(52.91.185.49) 您好!臺灣時間:2018/12/11 12:07
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
本論文永久網址: 
line
研究生:陳韋儒
研究生(外文):Wei-Ru Chen
論文名稱:基於注意力機制長短期記憶深度學習 之機器剩餘可用壽命預估
論文名稱(外文):Attention-based Long Short-Term Memory Deep Learning for Estimating Machinery Remaining Useful Life
指導教授:江振瑞江振瑞引用關係
指導教授(外文):Jehn-Ruey Jiang
學位類別:碩士
校院名稱:國立中央大學
系所名稱:資訊工程學系
學門:工程學門
學類:電資工程學類
論文出版年:2018
畢業學年度:106
語文別:中文
論文頁數:48
中文關鍵詞:智慧工廠剩餘可用壽命深度學習遞歸神經網路長短期記憶注意力機制
外文關鍵詞:Smart FactoryRemaining Useful LifeDeep LearningRecurrent Neural NetworkLong Short Term MemoryAttention-based Mechanism
相關次數:
  • 被引用被引用:0
  • 點閱點閱:19
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
受到德國工業4.0概念的影響,各大製造業為了保有競爭力,紛紛往「智慧化」生產的腳步邁進。利用產線的互聯網化,收集大量數據,再透過數據分析,達到自動調整生產流程、能源管理智慧化、預測需求以降低庫存及預測機械故障等目標、進而以最有效率的方式製造彈性乃至即時的客製化產品。本篇論文著重於預測機器剩餘可用壽命(Remaining Useful Life, RUL),屬於機器預診斷的一環,是一種新的維運策略思維,透過生產製造過程中所產生的巨量資料進行分析,再進行分析預測,以利提前替換或維修,避免設備在運作的過程中突然停止,導致生命或財產的損失。
本篇論文利用遞歸神經網路(Recurrent Neural Network, RNN)深度學習(Deep Learning)方法,預估機器的剩餘可用壽命。並利用長短期記憶(Long Short-Term Memory, LSTM)模型,再加入基於注意力機制,對特別導致損壞的因子進行加權,使其更能萃取時間序列資料的特徵,達到精確預測機器的剩餘可用壽命。
我們以NASA所提供的C-MAPSS(Commercial Modular Aero-Propulsion System Simulation)資料集為實驗案例,以所提的方法預估飛機渦輪引擎的剩餘壽命,並以參考文獻中的各種方法如MLP、SVR、RVR和CNN、Stack LSTM為比較對象。實驗顯示,在均方根差(Root Mean Squared Error, RMSE)或是資料集本身定義的Scoring Function的評分準則下,所提的方法有最佳的預測能力。
Influenced by the revolutionary concept of German Industry 4.0, major manufacturing industries have been moving from automatic production into smart production for maintaining their competitiveness. Industry 4.0 advocates smart factories that use Internet-enabled assembly lines to collect large amounts of data and then through data analysis to achieve the goals of smartly adjusting production processes, intelligently saving energy, precisely forecasting customer demands, and accurately predicting mechanical failures. In general, smart factories can yield flexible and even customized products in the most efficient way. This paper focuses on estimating machine remaining useful life (RUL), which is a kind of the machine condition pre-diagnosis. By accurate RUL estimation, we can perform predictive maintenance, instead of preventive maintenance, to avoid sudden breakdown of machines/components during the operation process to prevent huge loss.

This paper proposes a Recurrent Neural Network (RNN) deep learning method to estimate the remaining useful life of machines, especially the aero-propulsion engines. The proposed method uses the Long Short-Term Memory (LSTM) model with the attention-based (AB) mechanism. The LSTM model is useful for extracting relationship between time-series data items that are far separated, and the AB mechanism can help emphasize different factors that affect the RUL in different time. The NASA C-MAPSS (Commercial Modular Aero-Propulsion System Simulation) dataset is taken to evaluate the URL estimation accuracy of the propose method. The evaluated results are compared with those of related methods, namely the MLP, SVR, RVR, CNN, Stack LSTM methods. Comparisons show that the proposed method is superior to the others in terms of the scoring function value defined by the C-MAPSS dataset, and the Root Mean Squared Error (RMSE) .
