自近代 19 世紀法拉第發現電磁感應並研製出第一台發電機後，電力之應用逐 漸普及化到工業與民生上。從中有諸多企業機構為防止因停電所造成損失，往往都會設置柴油發電機組，以便在危急之下有快速、穩定的備用電源能夠使用。然而這些發電機組平時大都處於備用狀態，因此當發生故障時，基於使用者對機組的不熟悉，時常無法立即處理問題。進而也導致不論問題之難易程度為何，使用者都仰賴技術工程師親自至現場進行處理。這樣的情況在交通相當不便利的越南更是為工 程師帶來莫大困擾，加上自 2020 年發生新冠疫情以來，更是難以前往現場進行檢修，使得發電機設備之維修作業面臨種種考驗。
為改善上述問題，故本研究將以柴油發電機故障之根因診斷為例，建構一套基於知識圖譜之專家系統，整個系統將採用使用率高的 Line 中的聊天機器人進行系統包裝。首先將針對市面上現有的發電機組之故障資訊進行整合，為各型號機組設計一套統一的標準檢查流程。而過程中會將問題區分為常見與複雜兩類，以常見問 題進行根本原因分析，建構常見問題檢索功能 ; 以複雜問題進行知識抽取與融合以及關聯性剖析，來建構出最終的知識圖譜。如此一來除了讓使用者在第一時間能 獲得實質幫助，也簡化了工程師傳統作法中繁雜的檢修流程，提升問題檢索與排除之效率，更為知識與專業技術做到更好的保存與傳承。

Since Michael Faraday discovered electromagnetic induction and developed the first generator in the 19th century, the application of electricity has gradually spread to industry and people’s livelihood. In order to prevent losses caused by power failure, many enterprises and organizations often install diesel generators so that they can have fast and stable backup power sources in an emergency. However, these generators are usually in standby mode, so when a failure occurs, users are often unable to deal with the problem immediately based on the user’s unfamiliarity with the generator set. Furthermore, regardless of the difficulty of the problem, users rely on technical engineers to be on scene to handle the problem. This situation is even more troublesome for engineers in Vietnam, where the transportation is quite inconvenient. In addition, the overhaul work of generator equipment has become even more difficult for engineers due to the outbreak of COVID-19 in 2020.
To improve the above problems, this study will take the root cause diagnosis of diesel generator failure as an example to construct an expert system based on knowledge graphs. The entire system will be packaged with LINE chatbot with a high usage rate. First, integrate the fault information of the existing generators on the market, and design a unified standard inspection process for each type of generator. In the process, problems are divided into two categories, which are common and complex; common problems are used for root cause analysis to construct common problem retrieval functions, while complex problems are used for knowledge extraction and fusion and relevance analysis to construct the final knowledge map. In this way, allowing users to get substantial assistance in the first place, it also simplifies the complicated overhaul process in the traditional practice of engineers, improves the efficiency of problem retrieval and elimination, and better preserves and inherits knowledge and expertise.

摘要 I
ABSTRACT II
誌謝 IV
目錄 V
表目錄 VII
圖目錄 VIII
一、 緒論 1
（一） 研究背景 1
（二） 研究目的 2
二、 文獻探討 3
（一） 柴油發電機 3
（二） 知識管理（KNOWLEDGE MANAGEMENT） 3
（三） 專家系統（EXPERT SYSTEM, ES） 6
（四） 根本原因分析（ROOT CAUSE ANALYSIS, RCA） 8
（五） 知識圖譜（KNOWLEDGE GRAPH） 11
三、 系統設計 14
（一） 需求分析 14
1. 廠商的需求分析 14
2. 使用者的需求分析 15
3. 工程師的需求分析 15
（二） 架構設計 16
1. 知識建構（Knowledge Construction） 20
2. 盤點現有常見問題（知識）或技術（操作）手冊整理 20
3. 知識根本原因分析 20
4. 建構知識圖譜 21
四、 研究實作與成果展示 23
