Abstract: Earthquake detection is the key step of automatic processing such as earthquake quick report and earthquake early warning. In recent years, the use of deep learning algorithm to detect earthquakes has developed rapidly. However, there are few detailed researches on data processing flow and neural network parameter optimization. Taking 8 321 near earthquake data observed by Xichang array as an example, this paper introduces in detail the data processing flow of detecting earthquakes by using the deep convolution neural network, such as data preprocessing, model training, waveform length, network layers, learning rate and probability threshold on the detection results. Then we detect the continuous waveform with the optimal model. Our research shows that data preprocessing, data augmentation can improve the detection accuracy and anti-interference ability of the model. The length of waveform window used for model training can be approximated to the maximum value from arrival time difference between S- and P- wave. The detection results of different network layers （5—8 layers） are similar. For seismic detection, it is more appropriate to set the learning rate as 10⁻⁴—10⁻³. The earthquakes detected by convolution neural network are related to the probability threshold. By drawing the tradeoff curve of precision with recall rate, it can provide a reference for selecting the appropriate probability threshold. This paper provides an important reference for further study of earthquake detection with deep learning algorithm.