Hybrid deep learning model for prediction of monotonic and cyclic responses of sand

被引:14
作者
Guan, Q. Z. [1 ]
Yang, Z. X. [2 ]
机构
[1] Zhejiang Univ, Ctr Balance Architecture, Dept Civil Engn, 866 Yuhangtang,Zijingang Campus, Hangzhou 310058, Peoples R China
[2] Zhejiang Univ, Comp Ctr Geotech Engn COMEGE, Engn Res Ctr Urban Underground Space Dev Zhejiang, Dept Civil Engn, 866 Yuhangtang Rd, Hangzhou 310058, Peoples R China
关键词
Constitutive response; Dataset; Deep learning; Hybrid model; Sand; HYPOPLASTIC CONSTITUTIVE MODEL; FINITE-ELEMENT-METHOD; NEURAL-NETWORK; EXPERIMENTAL DATABASE; YIELD SURFACE; BEHAVIOR; TESTS; VERIFICATION; CALIBRATION; SANISAND;
D O I
10.1007/s11440-022-01656-9
中图分类号
P5 [地质学];
学科分类号
0709 ; 081803 ;
摘要
The monotonic and cyclic behaviors of sand are of practical significance for various problems in geotechnical engineering. In this paper, a novel hybrid deep learning model was proposed for the prediction of the responses of sand undergoing monotonic and cyclic loading conditions; two popular neural networks, the long short-term memory network (LSTM) and temporal convolutional network (TCN) were employed. A synthetic dataset generated by a constitutive model was initially used to analyze the appropriate arrangement of the LSTM and TCN layers and compare the predictive performance of the hybrid model with those of the LSTM and TCN alone models. An experimental dataset based on available laboratory tests on Karlsruhe fine sand was also used to further demonstrate the model's capacity. The predictive results showed the superiority of the proposed hybrid model and reproduction of the constitutive responses of sand with a higher accuracy under both monotonic and cyclic loading conditions.
引用
收藏
页码:1447 / 1461
页数:15
相关论文
共 64 条
[1]  
Abadi M, 2016, PROCEEDINGS OF OSDI'16: 12TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P265
[2]   Deep learning for plasticity and thermo-viscoplasticity [J].
Abueidda, Diab W. ;
Koric, Seid ;
Sobh, Nahil A. ;
Sehitoglu, Huseyin .
INTERNATIONAL JOURNAL OF PLASTICITY, 2021, 136
[3]   FITTING AUTOREGRESSIVE MODELS FOR PREDICTION [J].
AKAIKE, H .
ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS, 1969, 21 (02) :243-&
[4]  
[Anonymous], 1990, Readings Speech Recognit, DOI DOI 10.1016/B978-0-08-051584-7.50037-1
[5]  
Bahdanau D, 2016, Arxiv, DOI [arXiv:1409.0473, DOI 10.48550/ARXIV.1409.0473]
[6]  
Bai Shaojie, 2019, P INT C LEARNING REP
[7]   Artificial neural network for stress-strain behavior of sandy soils: Knowledge based verification [J].
Banimahd, A ;
Yasrobi, SS ;
Woodward, PK .
COMPUTERS AND GEOTECHNICS, 2005, 32 (05) :377-386
[8]   Field Tests on Pile-Supported Embankments over Soft Ground [J].
Chen, R. P. ;
Xu, Z. Z. ;
Chen, Y. M. ;
Ling, D. S. ;
Zhu, B. .
JOURNAL OF GEOTECHNICAL AND GEOENVIRONMENTAL ENGINEERING, 2010, 136 (06) :777-785
[9]   A bounding surface model for anisotropically overconsolidated clay incorporating thermodynamics admissible rotational hardening rule [J].
Chen, Yanni ;
Yang, Zhongxuan .
INTERNATIONAL JOURNAL FOR NUMERICAL AND ANALYTICAL METHODS IN GEOMECHANICS, 2020, 44 (05) :668-690
[10]  
Cho K., 2014, C EMP METH NAT LANG, DOI DOI 10.3115/V1/W14-4012