Review of empowering computer-aided engineering with artificial intelligence

被引：2
作者：
Zhao, Xu-Wen [1 ]
Tong, Xiao-Meng [1 ]
Ning, Fang-Wei [1 ]
Cai, Mao-Lin [1 ]
Han, Fei [2 ]
Li, Hong-Guang [3 ]
机构：
[1] Beihang Univ, Sch Automat Sci & Elect Engn, Beijing 100191, Peoples R China
[2] Dalian Univ Technol, State Key Lab Struct Anal Ind Equipment, Dalian 116024, Liaoning, Peoples R China
[3] Shanghai Jiao Tong Univ, Sch Mech Engn, Shanghai 200240, Peoples R China
来源：
ADVANCES IN MANUFACTURING | 2025年
基金：
中国国家自然科学基金;
关键词：
Artificial intelligence (AI); Computer-aided engineering (CAE); Deep learning (DL); Computational mechanics; FINITE-ELEMENT-ANALYSIS; NEURAL-NETWORKS; MESH GENERATION; CFD DATA; FLUID-DYNAMICS; PREDICTION; DESIGN; MODELS; IDENTIFICATION; OPTIMIZATION;
D O I：
10.1007/s40436-025-00545-0
中图分类号：
T [工业技术];
学科分类号：
08 ;
摘要：
Computer-aided engineering (CAE) is widely used in the industry as an approximate numerical analysis method for solving complex engineering and product structural mechanical performance problems. However, with the increasing complexity of structural and performance requirements, the traditional research paradigm based on experimental observations, theoretical modeling, and numerical simulations faces new scientific problems and technical challenges in analysis, design, and manufacturing. Notably, the development of CAE applications in future engineering is constrained to some extent by insufficient experimental observations, lack of theoretical modeling, limited numerical analysis, and difficulties in result validation. By replacing traditional mathematical mechanics models with data-driven models, artificial intelligence (AI) methods directly use high-dimensional, high-throughput data to establish complex relationships between variables and capture laws that are difficult to discover using traditional mechanics research methods, offering significant advantages in the analysis, prediction, and optimization of complex systems. Empowering CAE with AI to find new solutions to the difficulties encountered by traditional research methods has become a developing trend in numerical simulation research. This study reviews the methods and applications of combining AI with CAE and discusses current research deficiencies as well as future research trends.
引用
收藏
页数：41
相关论文
共 200 条
[61]   Neural Networks-Based Aerodynamic Data Modeling: A Comprehensive Review [J].
Hu, Liwei ;
Zhang, Jun ;
Xiang, Yu ;
Wang, Wenyong .
IEEE ACCESS, 2020, 8 :90805-90823
[62]   Reconstruction of mesostructural material twin models of engineering textiles based on Micro-CT Aided Geometric Modeling [J].
Huang, W. ;
Causse, P. ;
Brailovski, V. ;
Hu, H. ;
Trochu, F. .
COMPOSITES PART A-APPLIED SCIENCE AND MANUFACTURING, 2019, 124
[63]   The Research on Deep Learning-Driven Dimensionality Reduction and Strain Prediction Techniques Based on Flight Parameter Data [J].
Huang, Wenbo ;
Wang, Rui ;
Zhang, Mengchuang ;
Yin, Zhiping .
APPLIED SCIENCES-BASEL, 2024, 14 (09)
[64]   On fast simulation of dynamical system with neural vector enhanced numerical solver [J].
Huang, Zhongzhan ;
Liang, Senwei ;
Zhang, Hong ;
Yang, Haizhao ;
Lin, Liang .
SCIENTIFIC REPORTS, 2023, 13 (01)
[65]   A convolutional neural network based crystal plasticity finite element framework to predict localised deformation in metals [J].
Ibragimova, Olga ;
Brahme, Abhijit ;
Muhammad, Waqas ;
Connolly, Daniel ;
Levesque, Julie ;
Inal, Kaan .
INTERNATIONAL JOURNAL OF PLASTICITY, 2022, 157
[66]   Surrogate modeling of elasto-plastic problems via long short-term memory neural networks and proper orthogonal decomposition [J].
Im, Sunyoung ;
Lee, Jonggeon ;
Cho, Maenghyo .
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2021, 385
[67]   Physics-informed neural networks for inverse problems in supersonic flows [J].
Jagtap, Ameya D. ;
Mao, Zhiping ;
Adams, Nikolaus ;
Karniadakis, George Em .
JOURNAL OF COMPUTATIONAL PHYSICS, 2022, 466
[68]   Extended Physics-Informed Neural Networks (XPINNs): A Generalized Space-Time Domain Decomposition Based Deep Learning Framework for Nonlinear Partial Differential Equations [J].
Jagtap, Ameya D. ;
Karniadakis, George Em .
COMMUNICATIONS IN COMPUTATIONAL PHYSICS, 2020, 28 (05) :2002-2041
[69]   Conservative physics-informed neural networks on discrete domains for conservation laws: Applications to forward and inverse problems [J].
Jagtap, Ameya D. ;
Kharazmi, Ehsan ;
Karniadakis, George Em .
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2020, 365
[70]   Plastic Deformation Behavior of Metal Materials: A Review of Constitutive Models [J].
Jia, Xiangdong ;
Hao, Kunming ;
Luo, Zhan ;
Fan, Zhenyu .
METALS, 2022, 12 (12)
234567891011