臺灣博碩士論文加值系統

售後服務的目標為維持或維護產品機能，而執行售服異常診斷所需知識有兩種來源，一者來自產品的本質，包括外觀、材質與功能等；另一種則來自產品的使用歷程，包含正常衰退和異常損耗。傳統上是以定期維護來發現異常並保持機能，但維護的內容仍可因機台使用歷程而異，且無法定義明確的整體因果。因此，建立可隨工作記載歷程並推估異常程度之知識結構與架構，方可提供即時的機台保修知識。由於機台表現乃由其本質與使用歷程綜合形成，故本研究提出一種本體架構，用以表述機台元件間之本質關聯，並可累計使用歷程之影響，未來可再以深度學習之方法求出單一機件受多重因素於產品表現之影響，藉此建構可推估機構異常之架構。

The purpose of service maintenance is to sustain the functionality of the mechanism, thus the knowledge required for fault diagnosis should include the product’s innate characters and its operational history. The characters will determine the performance upper limit while the history could lower it unevenly. Traditionally, a service check is planned according to the duration of usage, but the time defined is more by experiences and the causes of defects were unable to trace in an overall manner. It is believed that a knowledge structure that outlined part relationships and kept work history in parallel will provide a more explicit picture to depict the cause and effect. In this research, an ontology-based knowledge structure is defined to capture part connections and their operational history, and then to apply deep learning to reveal the influences from the adjacent components to a certain part. The outcome will provide closer predictions of part degeneration on a smart machine.

摘要...i
Abstract...ii
誌謝...iii
目錄...iv
表目錄...vi
圖目錄...vii
第一章 緒論...1
1.1研究背景...1
1.2研究動機...1
1.3研究目的...2
1.4 研究限制...2
1.5 章節描述...3
第二章 文獻探討...4
2.1 本體結構...4
2.1.1本體論的概念...4
2.1.2本體論組成要素...4
2.1.3本體論的相關應用...5
2.2 智慧系統...7
2.2.1智慧系統的介紹...7
2.2.2 智慧系統的應用...8
2.3 智慧服務...9
2.4 深度學習...10
2.4.1深度學習的介紹...10
2.4.2深度學習的應用...11
2.5 文獻總結...12
第三章 研究方法...14
3.1 研究概述...14
3.2 基礎相鄰層...17
3.3 機能本質層...19
3.4 操作歷程層...22
3.5 第二、三層和損壞結果的因果關係...24
第四章 實驗結果...26
4.1系統設備規格...26
4.2異常推理架構之開發...26
4.3實作範例...27
4.4結果分析...35
第五章 結論與建議...36
5.1結論與貢獻...36
5.2未來展望...36
參考文獻...38
Extended Abstract...41

