دورية أكاديمية
Incoming Work-In-Progress Prediction in Semiconductor Fabrication Foundry Using Long Short-Term Memory.
العنوان: | Incoming Work-In-Progress Prediction in Semiconductor Fabrication Foundry Using Long Short-Term Memory. |
---|---|
المؤلفون: | Tin TC; Faculty of Computer Science and Information Technology, Universiti Malaysia Sarawak, 94300 Kota Samarahan, Sarawak, Malaysia.; X-FAB Sarawak Sdn. Bhd., 1 Silicon Drive, Sama Jaya Free Industrial Zone, 93350 Kuching, Sarawak, Malaysia., Chiew KL; Faculty of Computer Science and Information Technology, Universiti Malaysia Sarawak, 94300 Kota Samarahan, Sarawak, Malaysia., Phang SC; X-FAB Sarawak Sdn. Bhd., 1 Silicon Drive, Sama Jaya Free Industrial Zone, 93350 Kuching, Sarawak, Malaysia., Sze SN; Faculty of Computer Science and Information Technology, Universiti Malaysia Sarawak, 94300 Kota Samarahan, Sarawak, Malaysia., Tan PS; X-FAB Sarawak Sdn. Bhd., 1 Silicon Drive, Sama Jaya Free Industrial Zone, 93350 Kuching, Sarawak, Malaysia. |
المصدر: | Computational intelligence and neuroscience [Comput Intell Neurosci] 2019 Jan 02; Vol. 2019, pp. 8729367. Date of Electronic Publication: 2019 Jan 02 (Print Publication: 2019). |
نوع المنشور: | Journal Article |
اللغة: | English |
بيانات الدورية: | Publisher: Hindawi Pub. Corp Country of Publication: United States NLM ID: 101279357 Publication Model: eCollection Cited Medium: Internet ISSN: 1687-5273 (Electronic) NLM ISO Abbreviation: Comput Intell Neurosci Subsets: MEDLINE |
أسماء مطبوعة: | Original Publication: New York, NY : Hindawi Pub. Corp. |
مواضيع طبية MeSH: | Machine Learning* , Neural Networks, Computer*, Memory, Long-Term/*physiology , Memory, Short-Term/*physiology, Forecasting ; Reproducibility of Results ; Semiconductors ; Time Factors |
مستخلص: | Preventive maintenance activities require a tool to be offline for long hour in order to perform the prescribed maintenance activities. Although preventive maintenance is crucial to ensure operational reliability and efficiency of the tool, long hour of preventive maintenance activities increases the cycle time of the semiconductor fabrication foundry (Fab). Therefore, this activity is usually performed when the incoming Work-in-Progress to the equipment is forecasted to be low. The current statistical forecasting approach has low accuracy because it lacks the ability to capture the time-dependent behavior of the Work-in-Progress. In this paper, we present a forecasting model that utilizes machine learning method to forecast the incoming Work-In-Progress. Specifically, our proposed model uses LSTM to forecast multistep ahead incoming Work-in-Progress prediction to an equipment group. The proposed model's prediction results were compared with the results of the current statistical forecasting method of the Fab. The experimental results demonstrated that the proposed model performed better than the statistical forecasting method in both hit rate and Pearson's correlation coefficient, r . |
References: | Science. 2006 Jul 28;313(5786):504-7. (PMID: 16873662) IEEE Trans Pattern Anal Mach Intell. 2013 Aug;35(8):1930-43. (PMID: 23787345) Neural Comput. 1997 Nov 15;9(8):1735-80. (PMID: 9377276) |
تواريخ الأحداث: | Date Created: 20190206 Date Completed: 20190412 Latest Revision: 20200225 |
رمز التحديث: | 20240628 |
مُعرف محوري في PubMed: | PMC6334351 |
DOI: | 10.1155/2019/8729367 |
PMID: | 30719036 |
قاعدة البيانات: | MEDLINE |
تدمد: | 1687-5273 |
---|---|
DOI: | 10.1155/2019/8729367 |