以國際糙度指標分析網級柔性鋪面養護最適化之研究

NCU Institutional Repository > 工學院 > 土木工程研究所 > 博碩士論文 > Item 987654321/570

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/570

题名:	以國際糙度指標分析網級柔性鋪面養護最適化之研究
作者:	姚志廷;Zh-Teng Yao
贡献者:	土木工程研究所
关键词:	養護;最適化;類神經網路;線性規劃;柔性鋪面
日期:	2001-06-29
上传时间:	2009-09-18 17:07:57 (UTC+8)
出版者:	國立中央大學圖書館
摘要:	台灣地區道路發展受限於空間與經費，新築道路數量將趨緩，對於龐大的各級舊有道路，必須進行養護與維修作業，以確保行車安全，並降低使用者成本、社會成本與環境成本。鋪面維護管理系統（Pavement Maintenance Management System ,PMMS）乃是針對鋪面維護相關的決策資訊進行系統化的收集、萃取、分析，在有限的維護經費下做最適當的運用。PMMS系統化的分析，最終目的便是提供決策者最適當的養護策略分析。本研究利用智慧型自動道路檢測車（Automatic Road Analyzer 簡稱ARAN）進行路網層級（Network Level）的鋪面檢測，蒐集相關鋪面決策資訊，並以SPSS(Statistical Package for the Social Science)對檢測資料進行相關的統計分析，並利用集群分析法（Cluster Analysis）建立鋪面家族(Pavement Family)，以決定其鋪面績效劣化模式。本研究以國際糙度指標（International Roughness Index）做為鋪面績效指標，並利用類神經網路(Artificial Neural Networks )進行該指標與鋪面破壞之相關性分析，以評估該指標於本土化應用之適用性。本研究以養護效益最大為單目標函數，分析路段養護最適時機，並建構最適養護策略，並以模糊線性規劃(Fuzzy Linear Programming)處理多目標決策問題，以LINDO軟體（Linear Interactive and Discrete Optimizer）求解線性規劃最適解。提供經費限制下，最適的養護決策。 The development of roads in Taiwan is limited by the space and the cost. The number of new constructing roads is growing slowly. Therefore, It is necessary to maintain a lot of old roads to assure the safety of traffic and to decrease the user, the society and the environment costs. The pavement maintenance management system（PMMS） is to collect and to analyze the decision information about the pavement maintenance in systematic way. The major purpose of PMMS is to give the decision makers the optimal analyses of the maintenance strategies. In this research, firstly we use the Automatic Road Analyzer to do the pavement test of network level and to collect the decision information about the pavements. Then, we apply SPSS (Statistical Package for the Social Science) to do some statistical analyses toward the test data. Besides, we take advantage of the cluster analysis to build the pavement family to decide the deteriorated models of pavement performance. In this research, we use the IRI (International Roughness Index) as the pavement performance index. In addition, we use ANN (Artificial Neural Networks) to do related analyses between IRI and the various damages of pavements in order to evaluate whether the index can be applied properly in local. We regard the maximum of maintenance benefit as the single object function to decide the best moment and the optimal strategy of pavement maintenance. At last, we use the methodology of fuzzy linear programming to deal with multiply object decision problems and apply LINDO（Linear Interactive and Discrete Optimizer）to solve the linear program solution. According to IRI, this research provides the optimal pavement maintenance strategies under the limited budget.
显示于类别:	[土木工程研究所] 博碩士論文

文件中的档案:

档案	大小	格式	浏览次数

在NCUIR中所有的数据项都受到原著作权保护.

社群 sharing

数据加载中.....