物聯網和人工智慧的快速發展為各個領域帶來卓越的改變。這些科技的發展促使了工業4.0的推進，工業4.0又稱為智慧製造，主要的目標是希望可以達成彈性化的自動生產程序。
在這篇論文中，我們利用真實產線的感測器數據來研究異常偵測分析，期望在產線的前期階段提早偵測到潛在的異常情形並提升準確率，以降低生產成本及減少生產時間。因為異常偵測的資料特性，異常的數據量相對於整體數據而言是非常有限的，除此之外，異常的表現情形往往並非一致，我們對此真實多變量感測時間序列資料提出了一個基於長短期記憶網路(LSTM)自動編碼器的非監督式的及時異常偵錯方法。在實驗中，其他作法僅能有約70%~85%的精確率和召回率，而我們所提出的方法則可以達到將近90%的準確度。

The emergence of IoT and AI has brought revolutionary change in various application domains. One of them is Industry 4.0, also called Smart Manufacturing, which aims to achieve highly flexible and automated production processes.
In this thesis, we study a use case of anomaly detection in smart manufacturing using the real data collected from the sensing devices of a factory production line. Our goal is to improve the anomaly detection accuracy at an earlier stage of production line, so that cost and time wasted by possible production failures can be reduced. To overcome the limited and irregular anomaly patterns found from our multivariate sensor dataset, we proposed an unsupervised real-time anomaly detection algorithm based on LSTM-based Auto-Encoder. Our evaluations show that our approach achieved almost 90\% accuracy for both precision and recall while other classification or regression based methods only reached 70%~85%.

[1] Bengio, Y., Simard, P., and Frasconi, P. Learning long-term dependencies
with gradient descent is difficult. IEEE Transactions on Neural Networks 5, 2
(March 1994), 157–166.
[2] Hochreiter, S. The vanishing gradient problem during learning recurrent neural
nets and problem solutions. International Journal of Uncertainty, Fuzziness
and Knowledge-Based Systems 6 (04 1998), 107–116.
[3] Hochreiter, S., and Schmidhuber, J. Long short-term memory. Neural computation 9 (12 1997), 1735–80.
[4] Kagermann, H., Lukas, W., and Wahlster, W. Industrie 4.0 - mit dem internet
der dinge auf dem weg zur 4. industriellen revolution. VDI Nachrichten (2011).
[5] Li, S., Xie, Y., Farajtabar, M., and Song, L. Detecting weak changes in dynamic events over networks. IEEE Transactions on Signal and Information
Processing over Networks PP (03 2016).
[6] Liu, H., Gegov, A., and Cocea, M. Rule-based systems: a granular computing
perspective. Granular Computing 1, 4 (Dec 2016), 259–274.
[7] Liu, J., Guo, J., Orlik, P., Shibata, M., Nakahara, D., Mii, S., and Takáč,
M. Anomaly detection in manufacturing systems using structured neural networks. In 2018 13th World Congress on Intelligent Control and Automation
(WCICA) (July 2018), pp. 175–180.
[8] Loganathan, G., Samarabandu, J., and Wang, X. Sequence to sequence pattern
learning algorithm for real-time anomaly detection in network traffic. In 2018
IEEE Canadian Conference on Electrical Computer Engineering (CCECE)
(May 2018), pp. 1–4.
[9] Lopez, F., Saez, M., Shao, Y., Balta, E. C., Moyne, J., Mao, Z. M., Barton, K.,
and Tilbury, D. Categorization of anomalies in smart manufacturing systems to
support the selection of detection mechanisms. IEEE Robotics and Automation
Letters 2, 4 (Oct 2017), 1885–1892.
[10] Lu, Y., Morris, K., and Frechette, S. Current standards landscape for smart
manufacturing systems. NIST: Gaitehrsburg 8107 (2016).
[11] Malhotra, P., Vig, L., Shroff, G., and Agarwal, P. Long short term memory
networks for anomaly detection in time series. In ESANN (2015).
25
[12] Orsenigo, C., and Vercellis, C. Combining discrete svm and fixed cardinality
warping distances for multivariate time series classification. Pattern Recogn.
43, 11 (Nov. 2010), 3787–3794.
[13] Pan, S. J., and Yang, Q. A survey on transfer learning. IEEE Transactions on
Knowledge and Data Engineering 22, 10 (Oct 2010), 1345–1359.
[14] Rakthanmanon, T., Campana, B., Mueen, A., Batista, G., Westover, B., Zhu,
Q., Zakaria, J., and Keogh, E. Searching and mining trillions of time series
subsequences under dynamic time warping. In Proceedings of the 18th ACM
SIGKDD International Conference on Knowledge Discovery and Data Mining
(New York, NY, USA, 2012), KDD ’12, ACM, pp. 262–270.
[15] Roy, J. Rule-based expert system for maritime anomaly detection, 2010.
[16] Seto, S., Zhang, W., and Zhou, Y. Multivariate time series classification using dynamic time warping template selection for human activity recognition.
In 2015 IEEE Symposium Series on Computational Intelligence (Dec 2015),
pp. 1399–1406.
[17] Shahid, N., Naqvi, I. H., and Qaisar, S. B. One-class support vector machines:
analysis of outlier detection for wireless sensor networks in harsh environments. Artificial Intelligence Review 43, 4 (Apr 2015), 515–563.
[18] Sutskever, I., Vinyals, O., and Le, Q. V. Sequence to sequence learning with
neural networks. CoRR abs/1409.3215 (2014).
[19] Tai, K. S., Socher, R., and Manning, C. D. Improved semantic representations
from tree-structured long short-term memory networks. In Proceedings of the
53rd Annual Meeting of the Association for Computational Linguistics and the
7th International Joint Conference on Natural Language Processing (Volume
1: Long Papers) (Beijing, China, July 2015), Association for Computational
Linguistics, pp. 1556–1566.
[20] Wang, K.-S., Li, Z., Braaten, J., and Yu, Q. Interpretation and compensation of
backlash error data in machine centers for intelligent predictive maintenance
using anns. Advances in Manufacturing 3, 2 (Jun 2015), 97–104.
[21] Wong, W.-K., Moore, A., Cooper, G., and Wagner, M. Rule-based anomaly
pattern detection for detecting disease outbreaks. In Eighteenth National Conference on Artificial Intelligence (Menlo Park, CA, USA, 2002), American
Association for Artificial Intelligence, pp. 217–223.
[22] Zheng, Y., Liu, Q., Chen, E., Ge, Y., and Zhao, J. L. Time series classification
using multi-channels deep convolutional neural networks. In Web-Age Information Management (Cham, 2014), F. Li, G. Li, S.-w. Hwang, B. Yao, and
Z. Zhang, Eds., Springer International Publishing, pp. 298–310.