A self-learning finite element extraction system based on reinforcement learning

2021 ◽  
pp. 1-29
Author(s):  
Jie Pan ◽  
Jingwei Huang ◽  
Yunli Wang ◽  
Gengdong Cheng ◽  
Yong Zeng
Keyword(s):  
Reinforcement Learning ◽  
Mesh Generation ◽  
Domain Knowledge ◽  
Domain Boundary ◽  
Automatic Generation ◽  
Extraction System ◽  
Generation Process ◽  
High Quality ◽  
Geometric Boundary ◽  
Self Learning

Abstract Automatic generation of high-quality meshes is a base of CAD/CAE systems. The element extraction is a major mesh generation method for its capabilities to generate high-quality meshes around the domain boundary and to control local mesh densities. However, its widespread applications have been inhibited by the difficulties in generating satisfactory meshes in the interior of a domain or even in generating a complete mesh. The element extraction method's primary challenge is to define element extraction rules for achieving high-quality meshes in both the boundary and the interior of a geometric domain with complex shapes. This paper presents a self-learning element extraction system, FreeMesh-S, that can automatically acquire robust and high-quality element extraction rules. Two central components enable the FreeMesh-S: (1) three primitive structures of element extraction rules, which are constructed according to boundary patterns of any geometric boundary shapes; (2) a novel self-learning schema, which is used to automatically define and refine the relationships between the parameters included in the element extraction rules, by combining an Advantage Actor-Critic (A2C) reinforcement learning network and a Feedforward Neural Network (FNN). The A2C network learns the mesh generation process through random mesh element extraction actions using element quality as a reward signal and produces high-quality elements over time. The FNN takes the mesh generated from the A2C as samples to train itself for the fast generation of high-quality elements. FreeMesh-S is demonstrated by its application to two-dimensional quad mesh generation. The meshing performance of FreeMesh-S is compared with three existing popular approaches on ten pre-defined domain boundaries. The experimental results show that even with much less domain knowledge required to develop the algorithm, FreeMesh-S outperforms those three approaches in essential indices. FreeMesh-S significantly reduces the time and expertise needed to create high-quality mesh generation algorithms.

scholarly journals SCFont: Structure-Guided Chinese Font Generation via Deep Stacked Networks

2019 ◽  
Vol 33 ◽  
pp. 4015-4022 ◽  
Author(s):  
Yue Jiang ◽  
Zhouhui Lian ◽  
Yingmin Tang ◽  
Jianguo Xiao
Keyword(s):  
Deep Learning ◽  
Domain Knowledge ◽  
State Of The Art ◽  
Automatic Generation ◽  
Chinese Characters ◽  
Generation System ◽  
Model Learning ◽  
High Quality ◽  
Large Numbers ◽  
Quantitative Assessments

Automatic generation of Chinese fonts that consist of large numbers of glyphs with complicated structures is now still a challenging and ongoing problem in areas of AI and Computer Graphics (CG). Traditional CG-based methods typically rely heavily on manual interventions, while recentlypopularized deep learning-based end-to-end approaches often obtain synthesis results with incorrect structures and/or serious artifacts. To address those problems, this paper proposes a structure-guided Chinese font generation system, SCFont, by using deep stacked networks. The key idea is to integrate the domain knowledge of Chinese characters with deep generative networks to ensure that high-quality glyphs with correct structures can be synthesized. More specifically, we first apply a CNN model to learn how to transfer the writing trajectories with separated strokes in the reference font style into those in the target style. Then, we train another CNN model learning how to recover shape details on the contour for synthesized writing trajectories. Experimental results validate the superiority of the proposed SCFont compared to the state of the art in both visual and quantitative assessments.

scholarly journals Automatic Generation of Children's Songs Based on Machine Statistic Learning

2018 ◽  
Vol 13 (03) ◽  
pp. 17
Author(s):  
Li Pan
Keyword(s):  
Machine Learning ◽  
Domain Knowledge ◽  
Language Model ◽  
Automatic Generation ◽  
Target Language ◽  
Generation Process ◽  
Statistical Machine Learning ◽  
Translation Model ◽  
Children's Songs ◽  
Relationship Of

In this paper, the automatic generation of children's songs is studied. First of all, according to the number of key lyrics submitted by the songwriter, statistical machine learning is used to expand and obtain more theme-related lyrics, and then the first sentence is generated through the language model automatically. On this basis, the subsequent sentences are generated through the statistical machine learning translation method. In the process of the generation, the statistical machine learning is used to expand the conception of the song, so as to get richer sentence candidates. The main features and contributions of the study are: Firstly, the statistical machine learning translation is put forward as the theoretical basis, the preceding and next sentence relationship of children's songs are mapped into the relation of the source language and target language in the statistical translation model, and the machine statistics learning translation model is designed with the integration of the domain knowledge of songs. Secondly, the statistical machine learning is used in the generation process to expand the lyrics words, thereby enhancing the theme and conception of the song. The experimental results have confirmed the effectiveness of the proposed method.

