Open AccessFast and accurate measurement of harmonic parameters employing hybrid adaptive linear neural network and filtered‐x least mean square algorithm
Author(s) -
Garanayak Priyabrat,
Panda Gayadhar
Publication year - 2016
Publication title -
iet generation, transmission and distribution
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.92
H-Index - 110
eISSN - 1751-8695
pISSN - 1751-8687
DOI - 10.1049/iet-gtd.2015.0684
Subject(s) - least mean squares filter , algorithm , convergence (economics) , noise (video) , artificial neural network , harmonic , harmonics , mean squared error , stability (learning theory) , control theory (sociology) , adaptive filter , computer science , signal (programming language) , mathematics , engineering , artificial intelligence , control (management) , quantum mechanics , voltage , machine learning , electrical engineering , economics , image (mathematics) , programming language , economic growth , statistics , physics
This study proposes a novel algorithm for fast and accurate measurement of fundamental, harmonics, sub‐ and inter‐harmonic parameters of a distorted current signal with additive noise. A novel hybrid technique called adaptive linear neural network and filtered‐x least mean square (ADALINE‐FXLMS) algorithm is employed for amplitude and phase estimation. The ADALINE‐FXLMS algorithm is the advancement of ADALINE least mean square (ADALINE‐LMS) algorithm. With the help of this proposed algorithm, the adaptive step‐size parameter is expanded up to the upper‐bound limit that results in further improvement of system stability. The convergence behaviour of the mean square errors for the noisy input signal is derived in details. By applying the proposed algorithm, the dynamic and steady‐state response are analysed with different signal‐to‐noise ratio values. The simulated results obtained from the proposed algorithm are compared with the results generated by the variable step‐size ADALINE‐LMS algorithm in order to demonstrate the tracking capability. Finally, a laboratory prototype model is developed to justify the efficacy of the analytical results. The motivation of applying the proposed hybrid algorithm is due to its successful implementation in a real‐time environment, faster convergence and simplicity structure.