the analyzer (218) uses the inspection information (236) to identify laminate nonconformities (238) in the laminate (208), generates nonconformity information (240) related to the laminate nonconformities (238), and uses a display system (214) for an augmented reality display (226) to display the nonconformity information (240) related to the laminate nonconformities (238) on the laminate (208).

[0199] 2. A nonconformity management system (210) according to claim 1, wherein, when using the inspection information (236) to identify laminate nonconformities (238) in the laminate (208), the analyzer (218) uses the stacking information (234) and the inspection information (236) to identify laminate nonconformities (238) in the laminate (208).

[0200] 3. The nonconformance management system (210) according to clause 1, wherein the analyzer (218) comprises an artificial intelligence system (242), and the nonconformance management system (210) further comprises:

[0201] an input system (216) that receives user input (225) for verifying the presence of a laminate nonconformity (238) in the laminate (208) identified by the analyzer (218); and

[0202] A trainer (500), the trainer (500) being in a computer system (220), the trainer (500) using the user input (225) and the inspection information (236) to train the artificial intelligence system (242).

[0203] 4. The nonconformity management system (210) of clause 3, wherein the artificial intelligence system (242) is trained using at least one of a supervised learning algorithm (516), an unsupervised learning algorithm (518), a reinforcement learning algorithm (520), or a transfer learning algorithm (520).

[0204] 5. The nonconformance management system (210) of clause 1, wherein the analyzer (218) comprises an artificial intelligence system (242), and the nonconformance management system (210) further comprises:

[0205] an input system (216) that receives user input (225), and

[0206] Wherein, when the confidence level of the identification of the laminate nonconforming item (238) in the laminate (208) identified by the analyzer (218) is less than a threshold for proceeding without the user input (225), the analyzer (218) requests the user input (225) to verify whether the identification of the laminate nonconforming item (238) in the laminate (208) identified by the analyzer (218) is correct.

[0207] 6. The non-conformity management system (210) according to clause 5, further comprising:

[0208] A trainer (500), the trainer (500) being in a computer system (220), the trainer (500) using the user input (225) and the inspection information (236) to train the artificial intelligence system (242).

[0209] 7. The nonconformance management system (210) of clause 1, wherein the analyzer (218) comprises an artificial intelligence system (242), and the nonconformance management system (210) further comprises:

[0210] an input system (216) that receives user input (225), and

[0211] Wherein, the analyzer (218), based on a setting indicating prompting an operator for verification, requests the user input (225) to verify whether the identification of the laminate nonconforming item (238) in the laminate (208) identified by the analyzer (218) is correct.

[0212] 8. The non-conformity management system (210) according to clause 7, further comprising:

[0213] A trainer (500), the trainer (500) being in a computer system (220), the trainer (500) using the user input (225) and the inspection information (236) to train the artificial intelligence system (242).

[0214] 9. A nonconformity management system (210) according to claim 1, wherein, when using the stacking information (234) to identify laminate nonconformities (238) in the laminate (208), the analyzer (218) uses an artificial intelligence system (242) to identify laminate nonconformities (238) in the laminate (208), and the artificial intelligence system (242) is trained using previous stacking information (504) recorded for a previous layer stack (204) of a previous workpiece (508), previous inspection information (510) related to a previous laminate (512) formed by the previous workpiece (508), and previous user input (514) identifying a previous laminate nonconformity (515) in the previous laminate (512).

[0215] 10. A nonconformance management system (210) according to claim 1, wherein the analyzer (218) uses the stacking information (234) to predict the occurrence of the laminate nonconformance (238) before the layer stack (204) is cured to form the laminate (208).

[0216] 11. The nonconformance management system (210) of clause 1, wherein the analyzer (218) uses nonconformance information (240) related to the laminate nonconformance (238) to identify a set of parts that can be formed from the laminate (208).

