The feasibility of design is based on its form (i.e., its geometric properties), function (i.e., its intended purpose), and behavior (i.e., how well it achieves its intended purpose when interacting with an environment or entity). Since features are a more compressed description of the essential characteristics of design concepts, analyzing a design problem in the feature space can potentially extract key information which is implicitly contained in the original design space.ĭeep learning-based generative models such as generative adversarial networks (GANs) or recurrent neural networks can be trained to discover features of a design underneath its visual appearance however, in the context of concept generation for design, there is a significant amount of domain knowledge embedded in a designer’s visual interpretation of a design that extends beyond the design’s form. In addition to tuning and comparing different design concepts, the designer can tune and compare their corresponding features searching for better designs or for studying the underlying connections between designs. To a human designer, the feature space is an alternative perspective to analyze a design problem. Once a neural network is properly trained, it associates designs with a lower-dimensional representation, also known as the feature or latent variable space. For instance, in many popular generative models, the input variable of a particular layer is often used as a lower-dimensional representation of the original design. One major advantage of deep learning methods over other data-driven methods is the ability of the neural network models to learn the features of a design, with minimal input from the designer. Specifically, deep learning-based generative design tools and approaches provide designers with a scalable means of generating novel design concepts. The emergence of generative design methods is accelerating the pace at which designers can explore and refine their ideas. In the case study, a number of techniques are explored to structure the generate-evaluate process in order to balance the need to generate feasible designs with the need for innovative designs. Z-tests on the performance scores of the generated aircraft models indicate a statistically significant improvement in the functionality of the generated models after three iterations of the training-evaluation process.
A case study involving a GAN model that is initially trained on 4045 3D aircraft models is used for demonstration, where a training data set that has been updated with GAN-generated and evaluated designs results in enhanced model generation, in both the geometric feasibility and performance of the designs. Once initially trained, the GAN can create additional training data itself by generating new designs, evaluating them in a physics-based virtual environment, and adding the high performing ones to the training set.
#TAY K 3D MODEL HOW TO#
The authors present a generative adversarial network (GAN) model that demonstrates how to generate 3D models in their native format so that they can be either evaluated using complex simulation environments or realized using methods such as additive manufacturing. Journal of Verification, Validation and Uncertainty Quantification.Journal of Thermal Science and Engineering Applications.Journal of Offshore Mechanics and Arctic Engineering.Journal of Nuclear Engineering and Radiation Science.Journal of Nondestructive Evaluation, Diagnostics and Prognostics of Engineering Systems.Journal of Nanotechnology in Engineering and Medicine.Journal of Micro and Nano-Manufacturing.Journal of Manufacturing Science and Engineering.Journal of Engineering Materials and Technology.Journal of Engineering for Sustainable Buildings and Cities.Journal of Engineering for Gas Turbines and Power.Journal of Engineering and Science in Medical Diagnostics and Therapy.Journal of Electrochemical Energy Conversion and Storage.Journal of Dynamic Systems, Measurement, and Control.Journal of Computing and Information Science in Engineering.Journal of Computational and Nonlinear Dynamics.Journal of Autonomous Vehicles and Systems.ASME Letters in Dynamic Systems and Control.ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering.Mechanical Engineering Magazine Select Articles.
0 kommentar(er)
