請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93856完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 呂良正 | zh_TW |
| dc.contributor.advisor | Liang-Jenq Leu | en |
| dc.contributor.author | 謝語哲 | zh_TW |
| dc.contributor.author | Yu-Che Hsieh | en |
| dc.date.accessioned | 2024-08-08T16:35:05Z | - |
| dc.date.available | 2024-08-09 | - |
| dc.date.copyright | 2024-08-08 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-08-02 | - |
| dc.identifier.citation | Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M. (2019). Optuna: A next-generation hyperparameter optimization framework. KDD ’19, page 2623–2631, NewYork, NY, USA. Association for Computing Machinery.
Breiman, L. (2001). Random forests. Machine learning, 45(1):5–32 He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 770–778. Ioffe, S. and Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning, pages 448–456. PMLR. LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., and Jackel, L. D. (1989). Backpropagation applied to handwritten zip code recognition. Neural Computation, 1(4):541–551. McCulloch, W. S. and Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, 5(4):115–133. Pan, S. J. and Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10):1345–1359. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You only look once: Unified, real-time object detection. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 779–788. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15(56):1929–1958. 李權恩 (2023)。應用深度學習預測 RC 建築之柱斷面設計。國立臺灣大學土木工程研究所碩士論文。 李牧軒 (2022)。應用深度學習輔助 RC 建築之柱斷面設計。國立臺灣大學土木工程研究所碩士論文。 陳穎君 (2021)。應用機器學習於混凝土抗壓強度預測及 RC 建築梁柱設計。國立臺灣大學土木工程研究所碩士論文。 | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93856 | - |
| dc.description.abstract | 應用深度學習模型預測建築物中二樓至頂樓的每根大梁的斷面設計，包含斷面尺寸、主鋼筋量與箍筋配置共三種類型的預測目標，每種預測目標會建立對應的人工神經網路 (ANN) 模型，並以真實設計建案作為資料庫工模型進行訓練、驗證、測試，並探討參數重要性以及模型的誤差表現。實際使用上僅需將建築物及大梁的相關參數輸入至模型即可得到模型的預測值，結構工程師可以此值作為基準去評估設計結果是否合理。
本研究的資料庫是使用 88 棟真實建案 (由築遠工程顧問公司提供) 自行建立，共有 27720 筆資料，每筆資料代表一根大梁。資料庫的特徵取自結構計算書、結構平面圖、柱配筋圖等，預測目標 (斷面尺寸、主筋量、箍筋配置) 則取自梁配筋詳圖。由於預測目標需要輸入的資訊量較為龐大，因此本研究建立一套自動化輸入流程，應用電腦視覺的技術自動讀取梁配筋圖上的資訊並輸入至資料庫，並且設立檢核機制以確保輸入資料庫的資訊是正確的；最後以真實建案做為輸入測試，從準確度及花費時間來探討此流程的效益。 | zh_TW |
| dc.description.abstract | Applying deep learning models to predict the cross-sectional design of each beam from the second floor to the top floor of a building, including three types of prediction targets: cross-sectional dimensions, the amount of main reinforcement, and the configuration of stirrups. A corresponding artificial neural network (ANN) model is established for each prediction target and is trained, validated, and tested using real construction projects as the database model. The importance of parameters and the model’s error performance are also explored. In practical use, the relevant parameters of the building and beams only need to be input into the model to obtain the model’s predicted values. Structural engineers can use these values as a benchmark to evaluate the reasonableness of their design results.
