Access Journal

Access to Science, Business, Innovation in the Digital Economy

Models and intellectual technologies used for analysis and process management under uncertainty

Published Online: May 31, 2022
Views: 371
Downloads: 9
Download PDF

Abstract:
Objectives: Modern production activity of railway transport of Ukraine (RTU) is characterized by high the level of complexity of processes and a wide range of conditions of uncertainty. The article is devoted to the tasks of development of unified automated intelligent analysis and control technologies indeterminate RTU processes in case of uncertainty. Methods / Approach: To achieve the goal a new model of the concept of formation of automated intellectual technologies of RTU is offered, implementation of which is based on a modular platform of unified analytical services designed for effective solution of certain typical tasks (diagnosis, classification, forecasting, management, etc.). The concept as a system includes stages of research of properties of processes, theoretical and methodological basis and methods of modeling and automated control, scenarios and intelligent acceptance procedures decisions in case of uncertainty. Results: As examples of application of the concept to the formation of unified technologies RTU presented intelligent services for diagnosing processes with several categories of uncertainty, as well as analysis and forecasting the parameters of anti-resistance processes. The analysis procedures developed in the article differ using the scheme of fuzzy control method Takagi-Sugeno adapted for diagnostic tasks with the uncertainty of different types (statistical, fuzzy, etc.), which is provided by the use integrated indicator – the reliability index, as well as the formal capabilities of the individual accounting for the importance of controlled variables of the process model together for all rules of diagnosis, and for each rule separately. By aggregating the levels of time series of non-deterministic RTU processes developed and researched correct mathematical models and algorithms designed for unified procedures classification and research of properties of anti-persistent processes of railway transport. Conclusions: In order to develop unified intelligent automated technologies RTU developed a concept analysis and management of non-deterministic RTU processes in case of uncertainty based on the platform analytical services. In work at formation of the specified services of the automated intellectual The technology has developed advanced diagnostic procedures that use Takagi-Sugeno-type models for several categories of uncertainty, as well as methods for classifying anti-persistence processes, algorithms interpolation of levels within aggregation ranges, analysis models and short-term forecasting processes designed to develop the theoretical basis and means of improving automated systems RTU.
Keywords:
Pages:
185-200
JEL Classification:
C02, C05, R42
How to cite:
Skalozub, V., Horiachkin, V., Klymenko, I . (2022). Models and intellectual technologies used for analysis and process management under uncertainty. Access to science, business, innovation in digital economy, ACCESS Press, 3(2): 185-200
References:
  • Bajbuz, O.G. & Dolgіh, A.O. (2019) Comparative analysis of time series forecasting models effectiveness by means of a multi-criteria procedure on the example of financial indicators. “The Journal of Zhytomyr State Technological University” / Engineering, (1(83): 130–141. https://doi.org/10.26642/tn-2019-1(83)-130-141
  • Boyko, R. О., Zagorovska, L. G., & Yarova, Т. V. (2013) Informative providing of task of prognostication of feasibility indicators of functioning of technological complex. Eastern-European Journal of Enterprise Technologies, 3(10(63): 62–64. https://doi.org/10.15587/1729-4061.2013.14866
  • Byt’ko Т. V. & Prokhorchenko H.O. (2015) Formuvannia protsedury avtomatyzovanoi pobudovy hrafiku rukhu poizdiv na osnovi alhorytmu shtuchnykh bdzholynykh kolonii. [The formation procedure automation development train scheduling algorithm based on artificial bee colonies], Transport systems and transportation technologies, 9: 10-15. https://doi.org/10.15802/tstt2015/49348
  • Chen, X., & Siau, K. (2020). Business Analytics/Business Intelligence and IT Infrastructure: Impact on Organizational Agility. Journal of Organizational and End User Computing (JOEUC), 32(4), 138-161. http://doi.org/10.4018/JOEUC.2020100107
