English  |  正體中文  |  简体中文  |  Items with full text/Total items : 27454/39300
Visitors : 2535010      Online Users : 32
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search
LoginUploadHelpAboutAdminister

Please use this identifier to cite or link to this item: http://ntour.ntou.edu.tw:8080/ir/handle/987654321/43039

Title: 基礎深開挖之數值模擬
Numerical Simulation of Deep Excavation
Authors: Wu, Chien-Yi
吳建逸
Contributors: NTOU:Department of Harbor and River Engineering
國立臺灣海洋大學:河海工程學系
Keywords: 深開挖;壁體變位;多層函數連結網路;礫石層;土壤彈性模數;數值模擬
deep excavation;multilayer function-link neural network;projects the system;gravel;elastic modulus;numerical simulation
Date: 2016
Issue Date: 2017-05-24T08:40:51Z
Abstract: 目前在土木工程界所使用之開挖行為預測分析軟體,一維分析以RIDO、TORSA程式為主,而二、三維分析仍以PLAXIS、FLAC程式為最多,近年國外仍有GTS 3D、SoilWorks 2D等新開發軟體引進,並日漸受學術與工程業界採用。除以上採數值分析外,近十多年,人工智慧(artificial intelligence)的技術在各領域的應用上已有許多相當成功貢獻,目前較常被使用者運用在開挖壁體變位預測上之類神經網路,皆採用監督式學習型態之應用倒傳遞類神經網路(BPN)。針對基礎深開挖擋土壁體變位之研究,本研究分為兩部份,一為利用類神經網路建立一開挖後壁體變位預測系統,一為使用PLAXIS及SoilWorks程式反推於礫石層分析時,不同程式於土壤彈性模數選用之合宜範圍。 本研究以類神經網路中,運用高度運算及學習能力的網路系統,發展一套改良型之多層函數連結網路(multilayer functional-link network,MFLN)預測模式來預測未開挖之壁體變位。根據測試與驗證結果顯示,逐項所建構之多層函數連結網路(MFLN)預測模式,不管在每一觀測點變位值、最大壁體變位值及其發生位置預測上,皆有不錯的預測結果。與BPN網路及RIDO程式預測準確度相比,有所提升約5%以上。 另數值分析,以選用二維PLAXIS及SoilWorks程式為研究工具,蒐集新北市新店地區礫石層開挖案例,使用擋土壁體變位量進行深開挖分析使用參數之回饋分析,以期能提供該分析案例區域或相似地層於不同分析程式數值模擬分析參數,土壤彈性模數選用建議範圍。由結果顯示,PLAXIS取用7840N~9800N(kN/m2),SoilWorks取用2450N~3430N(kN/m2),可合理預估最終開挖階段之最大變形量。
Before design and construction of deep excavation, for the sake of construction safety and protection of adjacent buildings, prediction and measurement of diaphragm wall deflection are very important so as to avoid failures of the supporting system. This paper attempts to predict the diaphragm wall deflection in deep excavation by using multilayer function-link neural network(MFLN) learning model. 17 case histories of deep excavation from construction projects are collected for training and verification. From the results of this research, it is shown that the MFLN model can reasonably predict both magnitude and location of the maximum deflection of the braced wall in deep excavation. In addition, this study analyzed gravel excavation cases in the Xindian District in Taiwan. The retaining wall deformation was used (instead of parameters usually employed in deep excavation analysis) in a back analysis for providing suggestions regarding the ideal range of the soil elastic modulus for numerical simulation analysis parameters in the Xindian District stratum or in strata similar to that in the Xindian District. This study used the PLAXIS and SoilWorks program to analyze the gravel layer in the district. The assessment results indicated PLAXIS program the range of the soil elastic modulus was set between 7.84N and 9.8N MPa. SoilWorks program the range of the soil elastic modulus was set between 2.45N and 3.43N MPa., the maximum deformation of the wall in the final excavation stage was reasonably estimated.
URI: http://ethesys.lib.ntou.edu.tw/cgi-bin/gs32/gsweb.cgi?o=dstdcdr&s=G0029952002.id
http://ntour.ntou.edu.tw:8080/ir/handle/987654321/43039
Appears in Collections:[河海工程學系] 博碩士論文

Files in This Item:

File Description SizeFormat
index.html0KbHTML38View/Open


All items in NTOUR are protected by copyright, with all rights reserved.

 


著作權政策宣告: 本網站之內容為國立臺灣海洋大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,請合理使用本網站之內容,以尊重著作權人之權益。
網站維護: 海大圖資處 圖書系統組
DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback