基于模糊C均值聚类-支持向量机的海底沉积物分类识别
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
在总结了目前海底底质分类研究的基础之上,率先提出利用计算机数值模拟技术对海底底质进行分类识别研究。相较于目前海底底质分类研究中所使用的水槽实验法,提出采用计算机数值正演技术模拟实际地震勘探中数据采集过程。在分类识别算法上,分别采用支持向量机(SVM)和模糊C均值聚类(FCM)算法对采集的数据进行分类,为使支持向量机分类识别率达到最大,引入差分进化算法对支持向量机中关键参数进行最优化搜索,并研究了向原始地震记录中加入10%,30%,50%的高斯白噪音时算法的稳定性。在分析了这两种算法分类识别的正确率及其各自的优缺点后,提出了海底底质分类识别的两步法,即(1)先利用模糊C均值聚类进行一粗糙的预测分类,在每一类中挑选聚类性较好的数据作为支持向量机的训练样本;(2)将上一步中筛选的样本作为支持向量机的训练样本,并用差分进化算法优化支持向量机分类参数,再利用训练好的支持向量机对其余数据做预测分类。鉴于计算机数值模拟的可重复性、高效快速性及本文提出的模糊C均值聚类-支持向量机方法的鲁棒性,为便于开展进一步研究,归纳总结了一套行之有效的采用计算机数值模拟技术开展海底底质分类识别研究的一般化流程。
Basis on the previous research about the classification of sediment, Here, for the first time, we proposed the application of numerical simulation technology in classification of seabed sediment. Compared to the currently used flume method in the classification of sediment, we proposed the usage of computer technology to simulate the seismic acquisition process in practical exploration. In the classification and recognition algorithms, the support vector machine and fuzzy C mean clustering methods(FCM) were used to classify the data acquired. To maximize the accuracy of support vector machine(SVM), we introduced the evolutionary difference algorithm to optimize the values of the key parameters of support vector machine classification model. Then, to further study the stability of the methods, 10%, 30% and 50% of Gaussian white noise was added into the original data. After full analysis of the advantages and disadvantages of both approaches from its principle and classification accuracy, we designed a two-step classifier which combined the fuzzy C mean clustering and support vector machine. Firstly, the unsupervised classification algorithm, FCM, was used to classify the data preliminarily, and screened the samples with good clustering. Secondly, those selected data in step 1 were served as train samples of support vector machine model. The differential evolution algorithm was used to optimize the key parameters of support vector machine model, then the optimized support vector machine model was used to classify the remaining data. Finally, Based on the repeatable, convenient characters of the computer simulation and the relevant high accuracy and the robustness of FCM-SVM, a total solution of a classification, which will be easier, deeper, further to study the feature of reflection from sediment is proposed in the article.
引文
[1]Mackenzie K V.Reflection of sound from coastal bottoms[J].Acoust Soe Am,1960,32(2):221-231.
    [2]Biot M A.Theory of propagation of elastic waves in a fluid-saturated porous solid,I.Low-frequency range[J].Acoust Soc Am,1956,28(2):168-178.
    [3]Biot M A.Theory of propagation of elastic waves in a fluid-saturated porous solid,II.high-frequency range[J].Acoust Soc Am,1956,28(2):168-179.
    [4]Biot M A.Mechanics of deformation and acoustic propagation in porous Media[J].Journal of Applied Physics,1964,33(4):1482-1498.
    [5]孟金生,关定华.海底沉积物的声学方法分类[J].声学学报,1982,7(6):337-343.
    [6]王正垠,马远良.宽带声呐湖底沉积物分类研究[J].声学学报,1996,4:517-524.
    [7]刘建国,李志舜.基于连续小波变换的湖底回波特征提取[J].西北工业大学学报,2006,1:111-114.
    [8]卜英勇,张超,聂双双.基于离散小波变换的水下回波信号尾波包络特征提取[J].郑州大学学报(工学版),2007,4:80-83.
    [9]邓跃红,聂双双.基于小波变换的水下超声波测距方法研究[J].郑州大学学报(工学版),2007,28(4):75-79.
    [10]裴正林.双相各向异性介质弹性波传播交错网格高阶有限差分法模拟[J].石油地球物理勘探,2006,41(2):137-143.
    [11]杨顶辉.双相各向异性介质中弹性波方程的有限元解法及波场模拟[J].地球物理学报,2002,45(4):575-583.
    [12]Zhu X,Mcmechan G A.Numerical simulation of seismic responses of poroelastic reservoirs using Biot theory[J].Geophysics,1991,56(3):328-339.
    [13]王东,张海澜,王秀明.部分饱和孔隙岩石中声波传播数值研究[J].地球物理学报,2006,49(2):524-532.
    [14]姚姚,奚先.随机介质模型正演模拟及其地震波场分析[J].石油物探,2002,41(1):31-36.
    [15]奚先,姚姚.随机介质模型的模拟与混合型随机介质[J].地球科学-中国地质大学学报,2002,27(1):67-71.
    [16]Li C P,Liu X W.Study on the scales of heterogeneous geologic bodies in random media[J].Applied Geophysics,2011,4:363-369.
    [17]殷学鑫,刘洋.二维随机介质模型正演模拟及其波场分析[J].石油地球物理勘探,2011,6:862-872
    [18]李红星,陶春辉.双相各向异性随机介质伪谱法地震波场特征分析[J].物理学报,2009,4:2836-2842.
    [19]Mavko G,Mukerji T,Dvorkin J.the rock physics handbook:tools for seismic analysis in porous media[M].Cambridge:Cambridge university press,2003.
    [20]Gassmann F.Uber die Elastizitat porous media[J].Vier der Natur Gesellschaft in Zurich,1951,96:1-23.
    [21]Gessrtsna J,Smit D C.Some aspects of elastic wave propagation in a fluid-saturated porous solids[J].Geophysics,1990,95:15643-15656.
    [22]Zeng Y Q,He J Q,Liu Q H.The applieation of the perfeetly matehed layer in numerical modeling of wave propagation in poroelastic media[J].Geophsics,2001,66(4):1258-1266.
    [23]Haykin S.神经网络原理(第二版)[M].叶世伟译.北京:机械工业出版社,2004:229-237.
    [24]Cortes C,Vapnik V N.Support vector networks[J].Machine Learning,1995,20:273-297.
    [25]Vapnik V N.Statistical learning theory[M].New York:Wiley,1998.
    [26]Rainer S,Kenneth P.Differential evolution:A simple and efficient adaptive scheme for global optimization over continuous spaces[J].Global Optimization,1997,11:341-359.
    [27]Bezdek J C.Pattern Recognition with Fuzzy objective Function Algorithms[M].New York:Plenum Press,1981.
    [28]Bezdek J C,Hathaway R J.Recent convergence results for the fuzzy c-means clustering algorithm[J].Classifieation,1988,5(2):237-247.
    [29]高新波,李洁,谢维信.FCM算法中参数m的优选[J].模式识别与人工智能,2000,13(1):7-11.
    [30]Folk R L,Andrews P B,Lewis D W.Detrital sedimentary rock classification and nomenclature for use in New Zealand[J].New Zealand Journal of Geology and Geophysics,1970,13:937-968.
    [31]Daubechies I.小波变换十讲[M].李建平,杨万年,译.北京:国防工业出版社,2004:56-99.

版权所有:© 2023 中国地质图书馆 中国地质调查局地学文献中心