The influence of the coal mine geographic environment on the electromagnetic transmission might result in the
difficulty of wireless positioning under the mine. Concerning that the influence of the underground working face on the
wireless signal attenuation is mainly reflected through the electricity path attenuated and based on the underground
geographic differences, two corresponding electromagnetic loss models are established. Under the conditions of low
energy consumption and no need for hardware devices, RISS algorithm is found suitable to be used in the underground
coal mine. However, the problems of large error and poor precision still exist. This paper first introduces the standard
deviation threshold, TSA, as decided by the practical environment; then compares it with the standard deviation, RSA,
obtained by the calculation of every target node to finally obtain the modified value of RSS. Based on that, the BP
algorithm is introduced for learning training, improvement of the positioning error rate and the system’s positioning
precision.