350 rub
Journal Neurocomputers №10 for 2015 г.
Article in number:
The method of fuzzy production rules to identify non-deterministic objects
Keywords: homogeneous structure fault tolerance majorization error-correction coding redundancy
Authors:
T.S. Legotkina - Ph.D. (Eng.), Associate Professor, Department of Automation and Telemechanics, Perm National Research Polytechnic University. E-mail: luda@at.pstu.ac.ru Y.N. Khizhnyakov  Dr.Sc. (Eng.), Professor, Associate Professor, Department of Automation and Telemechanics, Perm National Research Polytechnic University. E-mail: luda @ at.pstu.ac.ru
Abstract:
Structural and parametrical identification is utilized to build a mathematical model. Structural identification requires permanent specification by mathematical means with experimental tests. Parametrical identification determines object parameters on the basis of a known model structure. The adequacy of a model is determined according to the proximity criteria. (Cosco, Wang, etc.). The article studies the production rules method which allows to nullify the approximation error. The comparative analysis of different types of functions recovery is presented with the use of production rules on the basis of Sugeno-Tacagi model. The study shows that the increase of the amount of production rules during determined intervals proves its theoretical significance. The production rules method has a good interference immunity and can be used to identify undetermined objects. The construction of installed model (identification) of undetermined object (air engine) with the help of a mathematical model in medium SCADE Suite has been proved by theoretical research in the field of production rules method. The installed model consists of adaptive fazzificator and adaptive defazzificator. The fazzificator and defazzificator are adopted to the installed model by means of neurons with consistent radiation.
Pages: 37-42
References

 

  1. Rotach V.JA. Teorija avtomaticheskogo upravlenija. Uchebnik dlja vuzov. Izd-e 3-e, pererab. i dop. M.: Izdatelstvo MEHI. 2004. 400 s.
  2. Borisov V.V., Kruglov V.V., Fedulov A.S. Nechetkie modeli i seti. M.: Gorjachaja linija-Telekom. 2007. 284 s.
  3. KHizhnjakov JU.N. Algoritmy nechetkogo, nejjronnogo i nejjro-nechetkogo upravlenija v sistemakh realnogo vremeni: ucheb. posobie. Perm: Izd-vo Perm. nac. issled. politekh. un-ta. 2013. 156 s.
  4. Legotkina T.S., Danilova S.A. Metody identifikacii sistem: ucheb. posobie. Perm: Izd-vo Perm. gos. tekhn. un-ta. 2008. 123 s.
  5. Sigeru Omatu, Marzuki KHalid, Rubija JUsof Nejjroupravlenie i ego prilozhenija Neuro-Control and its Application. M.: IPRZHR. 2000. 272 s.