DSP control shunt APF with harmonic extraction by adaptive neural network

2008 IEEE Region 10 and the Third International Conference on Industrial and Information Systems

2008

In this paper, a fast and simple technique to generate the current reference to compensate for the harmonics and reactive power in a shunt type active power filter (APF) is developed. A voltage source inverter (VSI) is operated in the current controlled mode for this purpose. For fast generation of the reference current in the APF, the dc link voltage of the VSI is always sensed and an initial estimate is derived through an ANN based PI controller. It has been observed that this method works fine for balanced load. Unbalance in load and also uncertainty/mismatch in the filter parameters, deteriorate the system performance. To overcome this drawback, an Adaline based technique is incorporated. Weights of Adaline are tuned to minimize the Total Harmonic Distortion (THD) of the source current.Extensive simulations have confirmed the validity of the proposed scheme for all kinds of load (balanced and unbalanced) for a three phase three wire system.

Section: Adaptive Current Detection Techniquementioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

ANN (Adaline) Based Harmonic Compensation for Shunt Active Power Filter with Capacitor Voltage Based Predictive Technique

2008 IEEE Region 10 and the Third International Conference on Industrial and Information Systems

2008

“…Furthermore, these schemes also estimate wrongly if training sets are varied from the actual set. To overcome this drawback Adaline based adaptive ANN is also used for reference generation [15][16][17][18]. On-line training of Adaline is time consuming, thus introducing delay in compensation.…”

Section: Introductionmentioning

confidence: 99%

“…Further investigation is required to explore the potentiality of those schemes. Artificial Neural Network (ANN) [9][10][11][12][13][14][15][16][17][18] also has been applied for reference generation of shunt active power filter. ANN offers two very important features that suit the requirement of the reference generation.…”

Section: Introductionmentioning

confidence: 99%

Predictive and Adaptive ANN (Adaline) Based Harmonic Compensation for Shunt Active Power Filter

2008 IEEE Region 10 and the Third International Conference on Industrial and Information Systems

2008

Estimation of the current-reference to compensate for the harmonic and reactive component of the load current is important in a shunt type Active Power Filter. This paper applies ANN based predictive and adaptive reference generation technique. Predictive scheme extracts the information of the fundamental component through an ANN that replaces a low pass filter. This ANN based low pass-filter is trained offline with large number of training set to predict the fundamental magnitude of load current. These predictive reference generation techniques work well for load change pattern closer to the trained data and for clean source voltage. However, the performance deteriorates in case of distortion in source voltage and also if training data drifts quite significantly from test data. To overcome this, an Adaline based ANN is applied after the operation of the predictive algorithm. It has been shown that the combined predictive adaptive approach offers better performance. Extensive results from simulation have confirmed the usefulness of the proposed technique.

“…are also applied for purpose of reference generation [21][22].Further investigation is required to explore the potentiality of the those scheme. Artificial Neural Network (ANN) ( [6][7][8][9][10][11][12][13][14][15][16]), has been applied for reference generation of shunt active power filter. ANN offers two very important features that suit the requirement of the reference generation.…”

Section: Introductionmentioning

confidence: 99%

Harmonic elimination and reactive power compensation through a shunt active power filter by twin neural networks with predictive and adaptive properties

2009 IEEE International Conference on Industrial Technology

2009

A method for controlling an active power filter using Artificial Neural Network(ANN) is presented in this paper. This paper applies ANN based predictive and adaptive reference generation technique. Predictive scheme extracts the information of the fundamental component through an ANN that replaces a low pass filter. This ANN based low pass-filter is trained offline with large number of training set to predict the fundamental magnitude of load current. This predictive reference generation technique works well for clean source voltage. However, the performance deteriorates in case of distortion in source voltage and also with noise. To overcome this, an Adaline based ANN is applied after the operation of the predictive algorithm. It has been shown that the combined predictive-adaptive approach offers better performance. Simulation results and experimental results are presented to confirm the usefulness of the proposed technique.. Index Terms-Shunt Active Power Filter, Voltage SourceInverter, Current control, Non linear load, Adaline.