Artificial Intelligence Approach to Real-Time Selective Harmonic Elimination in Voltage Source Multilevel Inverter
Adeyemo1, I. A., Ojo, J. A.2, Babajide, D. O.3
1Adeyemo, I. A., Department of Electronic & Electrical Engineering, Ladoke Akintola University of Technology, PMB 4000, Ogbomoso, Oyo State, Nigeria.
2Ojo, J. A., Department of Electronic & Electrical Engineering, Ladoke Akintola University of Technology, PMB 4000, Ogbomoso, Oyo State, Nigeria.
3Babajide, D. O., Department of Electronic & Electrical Engineering, Ladoke Akintola University of Technology, PMB 4000, Ogbomoso, Oyo State, Nigeria.
Manuscript received on September 15, 2018. | Revised Manuscript received on September 19, 2018. | Manuscript published on November 30, 2018. | PP: 7-13 | Volume-8 Issue-4, November 2018. | Retrieval Number: D3160118418/2018©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Real-time application of Selective Harmonic Elimination-Pulse Width Modulation (SHE-PWM) technique is limited due to the heavy computational cost involved in solving a specified number of transcendental nonlinear equations known as Selective Harmonic Elimination (SHE) equations that contain trigonometric functions. Traditional methods of solving SHE equations include numerical techniques, and derivative free evolutionary algorithms. However, none of these methods can compute the switching angles in real time.In this paper, a twophase adaptive algorithm is proposed for real-time generation of optimal switching angles in multilevel inverters. In the firstphase, optimal switching angles are calculated offline using real coded genetic algorithm (RCGA). In the second phase, results of RCGA are used to train an ANFIS model. Simulation of an 11-level inverter in MATLAB/Simulink reveals that the proposed method is highly efficient for online harmonic reduction in multilevel inverter.
Keywords: Multilevel Inverter, Real Coded Genetic Algorithm (RCGA), Adaptive Neuro-Fuzzy Inference System (ANFIS), and harmonics.