The invention discloses a distribution network fault line selection method based on a random matrix and a Hausdorff distance. Three-phase current sampling values of a feeder line before and after fault are selected, through blocking and translation processing, white Gaussian noise is added, a state data matrix is generated, a product matrix is obtained by using equivalent transformation of singular values of the random matrix, a standard matrix product is obtained by normalization, eigenvalue vectors are acquired, probability statistics is carried out, eigenvalue vectors with the probabilitiesP to be smaller than 10% are used as outliers to be filtered, a Hausdorff distance algorithm is adopted, the Hausdorff distances between the eigenvalue vector of a certain feeder line and the eigenvalue vectors of other feeder lines are calculated, the maximum value is removed, averaging is carried out to obtain an average Hausdorff distance of the feeder line, if the average distance is larger than a threshold, fault of the feeder line is judged, and if the average Hausdorff distance of each feeder line is smaller than the threshold, fault of a connected bus is judged. A fault feeder line and a fault bus can be judged accurately, the judgment does not rely on a distribution network model and is not influenced by a fault location, transition resistance, an initial phase angle and a line type, and the practicability is good.