Voltage and current waveforms of a distribution or a transmission system are not pure sinusoids. There are distortions in these waveforms that consist of a combination of the fundamental frequency, harmonics and high frequency transients. This work presents an approach of a harmonic identification method for distorted waveforms in Electric Power Systems. The proposed method is based on a Genetic Algorithm, which is a technique for optimization inspired by genetics and natural evolution. The proposed algorithm was tested with simulated data. The effect of the size of the initial population, the crossover rate and the mutation rate were studied. The results demonstrate that the method presented is precise if compared with the traditional Fourier Transform.