[0217] 12. A nonconformance management system (210) according to claim 1, wherein the nonconformance information (240) describing the laminate nonconformance (238) includes at least one of the following: location, area containing the laminate (208) nonconformance, nonconformance type, laminate status, laminate part number or laminate component part.

[0218] 13. The non-conformity management system (210) according to clause 1, further comprising:

[0219] An identifier (254) is associated with the workpiece (206), wherein the identifier (254) identifies a laminate (208) formed from the workpiece (206).

[0220] 14. The nonconformance management system (210) of clause 13, wherein the identifier (254) is selected from one of the following: a barcode, a radio frequency identifier, text, a visual code, and a machine-readable identifier.

[0221] 15. The non-conformity management system (210) according to clause 3, wherein the input system (216) is selected from at least one of the following: a mouse, a keyboard, a gesture detection device, a camera, a virtual reality glove, a microphone, a gaze tracker or a motion detector.

[0222] 16. The nonconformity management system (210) according to clause 1, wherein the display system (214) is selected from at least one of the following: a projector, a laser projector, smart glasses, smart contact lenses, a tablet computer, a mobile phone, or a mobile computing device with a camera and a display device.

[0223] 17. The nonconformance management system (210) of clause 1, wherein the workpiece platform (230) is the inspection platform (232).

[0224] 18. A nonconformity management system (210) according to claim 1, wherein the layer stack (204) includes a first outer layer (248), a core layer (250) and a second outer layer (252), wherein the core layer (250) is located between the first outer layer (248) and the second outer layer (252).

[0225] 19. A nonconformity management system (210) according to clause 18, wherein the first outer layer (248) is selected from one of a thermoplastic layer and a polyvinyl fluoride layer; the second outer layer (252) is selected from one of a thermoplastic layer and a polyvinyl fluoride layer; and wherein the core layer (250) is selected from one of a resin layer, a carbon layer and a honeycomb layer.

[0226] 20. The nonconformance management system (210) of clause 18, wherein the layer stack (204) further comprises at least one of a release sheet, a textured blanket, or a coating.

[0227] 21. A non-conforming item management system (210), the non-conforming item management system (210) comprising:

[0228] a sensor system (212) that records stacking information (234) related to a stack of layers (204) forming a workpiece (206); and

[0229] An analyzer (218) is included in a computer system (220), the analyzer (218) using the stacking information (234) to predict a laminate nonconformity (238) in a laminate (208) formed by curing the layer stack (204), generating change information (302) indicating a change in the layer stack (204) that reduces the likelihood that the laminate nonconformity (238) will exist when the layer stack (204) is cured to form the laminate (208), and displaying the change information (302) indicating the change in the layer stack (204) on a real-time view of the layer stack (204) using a display system (214) for an augmented reality display (226).

[0230] 22. A nonconformity management system (210) according to clause 21, wherein the analyzer (218) identifies stacking nonconformities (304) in the layer stack (204), and the change information (302) includes instructions to resolve the stacking nonconformities (304) in the layer stack (204), thereby reducing the likelihood that the laminate nonconformities (238) will exist when the layer stack (204) is cured to form the laminate (208).

[0231] 23. A nonconformity management system (210) according to clause 21, wherein the analyzer (218) analyzes inspection information (236) to determine whether the laminate nonconformity (238) exists in the laminate (208), and when the laminate nonconformity (238) exists in the laminate (208), nonconformity information (240) related to the laminate nonconformity (238) is displayed on a real-time view of the laminate (208) used for the augmented reality display (226).

[0232] 24. A nonconforming item management system (210) according to clause 21, wherein the change information (302) includes at least one of the following: the stacking nonconforming item type of the stacking nonconforming item (304), the location of the layer stack (204) containing the stacking nonconforming item (304), or instructions for resolving the stacking nonconforming item (304).

[0233] 25. The nonconformance management system (210) of clause 21, wherein the layer stack (204) comprises a first outer layer, a core layer, and a second outer layer, wherein the core layer is located between the first outer layer and the second outer layer.

