Integrating Geometric Data into Topology Optimization via Neural Style Transfer

Abstract

This research proposes a novel topology optimization method using neural style transfer to simultaneously optimize both structural performance for a given loading condition and geometric similarity for a reference design. For the neural style transfer, the convolutional layers of a pre-trained neural network extract and quantify characteristic features from the reference and input designs for optimization. The optimization analysis is evaluated as a single weighted objective function with the ability for the user to control the influence of the neural style transfer with the structural performance. As seen in architecture and consumer-facing products, the visual appeal of a design contributes to its overall value along with mechanical performance metrics. Using this method, a designer allows the tool to find the ideal compromise of these metrics. Three case studies are included to demonstrate the capabilities of this method with various loading conditions and reference designs. The structural performances of the novel designs are within 10% of the baseline without geometric reference, and the designs incorporate features in the given reference such as member size or meshed features. The performance of the proposed optimizer is compared against other optimizers without the geometric similarity constraint.

Deep learning in computational mechanics: a review

“…Within generative design, the generator can also be considered as a reparametrization of the design space that reduces the number of design variables. With autoencoders, the latent vector serves as the design parameter [553,554], which is then optimized 25 . Similarly, [556] find that point cloud autoencoders [117,557,558] are advantageous as geometric dimensionality reduction tools (potentially combined with performance features) for efficiently exploring the design space.…”

Optimization Design of Bridge Inspection Vehicle Boom Structure Based on Improved Genetic Algorithm

“…This method also pre-trains the convolutional layers of the neural network and extracts quantitative features from the reference and input data to perform structural optimization. Test results show that the use of this method to optimize the design of mechanical components resulted in the production of components with a 16.7% reduction in dead weight with only a 2.82% increase in maximum stress [26].…”

Special Issue: The Science and Technology of 3D Printing

“…This Special Issue contains eleven articles, including three reviews [ 3 , 4 , 5 ], one perspective article [ 6 ], and seven research articles [ 7 , 8 , 9 , 10 , 11 , 12 , 13 ] from leading institutes in the United States, China, Australia, Germany, Sweden, the Netherlands, Slovakia, the Czech Republic, Egypt, and United Arab Emirates. These articles cover the 3D printing of diverse materials such as metallic materials [ 5 , 7 , 8 , 9 , 10 , 11 , 12 , 13 ], composites [ 4 , 6 ], and soft materials [ 3 ].…”

“…The articles in this Special Issue cover a wide variety of experimental [ 8 , 9 , 10 , 11 , 13 ], theoretical [ 12 ], and data-science [ 7 ]-based research on the science and technology of 3D printing. For example, experimental investigations were performed to identify the most important factors that affect the microstructure and properties of Ti-6Al-4V parts printed using powder bed fusion [ 9 , 11 ].…”