Stress Analysis of Segmental Tunnel Lining Using Artificial Neural Network

Rastbood, A.; Gholipour, Yaghob; Majdi, Abbas

doi:10.3311/ppci.9700

Cited by 9 publications

(8 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rastbood et al applied MLP to predict yield stresses and displacement of segmental tunnel lining rings based on the results obtained from the numerical method [12]. It is concluded that among all input variables, height is the most effective parameters on outputs parameters.…”

Section: G Other Applicationsmentioning

confidence: 99%

“…Mahdevari et al estimated the unknown nonlinear relationship between the rock parameters and tunnel convergence by using the data from the Ghomroud water conveyance tunnel in Iran [11]. Rastbood et al developed an ANN to predict the stresses executed on segmental tunnel lining [12]. Wu et al applied ANN to verify the proposed tunnel ventilation system with variable jet speed [13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of Artificial Neural Network in Tunnel Engineering: A Systematic Review

Wang

Wei

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Due to the lack of living space and the increase in population, there has been a construction boom in the underground space to improve the quality of human life. Tunnel engineering plays a vital role in the development of underground space. In addition to traditional methods, some intelligent methods such as artificial neural networks (ANNs) have been applied to various problems in the tunnel domain in recent years. This paper systematically reviews the application of ANNs from different aspects of tunnel engineering. It reveals that the backpropagation algorithm (BPA) and Levenberg-Marquardt algorithm (LMA) are the most widely used. Due to the limitations of some original models, some scholars use optimization algorithms such as particle swarm optimization (PSO) and genetic algorithm (GA) to optimize the original ANNs to obtain better prediction results. A comparison between the ANN-based methods and methods like statistical methods is conducted. Finally, the following conclusions can be drawn: (1) The recommended ratio of the training set and test set is 3:1; (2) The advantage of optimized ANNs is not apparent when the optimization algorithm varies. Additionally, the performance of ANNs is always better than that of statistical methods.

show abstract

Section: G Other Applicationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Application of Artificial Neural Network in Tunnel Engineering: A Systematic Review

Wang

Wei

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…to identify the in uence of each input variable on the output parameters [39]. By analyzing the time history of the software Plaxis 2D, it was determined that the acceleration history of the key points of the model was dependent on the soil mechanical parameters such as friction angle (φ), cohesion (C), dilation angle (ψ), soil unit weight (c), and Poisson's ratio (υ).…”

Section: Sensitivity Analysis Sensitivity Analysis Was Performedmentioning

confidence: 99%

Seismic Acceleration Spectrum of Ground Surface under Urban Subway Tunnels with Circular Cross Sections in Soil Deposits Based on SSI

Fakhriyeh

Vahdani

Gerami

2019

Shock and Vibration

View full text Add to dashboard Cite

Underground tunnels with circular cross section nowadays have great application in the field of transportation. One of their most prominent uses is the subway, built with the help of tunnel boring machines (TBMs). The design of ground-surface structures in the far field is related to the horizontal component of the peak ground of acceleration. Therefore, in this study, we tried to change the frequency of the soil-tunnel system by changing the overburden depth, diameter, and lining thickness of the tunnel, as well as changes in the soil specification, and calculate the maximum acceleration of the ground’s surface in the presence of the tunnel. The relationship between the peak horizontal acceleration of the ground surface and the frequency of the soil-tunnel system will result in the production of a horizontal acceleration spectrum. The results show that the amplification of ground surface depends on the period of the soil-tunnel system, the characteristics of the model, and the status of the point studied at the ground surface relative to the tunnel. On the projection of the center of the tunnel on the surface of the ground, the presence of the tunnel, rarely, at a long period, is effective in amplifying the spectral acceleration. While moving away from the image of the center of the tunnel on the surface of the ground, the presence of the tunnel in many cases, in long periods, amplifies spectral acceleration. The presence of the tunnel amplifies the spectral acceleration on the ground surface above 11%, while the presence of a tunnel reduces the spectral acceleration on the ground surface by up to 15% (attenuation). Using Plaxis 2D and Ansys finite element software, the case study was conducted on a Delhi subway tunnel with horizontal components of acceleration records similar to the construction site.

