| DC 欄位 |
值 |
語言 |
| DC.contributor | 營建管理研究所在職專班 | zh_TW |
| DC.creator | 陳俞均 | zh_TW |
| DC.creator | Yu-Chun Chen | en_US |
| dc.date.accessioned | 2019-6-27T07:39:07Z | |
| dc.date.available | 2019-6-27T07:39:07Z | |
| dc.date.issued | 2019 | |
| dc.identifier.uri | http://ir.lib.ncu.edu.tw:88/thesis/view_etd.asp?URN=106355001 | |
| dc.contributor.department | 營建管理研究所在職專班 | zh_TW |
| DC.description | 國立中央大學 | zh_TW |
| DC.description | National Central University | en_US |
| dc.description.abstract | 近十年來由於工業的快速發展,使得臺灣的能源需求急劇增加。在滿足電力需求方面，再生能源扮演著重要角色，此時需要更多的超高壓架空輸電鐵塔來支援台灣之輸電網路。我們需要一種快速、準確和自動的成本估算工具來取代既有之手動估算方式。
本研究目的係利用支持向量迴歸來開發一種可預測超高壓輸電鐵塔專案施工成本之工具。首先透過文獻回顧為歷史數據資料蒐集以及超高壓鐵塔基礎之成本估算屬性提供了研究方向。接著本研究蒐集了全臺灣近十年的超高壓鐵塔歷史興建資料。從2010 年至2019年總共建造了317座超高壓鐵塔基礎，故本研究之數據來源共有317組，其中有75座鐵塔基礎因為缺少部分數據資訊而予以捨棄，最終有238組數據(佔總數75%)被納入本研究之SVR模型開發，作為本研究之數據來源。
本研究選用C=50和γ=0.05和 5折交叉驗證來建構SVR預測模型，SVR模型得出預測結果之準確率為97.91%，RMSE=0.0989，R2=0.9924。而多元線性迴歸預測之準確率為90.66%，RMSE=0.5211和R2=0.8091。兩者之預測結果相比，本研究所提出之SVR預測模型在預測超高壓鐵塔專案施工成本是極為有效的解決方案。 | zh_TW |
| dc.description.abstract | Energy demands in Taiwan have dramatically increased due to rapid industrial development in the recent decade. Renewable energy is playing an important role in filling out the demands and requires more Extra-High Voltage (EHV) transmission towers to support Taiwan electrical transmission network. A prompt, accurate, and automatic cost estimation tool is desired to replace the current manual estimation.
The study objective is to develop a tool using support vector regression (SVR) that can predict construction cost for EHV transmission tower projects. Literature review leads a way to collect historical data and what the attributes of cost estimation for EHV transmission tower foundations. The study targets the total historical data in recent decade in Taiwan. As a result, there are 317 EHV transmission towers built from 2010 to 2019 having 317 sets for the data source. Eliminating 79 sets due to missing information, 238 data sets (75% of the total) of EHV transmission tower foundations are taken into consideration for the SVR model development.
Having the C=50 and γ=0.05 set and 5 fold cross validation, the proposed SVR model yields the prediction result with an accuracy at 97.91% as RMSE=0.0989 and R2 = 0.9924. Compared to the result from multi-linear regression at 90.66% as RMSE=0.5211 and R2 = 0.8091, the proposed SVR model is an effective solution to predict construction cost for extra-high voltage transmission tower projects. | en_US |
| DC.subject | 能源 | zh_TW |
| DC.subject | 超高壓架空鐵塔基礎 | zh_TW |
| DC.subject | 施工成本估算 | zh_TW |
| DC.subject | 支持向量迴歸 | zh_TW |
| DC.subject | Energy | en_US |
| DC.subject | EHV transmission tower foundation | en_US |
| DC.subject | construction cost estimation | en_US |
| DC.subject | support vector regression | en_US |
| DC.title | 利用支持向量迴歸建構超高壓架空鐵塔基礎費用預測模型 | zh_TW |
| dc.language.iso | zh-TW | zh-TW |
| DC.title | Predicting Construction Cost For Extra-High Voltage Transmission Tower Foundations Using Support Vector Regression | en_US |
| DC.type | 博碩士論文 | zh_TW |
| DC.type | thesis | en_US |
| DC.publisher | National Central University | en_US |