Design features of a smart decision support system for restoring compliance of main pipeline facilities

UDK: 622.692.4.053

DOI: 10.24887/0028-2448-2026-5-126-131

Key words: decision support system (DSS), structural architecture, knowledge base, smart transducer, main pipeline (MP)

Authors: E.R. Ibragimov (The Pipeline Transport Institute LLC, RF, Moscow); L.V. Grigoriev (The Pipeline Transport Institute LLC, RF, Moscow); A.S. Chernyatin (The Pipeline Transport Institute LLC, RF, Moscow); A.I. Baryshev (The Pipeline Transport Institute LLC, RF, Moscow)

The following article discusses the design features of a smart decision support system (DSS) for restoring compliance of main pipeline (MP) facilities. At the present time an analysis and assessment of geotechnical survey results for main pipeline facilities, along with decisions on the need for remedial measures to bring them into compliance, are carried out by experts using applicable state and industry standards, specialized software, and geographic information systems. Therefore this process is time-consuming, and the results of such process largely depend on the expert’s qualification. Due to the reasons described above smart DSSs are used to determine the actual and predicted state of MP facilities in geotechnical monitoring tasks and to improve the efficiency of analyzing large datasets on the condition of MP facilities and external factors, as well as forecasting their changes under complex ambient conditions. Based on the requirements for the intended use and operating conditions of artificial intelligence methods together with the classical theory of sets, and after removing restrictions on their application, a generalized structural architecture was developed for a smart, specialized, hybrid DSS, which is operating on the basis of hybrid methods for studying decision-making processes which is aimed at bringing MP facilities into compliance.

References

1. Andreychik A.V., Andreychikova O.N., Prinyatie resheniy v usloviyakh neopredelennosti. Ot metoda analiza ierarkhiy do nechetkikh modeley (Decision making under uncertainty: From analytic hierarchy processing to fuzzy models), Moscow: Lenand Publ., 2021, 800 p.

2. Larichev O.I., Teoriya i metody prinyatiya resheniy (Theory and methods of decision making), Moscow: Logos Publ., 2000, 296 p.

3. L'vovskiy S.M., Printsipy kompleksnogo analiza (Principles of complex analysis), Moscow: Publ. of MTsNMO, 2017, 304 p.

4. Shannon C.E., Raboty po teorii informatsii i kibernetike (Works on information theory and cybernetics): Translation into Russian, Moscow: Izdatel'stvo inostrannoy literatury Publ., 1963, 824 p.