An improved bidirectional generative adversarial network model for multivariate estimation of correlated and imbalanced tunnel construction parameters
作者机构：State Key Laboratory of Hydraulic Engineering Simulation and SafetyTianjin UniversityTianjin300072China Hanjiang to Weihe River Valley Water Diversion Project Construction Co.Ltd.Xi’an710024China
出 版 物：《Journal of Rock Mechanics and Geotechnical Engineering》 (岩石力学与岩土工程学报（英文版）)
年 卷 期：2023年第15卷第7期
页 面：1797-1809页
核心收录：
学科分类：070801[理学-固体地球物理学] 07[理学] 0708[理学-地球物理学]
基 金：supported by National Natural Science Foundation of China(Grant Nos.52279137 52009090)
主 题：Multivariate parameters estimation Correlated and imbalanced parameters Bidirectional generative adversarial network(BiGAN) Joint discriminator Zero-centered gradient penalty(0-GP)
摘 要：Estimation of construction parameters is crucial for optimizing tunnel construction *** to the influence of routine activities and occasional risk events,these parameters are usually correlated and *** solve this issue,an improved bidirectional generative adversarial network(BiGAN)model with a joint discriminator structure and zero-centered gradient penalty(0-GP)is *** this model,in order to improve the capability of original BiGAN in learning imbalanced parameters,the joint discriminator separately discriminates the routine activities and risk event durations to balance their influence ***,the self-attention mechanism is embedded so that the discriminator can pay more attention to the imbalanced ***,the 0-GP is adapted for the loss of the discrimi-nator to improve its convergence and stability.A case study of a tunnel in China shows that the improved BiGAN can obtain parameter estimates consistent with the classical Gauss mixture model,without the need of tedious and complex correlation *** proposed joint discriminator can increase the ability of BiGAN in estimating imbalanced construction parameters,and the 0-GP can ensure the stability and convergence of the model.
维普期刊数据库