scispace - formally typeset
Search or ask a question

Adaptive radial basis function neural networks-based real time harmonics estimation and PWM control for active power filters

01 Jan 2012-
About: The article was published on 2012-01-01 and is currently open access. It has received 5 citations till now. The article focuses on the topics: Harmonics & Artificial neural network.

Content maybe subject to copyright    Report

Citations
More filters
Journal ArticleDOI

35 citations


Cites background from "Adaptive radial basis function neur..."

  • ...The main goal of APF is to maintain low THD by canceling all the harmonic components caused by nonlinear loads.(125)...

    [...]

Proceedings ArticleDOI
01 Jan 2017
TL;DR: The new models of total harmonics distortion reduction using adaptive, Weiner, and Kalman filters are presented and it is shown thatKalman filters give the best performance as compared to adaptive and Weiner filters.
Abstract: Total harmonics distortion (THD) is one of the main problems in power systems due to its effects in generating undesirable issues in power quality. These effects include heating (in transformers, capacitors, motors, and generators), disoperation of electronic equipment, incorrect readings on meters, disoperation of protective relays, and communication interference. Besides these problems, harmonics affect the power quality in both transmission and distribution systems. Different techniques have been used to mitigate the effects of harmonics. These techniques include; passive filters, active power filter, artificial intelligent, and adaptive selective harmonics reductions. Each method has some advantages and disadvantages. This paper presented new models of total harmonics distortion reduction using adaptive, Weiner, and Kalman filters. In order to test the performance of the presented methods, the output current of a single phase inverter circuit was used as a study case. The new models reduced the total harmonics distortion from by more than 50% however Kalman filters give the best performance as compared to adaptive and Weiner filters.

15 citations


Cites methods from "Adaptive radial basis function neur..."

  • ...Power Converters are used to realize the reference signals, which are injected into the load to eliminate the harmonics [3]....

    [...]

Dissertation
01 Jan 2001
TL;DR: In this paper, a single phase shunt active power filter (APF) using a bi-directional full-bridge converter with capacitive energy storage to compensate for the harmonics generated by nonlinear loads is proposed.
Abstract: This paper studies a single phase shunt active power filter (APF) using a bi-directional full-bridge converter with capacitive energy storage to compensate for the harmonics generated by nonlinear loads. The usage of a capacitor as a reactive power source for the APF simplifies the circuitry. The harmonic current reference is obtained by feeding the load current signal into a 50 Hz notch filter. The simple and fast hysteresis control strategy involving only a few analog and logic components makes it attractive for the low power domestic application. The usefulness of the proposed control algorithm is confirmed by simulation as well as by experimental results.

15 citations

Journal ArticleDOI
TL;DR: Almaita et al. as discussed by the authors used an adaptive Radial Basis Function Neural Networks (RBFNN) algorithm to estimate the fundamental and harmonic components of nonlinear load current, and an extensive investigation was carried out to propose a systematic and optimal selection of the adaptive RBFNN parameters.
Abstract: In this paper, an adaptive Radial Basis Function Neural Networks (RBFNN) algorithm is used to estimate the fundamental and harmonic components of nonlinear load current. The performance of the adaptive RBFNN is evaluated based on the difference between the original signal and the constructed signal (the summation between fundamental and harmonic components). Also, an extensive investigation is carried out to propose a systematic and optimal selection of the Adaptive RBFNN parameters. These parameters will ensure fast and stable convergence and minimum estimation error. The results show an improving for fundamental and harmonics estimation comparing to the conventional RBFNN. Also, the results show how to control the computational steps and how they are related to the estimation error. The methodology used in this paper facilitates the development and design of signal processing and control systems. Article History : Received Dec 15, 2016; Received in revised form Feb 2 nd 2017; Accepted 13rd 2017; Available online How to Cite This Article : Almaita, E.K and Shawawreh J.Al (2017) Improving Stability and Convergence for Adaptive Radial Basis Function Neural Networks Algorithm (On-Line Harmonics Estimation Application). International Journal of Renewable Energy Develeopment, 6(1), 9-17. http://dx.doi.org/10.14710/ijred.6.1.9-17

5 citations


Cites background or methods from "Adaptive radial basis function neur..."

  • ...In this paper, which is an extension to the works in (Almaita, 2012; Almaita & Asumadu, 2011a, 2011b), a systematic approach is introduced to select the parameters of the adaptive RBFNN algorithm....

    [...]

  • ...In this paper, which is an extension to the works in (Almaita, 2012; Almaita & Asumadu, 2011a, 2011b), a systematic approach is introduced to select the parameters of the adaptive RBFNN algorithm....

