現在位置首頁 > 博碩士論文 > 詳目
論文中文名稱:以類神經網路預測炸震夯實之成效 [以論文名稱查詢館藏系統]
論文英文名稱:Using Artificial Neural Network to Predict the Effect of Blasting Densification [以論文名稱查詢館藏系統]
院校名稱:臺北科技大學
學院名稱:工程學院
系所名稱:資源工程研究所
畢業學年度:100
出版年度:101
中文姓名:詹偉弘
英文姓名:Wei-Hung Chan
研究生學號:98798004
學位類別:碩士
語文別:中文
口試日期:2012-01-11
論文頁數:119
指導教授中文名:丁原智
口試委員中文名:王泰典;俞旗文
中文關鍵詞:炸震夯實類神經網路砂質土壤
英文關鍵詞:Blasting densificationartificial neural networksandy soil
論文中文摘要:台灣位於西太平洋地震帶,每月中發生數以千計次地震,其中九二一地震造成土壤液化並帶來重大災害,因此,如何在建築物施工前將地盤改良將是一項重要的防治工程。
本研究分為兩部份,第一部份使用炸震夯實法,規畫佈孔設計並配置炸藥,藉由炸藥引爆時產生之高壓震波,使爆源附近之砂質土壤(sandy soil)產生土壤液化,待液化現象消退後,鑽取土樣進行土壤性質試驗。炸震夯實工法所使用的炸藥藥量、炮管深度、炮孔間距及土壤顆粒之震動速率為實驗設計參數,而炸震夯實之成效取決於含水量、孔隙率、飽和度及相對密度等土壤性質試驗之結果。
第二部份使用倒傳遞類神經網路,包含輸入層、隱藏層及輸出層,各層人工神經元藉由加權鏈結值與閥值連接,經由多次訓練與學習,將訓練值與實際值的誤差回饋於權值,以調整權值與閥值直到網路收斂為止。最後比較含水量、孔隙率、飽和度及相對密度預測值與實際值之誤差。
實驗結果顯示,施炸後土壤性質參數中之含水量、孔隙率及飽和度會隨時間增加而下降,相對密度則隨時間增加而上升;倒傳遞類神經網路預測之誤差範圍皆在20%以內,其中最大誤差百分比為19%。
論文英文摘要:Taiwan located on West-Pacific seismic belt, thousands of earthquakes occurred around Taiwan in a month. The most famous 921 earthquake which known as Chi-chi earthquake induced soil liquefaction and caused huge damage. Thurs, how to improve the building ground before construction is an important improvement project.
This research departs in to two parts:
The first part used blasting densification to improve land site. The blasting holes and explosives were designed and set. The sandy soil around the blasting sources was liquefied by high pressure shock waves which were caused by blasting. Drilling and receiving soil samples to conduct soil character tests. The site experiment factors included the weight of explosives, the depth of blasting holes, the distance of blasting holes and the vibration velocity of soil particles. The effect of blasting densification depended on the results of soil character test including water content, porosity, saturation and relative density.
The second part used back-propagation neural network. It contented input layer, hiding layer and output layer. Each neurons of layer were connected by weights and biases. After training and learning repeatedly, the errors between training values and real test values were feedback to weights, and regulated the weights and biases until the network was convergence. The predicting values of water content, porosity, saturation and relative density were compared to real test values and the errors were discussed in the end.
The result of experiment shows that the values of water content, porosity and saturation increased when time increased, but the values of relative density decreased when time increased; the range of error which was predicted by back-propagation neural network is under 20%, the largest error percentage is 19%.
