Abstract: In order to protect the safety of the coal mine workers and reduce economic losses, an assessment method for coal mine safety status based on multi-sensor data fusion was proposed. The data from sensors of gas concentration, temperature, wind speed, carbon monoxide, dust and others from the underground was first handled, the batch estimate pretreatment methods based on the average value were used to get the first level fusion result, and then the D-S evidence theory was used to eliminate the uncertainty in the assessment and improve the accuracy. At last, a specific case was used to verify the feasibility of the proposed method. The result shows that the assessment method is of a high degree of accuracy, and it can provide decision support for the assessment and judgment of the state of coal mine safety.

Key words: sensor, data fusion, gas concentration, batch estimation, D-S evidence theory