Stream analytics and adaptive windows for operational mode identification of time-varying industrial systems

Name: Stream analytics and adaptive windows for operational mode identification of time-varying industrial systems
Author: Khodabakhsh, Athar, Arı, İsmail, Bakır, M., Alagoz, S. M.

İsim	Stream analytics and adaptive windows for operational mode identification of time-varying industrial systems
Yazar	Khodabakhsh, Athar, Arı, İsmail, Bakır, M., Alagoz, S. M.
Basım Tarihi:	2018-09-07
Basım Yeri	- IEEE
Konu	Operational mode identification, Sensor, Linear regression, Stream data, Adaptive window, Outlier detection
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	978-1-5386-7232-7
Kayıt Numarası	995a4e6a-5d20-4e04-8e1d-28f6c417b51a
Lokasyon	Computer Science
Tarih	2018-09-07
Notlar	TUPRAS
Örnek Metin	It is necessary to develop accurate, yet simple and efficient models that can be used with high-speed industrial data streams. In this paper, we develop a mode identification technique using stream analytics and show that it may be more effective than batch models, especially for time-varying systems. These industrial systems continuously monitor hundreds of sensors, but the relationships among variables change over time, which are identified as different operational modes. To detect drifts among modes, predictive modeling techniques such as regression analysis, K-means and DBSCAN clustering are used over sensor data streams from an oil refinery and models are updated in real-time using window-based analysis. Finally, an adaptive window size tuning approach based on the TCP congestion control algorithm is discussed, which reduces model update costs as well as prediction errors.
DOI	10.1109/BigDataCongress.2018.00042

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Stream analytics and adaptive windows for operational mode identification of time-varying industrial systems

Yazar Khodabakhsh, Athar, Arı, İsmail, Bakır, M., Alagoz, S. M.

Basım Tarihi 2018-09-07

Basım Yeri - IEEE

Konu Operational mode identification, Sensor, Linear regression, Stream data, Adaptive window, Outlier detection

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 978-1-5386-7232-7

Kayıt Numarası 995a4e6a-5d20-4e04-8e1d-28f6c417b51a

Lokasyon Computer Science

Tarih 2018-09-07

Notlar TUPRAS

Örnek Metin It is necessary to develop accurate, yet simple and efficient models that can be used with high-speed industrial data streams. In this paper, we develop a mode identification technique using stream analytics and show that it may be more effective than batch models, especially for time-varying systems. These industrial systems continuously monitor hundreds of sensors, but the relationships among variables change over time, which are identified as different operational modes. To detect drifts among modes, predictive modeling techniques such as regression analysis, K-means and DBSCAN clustering are used over sensor data streams from an oil refinery and models are updated in real-time using window-based analysis. Finally, an adaptive window size tuning approach based on the TCP congestion control algorithm is discussed, which reduces model update costs as well as prediction errors.

DOI 10.1109/BigDataCongress.2018.00042