Study On Hierarchical Localization Algorithm Based On Mesh Dividing For Coal Mine

The development of mine Internet of things popularized the application of Wi Fi technology in coal mine underground. How to realize the function of location used to track the position information of miners in the Wi Fi network has become one of the hot topics. Due to the limitations of indoor location technology, the positioning performance was poor when used in coal mine. In this thesis, the coal mine underground positioning based on Wi Fi network was studied.The common positioning algorithms on Wi Fi network were briefly introduced first. By analyzing these algorithms, it was pointed out that scene positioning method was more suitable for the coal mine underground. As the theory of scene positioning method was fingerprint matching, the paper introduced statistical machine learning theory into the positioning. Fingerprint matching in scene position method was converted into classification in a support vector machine.In order to improve the accuracy of the classification, the paper focused on optimizing the parameters of support vector machine. The simulation results show that the classification accuracy can reach 98.88%, with use of heuristic optimization algorithm to optimize the parameters of support vector machine.Through analysis of the actual scene environment, the hierarchical localization algorithm was proposed in this paper. The algorithm based on hierarchical thinking implemented stepwise refinement localization ranging from large to small area. Compared with scene position method traditional, the experiment results show that, the proposed algorithm makes full use of advantages and avoids the disadvantages of the traditional algorithms. What’s more, the proposed algorithm can obtain better location precision and stability and the average positioning accuracy is improved about 10%.