show abstract

“…Neural network is not new in machine learning, but it has been widely used for various applications over the last two decades thanks to the tremendous improvement in computational technology and innovative data mining algorithms. More and more researchers have interest in applying neural network on civil engineering problem, such as tunneling settlement (Ocak and Seker, 2013), building damage (Moosazadeh et al, 2019), structural forces (Rastbooda et al, 2017). Analysis of pressure grouting has been carried out with neural network which give enlightening results (Zettler et al, 1997).…”

Section: Neural Networkmentioning

confidence: 99%

“…The solutions of governing equation for the aquifer are derived using diverse methods in which there are exact solutions and approximations. The exact solutions utilize complex variable method (Fang et al, 2015;Fattah et al, 2010;Kolymbas and Wagner, 2007) and mirror image method (Li et al, 2018b;Rastbooda et al, 2017), and approximation applies axisymmetric modelling method (Goodman et al, 1964;Hwang and Lu, 2007), as shown in Figure 3.2. In the complex variable method (CVM), the semi-infinite aquifer is mapped conformally to two circles with the same centre in polar coordinate.…”

Section: Solutions Derivation For Water Inflow In Aquifermentioning

confidence: 99%

Analysis of grouting design based on water control for rock tunnels

Liu¹

View full text Add to dashboard Cite

I would like to thank my supervisor, Assoc. Prof Zhao Zhiye, for giving me a valuable chance to pursuit a Ph.D. at NTU. Without his constant support and guidance, I am unable to finish this work. Prof. Zhao is a role model who shows me correct attitudes and approaches in research. He is so patient that never blames me even when troubles are brought due to the slow progress. Instead, he would discuss openly and try hard to offer help. From time to time, I know clearly that my PhD career would be much more difficult without his support. I am too shy to say '' Thank you" to his face, but I want to give the most gratitude to him and give sincere wishes for his and his family's health and happiness.I would like to thank Dr. Xiao Fei, who spent a lot of efforts in guiding me. He not only taught me methods in perusing my target but also shows me what a good personality is like. He is a best friend and a valuable mentor in my research and life. I would like to give him best wishes for health and his pursuit to be a good scholar. I would like to thank Dr. Chen Huimei for her constant care and help of my work and life. I would like to thank Dr. Sun Jianping for his help and encouragement in my PhD Study. And I would like to thank all group members for giving me good advices whenever I need. Best wish to them! I would like to thank Prof. Cheng Niansheng for his trust and recommendation which give me such a luck to be Prof. Zhao's student. I would like to thank NTU for giving me this offer and relevant training which is highly above my expectation. I love NTU! I would like to thank my dear friend, Zhao Ya and Zhou Miaomiao, who always trust me, stand on my behalf whenever I need, and encourage me to overcome all the obstacles. I would like to thank my parents for finally understanding my decision on leaving them to pursue my PhD. I would like to thank Dr. Si Jinhua for his accompany during PhD career.Finally, I want to thank myself for suggesting me ''have one more trial'' whenever I want to give up.

show abstract

Stress Analysis of Segmental Tunnel Lining Using Artificial Neural Network

Abstract: The paper describes an artificial neural network method (ANNM)

Cited by 9 publications

References 37 publications

Application of Artificial Neural Network in Tunnel Engineering: A Systematic Review

Application of Artificial Neural Network in Tunnel Engineering: A Systematic Review

Seismic Acceleration Spectrum of Ground Surface under Urban Subway Tunnels with Circular Cross Sections in Soil Deposits Based on SSI

Analysis of grouting design based on water control for rock tunnels

Contact Info

Product

Resources

About