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

Abstract 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.

[1]  Fulei Chu,et al.  Free vibration analysis of rotating functionally graded CNT reinforced composite cylindrical shells with arbitrary boundary conditions , 2019, Composite Structures.

[2]  Chenchen Sun,et al.  High efficient load paths analysis with U* index generated by deep learning , 2019, Computer Methods in Applied Mechanics and Engineering.

[3]  Qingjie Liu,et al.  Road Extraction by Deep Residual U-Net , 2017, IEEE Geoscience and Remote Sensing Letters.

[4]  Daniel Rueckert,et al.  A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction , 2017, IEEE Transactions on Medical Imaging.

[5]  Genki Yagawa,et al.  Computational mechanics enhanced by deep learning , 2017 .

[6]  Oral Büyüköztürk,et al.  Deep Learning‐Based Crack Damage Detection Using Convolutional Neural Networks , 2017, Comput. Aided Civ. Infrastructure Eng..

[7]  Garth Pearce,et al.  On interpreting load paths and identifying a load bearing topology from finite element analysis , 2011 .

[8]  In Gwun Jang,et al.  Deep learning for determining a near-optimal topological design without any iteration , 2018, Structural and Multidisciplinary Optimization.

[9]  Hiroaki Hoshino,et al.  Vibration reduction in the cabins of heavy-duty trucks using the theory of load transfer paths , 2003 .

[10]  Toshiaki Sakurai,et al.  Reduction of Calculation Time for Load Path U * Analysis of Structures , 2007 .

[11]  Paul W. Fieguth,et al.  A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure , 2015, Adv. Eng. Informatics.

[12]  Satchi Venkataraman,et al.  Comparison of Quantitative and Qualitative Information Provided by Different Structural Load Path Definitions , 2009 .

[13]  Yi Gao,et al.  FEA-Net: A Physics-guided Data-driven Model for Efficient Mechanical Response Prediction , 2020, Computer Methods in Applied Mechanics and Engineering.

[14]  D. Kelly,et al.  Interpreting load paths and stress trajectories in elasticity , 2000 .

[15]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  F. Chu,et al.  A unified solution for vibration analysis of laminated functionally graded shallow shells reinforced by graphene with general boundary conditions , 2020 .

[17]  Fazhi He,et al.  A dividing-based many-objective evolutionary algorithm for large-scale feature selection , 2019, Soft Computing.

[18]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Qingguo Wang,et al.  Design assessment of a multiple passenger vehicle component using load transfer index ($$ {\text{U}}^{*} $$U∗) method , 2018 .

[20]  D. Kelly,et al.  A procedure for determining load paths in elastic continua , 1995 .

[21]  Christine Q. Wu,et al.  Experimental validation of the U* index theory for load transfer analysis , 2017 .

[22]  Tao Mei,et al.  Look Closer to See Better: Recurrent Attention Convolutional Neural Network for Fine-Grained Image Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  N. D. Duc,et al.  Nonlinear Dynamic Response of Functionally Graded Porous Plates on Elastic Foundation Subjected to Thermal and Mechanical Loads , 2018 .

[24]  Yunsong Li,et al.  Hyperspectral image reconstruction by deep convolutional neural network for classification , 2017, Pattern Recognit..

[25]  K. Almitani.  Buckling Behaviors of Symmetric and Antisymmetric Functionally Graded Beams , 2018 .

[26]  Kunihiro Takahashi,et al.  Load Transfer in Truck Cab Structures under Initial Phase of Frontal Collision , 2010 .

[27]  Heng Li,et al.  Onset detection of ultrasonic signals for the testing of concrete foundation piles by coupled continuous wavelet transform and machine learning algorithms , 2020, Adv. Eng. Informatics.

[28]  Shengdong Zhang,et al.  NLDN: Non-local dehazing network for dense haze removal , 2020, Neurocomputing.

[29]  A. S. Sayyad,et al.  A New Quasi-3D Model for Functionally Graded Plates , 2019 .

[30]  Martina Schnellenbach-Held,et al.  A machine learning approach for the support of preliminary structural design , 2005, Adv. Eng. Informatics.

[31]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[33]  邦弘 高橋.  「相対剛性」による構造物の表現とSaint Venantの原理 , 1986 .

[34]  Christine Q. Wu,et al.  Demonstration of the effectiveness of U*-based design criteria on vehicle structural design , 2018 .

[35]  Wei Sun,et al.  A deep learning approach to estimate stress distribution: a fast and accurate surrogate of finite-element analysis , 2018, Journal of The Royal Society Interface.

[36]  Yiteng Pan,et al.  Learning social representations with deep autoencoder for recommender system , 2020, World Wide Web.

[37]  Yi Zhou,et al.  An efficient GPU-based parallel tabu search algorithm for hardware/software co-design , 2020, Frontiers of Computer Science.

[38]  Jun Hong,et al.  Investigation into the topology optimization for conductive heat transfer based on deep learning approach , 2018, International Communications in Heat and Mass Transfer.

[39]  Chen Lu,et al.  Intelligent fault diagnosis of rolling bearing using hierarchical convolutional network based health state classification , 2017, Adv. Eng. Informatics.

[40]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[41]  Md Zahangir Alom,et al.  Recurrent residual U-Net for medical image segmentation , 2019, Journal of medical imaging.