Format: HTML | BibTeX | DC | EndNote | NLM | MARC | MARCXML
000000151 001__ 151
000000151 037__ $$aENY-ARTICLE-2008-116
000000151 041__ $$aeng
000000151 088__ $$aI07/1993/I-141
000000151 100__ $$aCichocki, A$$uWarsaw University of Technology, Poland
000000151 245__ $$aNeural networks for real-time estimation of the basic waveforms of voltages and currents encountered in power systems
000000151 260__ $$c1992-06-02
000000151 300__ $$a12p
000000151 500__ $$aInternational Journal of Electronics. 1993 vol. 74, No 2, pp. 307-318
000000151 520__ $$aAn electronic artificial neural network architecture is presented for estimating the parameters of a sine wave distorted by a DC exponential signal and corrupted by noise. In the proposed approach a finite set or sampled data from noisy measurements is used to implement Lp-norm. The standard least-squares (L2 -norm) criterion is considered as a special case. Mathematical algorithms are presented in detail and associated architectures of analogue artificial neural networks are proposed. Extensive computer simulations are used to demonstrate the validity and performance of the proposed algorithms and neural network realizations. The proposed methods seems to be particularly useful for real-time, high-sped and low-cost estimations of parameters of sinusoidal signals.
000000151 6531_ $$aneural network
000000151 6531_ $$adistorted signals
000000151 6531_ $$aparameter estimation
000000151 6531_ $$asignal processing
000000151 700__ $$aLobos, T$$uWroclaw University of Technology, Poland
000000151 8560_ $$fzbigniew.leonowicz@pwr.wroc.pl
000000151 8564_ $$uhttp://zet10.ipee.pwr.wroc.pl/record/151/files/$$zAccess to Fulltext
000000151 909CO $$ooai:zet10.pwr.wroc.pl:151$$pglobal
000000151 980__ $$aARTICLE