Deep residual U-net with input of static structural responses for efficient U* load transfer path analysis

Zhao，Shengjie1; Wu，Nan1; Wang，Quan2,3

2020-10-01

10.1016/j.aei.2020.101184

ADVANCED ENGINEERING INFORMATICS   影响因子和分区

1474-0346

1873-5320

U* index theory is widely used to illustrate the load transfer paths inside an engineering structure. However, the conventional U* load transfer path analysis based on the finite element method is computationally demanding especially for large-scale structures. In this research, a convolutional neural network based on the architecture of residual U-Net is introduced to realize high-efficiency U* estimation of plate-type structures with arbitrary dimensions, boundary conditions, and loading conditions for the first time. Besides the geometrical information of the structures, the static structural responses including the feature maps of nodal displacement and stress are involved in the network input. Different input data combinations are experimented to study how they contribute to the model training. It is noticed that the stress and displacement data can significantly lower the output errors in U* prediction, and the geometrical information helps in noise reduction in U* contour graphs. The proposed method is tested with homogeneous plates and functionally graded plates respectively indicating its remarkable performance in load transfer path prediction. Moreover, this method shortens the U* calculation time by over 95% compared to the conventional finite element method. The improved efficiency of load transfer path analysis greatly facilitates the implementation of structural analysis, design, and optimization.

Convolutional neural network Deep learning Deep residual U-Net Finite element analysis Load transfer path analysis U* index theory

SCI ; EI

英语

其他

Computer Science ; Engineering

Computer Science, Artificial Intelligence ; Engineering, Multidisciplinary

WOS:000607575400037

ELSEVIER SCI LTD

20204209342752

Regression analysis ; Structural analysis ; Convolutional neural networks ; Deep neural networks ; Noise abatement ; Convolution ; Plates (structural components) ; Efficiency

Structural Design, General:408.1 ; Structural Members and Shapes:408.2 ; Ergonomics and Human Factors Engineering:461.4 ; Information Theory and Signal Processing:716.1 ; Acoustic Noise:751.4 ; Production Engineering:913.1 ; Numerical Methods:921.6 ; Mathematical Statistics:922.2

ENGINEERING

2-s2.0-85092283986

Scopus

1.Department of Mechanical Engineering,University of Manitoba,Winnipeg,R3T 5V6,Canada
2.Department of Mechanics and Aerospace Engineering,Southern University of Science and Technology,Shenzhen,518055,China
3.Department of Civil and Environmental Engineering,Shantou University,Shantou,515063,China

Zhao，Shengjie,Wu，Nan,Wang，Quan. Deep residual U-net with input of static structural responses for efficient U* load transfer path analysis[J]. ADVANCED ENGINEERING INFORMATICS,2020,46.

Zhao，Shengjie,Wu，Nan,&Wang，Quan.(2020).Deep residual U-net with input of static structural responses for efficient U* load transfer path analysis.ADVANCED ENGINEERING INFORMATICS,46.

Zhao，Shengjie,et al."Deep residual U-net with input of static structural responses for efficient U* load transfer path analysis".ADVANCED ENGINEERING INFORMATICS 46(2020).