    [...]

  • ...An adaptive version of RBFNN has been introduced in ( Almaita, 2012)....

    [...]

Proceedings ArticleDOI
01 Oct 2019
TL;DR: The algorithm is used to estimate the fundamental and harmonic components of nonlinear load current and the performance of the adaptive RBFNN is evaluated based on the difference between the original signal and the constructed signal.
Abstract: In this paper, An adaptiveRadial Basis Function Neural Networks (RBFNN)algorithm is used to estimate the fundamental and harmonic components of nonlinear load current. The learning rates for adaptive RBFNN are further investigated to minimize the total error and to minimize the error in each of the fundamental and harmonics components. The performance of the adaptive RBFNN is evaluated based on the difference between the original signal and the constructed signal (the summation between fundamental and harmonic components). The methodology used in this paper facilitates the development and design of signal processing and control systems. This is done by training the system and obtaining the initial parameters for the RBFNN based on simulation. After that, the adaptive RBFNN can be in the real system with these initial parameters.

Cites methods from "Adaptive radial basis function neur..."

  • ...An adaptive version of RBFNN was proposed in [13],[18]-[20]....

    [...]

References
More filters
Journal ArticleDOI
TL;DR: This work proposes a network architecture which uses a single internal layer of locally-tuned processing units to learn both classification tasks and real-valued function approximations (Moody and Darken 1988).
Abstract: We propose a network architecture which uses a single internal layer of locally-tuned processing units to learn both classification tasks and real-valued function approximations (Moody and Darken 1988). We consider training such networks in a completely supervised manner, but abandon this approach in favor of a more computationally efficient hybrid learning method which combines self-organized and supervised learning. Our networks learn faster than backpropagation for two reasons: the local representations ensure that only a few units respond to any given input, thus reducing computational overhead, and the hybrid learning rules are linear rather than nonlinear, thus leading to faster convergence. Unlike many existing methods for data analysis, our network architecture and learning rules are truly adaptive and are thus appropriate for real-time use.

4,406 citations


"Adaptive radial basis function neur..." refers background or methods in this paper

  • ...In the first stage the K-means [8, 93] clustering algorithm is used to locate the centers in the input data space regions where significant data are present (shown as I in Figure 3....

    [...]

  • ...The hybrid learning process has two different stages; (i) finding suitable locations for the radial basis functions centers of the hidden neurons [8, 93] and (ii) finding the weights between the hidden and output layers....

    [...]

  • ...7 illustrates one of the RBFNN training processes called hybrid learning process [93]....

    [...]

Journal ArticleDOI
TL;DR: In this paper, a new instantaneous reactive power compensator comprising switching devices is proposed, which requires practically no energy storage components, and is based on the instantaneous value concept for arbitrary voltage and current waveforms.
Abstract: The conventional reactive power in single-phase or three- phase circuits has been defined on the basis of the average value concept for sinusoidal voltage and current waveforms in steady states. The instantaneous reactive power in three-phase circuits is defined on the basis of the instantaneous value concept for arbitrary voltage and current waveforms, including transient states. A new instantaneous reactive power compensator comprising switching devices is proposed which requires practically no energy storage components.

3,331 citations


"Adaptive radial basis function neur..." refers methods in this paper

  • ...The decomposed p or/and q are used to calculate the reference currents in the α-β-0 domain as shown in [29, 30]....

    [...]

  • ...[29] introduced the most popular technique for harmonic extraction, which is called the instantaneous power theory....

    [...]

Journal ArticleDOI
TL;DR: This paper presents a comprehensive review of active filter configurations, control strategies, selection of components, other related economic and technical considerations, and their selection for specific applications.
Abstract: Active filtering of electric power has now become a mature technology for harmonic and reactive power compensation in two-wire (single phase), three-wire (three phase without neutral), and four-wire (three phase with neutral) AC power networks with nonlinear loads. This paper presents a comprehensive review of active filter (AF) configurations, control strategies, selection of components, other related economic and technical considerations, and their selection for specific applications. It is aimed at providing a broad perspective on the status of AF technology to researchers and application engineers dealing with power quality issues. A list of more than 200 research publications on the subject is also appended for a quick reference.

2,311 citations


"Adaptive radial basis function neur..." refers background or methods in this paper

  • ...Literature contains many algorithms are used to drive the SAPF circuit [47, 49, 72, 88, 89, 95-97]....

    [...]