[0234] 26. A nonconformity management system (210) according to clause 25, wherein the first outer layer is selected from one of a thermoplastic layer and a polyvinyl fluoride layer; the second outer layer is selected from one of a thermoplastic layer and a polyvinyl fluoride layer; and wherein the core layer is selected from one of a resin layer, a carbon layer and a honeycomb layer.

[0235] 27. The nonconformance management system (210) of clause 25, wherein the layer stack (204) further comprises at least one of a release sheet, a textured blanket, or a coating.

[0236] 28. A non-conforming item management system (210), the non-conforming item management system (210) comprising:

[0237] a sensor system (212) that detects a laminate (208) on an inspection platform (232), wherein the laminate (208) is formed by curing a workpiece (206) including a ply stack (204); and

[0238] An analyzer (218) in a computer system (220), the analyzer (218) using stacking information (234) recorded by the sensor system (212) to determine whether a laminate nonconformity (238) exists in the laminate (208), generating nonconformity information (240) related to the laminate nonconformity (238) when the laminate nonconformity (238) is detected, and displaying information related to the laminate nonconformity (238) on the laminate (208) using a display system (214) for an augmented reality display (226). ) related to nonconforming items (240), wherein the analyzer (218) uses an artificial intelligence system (242) to determine whether the laminate nonconforming item (238) exists in the laminate (208), and the artificial intelligence system (242) is trained using previous stacking information (504) recorded for a previous workpiece (508), previous inspection information (510) related to a previous laminate (512) formed by the previous workpiece (508), and previous user input (514) related to previous nonconforming items (515) in the previous laminate (512).

[0239] 29. The nonconformity management system (210) according to clause 28, further comprising:

[0240] an input system (216) for receiving user input,

[0241] Wherein, the analyzer (218) requests the user input (225) to verify whether the confidence level of the identification of the laminate non-conformance item (238) in the laminate (208) identified by the analyzer (218) is less than a threshold value for proceeding without the user input.

[0242] 30. The non-conformance item management system (210) according to clause 28, the non-conformance item management system (210) further includes:

[0243] An input system (216), the input system (216) receives user input, and

[0244] Wherein, when the confidence level of the identification of the laminate non-conformance item (238) in the laminate (208) identified by the analyzer (218) is less than a threshold value for proceeding without the user input, the analyzer (218) requests the user input to verify whether the identification of the laminate non-conformance item (238) in the laminate (208) identified by the analyzer (218) is correct.

[0245] 31. The non-conformance item management system (210) according to clause 30, the non-conformance item management system (210) further includes:

[0246] A trainer (500), the trainer (500) is in a computer system (220), the trainer (500) uses the user input to train the artificial intelligence system (242).

[0247] 32. The non-conformance item management system (210) according to clause 28, the non-conformance item management system (210) further includes:

[0248] An input system (216), the input system (216) receives user input (225), and

[0249] Wherein, the analyzer (218) requests the user input to verify whether the identification of the laminate non-conformance item (238) in the laminate (208) identified by the analyzer (218) is correct based on a setting indicating a prompt to the operator for verification.

[0250] 33. The non-conformance item management system (210) according to clause 32, the non-conformance item management system (210) further includes:

[0251] A trainer (500), the trainer (500) is in a computer system (220), the trainer (500) uses the user input (225) to train the artificial intelligence system (242).

[0252] 34. The non - conforming item management system (210) according to clause 28, wherein the analyzer (218) uses non - conforming item information (240) related to the laminate non - conforming items (238) to identify a set of parts that can be formed from the laminate (208).

[0253] 35. A method for managing the manufacture of a laminate (208), the method comprising:

[0254] Recording (900) stacking information (234) related to a stack (204) on a workpiece platform (230) by a sensor system (212), wherein the stack (204) forms a workpiece (206);

[0255] Recording (902) inspection information (236) related to a laminate (208) on an inspection platform (232) by the sensor system (212), wherein the laminate (208) is formed by curing the workpiece (206);

[0256] Receiving (904) a user input (225) through a user input system (216), the user input (225) describing laminate non - conforming items (238) in the laminate (208) on the inspection platform (232); and

[0257] Training (906) an artificial intelligence system (242) by a computer system (220) using the stacking information (234), the inspection information (236), and the user input (225) describing the laminate non - conforming items (238).