（一） 概念性驗證（PROOF OF CONCEPT, POC） 23
1. 架構流程與單元說明 23
2. 基礎檢查流程 26
3. 各類故障問題整理及分級 27
（二） 實作成果與畫面展示 30
1. 功能概述 30
2. 畫面展示與說明 31
（三） 比較與效益分析 36
摘要 I
ABSTRACT II
誌謝 IV
目錄 V
表目錄 VII
圖目錄 VIII
一、 緒論 1
（一） 研究背景 1
（二） 研究目的 2
二、 文獻探討 3
（一） 柴油發電機 3
（二） 知識管理（KNOWLEDGE MANAGEMENT） 3
（三） 專家系統（EXPERT SYSTEM, ES） 6
（四） 根本原因分析（ROOT CAUSE ANALYSIS, RCA） 8
（五） 知識圖譜（KNOWLEDGE GRAPH） 11
三、 系統設計 14
（一） 需求分析 14
1. 廠商的需求分析 14
2. 使用者的需求分析 15
3. 工程師的需求分析 15
（二） 架構設計 16
1. 知識建構（Knowledge Construction） 20
2. 盤點現有常見問題（知識）或技術（操作）手冊整理 20
3. 知識根本原因分析 20
4. 建構知識圖譜 21
四、 研究實作與成果展示 23
（一） 概念性驗證（PROOF OF CONCEPT, POC） 23
1. 架構流程與單元說明 23
2. 基礎檢查流程 26
3. 各類故障問題整理及分級 27
（二） 實作成果與畫面展示 30
1. 功能概述 30
2. 畫面展示與說明 31
（三） 比較與效益分析 36
五、 回顧與展望 39
（一） 研究結論 39
（二） 未來展望 40
參考文獻 41

1. 劉得政, "機電設備、監控及資料收集系統之技術整合研究-以柴油發電機組為例," 碩士, 機電整合研究所, 東南科技大學, 新北市. [Online]. Available:https://hdl.handle.net/11296/c2hq4a
2. 何鵬萬, "以維修紀錄推估裝備系統可靠度建構維護政策之研究:(以海軍艦艇 柴油發電機為例)," 撰者, 2011.
3. 張丁皇,"緊急發電機維護保養及故障分析,"碩士,電機工程系, 國立高雄科技大學, 高雄市, 2020. [Online]. Available: https://hdl.handle.net/11296/gm26sr
4. 江明儒, "考量最佳化國軍裝備柴油發電機保養與維修成本下之保養週期," 碩士, 工業工程與管理系碩士班, 明志科技大學, 新北市, 2017. [Online].Available: https://hdl.handle.net/11296/6899r3
5. D. Paschek, L. Ivascu, and A. Draghici, "Knowledge management–the foundation for a successful business process management," Procedia-Social and Behavioral Sciences, vol. 238, pp. 182-191, 2018.
6. R. V. Domínguez Gonzalez and M. F. Martins, "Knowledge management: an analysis from the organizational development," Journal of technology management & innovation, vol. 9, no. 1, pp. 131-147, 2014.
7. A. D. K. BELLO, "Critical success factors of knowledge management in Albania business organizations," European Journal of Research and Reflection in Management Sciences Vol, vol. 3, no. 2, 2015.
8. M. Alavi and D. E. Leidner, "Knowledge management and knowledge management systems: Conceptual foundations and research issues," MIS quarterly, pp. 107-136,2001.
9. A. P. TSEKHOVOY, A. S. ZHOLTAYEVA, and A. V. STEPANOV, "The role of knowledge management in organizational development," Revista ESPACIOS, vol.40, no. 25, 2019.
10. S. M. Lee and S. Hong, "An enterprise‐wide knowledge management system infrastructure," Industrial Management & Data Systems, 2002.
11. M. Kordab and J. Raudeliūnienė, "Knowledge management cycle: a scientific literature review," in 10th International Scientific Conference „Business and Management 2018 “, 2018.
12. 邱鶴倫 and 彭德保, "應用知識管理於設備維修流程之研究與實作--以半導體設備產業為例," 2002.
13. 黃明達 and 劉育辰, "電腦維修知識管理系統之研究-以淡江大學為例," 資訊管理展望, vol. 13, no. 2, pp. 171-196, 2011.
14. V. Kontargyri et al., "An expert system for fault diagnosis, repairing and maintenance of electrical machines," in Proceedings of the 6th conference on Applications of electrical engineering, 2007: Citeseer, pp. 166-171.
15. S. Jingping, M. Jichang, N. Jiahua, and W. Ermao, "An intelligent fault diagnosis expert system based on fuzzy neural network," Journal of Vibration and Shock, vol. 36, no. 4, pp. 164-171, 2017.
