Underground location algorithm based on random forest and environmental factor compensation

Springer Science and Business Media LLC - Tập 8 - Trang 1108-1117 - 2021
Xin Qiao1, Fei Chang2
1School of Electronic Engineering, Chaohu University, Chaohu, China
2Huishang Futures Co. LTD, Hefei, China

Tóm tắt

Aiming at the poor location accuracy caused by the harsh and complex underground environment, long strip roadway, limited wireless transmission and sparse anchor nodes, an underground location algorithm based on random forest and compensation for environmental factors was proposed. Firstly, the underground wireless access point (AP) network model and tunnel environment were analyzed, and the fingerprint location algorithm was built. And then the Received Signal Strength (RSS) was analyzed by Kalman Filter algorithm in the offline sampling and real-time positioning stage. Meanwhile, the target speed constraint condition was introduced to reduce the error caused by environmental factors. The experimental results show that the proposed algorithm solves the problem of insufficient location accuracy and large fluctuation affected by environment when the anchor nodes are sparse. At the same time, the average location accuracy reaches three meters, which can satisfy the application of underground rescue, activity track playback, disaster monitoring and positioning. It has high application value in complex underground environment.

Tài liệu tham khảo

Breiman L (2001) Random forests. Mach Learn 45:5–32 Chen G, Zhang Y, Wang Y et al (2015) Unscented Kalman Filter algorithm for WiFi-PDR integrated indoor positioning. Acta Geodaetica et Cartographica Sinica 44(12):1314–1321 Cui LZ, Li L, Yuan MM et al (2013) Research on underground coal mines positioning algorithms based on kernel function and particle filter. Chin J Sens Actuat 26(12):1728–1733 Ding EJ, Qiao X, Chang F et al (2013) Improvement of weighted centroid localization algorithm for WSNs based on RSSI. Trans Microsyst Technol 32:53–56 Ding E, Qiao X, Chang F (2014) Iterative algorithm for Quasi-Newton in WSN based on modifying average hopping distances. WIT Trans Eng Sci 87:589–596 Feng W, Chao S, Jincheng Ji et al (2015) Three-dimensional positioning algorithm based on TDOA and AOA in coal mine underground. Ind Mine Autom 41(5):78–82 Han DS, Yang W, Liu X et al (2013) A weighted centroid localization algorithm based on received signal-strength indicator for underground coal mine. J China Coal Soc 38(3):522 Hu QS, Wu LX, Zhang S, Ding EJ (2014) Placement of positioning WSN in coal face and energy consumption analysis. J China Univ Min Technol 43(2):351–355 Hu QS, Zhang S, Wu LX, Ding EJ (2016) Localization techniques of mobile objects in coal mines: challenges, solutions and trends. J China Coal Soc 41(5):1059–1068 Wang JH (2014) Development and prospect on fully mechanized mining in Chinese coal mines. Int J Coal Sci Technol 1(3):253–260 Li XH (2013) Using" random forest" for classification and regression. Chin J Appl Entomol 50(4):1190–1197 Li L, Zhang ZH et al (2017) Precision positioning algorithm in coal mine tunnel based on RSSI. J China Univ Min Technol 46(1):183–191 Peng Y, Wang D (2014) A review: wireless sensor networks localization. J Electron Meas Instrum 25(5):389–399 Qiao X. (2015) Localization Algorithm of Wireless Sensor Network and Its Improvement Based on DV-Hop. China University of Mining and Technology. Qiao X, Yang H-S, Wang Z-C (2017) Iterative LM algorithm in WSN–utilizing modifying average hopping distances. Int J Online Eng (iJOE) 13(10):4–20 Sun JP (2013) Research of mine wireless broadband transmission technology. Ind Mine Autom 39(2):1–5 Sun JP, Li CX (2014) TOA underground coal mine target positioning method based on WiFi and timing error suppression. J China Coal Soc 39(1):192–197 Wang DD (2009) Research of planning and aplication of AP in digital mines WLAN system. Jiaotong University, Beijing Wu J R, Cui R, et al. (2018) Mine personnel fusion location system. Industry and Mine Automation. Yang W, Liusheng H, Wei Y (2010) A novel real-time coal miner localization and tracking system based on self-organized sensor networks. EURASIP J Wirel Commun Netw. https://doi.org/10.1155/2010/142092 Yang C, Feng L et al (2013) A wireless positioning method based on data interpolation and weighted index for mine locomotive. J Hefei Univ Technol Nat Sci Ed 11:1331–1334 Zhang XZ (2015) Study on mine WLAN terminal design and roaming switch technology. University of Mining and Technology, China