Abstract: The underground intelligent system of coal mine is formed by many subsystems, such as communication, sensing, regulation and so on.In order to effectively cooperate with fully mechanized mining automation system, realize the automatic and intelligent mining of the working face, reduce the possibility of safety accidents as much as possible, and ensure the safe and efficient mining of the working face, based on traditional mining technology and advanced information technologies such as big data and artificial intelligence, we build a multi-information fusion system to integrate and analyze multiple data sources and heterogeneous data such as safety monitoring and monitoring of coal working face, equipment operating conditions, mining process and manual measurement, and conduct regional qualitative and quantitative analysis, evaluation and prediction of coal working face.The inversion of area security status is carried out.At the same time, the system is applied to Hanjiawan Coal mine, and the results show that the application of this system changes the traditional information fusion into measurement mode, effectively reduces the risk of equipment or personnel damage and the loss of shutdown and production caused by the bad working face environment in the mining process, and guarantees the safe and efficient production of the mine.