Preface:machine-learning approaches for computational mechanics
Machine-learning(ML)approaches have gained significant attention in recent years for their potential to revolutionize various scientific research fields,including computational mechanics,materials science,and biomedical engineering.In the field of computational mechanics,various neuralnetwork models such as feedforward neural networks,convolutional neural networks,recurrent neural networks,and graph neural networks have been implemented for solid me-chanics to predict structural responses and perform damage detection.Additionally,Gaussian process(GP)regression and deep neural operator have been used to develop surrogate models of complex fluid systems to approximate expensive simulation of physics-based models,which can greatly accelerate many computational intensive tasks in traditional computational fluid dynamics.Moreover,reinforcement learning techniques and deep generative modeling have been developed to simulate the transient behavior of complex materials,including composites and foams,under different loading conditions.
mechanics、learning、approaches、computational、machine、preface
44
O4-09;TF58;R338.1
2023-08-17(万方平台首次上网日期,不代表论文的发表时间)
共4页
1035-1038