Abstract
As part of the study, a control scheme with the adaptation of the coefficients of the neuron-fuzzy regulator implemented. The area difference method used as a training method for the network. It improved by adding a rule base, which allows choosing the optimal learning rate for individual neurons of the neural network. The neural network con- troller applied as a superstructure of the PID controller in the process control scheme. The dynamic object can function in different modes. This technological process operates in different modes in terms of loading and temperature set- points. Because of experiments, the power consumption and the amount of time required maintaining the same absorp- tion process, using a conventional PID controller and a neural-network controller evaluated. It concluded that the neuro- fuzzy controller with a superstructure reduced the transient time by 19%.
Keywords
neural network, PID controller, neural network optimizer, area difference method, nonlinear systems.
1. Brown, M. P., Austin K. (2005) The New Physique: 25-30.
2. Brown, M. P., Austin K. (2004) Appl. Phys.: 2503-2504.
3. Wang, R.T. (1999) In Classic Physiques: 212-213.
4. Smith, C.D., Jones, E.F. (2002) Load-cycling in cubic press: 651-654.
5. Jackson, B.R., Pitman, T. (2004). Patent No. 6,345,224.
6. Davids, D.L. (1998) Recovery effects in binary aluminum alloys.
7. Kalandarov, P.I. Logunova, O.S., Andreev, S.M. (2021) Nauchnye osnovy vlagometrii, Tashkent : 175.
8. Ismatullaev, P.R., Kalandarov, P.I. (2011) Pribory, 7 (133): 40-44.
9. Kalandarov, P.I., B.M. Temerbekova (2012) Vestnik Nacional'nogo tekhnicheskogo universiteta Ukrainy «Kievskij politekhnich- eskij institut». Seriya: Priborostroenie, № 43: 126-133.
10. Iskandarov, B.P., Kalandarov, P.I. (2013) Measurement Techniques, 7: 827-830.
Siddikov I.H., Kalandsrov P.I., Yadgarova D.B. and Ismatullaev X.N. (2021) Algorithm of neuro-fuzzy controller parameter adapta- tion. Software of systems in the industrial and social fields, 9 (1): 22-28. DOI: 10.18503/2306-2053-2021-9-1-22-28.