scholarly journals Automatic Generation of Photorealistic Image Fillers for Privacy Enabled Urban Basemaps using Generative Adversarial Networks

2019 ◽  
Vol 1 ◽  
pp. 1-8
Author(s):  
Amgad Agoub ◽  
Yevgeniya Filippovska ◽  
Valentina Schmidt ◽  
Martin Kada
Keyword(s):  
Image Data ◽  
Automatic Generation ◽  
Generative Models ◽  
Aerial Images ◽  
Generative Adversarial Networks ◽  
Sensitive Information ◽  
Generation Process ◽  
High Quality ◽  
Privacy And Security ◽  
Adversarial Networks

<p><strong>Abstract.</strong> The abundance of high-quality satellite images is salutary for many activities but raises also privacy and security concerns. Manually obfuscating areas subject to privacy issues by applying locally pixelization techniques leads to undesirable discontinuities in the visual appearance of the depicted scenes. Alternatively, automatically generated photorealistic fillers can be used to obfuscate sensitive information while preserving the original visual aspect of high-resolution aerial images.</p><p>Recent advances in the field of Deep Learning (DL) enable to synthesize high-quality image data. Particularly, generative models such as Generative Adversarial Networks (GANs) can be used to produce images that can be perceived as photorealistic even by human examiners. Additionally, Conditional Generative Adversarial Networks (cGANs) allow control over the image generation process and results. These developments give the opportunity to generate photorealistic fillers for the purpose of privacy and security in image data used within city models while preserving the quality of the original data. However, according to our knowledge, little research has been done to explore this potential. In order to close this gap, we propose a novel framework that is designed to correspond to the mentioned end goal and produces promising results.</p>

Deep reinforcement learning enabled self-learning control for energy efficient driving

2019 ◽  
Vol 99 ◽  
pp. 67-81 ◽  
Author(s):  
Xuewei Qi ◽  
Yadan Luo ◽  
Guoyuan Wu ◽  
Kanok Boriboonsomsin ◽  
Matthew Barth
Keyword(s):  
Reinforcement Learning ◽  
Energy Efficient ◽  
Learning Control ◽  
Self Learning

scholarly journals Cartesian Mesh Generation with Local Refinement for Immersed Boundary Approaches

2021 ◽  
Vol 9 (6) ◽  
pp. 572
Author(s):  
Luca Di Di Angelo ◽  
Francesco Duronio ◽  
Angelo De De Vita ◽  
Andrea Di Di Mascio
Keyword(s):  
Mesh Generation ◽  
Cfd Simulation ◽  
Automatic Generation ◽  
Uniform Grid ◽  
Immersed Boundary ◽  
Adaptive Grids ◽  
Local Refinement ◽  
User Interactions ◽  
Cartesian Mesh ◽  
Time Required

In this paper, an efficient and robust Cartesian Mesh Generation with Local Refinement for an Immersed Boundary Approach is proposed, whose key feature is the capability of high Reynolds number simulations by the use of wall function models, bypassing the need for accurate boundary layer discretization. Starting from the discrete manifold model of the object to be analyzed, the proposed model generates Cartesian adaptive grids for a CFD simulation, with minimal user interactions; the most innovative aspect of this approach is that the automatic generation is based on the segmentation of the surfaces enveloping the object to be analyzed. The aim of this paper is to show that this automatic workflow is robust and enables to get quantitative results on geometrically complex configurations such as marine vehicles. To this purpose, the proposed methodology has been applied to the simulation of the flow past a BB2 submarine, discretized by non-uniform grid density. The obtained results are comparable with those obtained by classical body-fitted approaches but with a significant reduction of the time required for the mesh generation.

scholarly journals Self-Learning Multi-Objective Service Coordination Using Deep Reinforcement Learning

2021 ◽  
pp. 1-1
Author(s):  
Stefan Schneider ◽  
Ramin Khalili ◽  
Adnan Manzoor ◽  
Haydar Qarawlus ◽  
Rafael Schellenberg ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Service Coordination ◽  
Multi Objective ◽  
Self Learning

Reinforcement Learning for Cloud Computing Digital Library

2014 ◽  
Vol 571-572 ◽  
pp. 105-108
Author(s):  
Lin Xu
Keyword(s):  
Artificial Intelligence ◽  
Cloud Computing ◽  
Reinforcement Learning ◽  
Digital Library ◽  
Learning Algorithms ◽  
Experimental Results ◽  
Current Status ◽  
Self Learning ◽  
New Framework

This paper proposes a new framework of combining reinforcement learning with cloud computing digital library. Unified self-learning algorithms, which includes reinforcement learning, artificial intelligence and etc, have led to many essential advances. Given the current status of highly-available models, analysts urgently desire the deployment of write-ahead logging. In this paper we examine how DNS can be applied to the investigation of superblocks, and introduce the reinforcement learning to improve the quality of current cloud computing digital library. The experimental results show that the method works more efficiency.

Sign in / Sign up

Export Citation Format

Share Document