Steady State Modeling and ANFIS Based Analysis of Self-Excited Induction Generator

Self-excited induction generator (SEIG) has the ability to generate power at varying speed, which facilitates its application for wind energy conversion in remote and windy areas. Estimation of the generator behavior under actual operating conditions is essential, but the SEIG analysis with conventional techniques take long time with fatigued mathematical procedures. This paper presents a new technique for the performance analysis of a three phase SEIG supplying an isolated resistive load using adaptive neuro-fuzzy inference system (ANFIS). Proposed ANFIS model has been implemented to predict the effect of prime mover speed, capacitance and load on generated voltage of SEIG. Experimental data is used for the training of ANFIS. Results obtained from the trained have been compared with the experimental results. The comparison confirms the validity and accuracy of the ANFIS based modeling of induction generator.