16. F. Gao, L. J. Xiao, W. Y. Zhong, and W. Liu, "Fault diagnosis of shearer based on fuzzy inference," in Applied Mechanics and Materials, 2011, vol. 52: Trans Tech Publ, pp. 1577-1580.
17. C.-C. Long, "應用於微電網故障保護之專家系統," National Central University,2018.
18. C. Liang, S. Wang, R. Chen, S. Zhao, and Y. Wu, "Research on Ship Electronic Power System Fault Diagnosis Based on Expert System," in IOP Conference Series: Materials Science and Engineering, 2020, vol. 738, no. 1: IOP Publishing, p. 012017.
19. J. J. Rooney and L. N. V. Heuvel, "Root cause analysis for beginners," Quality progress, vol. 37, no. 7, pp. 45-56, 2004.
20. Y. Y. Wee, W. P. Cheah, S. C. Tan, and K. Wee, "A method for root cause analysis with a Bayesian belief network and fuzzy cognitive map," Expert Systems with Applications, vol. 42, no. 1, pp. 468-487, 2015.
21. A. M. Doggett, "Root cause analysis: a framework for tool selection," Quality Management Journal, vol. 12, no. 4, pp. 34-45, 2005.
22. K. B. Korb and A. E. Nicholson, Bayesian artificial intelligence. CRC press, 2010.
23. W. E. Wong, R. Gao, Y. Li, R. Abreu, and F. Wotawa, "A survey on software fault localization," IEEE Transactions on Software Engineering, vol. 42, no. 8, pp. 707- 740, 2016.
24. T. Sun and Q. Wang, "Multi-source fault detection and diagnosis based on multi- level Knowledge Graph and Bayesian theory reasoning (S)," in SEKE, 2019, pp. 177-232.
25. B. Kosko, "Fuzzy cognitive maps," International journal of man-machine studies, vol. 24, no. 1, pp. 65-75, 1986.
26. L. Zhang, A. A. Chettupuzha, H. Chen, X. Wu, and S. M. AbouRizk, "Fuzzy cognitive maps enabled root cause analysis in complex projects," Applied Soft Computing, vol. 57, pp. 235-249, 2017.
27. W. Yue, X. Chen, W. Gui, Y. Xie, and H. Zhang, "A knowledge reasoning Fuzzy- Bayesian network for root cause analysis of abnormal aluminum electrolysis cell condition," Frontiers of Chemical Science and Engineering, vol. 11, no. 3, pp. 414- 428, 2017.
28. D. Fensel et al., "Introduction: What Is a Knowledge Graph?," in Knowledge Graphs: Springer, 2020, pp. 1-10.
29. A. J. Kumar, C. Schmidt, and J. Köhler, "A knowledge graph based speech interface for question answering systems," Speech Communication, vol. 92, pp. 1-12, 2017.
30. B. Liang, N. Chen, Y. Xie, R. Wang, and Y. Chen, "Grey Fault Detection Method Based on Context Knowledge Graph in Container Cloud Storage," in CCF Conference on Computer Supported Cooperative Work and Social Computing, 2019: Springer, pp. 65-80.
31. H. Huang, Y. Chen, B. Lou, Z. Hongzhou, J. Wu, and K. Yan, "Constructing Knowledge Graph from Big Data of Smart Grids," in 2019 10th International Conference on Information Technology in Medicine and Education (ITME), 2019: IEEE, pp. 637-641.
32. Q. Wang, Z. Mao, B. Wang, and L. Guo, "Knowledge graph embedding: A survey of approaches and applications," IEEE Transactions on Knowledge and Data Engineering, vol. 29, no. 12, pp. 2724-2743, 2017.
33. Y. Chi, C. Yu, X. Qi, and H. Xu, "Knowledge Management in Healthcare Sustainability: A Smart Healthy Diet Assistant in Traditional Chinese Medicine Culture," Sustainability, vol. 10, no. 11, p. 4197, 2018.
34. J. Webber, "A programmatic introduction to neo4j," in Proceedings of the 3rd annual conference on Systems, programming, and applications: software for humanity,2012, pp. 217-218.
35. Y. Luan, L. He, M. Ostendorf, and H. Hajishirzi, "Multi-task identification of entities,relations, and coreference for scientific knowledge graph construction," arXiv preprint arXiv:1808.09602, 2018.