利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

8 条记录 (耗时 0.012 秒)

    PROCEDE POUR REALISER UNE REPRESENTATION DES TEXTURES D'UNE STRUCTURE GEOLOGIQUE
    1.
    发明公开
    PROCEDE POUR REALISER UNE REPRESENTATION DES TEXTURES D'UNE STRUCTURE GEOLOGIQUE 失效
    用于生产地质构造的纹理

    公开(公告)号：EP0796443A1

    公开(公告)日：1997-09-24

    申请号：EP96931108.0

    申请日：1996-09-11

    申请人： ELF AQUITAINE PRODUCTION

    发明人： KESKES, Naamen ,  RABILLER, Philippe ,  YE, Shinju

    IPC分类号： G01V1 ,  E21B41

    CPC分类号： G01V1/34 ,  E21B2041/0028 ,  G01V1/301 ,  G01V1/38

    摘要： Method for obtaining a representation of the textures of a geological structure, characterised in that images characteristic of the sedimentology of said environment are formed, parameters corresponding to the nature of said images are estimated at every point of each image and in a spatial domain around said point, so as to determine a texture vector for each of said points and to obtain a set of texture vectors; texture vectors representative of the characteristic textures of said geological environment are selected in said set of texture vectors; a neural network formed of cells distributed in two dimensions, and which contains as many cells as characteristic textures, is used, and the selected texture vectors are used to submit said neural network to a learning process so that a final topology map of the textures characteristic of said geological environment is obtained.

    METHODE DE RECONNAISSANCE AUTOMATIQUE DE FACIES SISMIQUES
    6.
    发明公开
    METHODE DE RECONNAISSANCE AUTOMATIQUE DE FACIES SISMIQUES 失效
    程序自动检测地震kenmerken的

    公开(公告)号：EP0808467A1

    公开(公告)日：1997-11-26

    申请号：EP96931107.0

    申请日：1996-09-11

    申请人： ELF AQUITAINE PRODUCTION

    发明人： KESKES, Naamen

    IPC分类号： G01V1

    CPC分类号： G01V1/301 ,  Y10S706/929

    摘要： An automatic seismic pattern recognition method is characterised in that it includes determining a given number of seismic patterns to be recognised; providing a set of seismic trace portions for said region; defining a pattern recognition parameter common to all the trace portions, and determining the value of said parameter for each of the trace portions of the set; selecting trace portions among said set; selecting a one-dimensional neural network containing as many cells as there are patterns to be recognised, each cell being assigned a value of the recognition parameter; submitting the neural network to a learning process with the selected trace portions, so that at the end of said process, each cell matches a pattern to be recognised, and that said patterns are progressively ordered; presenting each trace portion of said set to be processed to the classified and ordered neural network; and attributing to each trace portion presented to the network the number of the cell closest to it. The invention is particularly useful for recognising seismic patterns between two horizons defined by plotting a seismic section.