Output signal based combination of two NLMS adaptive filters--transient analysis/Valjundsignaalidel baseeruv adaptiivsete NLMS-filtrite kombinatsioon: koonduvusanaluus

• Published in: Proceedings of the Estonian Academy of Sciences Vol. 60; no. 4; p. 258
• Main Author: Trump, Tonu
• Format: Journal Article
• Language: English
• Published: Estonian Academy Publishers 01-12-2011
• Subjects: Algorithms; Analysis; Lambda calculus; Estonia
• ISSN: 1736-6046
• DOI: 10.3176/proc.2011.4.06

A combination of two complex normalized least mean square (NLMS) adaptive filters that adapt on the same input signal at the same time is investigated. One of the filters has a large and the other one has a small step size. The outputs of the filters are combined together through a mixing parameter X. This combination is an interesting new way of achieving simultaneously a fast initial convergence and a small steady state error of an adaptive algorithm. The mixing parameter is computed from the output signals of the individual filters. The expressions characterizing the time evolution of the mean square deviation and the excess mean square error of the combination scheme are derived. The theoretical results are verified by simulations. Key words: adaptive algorithms, combination, analysis. On uuritud kahe adaptiivse NLMS-filtri, mis adapteeruvad samadele sisendsignaalidele, kombinatsiooni. Uhel filtril on suur ja teisel vaike sammu pikkus. Filtrite valjundid kombineeritakse X-parameetri abil, mille leiame filtrite valjundsignaalidest. Selline kombinatsioon on uus viis saavutada iiheaegselt adaptiivse algoritmi kiire koonduvus ja vaike valjakujunenud oleku viga. Artiklis on tuletatud valemid, mis voimaldavad arvutada ruutkeskmise vea kogu filtri too kestel. Teoreetilised tulemused on arvutikatsetega kontrollitud.