关键词: 煤矿井下, 指纹匹配定位, fuzzy C-Means clustering算法, 区域划分, 指纹库更新, hidden Markov model运动轨迹模型, adaptive network-based fuzzy inference system定位模型, 定位精度

Abstract: According to the characteristics of underground environment, a fingerprint location algorithm based on dynamic fingerprint updating is proposed. FCM(Fuzzy C-Means Clustering) is used to divide the location area according to the signal distribution characteristics, and the training and learning model is established in each sub area. On the basis of FCM algorithm, a HMM(Hidden Markov Model) motion information sequence model based on the location of mobile users is proposed. The dynamic update of fingerprint database is realized by users unconsciously participating in the collection of RSSI(Received Signal Strength Indication) sequence. ANFIS(Adaptive Network-based Fuzzy Inference System) algorithm with self-learning ability is used to locate unknown nodes. The experimental results show that the accuracy of the fingerprint location algorithm based on dynamic fingerprint update can reach 1.6m, which can meet the real-time location requirements of the underground roadway.

Key words: underground coal mine, fingerprint matching and positioning, fuzzy C-Means clustering algorithm, divide the positioning area, dingerprint database update, hidden Markov model motion trajectory model, adaptive Network-based fuzzy inference system positioning model, positioning accuracy