Digital Core Modeling Based on Pretrained Generative Adversarial Neural Networks

Abstract

Accurately establishing a 3D digital core model is of great significance in oil and gas production. The physical experiment method and numerical modeling method are common modeling methods. With the development of deep learning technology, a variety of deep learning algorithms have been applied to digital core modeling. The digital core modeling method based on generative adversarial neural networks (GANs) has attracted wide attention due to its good quality and simple generation process. The disadvantage of this method is that the network needs thousands of trainings to achieve acceptable results. For this reason, this paper proposes to use the pretrained GANs for digital core modeling training, which can greatly reduce the number of network training while ensuring the core modeling effect. We can use the presented method to quickly complete the training and use the trained generator model to obtain multiple digital cores. By analyzing the quality of the generated cores from multiple aspects, it is revealed that the properties of the generated cores are in good agreement with the ones of the real core samples. The results indicate the reliability of the pretrained GAN method.

Automatic visual inspection of mechanical assemblies via 3Dpoint cloud classification with deep neural networks

“…In 3D UDA there are two major approaches: (1) the extension of the adversarial structures of Domain Adaptation from 2D to 3D, (2) Self-Supervised Learning (SSL) on 3D points to facilitate the learning of domain invariant features. Unlike previous work in a 2D environment, adversarial methods in a 3D environment have demonstrated flaws between a local geometric alignment and a global semantic alignment, by causing geometric distortions of clouds by trying to align domains [12]. This eliminates this approach.…”

PreRoutGNN for Timing Prediction with Order Preserving Partition: Global Circuit Pre-training, Local Delay Learning and Attentional Cell Modeling

“…Machine learning has been widely applied in EDA design flow, such as logic synthesis (Yuan et al 2023), placement (Mirhoseini et al 2021;Cheng and Yan 2021;Cheng et al 2022) and routing (Du et al 2023). However, accurate timing information can be accessed only after routing stage, which is time-consuming.…”