人工神经网络
位移场
趋同(经济学)
一致性(知识库)
计算机科学
断裂力学
脆性
流离失所(心理学)
一般化
能量最小化
断裂(地质)
代表(政治)
领域(数学)
算法
应用数学
机器学习
人工智能
有限元法
结构工程
数学分析
数学
材料科学
物理
工程类
心理治疗师
复合材料
心理学
量子力学
法学
经济增长
政治学
政治
经济
纯数学
作者
Bin Zheng,Tongchun Li,Huijun Qi,Lingang Gao,Xiaoqing Liu,Li Na Yuan
标识
DOI:10.1016/j.ijmecsci.2022.107282
摘要
Only a few studies have focused on the simulation of the crack propagation of quasi-brittle materials under complex loading inspired by physical-informed neural networks (PINN). Guided by the energy minimization principle rather than labelled data, we reconstruct the solution of displacement field after damage to predict crack propagation using PINN which maintains the thermodynamics consistency inherited from our proposed variable four-parameter damage model. Additionally, the framework of incremental pattern performs relatively efficiently with transfer learning. Consequently, a novel method for better convergence based on domain decomposition theory is proposed to identify complex boundaries. Based on gradient pathology, we develop a finite basis algorithm to solve the ill-condition problem. Whether under uniaxial tension, pure shear or mixed mode loading, the prediction results of displacement field fit well with simulations in the literature. Our research is meaningful for improving the generalization of neural networks and accelerating the optimization process which are necessary for further engineering applications.
科研通智能强力驱动
Strongly Powered by AbleSci AI