A Shunt Active Power Filter With Enhanced Performance Using ANN-Based Predictive and Adaptive Controllers

Abstract

This paper attempts to improve the dynamic performance of a shunt-type active power filter. The predictive and adaptive properties of artificial neural networks (ANNs) are used for fast estimation of the compensating current. The dynamics of the dc-link voltage is utilized in a predictive controller to generate the first estimate followed by convergence of the algorithm by an adaptive ANN (adaline) based network. Weights in adaline are tuned to minimize the total harmonic distortion of the source current. Extensive simulations and experimentations confirm the validity of the proposed scheme for all kinds of load (balanced and unbalanced) for a three-phase three-wire system.Index Terms-Adaline, current control, nonlinear load, shunt active power filter (APF), total harmonic distortion (THD), voltage source inverter.

An Improved New Technique to Compensate Reactive and Nonlinear Loads by Hybrid DSTATCOM Topology

“…As a tradeoff between these requirements, C = 10 μF is chosen. The value of k is found to be 0.42 using (8). With this value of k, L2 will be 0.6 mH.…”

Comparative Power Quality analysis of Conventional and Modified DSTATCOM Topology

“…[6,8,9]. Many soft computing based control algorithms such as neural network, fuzzy logic and adaptive neuro-fuzzy etc [11][12][13][14], have been also adopted for the control of VSI based DSTATCOM.…”

Fuzzy Inference System Based Power Factor Correction of Three Phase Diode Rectifier Using Field Programable Gate Array

“…Since three-phase diode rectifiers are widely used in industry, such as adjustable speed drives and dc power supplies (Thasananutariya and Chatratana, 2009;Chen and Luo, 2001;Grbovic et al, 2001), the harmonics generated by the diode rectifier in the line current is a main concern in power electronics. To eliminate the harmonic current generated by this type of harmonic source, the shunt Active Power Filter (APF) or series APF has been an effective solution (Corasaniti et al, 2009;Singh and Solanki, 2009;Lavopa et al, 2009;Rahmani et al, 2010;Vodyakho and Mi, 2009;Salmeron and Litran, 2010;Bhattacharya and Chakraborty, 2011). However, the rating of APF is normally small because of its partial power processing property.…”