基于模态理论和改进GMM的声发射源识别研究  

Acoustic Emission Signal Source Recognition Based on Modal Theory and Modified GMM

作　　者：杨勇[1,2] 李晶 朱作付 邓艾东[4] YANG Yong;LI Jing;ZHU Zuofu;DENG Aidong(School of Information Engineering,Xuzhou College of Industrial Technology,Xuzhou Jiangsu 221140,China;Key Laboratory of Underwater Acoustic Signal Processing of Ministry of Education,Nanjing Jiangsu 210096,China;School of Information Engineering,Najing Audit Unversity,Nanjing Jiangsu 211815,China;National Engineering Research Center of Power Generation Control and Safety,Nanjing Jiangsu 210096,China)

机构地区：[1]徐州工业职业技术学院信息工程学院,江苏徐州221140 [2]东南大学水声信号处理教育部重点实验室,江苏南京210096 [3]南京审计大学信息工程学院,江苏南京211815 [4]大型发电装备安全运行与智能测控国家工程研究中心,江苏南京210096

出　　处：《电子器件》2024年第1期128-133,共6页Chinese Journal of Electron Devices

基　　金：国家工程中心创新能力建设项目(6750100000);国家自然科学基金项目(52005267)。

摘　　要：基于模态声发射信号理论,提出了一种利用声学对数倒谱统计参数作为声发射信号特征参数的分析与提取方法。从声发射信号多模态特性出发,提出了一个基于改进高斯混合模型的声发射源信号识别系统。理论分析和实验结果表明,该方法能准确地判断声发射信号源,不仅能够应用于突发型声发射信号的识别,而且可以应用于连续型声发射信号的识别。Based on the modal acoustic emission signal theory,an analysis and interception method using the acoustic log cepstrum sta-tistical parameters as the feature parameters is proposed.According to the characteristic of the multiple modal acoustic emission signal,an acoustic emission source signal recognition system is proposed based on modified Gaussian mixture model.Theoretical analysis and experimental results show that the proposed method could accurately recognize the acoustic emission signal source.Meanwhile the modi-fied method could not only be applied to the recognition of emergency acoustic emission signals,but also be applied to the continuous type of acoustic emission signals.

关 键 词：声发射信号 倒谱 高斯混合模型 识别 

分 类 号：TN912.3[电子电信—通信与信息系统]