  • ...Theoretically, the resultant source current (Is) should be harmonic free and in- phase with the AC mains voltage [88, 89, 91]....

    [...]

  • ...Series APFs are more suitable for harmonic-voltage source loads....

    [...]

  • ...Since it was introduced, APFs received strong attention from researchers in electrical power fields....

    [...]

  • ...27 Besides using Series APF to compensate for harmonic-voltage, it has been used to compensate negative-sequence voltage and regulate voltage in three-phase system [88]....

    [...]

Journal ArticleDOI
TL;DR: Current control techniques for three-phase voltage-source pulsewidth modulated converters, including bang-bang (hysteresis, delta modulation) controllers and predictive controllers with on-line optimization are reviewed.
Abstract: The aim of this paper is to present a review of current control techniques for three-phase voltage-source pulsewidth modulated converters. Various techniques, different in concept, have been described in two main groups: linear and nonlinear. The first includes proportional integral (stationary and synchronous) and state feedback controllers, and predictive techniques with constant switching frequency. The second comprises bang-bang (hysteresis, delta modulation) controllers and predictive controllers with on-line optimization. New trends in current control-neural networks and fuzzy-logic-based controllers-are discussed, as well. Selected oscillograms accompany the presentation in order to illustrate properties of the described controller groups.

2,086 citations


"Adaptive radial basis function neur..." refers methods in this paper

  • ...Several current control techniques have been used for active power filters [14, 44-52] such as space vector control, Proportional-Integral (PI) control, predictive control, deadbeat control, resonant control, sliding mode control, carrier phase shift SPWM, hysteresis current control, fuzzy control, and artificial neural networks control....

    [...]

Book
01 Jan 2007
TL;DR: The p-q theory in three-phase, four-wire Shunt Active Filters as discussed by the authors has been applied to power flow control in power electronics equipment and has been shown to be useful in many applications.
Abstract: Preface. 1. Introduction. 1.1. Concepts and Evolution of Electric Power Theory. 1.2. Applications of the p-q Theory to Power Electronics Equipment. 1.3. Harmonic Voltages in Power Systems. 1.4. Identified and Unidentified Harmonic-Producing Loads. 1.5. Harmonic Current and Voltage Sources. 1.6. Basic Principles of Harmonic Compensation. 1.7. Basic Principles of Power Flow Control. References. 2. Electric Power Definitions: Background. 2.1. Power Definitions Under Sinusoidal Conditions. 2.2. Voltage and Current Phasors and the Complex Impedance. 2.3. Complex Power and Power Factor. 2.4. Concepts of Power Under Non-Sinusoidal Conditions -Conventional Approaches. 2.5. Electric Power in Three-Phase Systems. 2.6. Summary. References. 3 The Instantaneous Power Theory. 3.1. Basis of the p-q Theory. 3.2. The p-q Theory in Three-Phase, Three-Wire Systems. 3.3. The p-q Theory in Three-Phase, Four-Wire Systems. 3.4. Instantaneous abc Theory. 3.5. Comparisons between the p-q Theory and the abc Theory. 3.6. Summary. References. 4 Shunt Active Filters. 4.1. General Description of Shunt Active Filters. 4.2. Three-Phase, Three-Wire Shunt Active Filters. 4.3. Three-Phase, Four-Wire Shunt Active Filters. 4.4. Shunt Selective Harmonic Compensation. 4.5. Summary. References. 5 Hybrid and Series Active Filters. 5.1. Basic Series Active Filter. 5.2. Combined Series Active Filter and Shunt Passive Filter. 5.3. Series Active Filter Integrated with a Double-Series Diode Rectifier. 5.4. Comparisons Between Hybrid and Pure Active Filters. 5.5. Conclusions. References. 6 Combined Series and Shunt Power Conditioners. 6.1. The Unified Power Flow Controller (UPFC). 6.2. The Unified Power Quality Conditioner (UPQC). 6.3. The Universal Active Power Line Conditioner (UPLC). 6.4. Summary. References. Index.

2,038 citations


"Adaptive radial basis function neur..." refers background or methods in this paper

  • ...[30] used high-pass filter and low-pass filter to decompose the power components....

    [...]

  • ...The decomposed p or/and q are used to calculate the reference currents in the α-β-0 domain as shown in [29, 30]....

    [...]

  • ...In this dissertation , two compensation strategies have been applied [30][13]....

    [...]

  • ...It mainly consists of three parts [30] : a....

    [...]

  • ...The voltages and currents of the rectifier are sampled and used to calculate the instantaneous active power p and imaginary power q based on p-q theory [30]....

    [...]