| Summary: | Present investigation focuses design & simulation study of a three phase three wire DSTATCOM deploying a conjugate gradient back propagation (CGBP) based icosϕ neural network technique. It is used for various tasks such as source current harmonic reduction, load balancing and power factor correction under various loading which further reduces the DC link voltage of the inverter. The proposed technique is implemented by mathematical analysis with suitable learning rate and updating weight using MATLAB/Simulink. It predicts the computation of fundamental weighting factor of active and reactive component of the load current for the generation of reference source current smoothly. It’s design capability is reflected under to prove the effectiveness of the DSTATCOM. The simulation waveforms are presented and verified using both MATLAB & real-time digital simulator (RTDS). It shows the better performance and maintains the power quality norm as per IEEE-519 by keeping THD of source current well below 5%. Keywords: CGBP based icosϕ neural network, DSTATCOM, MATLAB, RTDS
|
|---|
