Выполнен анализ существующих подходов к мониторингу, контролю и диагностике сложных технических систем и процессов. Рассмотрены возможности применения и особенности реализации существующих средств для исследования и анализа состояния технологических процессов и системы. Предложен подход, основанный на создании моделей двух типов: высокоточных имитационных моделей и упрощенных имитационных моделей пониженной точности. Базовым является использование упрощенных имитационных моделей. Результаты их работы используются для построения прогнозов состояния системы. В случае обнаружения отклонений в каком-либо элементе выполняется моделирование его состояния с использованием высокоточной модели. В результате анализа современных средств диагностики предложен подход на базе синтеза натурно-модельного метода и метода адаптации модели с помощью искусственной нейронной сети. Для реализации имитационных моделей используется высокоточный метод конечных элементов. Для реализации метода натурно-модельных испытаний предложено использовать упрощенные модели пониженного порядка. Преимуществом моделей пониженного порядка является снижение размерности решаемой задачи и повышение оперативности мониторинга. Показано, что полученные результаты могут быть использованы для решения широкого класса задач, основанных на средствах имитационного моделирования.
The analysis of existing approaches to monitoring, monitoring and diagnostics of complex technical systems and processes was performed. The possibilities of application and features of the implementation of existing tools for the study and analysis of the state of technological processes and systems are considered. An approach based on the creation of two types of models is proposed: high-precision imitation models and simplified imitational models of reduced accuracy. The basic is the use of simplified simulation models. The results of their work are used to build predictions of the state of the system. In case of detection of deviations in any element, its state is simulated using a high-precision model. As a result of the analysis of modern diagnostic tools, an approach based on the synthesis of the natural-model method and the model adaptation method using an artificial neural network has been proposed. For the implementation of simulation models using high-precision finite element method. To implement the method of full-scale model tests, it is proposed to use simplified models of reduced order. The advantage of reduced order models is to reduce the dimension of the problem being solved and to increase the monitoring efficiency. It is shown that the obtained results can be used to solve a wide class of problems based on simulation tools.
1. Dubrov V.I., Oganyan R.G., Narakidze N.D., Aleksanyan G.K. On the mathematical simulation of digital substation technological processes. Journal of Engineering and Applied Sciences. 2017. № 12 (2). Р. 276–282.
2. Oganyan R.G., Narakidze N.D., Shaykhutdinov D.V., Gorbatenko N.I., Maksuta S.O. Implementation of inverse calculation method in diagnostics of digital electric substations. IOP Conf. Series: Materials Science and Engineering 2017. № 177, A.n. 012083.
3. Дубров В.И., Оганян Р.Г., Наракидзе Н.Д., Алексанян Г.К. Разработка информационной системы для программно-аппаратной модели цифровой подстанции: сборник трудов XV Международной конференции NIDays 2016. М., 2016. С. 300–302.
4. Severson K., Chaiwatanodom P., Braatz R.D. Perspectives on Process Monitoring of Industrial Systems. 9th IFAC Symposium on Fault Detection, Supervision andSafety for Technical Processes SAFEPROCESS 2015: Paris, 2–4 September 2015. In: IFAC-PapersOnLine. 2015. Vol. 48. Issue 21. Р. 931–939.
5. Vieira G.G., Varela M.L.R., Putnik G.D., Machado J.M., Trojanowska J. Integrated platform for real-time control and production and productivity monitoring and analysis. The Romanian Review Precision Mechanics. Optics & Mechatronics. 2016. Issue 50. Р. 119–127.
6. Henseler J., Hubona G., Ray P.A. Using PLS path modeling in new technology research: updated guidelines. Industrial Management & Data Systems. 2016. Vol. 116 Issue: 1. Р. 2–20.
7. Bersimis S., Sgora A., Psarakis S. The application of multivariate statistical process monitoring in non-industrial processes, Quality Technology & Quantitative Management. 2018. Vol. 15. Issue 4. Р. 526–549.
8. Sliskovic D., Grbic R., Hocenski Z. Multivariate statistical process monitoring. Tehniki vjesnik. 2012. Vol. 19. Issue 1. Р. 33–41.
9. AlGhazzawi A., Lennox B. Monitoring a complex refining process using multivariate statistics. Control Engineering Practice. 2008. Vol. 16. Р. 294–307.
