Abstract: As a recently rising multi-layer neural network learning algorithm, deep learning has rapidly become a hot topic in various fields for its excellent performance. In order to attract more researchers in the field of coal mine safety to explore and discuss the deep learning and to promote the application of deep learning in the field of coal mine safety, this paper describes the progress and application of deep learning in the image recognition and voice recognition in recent years. This paper also analyzes the problems of the miners’ unsafe behavior and status monitoring and the fault detection of mechanical equipment in coal mines, and the training process of the model is proposed by using image recognition and sound recognition separately for corresponding problems.