[0258] 36. The method according to clause 35, the method further comprising:

[0259] Predicting (1100) laminate non - conforming items (238) in the laminate (208) using the stacking information (234), wherein the laminate (208) is formed by curing the stack (204);

[0260] Generating (1102) change information (302) indicating a change in the stack (204), the change reducing the likelihood that the laminate non - conforming items (238) will exist when the stack (204) is cured to form the laminate (208), and

[0261] Displaying (1104) the change information (302) indicating the change in the stack (204) on a real - time view of the stack (204) using a display system (214) for augmented reality display (226).

[0262] 37. The method according to clause 36, further comprising:

[0263] Another user input (225) is received, the other user input (225) verifying whether a laminate nonconformance (238) predicted for the laminate (208) exists in the laminate (208).

[0264] 38. The method according to clause 35, further comprising the steps of:

[0265] An identifier and nonconformance information (240) associated with the laminate nonconformance (238) are used to identify a set of parts and part types that can be formed from the laminate (208).

[0266] 39. The method according to clause 35, further comprising the steps of:

[0267] A state (400) of the laminate (208) is determined based on a set of patterns (404) for a set of parts (402).

[0268] 40. A method according to clause 35, wherein the user input (225) describing the laminate nonconformity (238) includes at least one of the location of the laminate nonconformity (238), the area containing the laminate nonconformity (238), the nonconformity type, or the laminate status.

[0269] 41. A method according to clause 35, wherein the layer stack (204) includes a first outer layer (248), a core layer (250) and a second outer layer (252), wherein the core layer (250) is located between the first outer layer (248) and the second outer layer (252).

[0270] 42. The method of clause 41, wherein the layer stack (204) further comprises at least one of a release sheet, a textured blanket, or a coating.

[0271] Many modifications and variations will be apparent to those of ordinary skill in the art. In addition, different illustrative embodiments may provide different features compared to other desired embodiments. The selected embodiments are chosen and described in order to best explain the principles of the embodiments, practical applications, and to enable others of ordinary skill in the art to understand the disclosure of various embodiments with various modifications suitable for the particular use contemplated.

Claims

1. A non-conforming item management system, the non-conforming item management system include: a workpiece platform supporting a stack of layers on which the layers are stacked to form a workpiece; an inspection platform supporting a laminate formed from the workpiece; a sensor system that records stacking information about a layer stack on the workpiece platform and records inspection information about a laminate on the inspection platform, wherein the laminate is formed by curing the workpiece; and An analyzer, wherein the analyzer is in a computer system, and the analyzer performs the following operations: using the inspection information to identify laminate nonconformities in the laminate, generating nonconformance information related to the laminate nonconformance, wherein the nonconformance information describing the laminate nonconformance includes a location of the laminate nonconformance and a laminate status, and wherein the laminate status determines whether the laminate nonconformance in the laminate affects a set of parts that can be formed from the laminate, using a display system for augmented reality display to display nonconformity information on the laminate related to the laminate nonconformity, displaying an area at said location of said laminate nonconformity, A pattern of laminate cuts for the set of parts is displayed onto the laminate using a display system for an augmented reality display, wherein the pattern regarding areas encompassing laminate nonconformities is configured to be viewed by a human operator as part of the augmented reality display.

2. The non-conforming item management system according to claim 1, in, The analyzer uses the stacking information and the inspection information to identify laminate nonconformities in the laminate when using the inspection information to identify laminate nonconformities in the laminate.

