The Boeing Company

Troy Winfree

Adriana Willempje Blom-Schieber

Sayata Ghose

Jeffrey David Poskin

Dustin D Fast

Brice Aaron Johnson

Alexander Rubin

Tyler M Holmes

Paul Zack Thunemann

Steven Michael Shewchuk

Samuel J Tucker

Brian P Justusson

Michael Drumheller

Andrew Lawrence Bauer

Rainer Johannes Romatka

Craig S Bosma

Philip L Stubblefield

Brittan A Farmer

Bryan W Lilley

Carla E Reynolds

Brandon Poe

Yadan Wu

Jordan A Severson

Kristin L Shaffer

A method of generating synthetic data for composite manufacturing inspection comprising creating a three-dimensional model of a composite layup; generating an inconsistency in the three-dimensional model of the composite layup; setting a camera position and a camera orientation in the three-dimensional model space; generating a captured image of the three-dimensional model and the inconsistency from the camera position and the camera orientation; and creating a secondary image from the captured image, the secondary image having colorations of a preselected inspection type.

Creating synthetic data for composite inspection

A method of manufacturing a composite structure includes accessing design data for the composite structure that is manufactured according to a process including forming a layup of plies of fibers using a machine tool. The method includes applying the design data to an ANN classifier to classify a localized inconsistency of a type of inconsistency on the composite structure, the localized inconsistency spatially referenced to a location on the composite structure. The method includes performing a root cause analysis to identify one or more of process parameters as a potential cause of the type of inconsistency, and modifying one or more of the geometric model, the layup design, or values of the one or more of the process parameters to address the potential cause.

Composite manufacturing using data analytics

A modeling system is provided which is configured to retrieve from the non-volatile memory the 3D virtual model of an object; define a domain of a parametric surface; project feature curves in the 3D virtual model into the domain of the parametric surface to generate a mapping based on the 3D virtual model and including a plurality of parametric curves; divide the plurality of parametric curves into horizontal and vertical feature curves; extend each of the horizontal feature and vertical feature curves; construct a horizontal interpolant connecting the extended horizontal feature curves; construct a vertical interpolant connecting the extended vertical feature curves; fit the horizontal and vertical interpolants as coordinates of a map to a new parametric domain; and compose the inverse of the map to the new parametric domain with the parametric surface to create a new parametric surface containing the feature curves as isoparametric curves.

Modeling system for 3D virtual model

A layup strategy analysis tool including a memory storing layup strategy analysis instructions and one or more processors configured to execute the layup strategy analysis instructions. During execution, the layup strategy analysis instructions obtain model data representing a three-dimensional (3D) model of an object to be formed using an automated fiber placement process. The layup strategy analysis instructions also obtain process data descriptive of the automated fiber placement process and one or more automated fiber placement machines. The layup strategy analysis instructions also generate output indicating a count of a number of tows that can be simultaneously applied during a single pass based on a geometry of the object and based on manufacturability constraints indicated by the process data.

Layup strategy analysis

A method of detecting defects in a composite layup includes capturing, using an infrared camera, reference images of a reference layup being laid up by a reference layup head. The method also includes manually reviewing the reference images for defects, and generating reference defect masks indicating defects in the reference images. The method further includes training, using the reference images and reference defect masks, a neural network, creating a machine learning model that, given a production image as input, outputs a production defect mask indicating the defect location and the defect type of each defect. The method also includes capturing, using an infrared camera, production images of a production layup being laid up by the production layup head, and applying the model to the production images to automatically generate a production defect masks indicating each defect in the production images.

Method of in-process detection and mapping of defects in a composite layup

A computer-based method for evaluating progressive damage in a metal test component includes providing Computed Tomography (CT) image data of the component to a processor and processing the CT image data via the processor, including detecting observable defects in the component. The method also includes characterizing the observable defects into corresponding defect categories, generating a data table of the observable defects and the corresponding defect categories, and embedding a collective set of data from the data table into a finite element model (FEM) of the component to thereby construct a modified FEM of the metal test component. Additionally, the method includes analyzing the modified FEM through an isotropic and/or anisotropic structural model, via the processor, to thereby generate a set of test results. A quality control action is then executed with respect to the metal test component based on the test results.

Progressive damage and failure analysis of metal parts using computed tomography

A method of planning fiber paths for a composite ply of a composite layup includes determining a first unit vector field. The first unit vector field represents a first approximation of target directions to be followed by tow centerlines of the composite ply. The first unit vector field is determined based on a specified rosette direction, a surface approximation of a nonplanar contoured surface of an object to be formed, and a fiber angle distribution. The method also includes determining, based on specified angle deviation bounds and the first unit vector field, a second unit vector field. The second unit vector field represents a second approximation of the target directions. The second approximation has reduced in-plane curvature relative to the first approximation. The method further includes planning a fiber placement head path for forming the composite ply of the composite layup based on the second unit vector field.

Fiber path planning to reduce in-plane curvature

A method of determining fibers paths for a composite ply includes generating a triangulated surface of the composite ply, and defining a first unit vector field establishing a 0-degree direction for the triangulated surface. A second unit vector field is defined by rotating, through specified fiber angles measured relative to the 0-degree direction, the first unit vector field about surface normals of the triangulated surface. A third unit vector field representing a gradient direction of a potential function is defined by rotating the second unit vector field over 90&#xb0; about the respective surface normals. The third unit vector field is scaled to create a non-unit vector field, and a first potential function is determined by performing a least-squares fit such that the direction and magnitude of the gradient best approximate the direction and the magnitude of the non-unit vector field. A normalization of the potential function uniformly distributes contour lines of the potential function across the triangulated surface. The contour lines are used as fiber paths for laying up courses of composite material to fabricate the composite ply.

System and method for determining the direction and spacing of fiber paths for a composite ply

A method of determining tow path surfaces associated with manufacturing a composite ply includes computing, from an initial tow path surface, a projected tow path surface corresponding to a projection of the initial tow path surface onto a layup surface. The method also includes determining, for particular start and end points, edge lengths of opposing sides of the projected tow path surface. The method further includes comparing a difference between the edge lengths of the opposing sides to a threshold, to determine if the amount of curvature along the projected tow path surface is acceptable.

Growing community of inventors

Seattle, WA, United States of America

Troy Winfree