Power quality is a relevant aspect in power distribution systems, which considers service continuity and distortion of the current and voltage waveforms, among others; in the first, the fault location plays a fundamental role. Considering the requirement of reliable tools to improve the distribution system operation, this dissertation analyses, on the one hand, the confidence of two fault location approaches versus the waveform distortion and on the other hand, the adequate selection of its adjusting-variables when using learning-based fault locators (LBFL).