簡易檢索 / 詳目顯示

回結果列表
研究生： 張馨云
Chang, Hsin-Yun
論文名稱： 具螺絲模具使用壽命預測功能之智慧倉儲管理系統
An Intelligent Warehouse Management System with the Function of Screw Molds Useful Lifetime Prediction
指導教授： 蔡佩璇
Tsai, Pei-Hsuan
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 製造資訊與系統研究所
Institute of Manufacturing Information and Systems
論文出版年： 2021
畢業學年度： 109
語文別： 中文
論文頁數： 50
中文關鍵詞： 智慧倉儲系統 、預防性維護 、K-近鄰演算法 、剩餘使用壽命預測
外文關鍵詞： Intelligent Manufacturing System, Preventive Maintenance, K-Nearest Neighbor, Remaining Useful Lifetime Prediction
相關次數： 點閱：102  下載：31 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 隨著資訊科技的發展，工業4.0是現今頗受關注的議題。然而仍有許多傳統產業尚未將新興科技的應用加入工廠管理中，對於製造流程中的工具零件之管理與維修處理方式，仍是使用傳統的倉儲管理以及矯正性維修(corrective maintenance)方法。工件的倉儲管理多半只記錄庫存資料，顯少進行生產歷程的資料記錄。當工件發生故障或受損而異常停擺時，才會進而採取相對應的處理。然而此一維修處理方式時常會造成無預警的停機狀況，以及非必要的損失。因此透過智慧倉儲系統的應用，進行工件生產歷程的資料記錄，得以用於工件剩餘使用壽命預測。透過提前預知工件可能的損壞時點，提早給予預防性處理，即可有效降低無預警故障而造成的損失，為預防性維護(preventive maintenance)方法的一種。
    本論文以台灣螺絲產業為主要研究對象，針對螺絲模具管理進行智慧倉儲系統的設計以及剩餘使用壽命的預測。台灣螺絲產業在國際上具有高市佔率，每年出口的螺絲數量及種類為全球產業中的冠軍。每一種螺絲有著不同特徵，並需要使用各式不同的螺絲模具進行製造。由此可知一間螺絲製造廠內的螺絲模具的種類其數量非常多，若不善管理則會增加人力以及製造成本的損失。本論文透過針對螺絲模具設計的資料庫結構進行生產歷程的資料蒐集，且運用K-近鄰演算法(K-Nearest Neighbor, kNN)進行剩餘使用壽命的預測。管理者可依據預測結果進行模具派工以及換模排程規劃，避免模具無預警損壞所造成生產成本的提升。

    This paper focuses on improving intelligent warehouse management system (IWMS) and remaining useful lifetime (RUL) prediction of screw molds to support screw industry usage. Taiwan’s screw industry is the lead of the screw market, the type and quantity of screws are the largest. Due to the great amount of molds in the screw factory, without proper management, the cost of human resources and manufacturing might keep getting higher.
    Through the design of IWMS for screw mold management and the RUL prediction with K-Nearest Neighbor (kNN) model, it is able for screw factories to perform mold dispatching and mold changing scheduling. In this paper, all tested data are from a Taiwanese screw factory. Features for RUL prediction are suggested by the senior staff in the cooperated screw factory. Selected features are being compared with one another for rating the importance for RUL prediction.
    The design of IWMS includes hardware and software systems, both are based on the needs of screw mold management. As for the result of screw mold RUL prediction, the accuracy does not perform as well as expected. The reason is that the selected features are not relevant enough for prediction. However, the prediction result that is one standard deviation less than the ground truth, can still be used for mold changing scheduling. The feature comparison result shows different opinion from the screw factory, the main related feature is mold supplier. Therefore, the factory should focus more on selecting mold suppliers for better quality.

