基于局部线性嵌入的特征融合方法在岩石破裂状态分类的应用  

Application of locally linear embedding-based feature fusion method in rock fracture state classification

作　　者：杨丽荣[1,2] 江川 黎嘉骏 曹冲 周俊 YANG Lirong;JIANG Chuan;LI Jiajun;CAO Chong;ZHOU Jun(College of Mechanical and Electrical Engineering,Jiangxi University of Science and Technology,Ganzhou 341000,China;Jiangxi Mining and Metallurgy Engineering Research Center,Ganzhou 341000,China)

机构地区：[1]江西理工大学机电工程学院,赣州341000 [2]江西省矿冶机电工程研究中心,赣州341000

出　　处：《应用声学》2023年第5期971-983,共13页Journal of Applied Acoustics

基　　金：国家自然科学基金项目(51464017);江西省教育厅科学技术项目(GJJ190452)。

摘　　要：为了获取岩石破裂过程有效的声发射信号特征,更好地对岩石破裂状态进行分类,提出一种基于流形学习算法的局部线性嵌入特征融合方法进行数据降维。以红砂岩为研究对象设计室内单轴压缩实验采集信号,然后对原始声发射信号预处理并对信号进行特征提取,以时域、频域下的特征向量重新组合成一组新的多维特征向量,采用主元分析和流形学习局部线性嵌入算法分别进行降维。比较两种算法降维后融合特征的聚类效果二维和三维分布图,使用局部线性嵌入算法降维后,4种状态分布相对更近,呈一条水平线趋势,且各状态交叉混叠数目较少,第一状态没有一个样本错判,且4个状态相比于主元分析降维后的聚类效果更集中。再比较两种算法降维后融合特征的敏感度之和,局部线性嵌入算法融合特征敏感度之和远大于主元分析算法,说明经过局部线性嵌入算法降维后得到的融合特征更多地表征了原始信号包含的局部信息,同时证明了局部线性嵌入算法相比主元分析算法具有更好的聚类效果。最后经局部线性嵌入特征融合下的砂岩破裂状态分类实验验证,融合特征后的识别率相对单一的时域特征识别提高了6%。该方法能显著提高岩石破裂状态分类的识别率,降维性能相对突出。In order to obtain the effective acoustic emission signal characteristics of the rock fracture process and better classify the rock fracture state,a locally linear embedding(LLE)feature fusion method is presented for data dimension reduction.The red sandstone was used as the research object and an indoor uniaxial compression experiment was designed to collect the signal.The original acoustic emission signal was then pre-processed and signal features were extracted the feature vectors in the time and frequency domains are recombined into a new set of multi-dimensional feature vectors,using principal component analysis(PCA)and manifold learning LLE algorithm respectively.Comparing the two algorithms after the fusion effect of two-dimensional and three-dimensional distribution,using LLE algorithm,four state distribution is relatively closer,showed a horizontal line trend,and each state cross aliasing number is less,the first state without a sample error,and four states compared with the PCA after the clustering effect is more concentrated.By comparing the sum of the sensitivity of fusion features of the two algorithms after dimension reduction,the sum of fusion features of LLE algorithm is much larger than that of PCA algorithm,which shows that the fusion features obtained by LLE algorithm after dimension reduction represent more of the local information contained in the original signal and proves that LLE algorithm has better clustering effect compared with PCA algorithm.Finally,according to the classification of sandstone fracture states under LLE feature fusion,the recognition rate of the fusion features increased by 6%compared with a single time-domain feature identification.It shows that this method can significantly improve the identification rate of rock rupture state classification,and the dimension reduction performance is relatively outstanding.

关 键 词：声发射信号 砂岩破裂状态分类 局部线性嵌入 主元分析 降维 融合特征敏感度 聚类效果 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] TD32[自动化与计算机技术—计算机科学与技术]