在半導體產業中持續改進產品良率是公司關鍵的問題之一，如何定義明確的問題與智能化線上監控也是必要的。基於預防大於治療的理念，監控設備參數的狀態能夠有效的避免生產製程偏差的產品。針對即時蒐集的設備參數，運用線上模型結合閘門循環單元網路執行預測與利用歷史參數資料建立的目標基準線兩者進行距離計算，並且利用兩階段監控能達到完善的預警效果。結合線上監控與累積和管制圖，提出一套持續更新流程，達到最後理想概念飄移中持續更新機制，改善產線對於品質管控與生產能力的穩定性。

Continuous improvement of product yield in the semiconductor industry is one of the company's key issues. How to define clear problems and intelligent online monitoring is also necessary. Based on the concept of prevention greater than treatment, monitoring the state of equipment parameters can effectively avoid products with manufacturing process deviations. For the equipment parameters collected in real time, the online model is used to calculate the distance between the network of the gate loop unit and the target baseline established by using the historical parameter data, and the two-stage monitoring can achieve perfect warning effect. Combined with online monitoring and accumulation and control charts, a continuous update process is proposed to achieve a continuous update mechanism in the final ideal concept drift, and to improve the stability of the production line for quality control and production capacity.

參考文獻
Altman, N. S. (1992). "An introduction to kernel and nearest-neighbor nonparametric regression." The American Statistician 46(3): 175-185.

Chapman, P., et al. (2000). "CRISP-DM 1.0: Step-by-step data mining guide." SPSS inc 16.

Cho, K., et al. (2014). "Learning phrase representations using RNN encoder-decoder for statistical machine translation." arXiv preprint arXiv:1406.1078.

Christopher Olah, Understanding LSTM Networks (2015), accessed 24 June 2019.
http://colah.github.io/posts/2015-08-Understanding-LSTMs/

Dreiseitl, S. and L. Ohno-Machado (2002). "Logistic regression and artificial neural network classification models: a methodology review." Journal of biomedical informatics 35(5-6): 352-359.

Gama, J., et al. (2014). "A survey on concept drift adaptation." ACM computing surveys (CSUR) 46(4): 44.

HAWKINS, D. M. (1993). "Cumulative sum control charting: an underutilized SPC tool." Quality Engineering 5(3): 463-477.

Hochreiter, S. and J. Schmidhuber (1997). "Long short-term memory." Neural computation 9(8): 1735-1780.

Jensen, W. A., et al. (2006). "Effects of parameter estimation on control chart properties: a literature review." Journal of Quality Technology 38(4): 349-364.

Jones, E. C., et al. (2010). "A framework for effective Six Sigma implementation." Total quality management 21(4): 415-424.

Jang, Bo-Kai, Chia-Yen Lee, (2018). Quality System Implementation of Machine Tool using Data Mining and Statistical Quality Control Methods.

Kotsiantis, S. B., et al. (2007). "Supervised machine learning: A review of classification techniques." Emerging artificial intelligence applications in computer engineering 160: 3-24.

Montgomery, D. C. (2007). Introduction to statistical quality control, John Wiley & Sons.

O'Loughlin, R. C. (2006). "Antitrust or Antitrade-Self-Assessment of Market Share Chills the Incentive to License Nanotechnology Patents in the European Union." Washburn LJ 46: 345.

Page, E. S. (1954). "Continuous inspection schemes." Biometrika 41(1/2): 100-115.

Pyzdek, T. (2003). "The six sigma." McGrow-Hill, New York.

Tague, N. R. (2005). The quality toolbox, ASQ Quality Press Milwaukee, WI.

Žliobaitė, I., et al. (2016). An overview of concept drift applications. Big data analysis: new algorithms for a new society, Springer: 91-114.