Impact Factor:

1.6

DOI number:

10.1080/0954898X.2024.2447281

Affiliation of Author(s):

College of Shipbuilding Engineering

Journal:

Network: Computation in Neural Systems

Place of Publication:

UK

Funded by:

National Key Research and Development Program of China (2019YFB1504403); Heilongjiang Excellent Yout

Key Words:

Gravity dam; reliability; deep learning network; Monte Carlo method(MC)

Abstract:

To improve the calculation accuracy of the Monte Carlo (MC) method and reduce the calculation time. Firstly, CNN and LSTM deep learning networks are introduced for designing nonlinear dynamic systems simulating dam stress. Then, spatial feature mining and sequence information extraction of nonlinear data of dam stress are carried out respectively, and a combined prediction model of dam stress depth (DS-FEM-CNN-LSTM) is proposed. Secondly, to solve the problem of a long time and heavy workload for the MC method to calculate a single sample point, the DOE test method is used to design the sample points. The weight factor and the distance to the failure surface are used as screening criteria. The reliability calculation method of the gravity dam (DS-FEM-CNN-LSTM-MC) is established. Finally, numerical results show that the proposed DSFEM- CNN-LSTM-MC method performs better than the existing methods in terms of computational time consumption and accuracy.

Note:

National Key Research and Development Program of China (2019YFB1504403); Heilongjiang Excellent Youth Fund Project (YQ2021E015); Key Program for International Scientific and Technological Innovation Cooperation between Governments (2019YFE0102500); National Natural Science Foundation of China (No.51509056)

Co-author:

Jun-Qi Ren,Jing Geng,Hsin-Pou Huang

First Author:

Ming-Wei Li

Indexed by:

Journal paper

Correspondence Author:

Wei-Chiang Hong

Discipline:

Engineering

Document Type:

J

Volume:

37

Issue:

2

Page Number:

389-418

ISSN No.:

0954-898X

Translation or Not:

no

Date of Publication:

2026

Included Journals:

SCI

Links to published journals:

https://www.tandfonline.com/doi/full/10.1080/0954898X.2024.2447281