The acquisition card is customized for distributed fiber optic vibration DVS system, with dual-channel synchronous sampling, 100M sampling rate, 12-bit, with trigger output function, and built-in averaging and differential algorithms. The DVS-ETH-100-1 is a 12-bit dual-channel high-speed data. 100MSps dual-channel high-speed acquisition fiber optic sensing demodulation card, which is a PCIe x8 Lane, dual-channel, 14bits respectively rate fiber optic sensing demodulation card, sampling rate of 100MSps. Onboard high-performance FPGA chip with abundant multiplier and RAM resources. At present, this distributed sensing technology has been used in long-distance natural gas and oil. Zhongyao Luo, Hao Wu, Zhao Ge, and Ming Tang This work was supported in part by the National Key Research and Development Program of China under Grant 2021YFB2800902; in part by the National Natural Science Foundation of China under Grant 62225110; and in part by the innovation Fund of WNLO. In this paper, we propose a convolutional neural network (CNN) to analyze DVS data and achieve high-accuracy event recognition fully. We conducted experiments outdoors and collected more than 10,000 sets of vibration data. Through training, the CNN acquired the features of the raw DVS data and.