10. Gye-Soo K. Partial Least Squares Structural Equation Modeling (PLS-SEM): An application in Customer Satisfaction Research. International Journal of u- and e- Service, Science and Technology. 2016. Vol. 9. No. 4. Р. 61–68.
11. Hebing L., Neymann T., Th?te T., Jockwer A., Engell S. Integrated condition monitoring and control of fed-batch fermentation processes. 11th IFAC Symposium on Dynamics and Control of Process SystemsIncluding Biosystems DYCOPS-CAB 2016: Trondheim, Norway, 6—8 June 2016. In: IFAC-PapersOnLine. 2016. Vol. 49. Issue 7. Р. 621–626.
12. Qi C., Li H.-L., Li S., Zhao X., Gao F. A fuzzy-based spatio-temporal multi-modeling for nonlinear distributed parameter processes. Journal Applied Soft Computing archive. 2014. Vol. 25. Issue C. Р. 309–321.
13. Wang T., Wang X., Zhang Y., Zhou H. Fault detection of nonlinear dynamic processes using dynamic kernel principal component analysis. In: 2008 7th World Congress on Intelligent Control and Automation, A.n. 10344337.
14. Dong Y., Qin S.J. Dynamic-Inner Partial Least Squares for Dynamic Data Modeling. 9th IFAC Symposium on Advanced Control of Chemical Processes ADCHEM 2015: Whistler, Canada, 7–10 June. In: IFAC-PapersOnLine. 2015. Vol. 48. Issue 8. Р. 117–122.
15. N’Doye I., Voos H., Laleg-Kirati T.-M., Darouach M. Adaptive Observer Design and Parameter Identification for a Class of Nonlinear Fractional-Order Systems. In: 53rd IEEE Conference on Decision and Control, December 15–17, 2014. Los Angeles, California, USA, A.n.: 7040477.
16. Du Y., Budman H., Duever T. Integration of fault diagnosis and control by finding a trade-off between the detectability of stochastic fault and economics. 19th IFAC World Congress. In: IFAC Proceedings Volumes. 2014. Vol. 47. Issue 3. Р. 7388–7393.
17. He D., Xi C., Lu A. Fault detection for switched T-S fuzzy systems in finite frequency domain. Advances in Difference Equations. 2016. Vol. 62. 62. DOI: 10.1186/s13662-016-0785-7.
18. Beck V.J., Arnold J.K. Parameter Estimation in Engineering and Science. Wiley, N.Y., 1977.
19. Young, C.P. Parameter estimation for continuous-time models – a survey. Automatica 17, 1981. Р. 23–29.
20. Mayadevi N, Vinodchandra S.S., Ushakumari S. A Review on Expert System Applications in Power Plants. International Journal of Electrical and Computer Engineering (IJECE). Feburary 2014. Vol. 4. No. 1. Р. 116–126.
21. Zhang K., Jiang B., Shi P., Cocquempot V. Observer-Based Fault Estimation Techniques. Springer, Switzerland. 2018.
22. Ooi S.E., Fang Y., Lim Y., Tan Y. Study of Adaptive Model Predictive Control for Cyber-Physical Home Systems: 5th ICCST 2018, Kota Kinabalu, Malaysia, 29–30 August 2018. DOI: 10.1007/978-981-13-2622-6_17.
23. Ku, W., Storer, H.R., Geogakis, C., 1994. Uses of state estimation for statistical process control. Computers & Chemical Engineering 18. С. 571-575.
24. Wong P.K., Xu Q., Jia M., Zhang C. Engineering Applications of Intelligent Monitoring and Control. Mathematical Problems in Engineering. 2017. Vol. 2017, A.n. 2945861.
25. Sicklinger S., Belsky V., Engelmann B., Elmqvist H., Olsson H., W?chner R., Bletzinger K.-U. Interface Jacobian-based Co-Simulation. International Journal for Numerical Methods in Engineering. 11 May 2014. № 98 (6). Р. 418–444.
26. Beghi A., Marcuzzi F., Martin P., Tinazzi F., Zigliotto M. Virtual prototyping of embedded control software in mechatronic systems: A case study // Mechatronics. 2016. Vol. 43. Р. 99–111.
27. Синютин С.А., Воронков О.Ю. Метод формирования модели пониженного порядка микроэлектромеханической системы встроенными средствами программного пакета Ansys // Инженерный вестник Дона. 2016. № 4. URL: ivdon.ru/ru/magazine/archive/n4y2016/3902 (дата обращения: 17.09.2018).
