One of the main problems of the data acquired by power utilities is the presence of outliers affecting the database measurements in the electrical system, damaging the analyzes of the distribution scenario. This work proposes a new module to complement the measurements made by the utilities. Two algorithms for outliers correction were developed using artificial intelligence techniques: fuzzy logic and artificial neural networks. The first technique, with a fuzzy approach, develops an inference system based on the variations of previous measurements to determine future variation. In the second algorithm developed using NN, the outliers were filled using a prediction model using 10 previous samples. To demonstrate the applicability of the developed methods, a case study is performed on a substation in a city of Paraíba.