Underground Personnel Positioning Method Based on Self-training and NLOS Suppression

Abstract

[Purposes] The research of precise location of underground personnel in coal mine is of great significance to protect their life safety. The ultra-wideband signal is susceptible to non-lineof- sight (NLOS) interference, which will seriously affects the positioning accuracy. [Methods] In order to solve the problem that the existing supervised learning methods for NLOS identification and suppression require long time, labor intensive feature, and high cost became of the needs to obtain training data and label allocation, a method for underground personnel positioning based on self-training and suppression of NLOS is proposed, and a new general data fusion framework is designed. First, PDR and map information are combined to remove infeasible positions, and multi-granularity mesh filters are used to estimate the position and heading, and the map information is fully utilized to generate weak labels. Second, through multi-sensor data fusion, the weak label is iteratively improved, and training samples are generated to realize autonomous collection of training data. Finally, the data of map, inertial sensor, and ultra-wideband measurement are fused by Bayesian estimation to infer the location. [Findings] Through the simulation tests in the downhole environment, the results show that for complex downhole scenes, the root-mean-square error of NLOS decreases from the original 1.02 to 0.32 m, the ranging error is improved by 69%, and the positioning result with the positioning error less than 0.3 m can be increased from 49% to 89%. Thus, the effectiveness of the proposed method for locating underground personnel is proved.

Keywords

• intelligent coal mine
• personnel positioning
• uwb
• nlos mitigation
• self-training