    摘要 I SUMMARY II 誌謝 VII 目錄 VIII 表目錄 XI 圖目錄 XII 第一章 緒論 1 1.1 研究動機與目的 1 1.2 研究問題 3 1.2.1 儲存位置管理 4 1.2.2 可重複使用模具之獨立辨識 4 1.2.3 模具使用歷程紀錄 4 1.2.4 模具剩餘使用壽命預測 5 1.3 研究方法 5 1.3.1 螺絲模具智慧櫃 5 1.3.2 螺絲模具資料庫 5 1.3.3 螺絲模具剩餘使用壽命預測 6 第二章 文獻探討 8 2.1 螺絲模具智慧櫃 8 2.1.1 倉儲系統硬體架構 8 2.1.2 智慧倉儲系統硬體架構 9 2.1.3 智慧藥盒硬體架構 10 2.1.4 無人商店硬體架構 11 2.2 螺絲模具資料庫 13 2.2.1 倉儲系統軟體架構 13 2.2.2 智慧倉儲系統軟體架構 14 2.2.3 智慧藥盒軟體架構 14 2.2.4 無人商店軟體架構 15 2.3 螺絲模具剩餘使用壽命預測 15 2.3.1 機器學習 15 第三章 螺絲模具智慧櫃系統之硬體結構 17 3.1 儲存 20 3.2 辨識 20 3.3 提示 20 3.4 環境控制 21 第四章 螺絲模具智慧櫃系統之資料庫結構 22 4.1 管理系統之資料庫 22 4.2 儲位管理 26 4.3 模具派工與排程規劃 27 第五章 螺絲模具剩餘使用壽命預測 28 5.1 資料前處理 28 5.1.1 填補遺漏值 29 5.1.2 類別資料處理 29 5.1.3 資料特徵縮放 29 5.1.4 離群值判別 30 5.2 特徵選取 31 5.2.1 主成分分析（Principal Component Analysis, PCA） 31 5.2.2 遺傳演算法（Genetic Algorithm, GA） 31 5.2.3 經驗法則 31 5.3 壽命預測實驗 32 5.3.1 資料切割 32 5.3.2 kNN演算法 33 5.3.3 實驗說明 33 5.4 特徵重要度比較 33 5.4.1 實驗說明 34 第六章 分析結果 35 6.1 實驗環境 35 6.2 實驗目標 35 6.3 實驗資料 35 6.3.1 螺絲模具使用歷程資料 35 6.3.2 離群值處理 37 6.4 壽命預測實驗結果 38 6.4.1 預測目標為M數未去除離群值的資料 38 6.4.2 預測目標為M數已去離群值的資料 39 6.4.3 預測目標為天數未去離群值的資料 39 6.4.4 預測目標為天數已去離群值的資料 40 6.4.5 結果比較 41 6.5 特徵重要度比較實驗結果 42 第七章 結論與建議 46 7.1 結論 46 7.2 給螺絲工廠的建議 46 7.3 未來研究 47 參考文獻 49