The database used in this study was self-built using 88 real construction projects (provided by Envision Engineering Consulting Co., Ltd.), comprising a total of 27,720 data entries, each representing a beam. The features of the database are extracted from structural calculation books, structural plans, and column reinforcement drawings, while the prediction targets (cross-sectional dimensions, main reinforcement amount, stirrup configuration) are taken from the beam reinforcement detail drawings. Due to the extensive amount of information required for the prediction targets, this study establishes an automated input process, applying computer vision technology to automatically read the information from the beam reinforcement drawings and input it into the database. A verification mechanism is set up to ensure the correctness of the information entered into the database. Finally, real construction projects are used as input tests to explore the efficiency of this process in terms of accuracy and time consumption. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-08-08T16:35:05Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-08-08T16:35:05Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 致謝 i
摘要 iii Abstract v 目次 vii 圖次 xi 表次 xiii 第一章 緒論 1 1.1 研究動機 1 1.2 文獻回顧 2 1.2.1 預測斷面設計 2 1.2.2 深度學習 2 1.2.3 電腦視覺 4 1.3 各章內容 5 第二章 研究方法 7 2.1 前言 7 2.2 ANN 7 2.3 ResNet 8 2.4 YOLO 9 2.5 相關方法 10 2.5.1 激活函數 10 2.5.2 損失函數 11 2.5.3 特徵重要性 11 2.5.4 調整超參數 12 第三章 資料庫 13 3.1 前言 13 3.2 基本假設 13 3.3 資料庫特徵 15 3.3.1 建築相關特徵 16 3.3.2 樓層相關特徵 17 3.3.3 大梁相關特徵 19 3.4 資料集切分 24 第四章 應用電腦視覺輔助資料庫建立 25 4.1 前言 25 4.2 應用方式 25 4.3 流程說明 27 4.4 評估指標 30 4.5 模型介紹 33 4.5.1 模型 A 33 4.5.2 模型 B 36 4.5.3 模型 C 39 4.6 實際流程範例與討論 41 4.6.1 實際流程範例 41 4.6.2 自動化流程結果討論 44 4.7 小結 45 第五章 大梁斷面尺寸預測 47 5.1 前言 47 5.2 預測目標 47 5.3 模型介紹 48 5.4 資料前處理 49 5.5 評估指標 50 5.6 訓練流程 51 5.6.1 訓練模型 52 5.6.2 資料庫的特徵選擇 52 5.6.3 超參數選擇 55 5.6.4 測試集表現 56 5.7 小結 57 第六章 大梁鋼筋量預測 59 6.1 前言 59 6.2 預測目標 59 6.3 模型介紹 61 6.4 資料前處理 62 6.5 評估指標 64 6.6 訓練流程 64 6.6.1 訓練模型 65 6.6.2 資料庫特徵選擇 66 6.6.3 超參數選擇 70 6.6.4 測試集表現 72 6.7 小結 75 第七章 結論與未來展望 77 7.1 結論 77 7.2 未來展望 80 參考文獻 81 附錄 一 — RC 建築資料庫建築特徵列表 83 | - |
| dc.language.iso | zh_TW | - |
| dc.subject | RC 建築 | zh_TW |
| dc.subject | 結構梁斷面設計 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 人工神經網路 | zh_TW |
| dc.subject | 卷積神經網路 | zh_TW |
| dc.subject | Deep Learning | en |
| dc.subject | RC building | en |
| dc.subject | Convolutional neural network | en |
| dc.subject | Artificial neural network | en |
| dc.subject | Section design of structural beam | en |
| dc.title | 應用深度學習輔助資料庫建立及 RC 建築之大梁斷面設計 | zh_TW |
| dc.title | Application of Deep Learning to Assist in Database Creation and Beam Section Design in RC Building | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 宋裕祺;黃仲偉;郭世榮 | zh_TW |
| dc.contributor.oralexamcommittee | Yu-Chi Sung;Chang-Wei Huang;Shyh-Rong Kuo | en |
| dc.subject.keyword | RC 建築,結構梁斷面設計,深度學習,人工神經網路,卷積神經網路, | zh_TW |
| dc.subject.keyword | RC building,Section design of structural beam,Deep Learning,Artificial neural network,Convolutional neural network, | en |
| dc.relation.page | 84 | - |
| dc.identifier.doi | 10.6342/NTU202402850 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2024-08-06 | - |
| dc.contributor.author-college | 工學院 | - |
| dc.contributor.author-dept | 土木工程學系 | - |
| 顯示於系所單位： | 土木工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-112-2.pdf | 8.03 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。