Abstract: An abnormality detection method of detecting abnormality of a blast furnace from tuyere images shot by cameras installed in vicinities of a plurality of tuyeres of the blast furnace includes: collecting, in a time-series manner, representative brightness vectors defined by representative brightnesses determined based on brightness values of respective pixels for each of the tuyeres image previously shot by the cameras at a same time; extracting a principal component vector by performing principal component analysis on the representative brightness vectors collected in the time-series manner; calculating, as an evaluation value, a length of a normal line drawn in a direction of the principal component vector from the representative brightness vector collected from the tuyere images shot by the cameras at the same time during an operation; and detecting the abnormality of the blast furnace by comparing the evaluation value with a predetermined threshold.

Abstract: A decision algorithm of discriminating a defect type and/or a defect level is automatically produced in a short time. The accuracy of defect classification in terms of a defect type or a defect level is improved.