The method of solution of equations with coefficients that contain measurement errors, using artificial neural network

Konrad Zajkowski

doi:10.1007/s00521-012-1239-0

The method of solution of equations with coefficients that contain measurement errors, using artificial neural network

Neural Comput Appl. 2014;24(2):431-439. doi: 10.1007/s00521-012-1239-0. Epub 2012 Nov 2.

Author

Konrad Zajkowski¹

Affiliation

¹ Division of Electrotechnics and Electronics, Technical University of Koszalin, 15-17 Raclawicka St., 75-620 Koszalin, Poland.

Abstract

This paper presents an algorithm for solving N-equations of N-unknowns. This algorithm allows to determine the solution in a situation where coefficients A_i in equations are burdened with measurement errors. For some values of A_i (where i = 1,…, N), there is no inverse function of input equations. In this case, it is impossible to determine the solution of equations of classical methods.

Keywords: Artificial neural network; Induction motor model; Measurement errors; Parameter identification.