İNOVATİF MODEL BAZLI ARIZA ERKEN UYARI YAZILIMIYLA BEKLENMEDİK DURUŞLARA SON VERME

Yıl 2016, Cilt: 57 Sayı: 672, 44 - 49, 08.02.2016

Ahmet Duyar İzzet Y. İzzet Y. Önel Harun Özdemir

Öz

Bu çalışmada, Tüpraş Rafinerisi’nde Endüstriyel Büyük Veri’den faydalanarak beklenmedik duruşların ve arızalı operasyonun engellenerek üretim ve enerji verimliliğinin artırılmasından bahsedilmektedir. iMCM adlı arıza erken uyarı yazılımı, motor ve ekipmanları sürekli izleyerek gelişmekte olan
arızaları erkenden tespit edebilmektedir. iMCM yazılımı, analiz edeceği verileri rafineride bulunan
motor koruma cihazlarından çekebilmektedir. Böylece motor ve ekipmanları durdurmaya ve ekstra
bir montaja gerek kalmamaktadır. iMCM, kestirimci bakımın faydalarını bilen ama pahalı veya uygulamasını zor bulan firmalar için çok uygun bir çözümdür. iMCM, ekonomik, uygulaması ve kullanımı
kolay ve faydası yüksek bir inovasyondur.

Anahtar Kelimeler

Büyük veri, iMCM, kestirimci bakım, erken uyarı sistemi, endüstriyel internet

AN INNOVATIVE MODEL-BASED EARLY WARNING SOFTWARE TO PREVENT UNPLANNED DOWNTIMES

Öz

This paper presents the use of Industrial Big Data at Tupras Refinery to increase productivity and
energy efficiency by preventing unplanned down time and faulty operation of the equipment. Data obtained from existing protection devices are used through analytics included in software called iMCM.
It provides the user with condensed information needed about pending faults of equipment, time to
failure and suggested actions anytime and anywhere it is needed. Both its installation and its use are
simple without requiring hardware installation, new hardware, sensors, cabling, equipment shutdown
and visits to the site. Its simplicity and its ease of use makes it possible for many companies that have
been aware of the benefits of predictive maintenance, but had found it too complicated. Analytics,
which was previously developed for the Space Shuttle Main Engine, gas turbines and helicopter engines, for early warning of pending faults of industrial equipment is used. 

Anahtar Kelimeler

Big data, iMCM, predictive maintenance, early warning system, industrial internet

Kaynakça

• 1. Annunziata, M., Evans, C. P. 2013. The Industrial Internet@Work, General Electric Company,https://www.ge.com/sites/default/files/GE_IndustrialInternetatWork_WhitePaper_20131028.pdf, son erişim tarihi: 24 Aralık 2015.
• 2. US Department of Energy, Energy Efficiency and Renewable Energy, Motor Tip Sheet #5. 2005. “Replace V-Belts with Cogged or Synchronous Belt Drives,” https://www1.eere.energy.gov/manufacturing/tech_assistance/pdfs/replace_vbelts_motor_systemts5.pdf, son erişim tarihi: 24 Aralık 2015.
• 3. US Department of Energy, "Energy Efficiency and Renewable Energy," Motor Tip Sheet #2. 2000 “Eliminate Voltage Unbalance” http://www.nrel.gov/docs/fy13osti/56005.pdf, son erişim tarihi: Aralık 2015.
• 4. US Department of Energy. 2013. http://www1.eere.energy.gov/femp/program/operations_maintenance.html, son erişim tarihi: 24 Aralık 2015.
• 5. Duyar, A., Merrill, W. C. 1992. “Fault Diagnosis for the Space Shuttle Main Engine,” AIAA Journal of Guidance, Control and Dynamics, vol. 15, no. 2, p. 384-389.
• 6. Litt, J., Kurtkaya, M., Duyar, A. 1995. “Sensor Fault Detection and Diagnosis of the T700 Turboshaft Engine,” AIAA Journal of Guidance, Control and Dynamics, vol. 187, no. 3, p. 640-642.
• 7. Musgrave, J. L., Guo, T., Wong, E., Duyar, A. 1997. “Real-Time Accommodation of Actuator Faults on a Reusable Rocket Engine,” IEEE Transactions Control Systems. Technology, vol. 5, no. 1, p. 100-109.
• 8. Duyar, A., Eldem, V., Merrill, W. C., Guo, T. 1994. “Fault Detection and Diagnosis in Propulsion Systems: A Fault Parameter Estimation Approach,” AIAA Journal of Guidance, Control and Dynamics, vol. 17, no. 1, p. 104-108.
• 9. Duyar, A. 2011. “Simplifying Predictive Maintenance,” GE Orbit Magazine, vol. 31, no. 1, p. 38-45.