A Layered Two-step Hidden Markov Model Position Method For Mine Environment

The safety of miners is of interest to all countries. In the event of a coal mine disaster, how to locate the miners remains the biggest and most urgent issue. Underground mine environments, which is also indoor environments, differ from other indoor environments because of its unique structure. Concrete walls and long corridors makes the propagation of RF signals quite different from that in open space. The aim of this study is to propose a precise positioning method for underground mine environments to a low cost and with acceptable accuracy.During the research work, this paper first studies common indoor location signals, including their suitability for different environments and their accuracy. By investigate the potential interference factor, the location signals which are not suitable for underground mine environments are excluded, and those which are suitable for mine environments are chosen. According to the requirement of low cost and high accuracy, this paper chooses WiFi signal as the applied location signal. Then in-depth learning and analysis of current geolocation methods for indoor areas have been carried out: theories, advantages, disadvantages and the level of suitability of each method for mine environment have been presented. The suitable methods have a common “jumping” problem, which is that the neighboring positioning results are far in physical location. Based on this problem, a layered two-step Hidden Markov Model has been proposed to simulate human walking in underground mine environments and an improved Viterbi algorithm suitable for the model has been implemented. The first layer is a Hidden Markov Model to model the moving task of a mobile unit and the second layer is a Markov Chain for simulating the moving state of the mobile unit. The proposed method successfully solve the “jumping” problem in other scenery based methods.The result of the positioning accuracy is quite satisfying compared to other positioning methods in the same category, in some walking paths the error can be within 1.5 meters. The proposed positioning method can be claimed to be quite suitable for underground mine environments to a low cost and with acceptable accuracy.