Physics-Guided, Physics-Informed, and Physics-Encoded Neural Networks and Operators in Scientific Computing: Fluid and Solid Mechanics

人工神经网络 人工智能 深度学习 计算机科学 物理
作者
Salah A. Faroughi,Nikhil M. Pawar,Célio Fernandes,Maziar Raissi,Subasish Das,Nima K. Kalantari,Seyed Kourosh Mahjour
出处
期刊:Journal of Computing and Information Science in Engineering [ASME International]
卷期号:: 1-45 被引量:15
标识
DOI:10.1115/1.4064449
摘要

Abstract Advancements in computing power have recently made it possible to utilize machine learning and deep learning to push scientific computing forward in a range of disciplines, such as fluid mechanics, solid mechanics, materials science, etc. The incorporation of neural networks is particularly crucial in this hybridization process. Due to their intrinsic architecture, conventional neural networks cannot be successfully trained and scoped when data is sparse, which is the case in many scientific and engineering domains. Nonetheless, neural networks provide a solid foundation to respect physics-driven or knowledge-based constraints during training. Generally speaking, there are three distinct neural network frameworks to enforce the underlying physics: (i) physics-guided neural networks (PgNNs), (ii) physics-informed neural networks (PiNNs), and (iii) physics-encoded neural networks (PeNNs). These methods provide distinct advantages for accelerating the numerical modeling of complex multiscale multi-physics phenomena. In addition, the recent developments in neural operators (NOs) add another dimension to these new simulation paradigms, especially when the real-time prediction of complex multi-physics systems is required. All these models also come with their own unique drawbacks and limitations that call for further fundamental research. This study aims to present a review of the four neural network frameworks (i.e., PgNNs, PiNNs, PeNNs, and NOs) used in scientific computing research. The state-of-the-art architectures and their applications are reviewed, limitations are discussed, and future research opportunities are presented in terms of improving algorithms, considering causalities, expanding applications, and coupling scientific and deep learning solvers.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
廉乐儿发布了新的文献求助10
1秒前
2秒前
天天快乐应助BEST采纳,获得10
2秒前
2秒前
wny完成签到,获得积分10
2秒前
baby的跑男完成签到,获得积分10
3秒前
boom完成签到,获得积分20
4秒前
4秒前
5秒前
5秒前
lesyeuxdexx完成签到 ,获得积分10
5秒前
郑郑郑幸运完成签到 ,获得积分10
5秒前
5秒前
学不动完成签到 ,获得积分10
6秒前
6秒前
千CCCC完成签到,获得积分20
6秒前
诚心梦之完成签到,获得积分10
7秒前
7秒前
7秒前
7秒前
666发布了新的文献求助10
7秒前
隐形曼青应助叶落知秋采纳,获得10
7秒前
天天快乐应助羊羊羊采纳,获得10
7秒前
李小羊发布了新的文献求助50
8秒前
科研通AI2S应助威武的笑卉采纳,获得10
8秒前
FashionBoy应助俭朴的一曲采纳,获得10
8秒前
9秒前
大民王发布了新的文献求助10
9秒前
9秒前
大方的云朵完成签到,获得积分10
9秒前
10秒前
SciGPT应助不想工作的小辉采纳,获得10
10秒前
科研通AI2S应助黄花采纳,获得10
10秒前
小二郎应助懦弱的傲霜采纳,获得10
11秒前
无语的凡梦完成签到,获得积分10
12秒前
小马甲应助loong采纳,获得30
12秒前
ALIN发布了新的文献求助10
12秒前
谦让高山完成签到,获得积分10
12秒前
12秒前
搞怪满天完成签到,获得积分10
12秒前
高分求助中
좌파는 어떻게 좌파가 됐나:한국 급진노동운동의 형성과 궤적 2500
Sustainability in Tides Chemistry 1500
TM 5-855-1(Fundamentals of protective design for conventional weapons) 1000
Cognitive linguistics critical concepts in linguistics 800
Threaded Harmony: A Sustainable Approach to Fashion 799
Livre et militantisme : La Cité éditeur 1958-1967 500
氟盐冷却高温堆非能动余热排出性能及安全分析研究 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3053115
求助须知:如何正确求助?哪些是违规求助? 2710358
关于积分的说明 7421333
捐赠科研通 2354967
什么是DOI,文献DOI怎么找? 1246568
科研通“疑难数据库(出版商)”最低求助积分说明 606146
版权声明 595975