This paper proposes a one-dimensional convolutional neural network and long short-term memory (1D CNN-LSTM)-based classification method for open-switch faults in a Vienna rectifier. Single and compound open-switch fault scenarios were established, and data for each operating condition were obtained. Based on these data, a 1D CNN-LSTM model was designed for fault classification. The results confirmed that the proposed model can distinguish the normal state from fault states and classify both single and compound faults.