Abstract: A method and system for detecting dirt on an electrode of an electromagnetic flowmeter are provided. The method includes: under three different conditions acquiring resistance values between the electrode and ground to form a first dataset, second datasets, and a sample set to be tested; extracting a positive definite feature matrix corresponding to each sample batch and calculating a Riemann center thereof; calculating a similarity index between the sample feature matrix and each of the first feature matrices and the second feature matrices; extracting l feature matrices with a largest similarity index, and calculating a local Riemann center thereof; and calculating proximity between the local Riemann center and each of the second Riemann centers, and determining that a Riemann center with the greatest proximity corresponds to dirt on the electrode corresponding to the sample set to be tested. The method can achieve a online rapid detection of dirt on the electrode.