  • Chernyak O.I. & Zakharchenko P.V. (2016). Prikladni aspecty prognozuvanya rozvitku skladnyh socialno-economochnih sistem. [ Applied aspects of forecasting the development of complex socio-economic systems]. Vydavets Tkachuk O.V. Berdyansk, 512p. https://doi.org/10.31812/0564/1252 (UA)
  • Dlask M., Kukal J. (2019) Hurst exponent estimation from short time series. SIViP 13, 263–269. https://doi.org/10.1007/s11760-018-1353-2
  • Katkova Т. І. (2018). Modeli i metody otsinky, prohnozuvannia ta upravlinnia stratehichnoiu diialnistiu pidpryiemstva v umovakh nevyznachenosti [Models and methods of assessment, forecasting and management of strategic activities of the enterprise in conditions of uncertainty] (Doctoral dissertation, NTU "KhPI") http://repository.kpi.kharkov.ua/handle/KhPI-Press/35128
  • Kozachenko D.V. & Hermanyuk Y.V. (2013) Matematychna model dlia doslidzhennia perevezennia vantazhiv u mizhnarodnomu spoluchenni. [Mathematical Model for Research of International Railroad Goods Transportation] Transport systems and transportation technologies, 5:28-32. https://doi.org/10.15802/tstt2013/19273
  • Nazzal, Mohammad & Saad, Mohammed. (2018). A general framework for sustainability assessment of manufacturing processes. Ecological Indicators. 97: 211-224. https://doi.org/10.1016/j.ecolind.2018.09.062
  • Qi Jingchao & Yang, Huijie. (2011). Hurst Exponents For Short Time Series. Physical review. E, Statistical, nonlinear, and soft matter physics. 84. 066114. http://dx.doi.org/10.1103/PhysRevE.84.066114
  • Ramazanov S.K., Stepanenko O.P., Chernyak O.I, Tishkov B.O. (2019) Forecasting models and technologies and the problem of designing the future: state analysis and individual results,(Ed.) Chernyak O.I., Zakharchenko P.V., Actual problems of forecasting the development of socio-economic systems, Melitopol, ISBN: 978-966-197-654-1,pp. 164-191
  • Saaty T. (2016). The Analytic Hierarchy and Analytic Network Processes for the Measurement of Intangible Criteria and for Decision-Making, (Ed.) Greco S., Ehrgott M., Figueira J., Multiple Criteria Decision Analysis: State of the Art Surveys, Springer New York, NY, http://dx.doi.org/10.1007/978-1-4939-3094-4_10, pp. 363-419
  • Skalozub, V. V., & Klymenko, I. V. (2018a). Method for planning non-determined operation processes of railway technical system park. Science and Transport Progress, (5(77): 7–18. https://doi.org/10.15802/stp2018/141430
  • Skalozub, V. V., Zhukovitskiy, I. V., Klymenko, I. V., & Zaets, А. Р. (2018b). Creation of Intellectual Decision Support Systems in a Unified Automated System for Managing Rail Freight in Ukraine. Systemni tekhnolohii: Rehionalnyi mizhvuzivskyi, 3(116): 153-162.
  • Skalozub V. V. & Ilman V. M. (2013) Prykladnyi systemnyi analiz intelektualnykh system transportu [Applied system analysis of intelligent transport systems] Dnipropetrovsk, DNURT named after academic V. Lazaryan, p. 214. (RU)
  • Skalozub V.V., Shynkarenko V.I., Tseitlin S.Y., & Cherednychenko М. S. (2017). Modeli ontolohychnoi pidtrymky avtomatyzovanykh system keruvannia vantazhnymy zaliznychnymy perevezenniamy v Ukraini. [Models of ontological support of automated control systems of freight railway transportation in Ukraine.], System Technologies, Vol. 5 No. 112: 153-165.
  • Vertelieva O. V. (2019), Matematychne modeliuvannia ekonomichnykh protsesiv v umovakh paradyhmalnykh zrushen. [Mathematical modeling of economic processes in conditions of paradigmal dispatches], Investytsiyi: praktyka ta dosvid, vol. 12, pp. 48–56. https://doi.org/10.32702/2306-6814.2019.12.48
  • Voronina, A.V. & Kopyl O.V. (2016) Pryjniattia stratehichnykh rishen' v umovakh nevyznachenosti ta ryzyku. [Making of strategic decisions in the conditions of uncertainty and risk]. Molodyj vchenyj 1 (28): 35-39. http://nbuv.gov.ua/UJRN/molv_2016_1(1)__10 (UA)
  • Zhukovyts’kyy I. V., Skalozub V. V., Ustenko A. B. & Klymenko I. V.(2018a) Formation of intelligent information technologies of railway transport based on models of analytical servers and ontological systems Information and control systems at railway transport 6: 3-11. DOI: https://doi.org/10.18664/ikszt.v0i6.151635
  • Zhukovyts’kyy I. V., Skalozub V. V. & Ustenko A. B. (2018b). Intelektualni zasoby upravlinnia parkamy tekhnichnykh system zaliznychnoho transportu [Intellectual Means of Control by the Parks of the Technical Systems of Railway Transport]. Dnipro, Standart – Servis, p. 190. (UA)

Publish your science journal

If you like ACCESS journals system, you can publish your journal with us at a reasonable price