28. Luo X., Zhang C., Jennings R.N. A hybrid model for sharing information between fuzzy, uncertain and default reasoning models in multi-agent systems. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems. 2002. № 10 (4). Р. 401–450.
29. KarnavasIoannis Y.K., Chasiotis C.I. A Simple Knowledge Base Software Architecture for Industrial Electrical Machine Design: Application to Electric Vehicle’s In-Wheel Motor. Conference: ISAT. 36th International Conference on Information Systems Architecture and Technology. At: Karpacz, Poland, 2015. Р. 1–10.
30. Reis M.S., Gins G. Industrial Process Monitoring in the Big Data/Industry 4.0 Era: From Detection, to Diagnosis, to Prognosis. Processes. 2017. Vol. 5. Issue 35. URL: https://brage.bibsys.no/xmlui/bitstream/handle/11250/2451637/16506_FULLTEXT.pdf?sequence=1&isAllowed=y DOI: 10.3390/pr5030035.
31. Oddan H. Multivariate Statistical Condition Monitoring. Norwegian University of Science and Technology, Trondheim. 2017.
32. Geman O., Saeid S., Costin C., Lhotska L. Challenges and Trends in Ambient Assisted Living and Intelligent Tools for Disabled and Elderly People. In: Conference: IWCIM Computational Intelligence for Multimedia Understanding conferenceAt: The Prague, Czech Republic. 2015. Vol. 1. DOI: 10.1109/IWCIM.2015.7347088.
33. Baccarini L.M.R., Rocha E Silva, V.V., De Menezes, B.R., Caminhas W.M. SVM practical industrial application for mechanical faults diagnostic. Expert Systems with Applications. 2011. Vol. 38. Issue 6. Р. 6980–6984.
34. Xia Q., Rao M., Dynamic case-based reasoning for process operation support systems. Engineering Applications of Artifical Intelligence. 1999. № 12 (3). С. 343–361.
35. Sun C.L., Uraikul V., Chan W.C., Tontiwachwuthikul P. An integrated expert system/operation research approach for automation of natural gas pipeline operations. Engineering Applications Artificial Intelligence. 2000. № 13 (4). Р. 465–475.
36. Wang Z.X., Liu Y., Griffin J.P. Neural net and expert system diagnose transformer faults. IEEE Computer Applications in Power. 2000. № 13. Р. 50–55.
37. Simani S. Residual generator fuzzy identification for automotive diesel engine fault diagnosis. International Journal of Applied Mathematics and Computer, Science. 2013. Vol. 23. Р. 419–438.
38. Jain C.L., Johnson P.R., Takefuji Y., Zadeh A.L. (Eds.). Knowledge-Based Intelligent Techniques in Industry. CRC Press, N.Y., 1999.
39. Kasabov K.N. Foundation of Neural Networks, Fuzzy Systems, and Knowledge Engineering. MIT Press., Cambridge, MA, 1996.
40. Verron S., Tiplica T., Kobi A. Fault detection and identification with a new feature selection based on mutual information. Journal of Process Control. 2008. Vol. 18. Issue 5. Р. 479–490.
41. Mrugalski M. Advanced neural network-based computational schemes for robust fault diagnosis. Cham: Springer, 2014.
42. Belarbi K., Bettou K., Mezaache A. Fuzzy neural networks for estimation and fuzzy controller design: simulation study for a pulp batch digester. Journal of Process Control. 2000. № 10. Р. 35–41.
43. Bakshi R.B., Stephanopoulos G. Representation of process trends – III multiscale extraction of trends from process data. Computers & Chemical Engineering. 1994. № 18 (4). Р. 267–302.
44. Bakshi R.B., Stephanopoulos G. Representation of process trends – IV induction of real-time patterns from operating data for diagnosis and supervisory control. Computers & Chemical Engineer¬ing. 1994. № 18 (4). Р. 267–302.
45. Пат. 2313815 Российская Федерация, МПК G 05 B 23/02. Устрои?ство и способ для контроля техническои? установки, содержащеи? множество систем, в частности установки электростанции. Фик Вольфганг, Аппель Мирко, Герк Уве; заявитель и патентообладатель Сименс Акциенгезелльшафт (DE). № 2005112459/09; заявл. 04.07.03; опубл. 10.09.05, Бюл. № 25. 10 с.