This work shows an application of a deep learning-based graphical tool for analyzing waveform distortion in wind power plants. The tool consists of a deep autoencoder followed by a clustering algorithm. Previous applications of such a tool have covered harmonic emission which follows daily patterns. The challenge of measurements in wind power plants is the intermittence of the power production, which can vary in a time frame of minutes and hours. To this point, this work proposes a modification of a DL method presented in the literature to address measurements from wind power plants. The method can automatically obtain the number of clusters. The method is applied to harmonic measurements from H2 to H50 and active power in a Brazilian wind power plant. The graphical results allowed obtaining the correlation between patterns of odd and even current harmonic with the active power generated by a wind power plant.