(1. School of Civil and Resource Engineering，University of Science and Technology Beijing，Beijing 100083，China；2. State Key Laboratory of High-efficient Mining and Safety of Metal Mines，Ministry of Education，University of Science and Technology Beijing，Beijing 100083，China；3. School of Safety Engineering，China University of Mining and Technology，
Xuzhou，Jiangsu 221116，China)
Abstract：In this paper，for characterization of the damage process and precursor characteristics of the coal samples，the acoustic emission(AE) location technology is used to describe damage evolution process of the coal the samples under cyclic loading and unloading. Based on k-means algorithm，the cluster analysis method of the temporal-spatial dimension is proposed to study the correlation of AE events. Based on the obtained results，AE events can be divided into three categories. The short-link AE events describe the evolution process of small-scale damage，having an obvious temporal-spatial migration characteristics. The middle-link AE events reflect the evolution process of the overall damage，evidenced by a “blank zone” in the temporal-spatial distribution image. The long-link AE events represent a random damage process，and temporal-spatial distribution is isolated relatively. Among the three types of AE events，the evolution process of the middle-link AE events has the highest correlation with coal samples buckling failure. The “blank zone” of the AE events shrinks significantly while the energy release increases obviously，which can be regarded as precursor characteristics of the coal samples buckling failure.
张志博1，2，李树杰1，2，王恩元3，刘夏楠1，2，张英华1，2 . 基于声发射事件时–空维度聚类分析的煤体损伤演化特征研究[J]. 岩石力学与工程学报, 2020, 39(S2): 3338-3347.
ZHANG Zhibo1，2，LI Shujie1，2，WANG Enyuan3，LIU Xianan1，2，ZHANG Yinghua1，2. Research on the damage evolution characteristics of coal based on cluster analysis of temporal-spatial dimension of acoustic emission events. , 2020, 39(S2): 3338-3347.
2020, Vol. 39 
