Variational autoencoders for 3D data processing

In modern manufacturing systems, quality monitoring is crucial for efficient and cost-effective production. Conventional systems rely on thresholds and process windows, but machine learning (ML) techniques promise greater accuracy and efficiency. However, pre-processing the data is still timeconsuming. This paper presents an approach to visually verify two Variational Autoencoders (VAEs) using contextual information such as print job numbers and timestamps, with the aim of predicting time series data from image data to optimize additive manufacturing processes in time. The approach focuses on the Digital Light Processing (DLP) printing process and emphasizes the importance of accurate data pre-processing and contextual visualization. The approach utilizes VAE-generated latent spaces to improve prediction accuracy in additive manufacturing and implement quality monitoring without thresholds and process windows.

show abstract

Reconstruction of Random Structures Based on Generative Adversarial Networks: Statistical Variability of Mechanical and Morphological Properties

Tashkinov,

Pirogova,

Kononov

et al. 2024

Mathematics

View full text Add to dashboard Cite

Generative adversarial neural networks with a variational autoencoder (VAE-GANs) are actively used in the field of materials design. The synthesis of random structures with nonrepeated geometry and predetermined mechanical properties is important for solving various practical problems. Geometric parameters of such artificially generated random structures can vary within certain limits compared to the training dataset, causing unpredicted fluctuations in their resulting mechanical response. This study investigates the statistical variability of mechanical and morphological characteristics of random 3D models reconstructed from 2D images using a VAE-GAN neural network. A combined multitool method employing different mathematical and statistical instruments for comparison of the reconstructed models with their corresponding originals is proposed. It includes the analysis of statistical distributions of elastic properties, morphometric parameters, and stress values. The neural network was trained on two datasets, containing models created based on Gaussian random fields. Statistical fluctuations of the mechanical and morphological parameters of the reconstructed models are analyzed. The deviation of the effective elastic modulus of the reconstructed models from that of the original ones was less than 5.7% on average. The difference between the median values of ligament thickness and distance between ligaments ranged from 3.6 to 6.5% and 2.6 to 5.2%, respectively. The median value of the surface area of the reconstructed geometries was 4.6–8.1% higher compared to the original models. It is thus shown that mechanical properties of the NN-generated structures retain the statistical variability of the corresponding originals, while the variability of the morphology is highly affected by the training set and does not depend on the configuration of the input 2D image.

show abstract

Variational autoencoders for 3D data processing

Cited by 3 publications

References 176 publications

Traversability Map Estimation for Agricultural Robots

Traversability Map Estimation for Agricultural Robots

Maschinelles Lernen als modernes Werkzeug für Additive Fertigung

Reconstruction of Random Structures Based on Generative Adversarial Networks: Statistical Variability of Mechanical and Morphological Properties

Contact Info

Product

Resources

About