3. The non-conforming item management system according to claim 1, in, The analyzer includes an artificial intelligence system, and the non-conforming item management system also includes: an input system that receives user input for verifying the presence of a laminate nonconformity in the laminate identified by the analyzer; a trainer in the computer system, the trainer using the user input and the inspection information to train the artificial intelligence system, wherein the artificial intelligence system is trained using at least one of a supervised learning algorithm, an unsupervised learning algorithm, a reinforcement learning algorithm, or a transfer learning algorithm, wherein, when the confidence level of the identification of the laminate nonconforming item in the laminate identified by the analyzer is less than a threshold value performed in the absence of the user input, the analyzer requests the user input to verify whether the identification of the laminate nonconforming item in the laminate identified by the analyzer is correct; and Wherein, a trainer in the computer system uses the user input and the inspection information to train the artificial intelligence system.

4. The non-conforming item management system according to any one of claims 1 to 3, in, When using the stacking information to identify laminate nonconformities in the laminate, the analyzer uses an artificial intelligence system to identify laminate nonconformities in the laminate, and the artificial intelligence system is trained using previous stacking information recorded for previous layer stacks of previous workpieces, previous inspection information related to previous laminates formed by the previous workpieces, and previous user input identifying previous laminate nonconformities in the previous laminates.

5. The non-conforming item management system according to any one of claims 1 to 3, in, The analyzer uses the stack-up information to predict the occurrence of laminate failures before the layer stack is cured to form the laminate.

6. The non-conforming item management system according to any one of claims 1 to 3, in, The analyzer uses nonconformance information associated with the laminate nonconformance to identify a set of parts that can be formed from the laminate.

7. The non-conforming item management system according to any one of claims 1 to 3, in, The nonconformance information describing the laminate nonconformance also includes at least one of the following: an area containing the laminate nonconformance, a nonconformance type, a laminate part number, or a laminate component part.

8. The non-conforming item management system according to claim 1, wherein the non-conforming item management system further comprises: include: An identifier is associated with the workpiece, wherein the identifier identifies a laminate formed from the workpiece.

9. The non-conforming item management system according to claim 8, in, The identifier is selected from one of: a barcode, a radio frequency identifier, text, a visual code, and a machine-readable identifier.

10. The non-conforming item management system according to any one of claims 1 to 3, in, The workpiece platform is the inspection platform.

11. The non-conforming item management system according to any one of claims 1 to 3, in, The layer stack comprises a first outer layer, a core layer and a second outer layer, wherein the core layer is located between the first outer layer and the second outer layer, wherein the first outer layer is selected from one of a thermoplastic layer and a polyvinyl fluoride layer; the second outer layer is selected from one of a thermoplastic layer and a polyvinyl fluoride layer; and wherein the core layer is selected from one of a resin layer, a carbon layer and a honeycomb layer, and Wherein, the layer stack further includes at least one of a release sheet, a textured blanket or a coating.

12. A method for treating a laminate having a laminate nonconformity, the method comprising the steps of: receiving inspection information of the laminate; using the inspection information to identify the laminate nonconformity in the laminate; generating nonconformity information related to the laminate nonconformity, wherein: the nonconformance information describing the laminate nonconformance includes a location of the laminate nonconformance and a laminate status, and wherein the laminate status determines whether the laminate nonconformance in the laminate affects a set of parts that can be formed from the laminate; displaying nonconformity information related to the laminate nonconformity on the laminate using a display system for augmented reality display; displaying an area at said location of said laminate nonconformity; and A pattern of laminate cuts for the set of parts is displayed onto the laminate using a display system for an augmented reality display, wherein the pattern regarding areas encompassing laminate nonconformities is configured to be viewed by a human operator as part of the augmented reality display.

13. The method according to claim 12, further comprising the steps of: A set of parts and part types that can be formed from the laminate are identified using the identifier and nonconformance information associated with the laminate nonconformance.

14. The method according to claim 12, further comprising the steps of: Based on a set of patterns for a set of parts, a condition of the laminate is determined.

Images