岩土工程学报2016，Vol.38Issue(10)：1849-1858,10.DOI:10.11779/CJGE201610014
基于EMD_SVD的矿山微震与爆破信号特征提取及分类方法
Feature extraction and classification of mine microseism and blast based on EMD-SVD
摘要
Abstract
To solve the difficult problem in identifying rock mass microseism and blasting vibration signals, a method for feature extraction and classificationis proposed based ontheempirical mode decomposition(EMD) and singular value decomposition(SVD). Firstly, the mine signalsare decomposed by EMD, and the IMF1 to IMF6 selected by correlation coefficients and variance contribution ratiosare the main intrinsic mode functions(IMFs). Then the SVDis used to obtain singular valuessi(i=1,2,L,6) of feature vector matrix constructed of the main IMFs.Furthermore, thesupport vector machine(SVM)is adopted to train, classify and recognizethesignals of Yongshabamine. The results show that there arelarge differences of singular values1s,s2 and3s between microseisms and blasts, and the best pattern recognitionis obtained when1s is 7.5 with an accuracy rate of 88.25%. In addition, the SVM method with an accuracy rate of 93%is better than the BP neural network method, Bayes method and boundary value method. In conclusion, the proposed method provides a new way forthefeature extraction and classification of mine microseism and blast.关键词
微震与爆破/分类识别/特征提取/经验模态分解/奇异值分解/支持向量机Key words
microseism and blast/pattern recognition/feature extraction/empirical mode decomposition/singular value decomposition/support vector machine分类
建筑与水利引用本文复制引用
尚雪义,李夕兵,彭康,董陇军,王泽伟..基于EMD_SVD的矿山微震与爆破信号特征提取及分类方法[J].岩土工程学报,2016,38(10):1849-1858,10.基金项目
国家自然科学基金项目（41272304）；国家重点研发项目（2016YFC0600706）；国家自然科学基金青年基金项目 （）
