A.V. Grivachev Post-graduate Student, South-Western State University (Kursk) E-mail: Garpun-22@mail.ru S.G. Emelyanov Dr.Sc. (Eng.), Professor, Rector, South-Western State University (Kursk) E-mail: rector@swsu.ru M.V. Borodin Ph.D. (Eng.), Associate Professor, Chair of Information Systems and Technologies, South-Western State University (Kursk) E-mail: borodin_mikhail@mail.ru

The article contains a description of the scheme of recognition and identification of risk for control system of robotic multi-functional machines with the a production processing. The task of managing a group of machines is non-deterministic scheme solutions. The sequence of control commands it essentially depends on uncertain data from the dynamically changing environment. These data are described in terms of risk-function achievement. Thus, the effective management of robotic multifunction machine depends on the solution of the problem of recognition and self-assessment of risks. To solve this problem, it is a hybrid model based on a production processing and the structural and functional scheme of recognition and risk identification. The scheme has 4 levels of processing. Central position is the third level that is as the level of structural and linguistic analysis. Implemented modification of a production cycle of the machine processing to ensure the timely processing of risk groups. For parallel generation options and their evaluation in a dynamically changing environment is based module conflict resolution with the original production expressions. These expressions are combined before- and after- numeric and string processing. The module uses a conflict resolution as an additional map information on the positions of machine, their weights and total topology of machines. Production terms takes into account the state of describing the active objects of the environment.

 

1. Kaljaev I.A., Gajjduk A.R. Odnorodnye nejjropodobnye struktury v sistemakh vybora dejjstvijj intellektualnykh robotov. M.: JAnus-K. 2000. 280 s.
2. Kaljaev I.A., Gajjduk A.R., Kapustjan S.G. Modeli i algoritmy kollektivnogo upravlenija v gruppakh robotov. M.: FIZMATLIT. 2009. 280 s.
3. Bobrovskijj S. Roboty gotovjatsja k razvedke i boju // PC Week/RE. 2001. № 43. S. 40-45.
4. Titenko E.A. i dr. Produkcionnaja mashina-generator dlja obrabotki simvolnykh dannykh diskretnykh obektov /// Izvestija JUgo-Zapadnogo gosudarstvennogo universiteta. Ser. Upravlenie, vychislitelnaja tekhnika, informatika. Medicinskoe priborostroenie. 2012. № 2. CH. 1 S. 111-115.
5. Metodicheskie rekomendacii po ocenke ehffektivnosti investicionnykh proektov. Oficialnoe izdanie. M.: EHkonomika. 2000. 421 s.
6. Grivachev A.V., Emeljanov S.G., Titenko E.A. Modificirovannaja produkcionnaja sistema dlja reshenija zadachi strukturnogo raspoznavanija obrazov // Naukoemkie tekhnologii. 2014. T. 15. № 12. S. 9-12.
7. Grivachev A.V. i dr. Upravlenie intellektualnymi robotami s ispolzovaniem produkcionnykh sistem // Materialy dokl. II region. nauchn.-prakt. konf. «Intellektualnye informacionnye sistemy: tendencii, problemy, perspektivy» (10 nojabrja 2014 g.). Kursk. 2014. S. 37-48.
8. Emeljanov S.G., Prjadko T.V.Strukturno-funkcionalnaja organizacija podsistemy raspoznavanija i ocenki slozhnostrukturirovannykh riskov // Izvestija Tulskogo gosudarstvennogo universiteta. Ser. EHkonomika. Upravlenie. Standartizacija. Kachestvo. Vyp. 3. Tula: TulGU. 2006. S. 18-20.