論文目次:中文摘要 I
英文摘要 II
誌謝 IV
目錄 V
表目錄 VII
圖目錄 VIII
第一章 緒論 1
1.1前言 1
1.2研究動機與目的 2
1.3研究方法與內容 2
1.4論文架構 3
第二章 文獻回顧 4
2.1土壤液化防治工法 4
2.1.1建物集中都會區之液化防治工法 4
2.1.2大面積新生地區域之液化防治工法 5
2.2炸震夯實工法 10
2.2.1炸震夯實工法之應用 12
2.2.2炸藥及爆破技術 14
2.2.3炸震設計及施工參數 16
2.3類神經網路 19
2.3.1發展背景 19
2.3.2實用案例 21
2.3.3神經元模型 21
2.3.4類神經網路分類 23
第三章 研究方法與步驟 25
3.1現地實驗設計 25
3.2土壤性質試驗 33
3.2.1土壤含水量測定試驗 35
3.2.2土壤顆粒比重試驗 37
3.2.3土壤粒徑分析試驗 40
3.2.4相對密度試驗 41
第四章 倒傳遞類神經網路 44
4.1倒傳遞類神經網路簡介 44
4.2網路建立 45
4.3網路運算 49
第五章 結果討論與建議 53
5.1土壤性質試驗結果 53
5.1.1土壤性質實驗數據 53
5.1.2震動波速與時間對含水量之影響 61
5.1.3震動波速與時間對孔隙率之影響 64
5.1.4震動波速與時間對飽和度之影響 67
5.1.5震動波速與時間對相對密度之影響 70
5.1.6單位藥量對土壤性質之影響 73
5.2類神經網路預測結果 79
5.2.1類神經網路預測含水量 79
5.2.2類神經網路預測孔隙率 81
5.2.3類神經網路預測飽和度 83
5.2.4類神經網路預測相對密度 85
第六章 結論與建議 87
6.1結論 87
6.2建議 88
參考文獻 90
附錄A 各時段各土層之土壤粒徑 94
附錄B 土壤含水量測定試驗結果 104
附錄C 土壤顆粒比重試驗、孔隙率及飽和度之結果 107
附錄D 相對密度試驗結果 111
附錄E 類神經網路輸入值 115
論文參考文獻:1. 王錦楨,以模糊類神經網路建立液化潛能評估模式,碩士論文,國立臺灣海洋大學,基隆,民國九十五年。
2. 林杰濱,地貌構造對爆破振動波影響的模擬分析研究,碩士論文,國立台北科技大學,台北,民國一百年。
3. 高茂森,土壤動態三軸試驗條件對液化潛能分析之影響,碩士論文,國立成功大學,台南,民國九十三年。
4. 倪勝火,土壤力學實驗手冊,國立成功大學,台南,民國九十五年。
5. 張吉佐、洪明瑞、張崇義、張惠文,台灣地區地盤改良技術之應用現況,地工技術,第78期,民國八十九年,第5-18頁。
6. 張吉佐、曾文德、許建裕,台灣濱海工業區的地盤改良工法,地工技術,第93期,民國九十一年,第53-68頁。
7. 辜炳寰,類神經網路於土壤液化評估之應用,碩士論文,國立成功大學,台南,民國九十一年。
8. 陶國隆,臺北盆地土壤液化潛能與災害潛勢微分區研究,碩士論文,國立成功大學,台南,民國九十二年。
9. 鄭惠隆,應用類神經網路初步建立路堤沉陷之預估模式,碩士論文,國立雲林科技大學,雲林,民國九十五年。
10. 蘇鼎鈞、周忠仁、莊孟翰,土壤液化防治工法及實例,亞新工程顧問股份有限公司,民國九十一年。
11. H. Bakhshandeh Amnieh, M. R. Mozdianfard, A. siamaki, “Predicting of blasting vibrations in Sarcheshmeh copper mine by neural network,” Safety Science, 48 (2010), 319-325.
12. H.J. Ma, S.T. Quek, K.K. Ang, “Soil–structure interaction effect from blast-induced horizontal and vertical ground vibration,” Engineering Structures, 26 (2004), 1661–1675.
13. Ian Flood, Bryan Bewick, Robert J Dinan, Hani A Salim, “Modeling blast wave propagation using artificial neural network methods,” Advanced Engineering Informatics, 23 (2009), 418-423.
14. Korhan Adalier, Ahmed Elgamal, “Mitigation of liquefaction and associated ground deformations by stone columns,” Engineering Geology, 75 (2004), 275-291.
15. Manoj Khandelwal, T. N. Singh, “Prediction of blast induced ground vibrations and frequency in opencast mine: A neural network approach,” Journal of Sound and Vrbration, 289 (2006), 711-725.
16. Michael Lersow, “Deep soil compaction as a method of ground improvement and to stabilization of wastes and slopes with danger of liquefaction, determining the modulus of deformation and shear strength parameters of loose rock,” Waste Management, 21 (2001), 161-174.
17. M. K. Gupta, R. C. Agrawal, “Seimotectonic and liquefaction studies of an industrial site in Northern India,” Soil Dynamics Earthquake Engineering, 17 (1998), 349-355.
18. Naotaka Kamijo, Hideaki Saito, Kazuhiro Kusama, Osamu Kontani, Robert Nigbor, “Seimic tests of a pile-supported structure in liquefiable sand using large-scale blast excitation,” Nuclear Engineering Design, 228 (2004), 367-376.
19. Xiaobing Lu, Peng Cui, “The liquefaction and displacement of highly saturated sand under water pressure oscillation,” Ocean Engineering, 31 (2004), 795–811.
20. Xiaoming Yuan, RuiSun, Longwei Chen, FuhuiTang, “A method for detecting site liquefaction by seismic records,” Soil Dynamics and Earthquake Engineering, 30 (2010), 270–279.
21. Zhongqi Wang, Yong Lu, Chunhua Bai, “Numerical analysis of blast-induced liquefaction of soil,” Computers and Geotechnics, 35 (2008), 196–209.
論文全文使用權限:不同意授權