    [1] Harry K.H. Chow, King Lun Choy, W.B. Lee, K.C. Lau, "Design of a RFID case-based resource management system for warehouse operations," Expert Systems with Applications, vol. 30, no. 4, pp. 561-576, May 2006.
    [2] 謝晴媺, “ISO 29158直接烙印條碼檢測 不同光源選擇對條碼檢測的重要性,” GS1 Taiwan Report, pp. 18-19, 2018.
    [3] Adnan Nuhic, Tarik Terzimehic, Thomas Soczka-Guth, Michael Buchholz, Klaus Dietmayer, “Health diagnosis and remaining useful life prognostics of lithium-ion batteries using data-driven methods.,” Journal of Power Sources 239, pp. 680-688, 2013.
    [4] 周鴻文, "叡揚資訊," 13 April 2021. [Online]. Available: https://www.gss.com.tw/blog/離群值之簡介. [Accessed 10 May 2021].
    [5] Girish Chandrashekar, Ferat Sahin, "A survey on feature selection methods," Computers & Electrical Engineering, vol. 40, no. 1, pp. 16-28, January 2014.
    [6] L. Zhang, Z. Liu, D. Luo, J. Li and H. Huang, "Review of remaining useful life prediction using support vector machine for engineering assets," International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering (QR2MSE), pp. 1793-1799, 2013.
    [7] Mutijarsa, R. A. Nugrahaeni and K., “Comparative analysis of machine learning kNN, SVM, and random forests algorithm for facial expression classification,” 2016 International Seminar on Application for Technology of Information and Communication (ISemantic), pp. 163-168, 2016.
    [8] C. Moore, “Amazon might open 3000 cashier- free Amazon Go stores by 2021,” Digital Trends, 2018.
    [9] Tsai, P. H., T. Y. Chen, C. Y. Yu, C. S. Shih and J. W. S. Liu, “Smart Medication Dispenser: Design, Architecture and Implementation,” IEEE Systems Journal, vol. 5, no. 1, pp. 99-110, March 2011.
    [10] Tsai PH., Liu J.W.S., “Intelligent Tools for Reducing Medication Dispensing and Administration Error.,” Foundations of Health Information Engineering and Systems. FHIES 2013. Lecture Notes in Computer Science, vol 8315. Springer, pp. 1-21, 2013.
    [11] O. T. Chen, Y. C. Zhang, Z. K. Lin, P. Kuo and Y. L. Lee, “Camera-in-Hand Robotic Arm Using a Deep Neural Network to Realize Unmanned Store Service,” 2019 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech), pp. 833-839, 2019.
    [12] Landgrebe, S. R. Safavian and D., “A survey of decision tree classifier methodology,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 21, no. 3, pp. 660-674, May/Jun 1991.
    [13] T. Huang, "Medium," 21 Jun 2018. [Online]. Available: https://chih-sheng-huang821.medium.com/機器學習-kernel-函數-47c94095171. [Accessed 10 May 2021].
    [14] Garner, Jim; Scott, Logan, “Results of Data Matrix Barcode Testing for Field Applications,” U.S. Department of Energy Office of Scientific and Technical Information, United States: N. p., 2019.
    [15] García, S., Luengo, J., Herrera, F., Data Preprocessing in Data Mining, Berlin: Intelligent Systems Reference Library, vol. 72. Springer, 2015.
    [16] A. C., Outlier Analysis. In: Data Mining., Switzerland: Springer, Cham, 2015.
    [17] "Wikipedia," 22 March 2021. [Online]. Available: https://en.wikipedia.org/wiki/Box_plot. [Accessed 15 May 2021].
    [18] Rousseeuw, P.J.; Hubert, M., “ Robust statistics for outlier detection.,” Data Min. Know. Discov., pp. 73-79, Jan 2011.
    [19] 蘇高玄、陳至安、謝金山, “kNN 插補法其參數對遺漏值之影響,” Journal of Kao Yuan University Vol.20, No.1, pp. 101-107, 2014.
    [20] "Wikipedia," 23 May 2021. [Online]. Available: https://en.wikipedia.org/wiki/Principal_component_analysis. [Accessed 25 May 2021].
    [21] F. Busetti, "Genetic algorithms overview," 2001. [Online]. Available: http://www.aiinfinance.com/gaweb.pdf. [Accessed 20 May 2021].
    [22] "Wikipedia," 07 April 2021. [Online]. Available: https://en.wikipedia.org/wiki/Genetic_algorithm. [Accessed 10 May 2021].
    [23] "Wikipedia," 26 5 2021. [Online]. Available: https://en.wikipedia.org/wiki/K-nearest_neighbors_algorithm. [Accessed 15 6 2021].
    [24] Quansheng Kuang and Lei Zhao, “ A practical GPU based kNN algorithm,” In Proceedings of the Second Symposium on International Computer Science and Computational Technology (ISCSCT ’09) , pp. 151-155, December 2000.
    [25] L. B., Machine learning with R. 2nd ed., Birmingham: Packt Publishing, 2015.
    [26] "Wikipedia," [Online]. Available: https://en.wikipedia.org/wiki/Root-mean-square_deviation. [Accessed 25 May 2021].

    下載圖示 校內：立即公開
    校外：立即公開
    QR CODE