Chen, F., Lu, C., Wu, H. and Li, M., 2017, “A semantic similarity measure integrating multiple conceptual relationships for web service discovery”, Expert Systems with Applications, Vol. 67, pp. 19-31.
Ding, L. Y., Zhong, B. T. Wu, S. and Luo, H. B., 2016, “Construction risk knowledge management in BIM using ontology and semantic web technology”, Safety Science, Vol. 87, pp. 202-213.
Embriette, H., The importance of controlled ontology, available at https://riffyn.com/blog/the-importance-of-controlled-ontology, retrieved June 15, 2020.
Exner, K., Smolka, E., Blüher, T. and Stark, R., 2019, “A method to design Smart Services based on information categorization of industrial use cases”, Procedia CIRP, Vol. 83, pp. 77-82.
Farquhar, A., Fike, R. and Rice, J., 1997, “The Ontolingua Server: a tool for collaborative ontology construction”, International journal of human-computer studies, Vol. 46, no. 6, pp. 707-727.
Goodfellow, I., Bengio, Y. and Courville, A., 2016, Deep learning, The MIT Press, Cambridge, Massachusetts.
Gruber, T. R., 1993, “A translation approach to portable ontology specifications”, Knowledge acquisition, Vol. 5, no. 2, pp. 199-220.
Hagedorn, T. J., Smith, B., Krishnamurty, S. and Grosse, I., 2019, “Interoperability of disparate engineering domain ontologies using basic formal ontology”, Journal of engineering design, Vol. 30, no. 10-12, pp. 625-654.
Hendler, J. and Berners-Lee, T., 2001, “Publishing on the semantic web”, Nature (London), Vol. 410, no. 6832, pp. 1023-1024.
Hildebrandt, C., Kocher, A., Kustner, C., Lopez-Enriquez, C., Muller, A.W., Caesar, B., Gundlach, C.S. and Fay, A., 2020, “Ontology Building for Cyber-Physical Systems: Application in the Manufacturing Domain”, IEEE transactions on automation science and engineering, Vol. 17, no. 3, pp. 1266-1282.
Huang, C., Cai, H., Xu, L., Xu, B., Gu, Y. and Jiang, L., 2019, “Data-driven ontology generation and evolution towards intelligent service in manufacturing systems”, Future Generation Computer Systems, Vol. 101, pp. 197-207.
Itread, 2019, ”知識圖譜學習與實踐(5)——Protégé使用入門”, available at https://www.itread01.com/content/1564401843.html, retrieved July 07, 2019.
Keith, D. F., 2017, “A Brief History of Deep Learning”, available at：https://www.dataversity.net/brief-history-deep-learning/#, retrieved February 07, 2017.
Khan, Z.M.A., Saeidlou, S. and Saadat, M., 2019, “Ontology-based decision tree 10odel for prediction in a manufacturing network”. Production & manufacturing research, Vol. 7, no. 1, pp. 335-349.
Lee, K. B., Cheon, S. and Kim, C. O., 2017, “A convolutional neural network for fault classification and diagnosis in semiconductor manufacturing processes”. IEEE Transactions on Semiconductor Manufacturing, Vol. 30, no. 2, pp. 135-142.
Liu, D., Lai, X., Xiao, Z., Liu, D., Hu, X. and Zhang, P., 2020, " Fault diagnosis of rotating machinery based on convolutional neural network and singular value decomposition ", Shock and vibration, Vol. 2020, pp. 1-13.
Mabkhot, M.M., Amri, S.K., Darmoul, S., Al-Samhan, A.M. and Elkosantini, S., 2020, “An ontology-based multi-criteria decision support system to reconfigure manufacturing systems”, IISE transactions, Vol. 52, no. 1, pp. 18-42.
Qin, Y., Lu, W., Qi, Q., Liu, X., Huang, M., Scott, P. J. and Jiang, X., 2018, “Towards an ontology-supported case-based reasoning approach for computer-aided tolerance specification”, Knowledge-Based Systems, Vol. 141, pp. 129-147.
Shen, Y., Li, Y., Zheng, H., Tang, B. and Yang, M., 2019, “Enhancing ontology-driven diagnostic reasoning with a symptom-dependency-aware naïve bayes classifier”, BMC Bioinformatics, Vol. 20, no. 1, pp. 330-330.
Untoro, M. C., Sarno, R. and Ariyani, N. F., 2019, “Reusability ontology in business processes with similarity matching”, Jurnal Informatika (Universitas Ahmad Dahlan), Vol. 12, no. 1, pp. 9-16.
Uschold, M. and Gruninger, M., 1996, “Ontologies: principles, methods and applications”, Knowledge engineering review, Vol. 11, no. 2, pp. 93-136.
Wang, Z., 2019, “Research on design method of intelligent service system in product processing under PSS concept”, Procedia CIRP, Vol. 83, pp. 705-709.
Welty, C. and Guarino, N., 2001, “Supporting ontological analysis of taxonomic relationships”, Data & Knowledge Engineering, Vol. 39, no. 1, pp. 51-74.
Zhang, F., Zhou, Z., Liu, Q. and Xu, W., 2017, “An intelligent service matching method for mechanical equipment condition monitoring using the fibre bragg grating sensor network”, Enterprise Information Systems, Vol. 11, no. 2, pp. 284-309.
Zhang, Z., Cao, L., Chen, X., Tang, W., Xu, Z. and Meng, Y., 2020, “Representation learning of knowledge graphs with entity attributes”. IEEE Access, Vol. 8, pp. 7435-7441.
Zhou, Q., Yan, P., Liu, H. and Xin, Y., 2019, “A hybrid fault diagnosis method for mechanical components based on ontology and signal analysis”, Journal of intelligent manufacturing, Vol. 30, no. 4, pp. 1693-1715.
Zhu, J., Lai, C. and Sun, Y., 2019, “Fault mechanism analysis for manufacturing system based on catastrophe model”, Mathematical problems in engineering, Vol. 2019, pp. 1-11.
王文君，2004，「初探 Ontology」，台灣大學建築與城鄉研究所，取自 http://myweb.ncku.edu.tw/~ftlin/course/CAAD/CourseInformation/document/Ontology.pdf，參考日期：2004/7/24。
方國定，1997，中醫診斷於老年長期照護應用之研究：以本體論為基礎研究，國立雲林科技大學資訊管理系暨研究所，行政院國家科學委員會專題研究計畫。
周秉誼，2018，「淺談Deep Learning原理及應用」，國立臺灣大學計資中心電子報(C&INC E-News)，第0038期，取自http://www.cc.ntu.edu.tw/chinese/ epaper/ 0038/20160920_3805.html，參考日期：2018/5/30。