赵国富,苏国韶*,胡诗红,黄京华.一种基于微震试验的硬岩破裂模式识别方法[J].实验力学,2022,37(1):107~117 |
一种基于微震试验的硬岩破裂模式识别方法 |
A recognition method of cracking types for hard rock based on microseisms tests |
投稿时间:2021-01-21 修订日期:2021-03-16 |
DOI:10.7520/1001-4888-21-015 |
中文关键词: 岩爆 微震 破裂类型 小波变换 支持向量机 |
英文关键词:rockburst microseismic cracking types wavelet analysis support vector machines |
基金项目:国家自然科学基金(51869003)资助;“水利工程岩石力学”广西高等学校高水平创新团队及卓越学者计划(20200432)资助 |
|
摘要点击次数: 792 |
全文下载次数: 97 |
中文摘要: |
深部工程岩爆灾害孕育过程中硬岩破裂模式的合理识别对岩爆预警具有重要意义。针对传统方法的局限性,本文在硬岩微震试验的基础上提出了一种基于微震信号的硬岩破裂模式识别方法。首先,通过巴西圆盘与直剪试验分别采集花岗岩张拉破裂及剪切破裂的微震信号;然后,利用小波分析方法对两类信号进行分解重构,将样本熵与微震信号幅度作为特征指标并构建训练样本;最后,采用训练样本训练支持向量机,建立硬岩拉剪破裂模式与特征指标的非线性映射关系。研究表明,该方法适用于硬岩拉剪破裂演化过程识别,可为岩爆灾害的合理预警提供有效手段。 |
英文摘要: |
Accurately identification of cracking types for hard rock during the incubation process of rockburst in engineering of great depth is of great significance to rockburst early warning. Aiming at the limitations of traditional methods, a recognition method of cracking types for hard rock based on microseismic signals is proposed on the basis of hard rock microseismic tests. Firstly, the tension and shearing microseismic signals are collected from the Brazilian disc split tests and the direct shearing tests, respectively. And then, the wavelet method is used to decompose and reconstruct the two types of signals. The sample entropy and the amplitude of microseismic signals are used as feature indicators to construct training samples. Finally, the training samples is used to train the support vector machine, thereby the nonlinear relationship between the hard rock tensile-shear failure mode and the feature indicators could be established. The results have shown that this method is feasible for the identification of hard rock tensile-shear failure evolution process, which can provide an effective way to achieve for reasonable early warning of rockburst disasters. |
查看全文 下载PDF阅读器 |
关闭 |
|
|
|
|
|