A system and method for synthesis and optimization of smoothed surfaced three-dimensional (3D) objects uses a trainable generative adversarial network (GAN). A generator network of the GAN includes a deconvolutional neural network configured to receive a latent vector and to generate control points and weights. A Bézier layer in the generator uses the control points and weights to generate surface points of a simulated 3D surface according to a parametric Bézier curve. A GAN discriminator network includes a convolutional neural network configured to discriminate between generated surface points and surface points corresponding to training data stored in a database. The convolutional network also predicts latent vector statistics through convolution of parameters.

Methods of determining a final space reservation for a new aircraft are disclosed. The methods include using parametric definitions of potential payloads to generate a population of representative payloads for use in creating an initial space reservation. The methods include accounting for and applying a variety of margins on each potential payload and taking the union of potential payloads. Alternatively, the union can be taken first and then the margins applied. A homogenous space reservation can be determined based upon a variety of differently shaped or sized payloads, including a margin build-up to mitigate risk of unknowns associated with future changes in specific payload shapes and sizes, build tolerances, environmental conditions, and/or loading and unloading motions and clearances. Once this space reservation is known, it is possible to design an external shape of a carrying vehicle by staying outside of this space reservation.

Computational numerical analysis for passenger seating assemblies can be performed by generating a combined computer numerical simulation based on two or more partial numerical simulations of different assemblies and/or virtual passengers or anthropomorphic test dummies (ATDs). The partial numerical simulations may be run for a common, nonzero period of time, after which first simulation data from the first numerical simulation and second simulation data from the second numerical simulation can be captured and used for generating the combined numerical simulation. The combined numerical simulation can simulate a collision between the different assemblies and/or virtual ATDs by assembling the first and second partial simulation data such that the modeled assemblies collide in the combined computer numerical simulation. Any suitable number of combined numerical simulations in a variety of specific variations may be regenerated using the first and second partial simulation data.

A method for determining a shim profile for assembling a first mating surface of a first part with a second mating surface of a second part includes: obtaining a baseline surface model of the first mating surface; scanning the first mating surface when the first part is in a deviated configuration to generate a scan-based surface model of the first mating surface; deforming the scan-based surface model of the first mating surface relative to the baseline surface model of the first mating surface to generate a first deformed surface model of the first mating surface; deforming the first deformed surface model of the first mating surface relative to a surface model of the second mating surface to generate a second deformed surface model of the first mating surface; and comparing the second deformed surface model of the first mating surface to the surface model of the second mating surface.

Methods of determining a final space reservation for a new aircraft are disclosed. The methods include using parametric definitions of potential payloads to generate a population of representative payloads for use in creating an initial space reservation. The methods include accounting for and applying a variety of margins on each potential payload and taking the union of potential payloads. Alternatively, the union can be taken first and then the margins applied. A homogenous space reservation can be determined based upon a variety of differently shaped or sized payloads, including a margin build-up to mitigate risk of unknowns associated with future changes in specific payload shapes and sizes, build tolerances, environmental conditions, and/or loading and unloading motions and clearances. Once this space reservation is known, it is possible to design an external shape of a carrying vehicle by staying outside of this space reservation.

An apparatus for designing a structural product includes memory to store computer-readable program code for an integrated development environment to establish a digital thread in a lifecycle of the structural product, and processing circuitry to execute the computer-readable program code. The apparatus is thereby caused to generate a graphical user interface from which the integrated development environment is accessible to cause the apparatus to generate an electromagnetic effects (EME) model of the structural product from authoritative data including a solid model of the structural product, and parameterize the EME model with one or more electrical properties. The apparatus is caused to produce a computational electromagnetics (CEM) model of the structural product from the parameterized EME model, perform a CEM analysis from the CEM model to generate a corresponding solution is generated, and post-process the corresponding solution.

A composite laminate designing method includes: deriving, on a basis of allowable strains corresponding to fiber orientation angles in a composite laminate having the fiber orientation angles, an allowable load region that represents in three dimensions a combination of an allowable X-direction load in a predetermined x direction in a plane orthogonal to a lamination direction in which layers of the composite laminate are laminated, an allowable Y-direction load in a y direction orthogonal to the x direction in the plane orthogonal to the lamination direction, and an allowable shearing load in a shearing direction in the plane orthogonal to the lamination direction; and determining whether a working load acting on the composite laminate is included within the allowable load region.

A reduced performance monitoring system for a tiltrotor aircraft includes a physical component of the tiltrotor aircraft configured to displace over time in response to an input, a simulation component configured to generate a simulated displacement response of the physical component, and a comparison module configured to compare a measured physical displacement response of the physical component to the simulated displacement response of the physical component.

An apparatus for designing a structural product includes memory to store computer-readable program code for an integrated development environment to establish a digital thread in a lifecycle of the structural product, and processing circuitry to execute the computer-readable program code. The apparatus is thereby caused to generate a graphical user interface from which the integrated development environment is accessible to cause the apparatus to generate an electromagnetic effects (EME) model of the structural product from authoritative data including a solid model of the structural product, and parameterize the EME model with one or more electrical properties. The apparatus is caused to produce a computational electromagnetics (CEM) model of the structural product from the parameterized EME model, perform a CEM analysis from the CEM model to generate a corresponding solution is generated, and post-process the corresponding solution.

A system and method for estimating the shear wall stress of an aerodynamic surface using a tuft visualization technique combined with a physics-informed neural network. The tuft visualization technique is a simplified method of generating velocity profile data of an aerodynamic model that can subsequently be used to generate a shear wall stress profile of the model. Systems and methods described herein also provide for additional input data using an augmented tuft and taps inputs for the physics-informed neural network to generate the shear wall stress profile.