天然地震论文：基于HMM和GMM天然地震与人工爆破识别算法研究

天然地震论文：基于HMM和GMM天然地震与人工爆破识别算法研究

【中文摘要】地震可看作是由地震波从震源向外传播过程中造成相关介质震动过程的集合。观测到的地震包括天然地震和人工爆破。人工爆破是由人的活动引起的地震,包括工业爆破地震、矿震和核爆等。目前人工爆破发生的频率越来越高,如果不作适当处理,易误将人工爆破归为天然地震。由地震波形来判断所发生的事件是否为人工爆破,对核爆侦查也具有重要意义。地震信号是非平稳非线性时变信号,本文利用短时平稳时变信号(如语音信号)处理中的较成熟的特征抽取算法和识别模型,试图应用于天然地震与人工爆破的识别中。本文从地震与爆破波形中提取了3种特征：美尔倒谱系数(Mel-Frequency Cepstrum Coefficients,简称MFCC)特征、线性预测倒谱系数(Linear Prediction Cepstrum Coefficients,简称LPCC)特征和基于希尔伯特-黄变换(Hilbert Huang Transform,简称HHT)的特征。文中详细介绍了MFCC、LPCC的基本理论和提取过程,并且阐述了HHT变换的基本理论以及它在地震信号中的应用和基于HHT特征参数的提取过程。本文对天然地震与人工爆破识别的方法采用隐马尔可夫模型(Hidden Markov Model,简称HMM)和高斯混合模型(Gaussian Mixture Model,简称GMM)。HMM是一种基于Markov链的统计模型,由HMM训练和HMM识别两部分组成。HMM有3个基本算法：前向-后向算法、Viterbi算法和Baum-Welch算法。而GMM是一种状态数为1的连续HMM。本文在Matlab中研究了MFCC特征和LPCC特征的维数对HMM模型识别效果的影响,以及信号样本点有效长度对HMM模型识别效果的影响；研究了GMM的模型阶数对GMM模型识别效果的影响,也研究了MFCC特征和LPCC特征的维数对GMM模型识别效果的影响,以及信号样本点有效长度对GMM模型识别效果的影响。结果表明,采用HMM作为识别模型时,这3种波形特征中,MFCC和LPCC比HHT特征识别效果好；而采用GMM识别模型时,同样也是MFCC和LPCC比HHT特征识别效果好。在比较HMM和GMM两种识别模型时,GMM识别性能高于HMM的识别性能,并且GMM的训练时间比HMM的训练时间少60%以上。

【英文摘要】Earthquake can be regarded as the assemblage of sequential earth medium quake processes due to seismic waves spread outward from the hypocenter. Being observed earthquakes include natural events and explosion events. Explosion is originated by human activities; it may be industrial explosion, mine tremor and nuclear explosion etc. The occurring of explosion is more and more regular. If not being properly treated, explosion event would be frequently erroneously considered as natural earthquake event. Recognizing observed event by seismic waves is the main means of nuclear explosion reconnaissance.Seismic signal is a non-steady non-linear time-variant signal. This thesis extends the feature extraction algorithms and recognition paradigms that having been successfully applied in short-time steady time-variant signal processing (such as speech processing), attempting to recognize earthquake and explosion more robust. Three kinds of features are extracted from seismic waves:Mel-Frequency Cepstrum Coefficient (MFCC) features, Linear Prediction Cepstrum Coefficient (LPCC) features and Hilbert Huang Transform (HHT)-based features. This paper introduces the basic theory and the extractive process of MFCC and LPCC; the paper also details the basic theory of HHT and its applications in seismic signal, and then describes how extract HHT-based features.Two recognition paradigms are utilized in the paper:Hidden Markov Model (HMM) and Gaussian Mixture Model (GMM). HMM is a statistical model based on Markov chain, being consisted of two stages:HMM training and HMM recognition. HMM is constituted by three basic algorithms:the forward-backward algorithm, Viterbi algorithm and Baum-Welch algorithm. GMM is a continuous HMM with only one stateUsing software of Matlabe, this thesis investigates the impact of MFCC’s or LPCC’s feature number on HMM’s correct recognition rate, and the impact of signal sampling valid length on HMM’s correct recognition rate. In addition, the impact of model order of GMM on its effect, the impact of MFCC’s or LPCC’s feature number on GMM’s correct recognition rate, and the impact of signal sampling valid length on GMM’s correct recognition rateThe results show that:for HMM recognition paradigms and these three kinds of features, MFCC features and LPCC features are better than HHT-based features; for GMM recognition paradigms and these three kinds of features, get the same conclusion:MFCC and LPCC are better than HHT. When comparing the two recognition paradigms, the correct recognition rates of GMM is better than HMM, moreover, the training time of GMM is at least 60% less than that of HMM.

【关键词】天然地震 人工爆破 隐马尔可夫模型 高斯混合模型

【英文关键词】Earthquake Explosion Hidden Markov Model Gaussian Mixture Model

【目录】基于HMM和GMM天然地震与人工爆破识别算法研究摘要3-4Abstract4-5第1章 绪论8-121.1 研究背景与意义8-91.2 天然地震与人工爆破波形的差异91.3 当前研究现状9-101.4 本文的主要工作10-12第2章 HHT变换的理论知识与在地震中的应用12-212.1 HHT变换的基本原理与方法12-152.1.1 经验模态分解(EMD)12-132.1.2 希尔伯特变换(HT)13-152.2 HHT在地震信号时频领域的分析应用15-202.3 小结20-21第3章 P波初至判断与地震信号特征提取21-313.1 P波初至判断21-243.1.1 STA/LTA方法的原理和计算方法21-223.1.2 计算基于EMD的P波初至点的步骤其结果22-243.2 分帧24-263.3 特征提取26-303.3.1 MFCC系数参数特征提取26-273.3.2 LPCC系数参数特征提取27-293.3.3 基于HHT变换特征参数提取29-303.4 小结30-31第4章 HMM和GMM的基本理论31-434.1 隐马尔可夫模型(HMM)31-384.1.1 HMM基本概念31-344.1.2 HMM识别算法34-384.2 高斯混合模型(GMM)38-424.2.1 GMM基本概念38-394.2.2 GMM参数估计39-414.2.3 GMM识别算法41-424.3 小结42-43第5章 基于HMM和GMM实验和分析43-595.1 软硬件平台435.2 数据集的选取43-465.3 HMM模型的建立和实验46-535.3.1 初始化HMM参数465.3.2 HMM训练46-505.3.3 HMM识别505.3.4 基于HMM的实验及其分析50-535.4 基于GMM的实验53-575.5 实验结果与分析57-585.6 小结58-59第6章 结论与展望59-61参考文献61-65攻读硕士期间的科研成果和获奖情况65-66致谢66-67

本文来源：https://www.2haoxitong.net/k/doc/26e1aa282af90242a895e5f0.html