Pregled bibliografske jedinice broj: 451619
Adaptive Elastic Fuzzy Logic Controller
Adaptive Elastic Fuzzy Logic Controller // 74th Annual Meeting of Mississippi Academy of Sciences / NA (ur.).
Hattiesburg (MS), 2010. str. 126-126 (predavanje, međunarodna recenzija, sažetak, znanstveni)
CROSBI ID: 451619 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Adaptive Elastic Fuzzy Logic Controller
Autori
Kuljaca, Ognjen ; Gadewadikar, Jyotirmay ; Horvat, Krunoslav
Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, znanstveni
Izvornik
74th Annual Meeting of Mississippi Academy of Sciences
/ NA - Hattiesburg (MS), 2010, 126-126
Skup
74th Annual Meeting of Mississippi Academy of Sciences
Mjesto i datum
Hattiesburg (MS), Sjedinjene Američke Države, 02.2010
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
adaptive; elastic fuzzy; control
Sažetak
We present an adaptive fuzzy logic controller that includes on-line tuning of the membership function centroids and spreads, as well as an additional parameter, the "elasticity". A novel membership function is introduced here that satisfies certain important properties, including an independent reaction when the elasticity is tuned. We provide architecture for an elastic fuzzy logic adaptive controller, using certain on-line tuning laws that are an enhanced form of backpropagation tuning. It is shown by simulation that the fuzzy logic controller that includes the new membership function and tuning of elasticity outperforms the standard adaptive fuzzy logic controller based on Gaussian membership functions. Adaptive fuzzy logic (AFL) systems are becoming more and more popular in control systems due to the ability to select initial membership functions (MFs) based on experience and intuition. However, the simulation results and practical application experience with AFL systems with Gaussian membership functions show that if the initial membership functions do not sufficiently cover the region where the initial states can be found, the learning process is relatively slow and sometimes a long time is needed to achieve small tracking errors. One possible solution for this problem is in the introduction of additional degrees of freedom in the controller design. An additional degree of freedom is achieved here by introducing the so-called "elasticity" in the definition of the membership functions. To allow the fully effective use of elasticity, a novel membership function is introduced in which the centroid, spread and elasticity are three mutually independent parameters.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika
POVEZANOST RADA
Projekti:
192-0361557-1564 - Inteligentno upravljanje hidroenergetskim postrojenjima
Ustanove:
Brodarski institut d.o.o.