INSTITUTE OF INFORMATION AND COMMUNICATION TECHNOLOGIES BULGARIAN ACADEMY
INSTITUTE OF INFORMATION AND COMMUNICATION TECHNOLOGIES BULGARIAN ACADEMY OF SCIENCE Intelligent Systems Department http: //www. iict. bas. bg/IS/en/index. html Assoc. Prof. Ph. D Lyubka Doukovska 10/2/2020 ACom. In: Advanced Computing for Innovation 1 http: //www. iict. bas. bg/acomin
DIAGNOSTIC AND RISK ASSESSMENT PREDICTIVE ASSET MAINTENANCE The DVU-10 -0267/10 is a project of the Institute of Information and Communication Technologies, Bulgarian Academy of Sciences 10/2/2020 ACom. In: Advanced Computing for Innovation 2 http: //www. iict. bas. bg
• The goal of the project is a holistic research of theoretical foundations, alternative algorithms, software and techniques for predictive asset maintenance. This includes prognosis diagnostics, risk assessment, decision making for preventive or corrective actions and generating a schedule for their execution. 10/2/2020 ACom. In: Advanced Computing for Innovation 3 http: //www. iict. bas. bg
• The subject of analysis is a device from Maritsa East 2 thermal power plant - a mill fan. The choice of the given power plant is not occasional. This is the largest thermal power plant on the Balkan Peninsula. 10/2/2020 ACom. In: Advanced Computing for Innovation 4 http: //www. iict. bas. bg
10/2/2020 ACom. In: Advanced Computing for Innovation 5 http: //www. iict. bas. bg
• Mill fans are main part of the fuel preparation in the coal fired power plants. The mill fans are used to mill, dry and feed the coal to the burners of the furnace chamber. They are together milling and transporting devices. Mill fans are most often used for power plants burning brown and lignite coal. 10/2/2020 ACom. In: Advanced Computing for Innovation 6 http: //www. iict. bas. bg
10/2/2020 ACom. In: Advanced Computing for Innovation 7 http: //www. iict. bas. bg
1 — rotor; 2 — body; 3 — separator; 4 — internal circulation duct; 5 — maintenance and control flap; 6 — duct for bigger fraction recirculation; 7 — dust quality control flap. Mill Fan 10/2/2020 ACom. In: Advanced Computing for Innovation 8 http: //www. iict. bas. bg
The boiler which milling system is studied is a Benson type oncethough sub-critical boiler. There are four mills per boiler. Each mill fan system has four radial bearings – two in the mill and two in the motor. Boiler Ep-690 -15, 4 -540 LT 10/2/2020 ACom. In: Advanced Computing for Innovation 9 http: //www. iict. bas. bg
• The Maritsa East 2 thermal power plant has four double blocks with direct-current boilers 175 MW each and four monoblocks with drum boilers 210 MW each. • The fuel for both types of blocks is one and the same, low-quality Bulgarian lignite coal from the “Trayanovo 1” and “Trayanovo 2” mines. 10/2/2020 ACom. In: Advanced Computing for Innovation 10 http: //www. iict. bas. bg
Maritsa East 2 Unit 1 Control Room 10/2/2020 ACom. In: Advanced Computing for Innovation 11 http: //www. iict. bas. bg
• Standard statistical and probabilistic (Bayesian) approaches for diagnostics are inapplicable to estimate mill fan vibration state due to non-stationarity, non-ergodicity and the significant noise level of the monitored vibrations. 10/2/2020 ACom. In: Advanced Computing for Innovation 12 http: //www. iict. bas. bg
List of papers • Koprinkova-Hristova P. , M. Hadjiski, L. Doukovska, S. Beloreshki - Recurrent Neural Networks for Predictive Maintenance of Mill Fan Systems, International Journal of Electronics and Telecommunications (JET), Versita, Warsaw, Poland, vol. 57, № 3, ISSN 0867 -6747, pp. 401406, 2011. • Balabanov T. , Koprinkova-Hristova P. , L. Doukovska, M. Hadjiski, S. Beloreshki - Neural Network Model of Mill-Fan System Elements Vibration for Predictive Maintenance, Proc. of the International Symposium on Innovations in Intelligent Sys. Tems and Applications, INISTA’ 11, 15 -18 June 2011, Istanbul, Turkey, ISBN: 978 -1 -61284 -920 -1, pp. 410 -414, 2011. 10/2/2020 ACom. In: Advanced Computing for Innovation 13 http: //www. iict. bas. bg
