建物震害毀損度預測模式之研究－倒傳遞類神經網路法之應用

A Forecast of Building Destruction in Earthquakes: Applications of Artificial Neural Network

鄒克萬(Ko-Wan Tsou) ； 張益三(Yih-San Chang) ； 杜建宏(Chien-Hung Tu)

《住宅學報》 15卷1期 (2006/06) Pp. 21-41

https://doi.org/10.6375/JHS.200606.0021

摘要

本研究係以文獻回顧之相關研究、921地震時七級震度之竹山地區建物毀損資料及現有建物調查之資料，尋求影響因子與變數，並將上述資料以倒傳遞類神經網路MATLAB6.5軟體，利用其具有學習及記憶能力加以訓練、測試及驗證，建立中低層建物震害毀損度預測模式，應用於嘉義市部分舊市區，並以地理資訊系統予以空間化，將建物毀損度分為安全、危險與倒塌三級，結果證明類神經網路具有預測建物震害毀損度之能力，且其誤判率較低，是為都市防災規劃值得推廣及應用的方法。

關鍵字

倒傳遞類神經網路 ； 建物震害毀損度 ； 誤判率

並列摘要

This research investigates potential variables of buding destruction in earthquakes and their influences by conducting an empirical study of Jwu-Shan area in Taiwan. Jwu-Shan was one of the most serious damaged areas during the 921 earthquake which was 7.0 magnitude. In this study, MATLAB6.5 software of back-propagation neural network was used with its superior attributes, i.e., learning and memory, to establish a forecast model of hazards in middle and lower buildings in an earthquake by means of training, testing and validation. The model was tested with the data of partial old communities in Chia-Yi. Damaged buildings were classified into 3 categories: safe, unsafe, and collapse by geography information system (GIS) with data spatialization and transformation. The results suggest that the artificial neural network is capable to forecast building destruction in earthquakes with a low error rate. The paper concludes with applications of a back-propagation neural network in planning urban disaster prevention.

並列關鍵字

back-propagation neural network ； building destruction in earthquakes ； error rate

參考文獻

吳佩姿(2004)。液化敏感區建物受損評估模式與土地利用評析之研究(碩士論文)。長榮大學土地管理與開發研究所。

吳淑芳(2004)。應用倒傳遞網路建構雨量與淹水間之關聯模型(碩士論文)。大同大學資訊工程研究所。

李秉乾、周天穎(2002)。利用921 大地震資料建立建築震害危險度評估模式。行政院國科會。

林銘祥(2000)。類神經網路於建築火災災害預估模式之應用(碩士論文)。國立成功大學土木工程研究所。

邱妍斐(2003)。大規模地震區域建築物總損壞推測之研究(碩士論文)。國立台北科技大學土木與技術防災研究所。