| DC 欄位 |
值 |
語言 |
| DC.contributor | 土木系營建管理碩士班 | zh_TW |
| DC.creator | 吳凱媛 | zh_TW |
| DC.creator | Kai-Yuan Wu | en_US |
| dc.date.accessioned | 2022-8-11T07:39:07Z | |
| dc.date.available | 2022-8-11T07:39:07Z | |
| dc.date.issued | 2022 | |
| dc.identifier.uri | http://ir.lib.ncu.edu.tw:88/thesis/view_etd.asp?URN=109355008 | |
| dc.contributor.department | 土木系營建管理碩士班 | zh_TW |
| DC.description | 國立中央大學 | zh_TW |
| DC.description | National Central University | en_US |
| dc.description.abstract | 營建業及物業管理產業是高度勞動密集型的產業，近年來營建業人力嚴重不足，營運維護作業大部分仍為人工作業方式，導致建築物無完整履歷保留，使管理品質及效率嚴重不足；然以建築物全生命週期觀點，完工後續營運時間至少數十年，甚至百年以上，期間所耗費的資源與金錢，遠超過當初建造所花費的成本，佔建築全生命週期成本80%以上。在房齡不斷老化及大量建築整修的背景下，設備保養對於建物永續、安全非常重要，維護管理應達到減少設備及設施故障造成之損失，及用以延長壽命之目的，保障使用者生命機能。也因如此，降低企業或公寓大廈在營運維護管理成本及設施設備維護上的開銷，是目前重大課題。
本研究藉由桃園市某園區建築物設施維修資料，建置營運維護產業雲端智慧平台，研究根據文獻回顧重新開發設施維修模組之系統介面，其分析4,737筆設施維修資料庫多數為30年以上至50年老舊建築所申請，並利用資料探勘中之自組映射圖類神經網路SOMCM演算法對設施維修類型進行分群，使其資料自行群聚，找出不同資料項目間的相互關係，顯現各群所特有之特性，進行人為解釋，提供後續園區營運維護管理之處置作為與建議。
研究結果可以看出空調的維修數量明顯與季節有關外，其餘的設備損壞均與季節無太大的關聯性，然設備修繕原因多數為設備老舊造成零件損壞、設備已達使用壽命、園區因人力擴編使相關硬體設備不足及房舍老舊既有建築設計已不符合實際需求。最後，研究成果及相關建議將提供該園區作為後續營運維護管理之參考，讓建築的硬體功能得以新的形式在建築中出現，使管理者更容易整體維護管理。 | zh_TW |
| dc.description.abstract | A feasible and user-friendly interface is one of keys that influence practicability to a successful platform. The research objective is to develop an operation-maintenance platform using SOM-based Cluster Merging (SOMCM) algorithm. A comprehensive literature review summarizes the interface framework, followed by the interface design. The novel SOMCM algorithm is developed to simplify operation and maintenance patterns and to generate useful information for maintenance. The empirical study is aimed at a large industrial park in Taoyuan City involving 46 buildings with 3,526 maintenance datasets. The outputs from the proposed method summarize 7 patterns for more efficient maintenance: (1) simplify current self-repair to outsourcing, (2) modify the current traditional contract type to open contract type, (3) adopt massive procurement for major facilities (e.g. air conditioning), (4) schedule power supply systems in a systematic and efficient way, (5) establish maintenance patterns as suggested to eliminate warehouse for spares, (6) re-allocate maintenance resources in a seasonal cycle, (7) set up a standby team to resolve emergency repairs. The findings can reduce significant amount of time and cost for the investigated industrial park. | en_US |
| DC.subject | 營建業管理平台 | zh_TW |
| DC.subject | 物業管理平台 | zh_TW |
| DC.subject | 設施維修模組 | zh_TW |
| DC.subject | 分群演算 | zh_TW |
| DC.subject | efficient operation and maintenance | en_US |
| DC.subject | platform interface | en_US |
| DC.subject | SOM-based Cluster Merging (SOMCM) | en_US |
| DC.subject | clustering | en_US |
| DC.subject | maintenance pattern | en_US |
| DC.title | 運用SOMCM分群演算法開發設計雲端智慧平台之營運維護產業介面-以桃園市某園區為例 | zh_TW |
| dc.language.iso | zh-TW | zh-TW |
| DC.title | Establishing smart cloud-IoT interface for project operation and maintenance using SOMCM algorithm – An empirical study for Taoyuan industrial park | en_US |
| DC.type | 博碩士論文 | zh_TW |
| DC.type | thesis | en_US |
| DC.publisher | National Central University | en_US |