List of papers • Doukovska L. , P. Koprinkova-Hristova, S. Beloreshki - Analysis of Mill Fan System for Predictive Maintenance, Proc. of the International Conference Automatics and Informatics, 3 -7 October 2011, Sofia, Bulgaria, ISSN 1313 -1869, pp. 331 -335, 2011. • Hadjiski M. , L. Doukovska, St. Kojnov - Nonlinear Trend Analysis of Mill Fan System Vibrations for Predictive Maintenance and Diagnostics, International Journal of Electronics and Telecommunications (JET), Versita, Warsaw, Poland, ISSN 0867 -6747, vol. 58, 4, pp. 351356, DOI: 10. 2478/v 10177 -012 -0048 -9, 2012. 10/2/2020 ACom. In: Advanced Computing for Innovation 14 http: //www. iict. bas. bg
List of papers • Hadjiski M. , L. Doukovska, P. Koprinkova-Hristova - Intelligent Diagnostic on Mill Fan System, Proc. of the 6 th IEEE International Conference on Intelligent Systems – IS’ 12, 6 -8 September 2012, Sofia, Bulgaria, ISBN 978 -1 -4673 -2782 -4, pp. 341 -346, 2012. • Nikov V. , P. Koprinkova-Hristova, L. Doukovska - Fuzzy Methods for Mill Fan Systems Technical Diagnostics, Proc. of the Federated Conference on Computer Science and Information Systems - Fed. CSIS’ 12, 9 -12 September 2012, Wroclaw, Poland, ISBN 978 -83 -60810 -51 -4, CD, pp. 139 -143, 2012. 10/2/2020 ACom. In: Advanced Computing for Innovation 15 http: //www. iict. bas. bg
List of papers • Hadjiski M. , L. Doukovska - Technical Diagnostics of Mill Fan System, Comptes rendus de l’Academie bulgare des Sciences, ISSN 1310 -1331, vol. 65, 12, pp. 1731 -1738, 2012. • Hadjiski M. , L. Doukovska - CBR approach for Technical Diagnostics of Mill Fan System, Comptes rendus de l’Academie bulgare des Sciences, ISSN 1310 -1331, vol. 66, 1, pp. 93 -100, 2013. 10/2/2020 ACom. In: Advanced Computing for Innovation 16 http: //www. iict. bas. bg
List of papers • Koprinkova-Hristova P. , L. Doukovska, P. Kostov - Working Regimes Classification for Predictive Maintenance of Mill Fan Systems, Proc. of the International Symposium on INnovations in Intelligent Sys. Tems and Applications – INISTA’ 13, CD, ISBN 978 -14799 -0661 -1 -13 -2013 IEEE, 2013. • Doukovska L. , S. Vassileva - Knowledge-based Mill Fan System Technical Condition Prognosis, Journal of the World Scientific and Engineering Academy and Society – WSEAS Transactions on Systems, Special Issue on Knowledge-based Modeling and Control of Мultifactorial Processes, Print ISSN 1109 -2777, E-ISSN 22242678, 2013 (accepted to review). 10/2/2020 ACom. In: Advanced Computing for Innovation 17 http: //www. iict. bas. bg
List of papers • Hadjiski M. , L. Doukovska, S. Vassileva - Intelligent Diagnostics of Mill Fan Technical Condition in Dust. Preparing Systems for 210 MW Power Units, International Journal of Computing and Informatics, Bratislava, Slovakia, ISSN 1335 -9150, 2013, (to be published). • Doukovska L. , S. Vassileva - Intelligent Methods for Process Control and Diagnostics of Mill Fan System, Cybernetics and Information Technologies (CIT), ISSN 1311 -9702, 2013, (to be published). 10/2/2020 ACom. In: Advanced Computing for Innovation 18 http: //www. iict. bas. bg
Conclusion • In the papers are presented promising results only using computational intelligence methods. • Adequate for the case methods of computational intelligence (fuzzy logic, neural networks and more general AI techniques – the precedents’ method (CBR), machine learning (ML)) must be used. 10/2/2020 ACom. In: Advanced Computing for Innovation 19 http: //www. iict. bas. bg
10/2/2020 ACom. In: Advanced Computing for Innovation 20 http: //www. iict. bas. bg
- Slides: 20