中文摘要 I
Abstract II
目錄 IV
圖目錄 V
表目錄 VI
一、緒論 1
1-1研究背景與動機 1
1-2研究目的與貢獻 2
1-3論文架構 2
二、背景知識 3
2-1神經網路(Artificial Neural Network, ANN) 3
2-1-1神經網路簡介 3
2-1-2神經網路的架構 4
2-1-3神經網路的學習方式 5
2-1-4倒傳遞學習演算法(Back-Propagation Algorithm) 6
2-2深度學習(Deep Learning) 8
2-2-1深度學習簡介 8
2-2-2遞歸神經網路(Recurrent Neural Network, RNN) 9
2-2-3長短期記憶(Long Short-Term Memory, LSTM) 10
2-2-4注意力機制(Attention Mechanism) 13
三、問題定義與研究 16
3-1問題定義 16
3-2文獻研究 19
四、研究方法 21
4-1資料前處理 21
4-1-1標籤定義 21
4-1-2資料標準化 22
4-2網路架構 24
五、實驗與分析 28
5-1實驗環境 28
5-2實驗結果 28
六、結論與未來展望 35
參考文獻 36
[1] Lee, E. A. (2008, May). Cyber physical systems: Design challenges. In Object oriented real-time distributed computing (isorc), 2008 11th ieee international symposium on (pp. 363-369). IEEE.
[2] Mitchell, Tom M. "Machine learning. 1997." Burr Ridge, IL: McGraw Hill 45.37 (1997): 870-877.
[3] Rosenblatt, Frank. "The perceptron: a probabilistic model for information storage and organization in the brain." Psychological review 65.6 (1958): 386.
[4] Rumelhart, David E., Geoffrey E. Hinton, and Ronald J. Williams. "Learning representations by back-propagating errors." nature323.6088 (1986): 533.
[5] Understanding LSTM Networks:
http://colah.github.io/posts/2015-08-Understanding-LSTMs/.
[6] Hochreiter, Sepp, and Jürgen Schmidhuber. "Long short-term memory." Neural computation 9.8 (1997): 1735-1780.
[7] Xu, Kelvin, et al. "Show, attend and tell: Neural image caption generation with visual attention." International Conference on Machine Learning. 2015.
[8] Saxena, Abhinav, et al. "Damage propagation modeling for aircraft engine run-to-failure simulation." Prognostics and Health Management, 2008. PHM 2008. International Conference on. IEEE, 2008.
[9] Wang, P., Youn, B.D., Hu, C., “A generic probabilistic framework for structural health prognostics and uncertainty management”, Mech. Syst. Sig. Process. 28,
622–637 (2012).
[10] T. Wang, J. Yu, D. Siegel, J. Lee, “A similarity-based prognostics approach for remaining useful life estimation of engineered systems”, in: Proceedings of the IEEE International Conference on Prognostics and Health Management(2008).
[11] Babu, Giduthuri Sateesh, Peilin Zhao, and Xiao-Li Li. "Deep convolutional neural network based regression approach for estimation of remaining useful life." International conference on database systems for advanced applications. Springer, Cham, 2016.
[12] Chang, C.C., Lin, C.J., “LIBSVM: a library for support vector machines”, ACM Trans. Intell. Syst. Technol. 2, 27:1–27:27 (2011).
[13] Tipping, M.E., “The relevance vector machine”, in Solla, S.A., Leen, T.K., Muller, K.R. (eds.) Advances in Neural Information Processing Systems, vol. 12, pp. 652–658. MIT Press, Cambridge (2000).
[14] Che-Sheng Hsu and Jehn-Ruey Jiang, "Remaining Useful Life Estimation Using Long Short-Term Memory Deep Learning," IEEE International Conference on Applied System Innovation 2018 (IEEE ICASI 2018), 2018.
[15] Heimes, Felix O. "Recurrent neural networks for remaining useful life estimation." Prognostics and Health Management, 2008. PHM 2008. International Conference on. IEEE, 2008.
[16] Bengio, Yoshua. "Practical recommendations for gradient-based training of deep architectures." Neural networks: Tricks of the trade. Springer, Berlin, Heidelberg, 2012. 437-478.
[17] Neural Networks for Machine Learning: https://zh-tw.coursera.org/learn/neural-networks.
[18] Duchi, J., Hazan, E., & Singer, Y., “Adaptive Subgradient Methods for Online Learning and Stochastic Optimization”, Journal of Machine Learning Research, 12, 2121–2159, 2011
[19] Opitz, David W., and Richard Maclin. "Popular ensemble methods: An empirical study." J. Artif. Intell. Res.(JAIR) 11 (1999): 169-198.
[20] Keras Documentation: https://keras.io/.
電子全文 電子全文(網際網路公開日期:20190801)
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