基于改进EFD-小波去噪算法的岩石压裂声发射信号分类  

Classification of rock fracture acoustic emission signals based on improved EFD-wavelet denoising algorithm

作　　者：王婷婷[1,2] 霍雨佳 赵万春[3,4] 史晓东[5] 李方 WANG Tingting;HUO Yujia;ZHAO Wanchun;SHI Xiaodong;LI Fang(School of Electrical and Information Engineering,Northeastern Petroleum University,Daqing 163318,China;Heilongjiang Provincial Key Laboratory of Network and Intelligent Control,Northeastern Petroleum University,Daqing 163318,China;School of Petroleum Engineering,Northeast Petroleum University,Daqing 163318,China;Key Laboratory of Continental Shale Oil and Gas Accumulation and Efficient Development of the Ministry of Education,Northeast Petroleum University,Daqing,163318,China;The 9th Oil Production Plant of Daqing Oilfield Co.,Ltd.,Daqing,163000,China)

机构地区：[1]东北石油大学电气信息工程学院,大庆163318 [2]东北石油大学黑龙江省网络与智能控制重点实验室,大庆163318 [3]东北石油大学石油工程学院,大庆163318 [4]东北石油大学陆相页岩油气成藏及高效开发教育部重点实验室,大庆163318 [5]大庆油田有限责任公司第九采油厂,大庆163000

出　　处：《无损检测》2025年第1期52-59,共8页Nondestructive Testing

基　　金：国家自然科学基金项目(52474036,52174022,52074088,51574088);黑龙江省自然科学基金资助项目(LH2024E008);黑龙江省博士后科研启动项目(LBH-Q21086);黑龙江省“揭榜挂帅”科技攻关项目(DQYT-2022-JS-758);黑龙江省省属高校基本科研业务费:控制科学与工程团队专项项目(2022TSTD-04)。

摘　　要：为准确识别岩石破裂过程中不同阶段产生的声发射信号,提出了一种改进经验傅里叶分解(Empirical Fourier decomposition,EFD)-小波去噪算法,对采集的声发射信号进行降噪处理后,将提取特征输入学习向量量化(Learning vector quantization,LVQ)算法中进行识别分类。首先,使用改进后的EFD算法将岩心破裂的声发射信号进行分解,设定方差贡献率为筛选条件,用小波阈值去噪法进一步滤除噪声后重构信号;然后,用高斯混合模型得到特征向量概率分布,对破裂过程的不同阶段进行分析;最后,提取声发射信号的参数构造特征向量,根据LVQ算法对岩心破裂声发射信号进行分类识别。试验结果表明,该方法可以依据声发射信号准确识别岩心破裂的不同阶段。In order to accurately identify the acoustic emission signals generated in different stages of rock fracture process,this paper proposed an algorithm based on improved empirical Fourier decomposition(EFD)combined with wavelet denoising to preprocess the collected acoustic emission signals for feature extraction and classification using Learning vector quantization(LVQ)algorithm.Firstly,the improved EFD algorithm was used to decompose the acoustic emission signals of rock core fracture,with variance contribution rate set as the screening criterion,and then the wavelet threshold denoising method was used to further filter out noise and reconstruct the signals.Then,Gaussian mixture model was used to obtain the probability distribution of feature vectors,and the different stages of fracture process were analyzed.Finally,the parameters of acoustic emission signals were extracted to construct feature vectors for classification and recognition of rock core fracture acoustic emission signals by LVQ algorithm.According to the experimental results,this method could accurately identify different stages of rock core fracture based on acoustic emission signals.

关 键 词：岩石破裂声发射信号 傅里叶分解 谱峭度 高斯混合模型 学习向量量化 

分 类 号：TB529[理学—物理] TD76[理学—声学] TG115.28[矿业工程—矿井通风与安全]