OTDR distr ibuted optical fiber sensing system is widely used in the field of safety monitoring,and its key task is to identify the type of vibrati on event.The recognition rate and robustness of traditional pattern recognition methods are not sufficient enough.Deep learning can extract features and reali ze classification spontaneously,with better accuracy and adaptability.Compared with the two-dimensional convolutional neural network (2D-CNN),the one-dimen si onal convolutional neural network (1D-CNN) has smaller net size and faster trai n ing speed.Set LeNet-5as the baseline network,this paper attained to classify the vibration events for Φ-OTDR with buried sensing fi ber which based on 1D-CNN .In addition,the optimal parameters to construct a LeNet-1D-V network was se le cted by comparing the influence of different structural hyperparameters on recog nition accuracy.The experiment results show that the LeNet-1D-V constructed i n this paper improves the classification accuracy rate from 92.3% to 94.6% in the classification of 5types of buried fiber vibration events,which provides a fou ndation for the classification of multiple event types detected by buried fiber.