Abstract: Determining potato rot species and establishing rapid detection methods to identify rot samples. In this study,the main pathogenic bacteria were identified by microbiological and molecular biology methods. The electronic nose was trained to recognize volatile compounds emitted by potatoes experimentally infected with the pathogens. Models were established to identify different stages of rot samples. The results showed that Aureobasidium pullulans was the main pathogenic bacteria of potatoes. The recognition rate of the K-nearest neighbor model was 90% for training set and 85% for predicting set. The recognition rate of the BP-ANN model was 93.75% for training set and 90% for predicting set. All stages of infection were well identified. The results provided a theoretical basis for the later application of electronic nose technology to the detection of rot disease of potato.