一种时序曲线的表示和识别方法  

Method of time-sequence curve’s expression and its recognition.

作　　者：李国和[1] 江希[1] 

机构地区：[1]中国石油大学计算机科学与技术系,北京102249

出　　处：《计算机工程与应用》2007年第31期236-239,共4页Computer Engineering and Applications

基　　金：国家自然科学基金(the National Natural Science Foundation of China under Grant No.60473125);中国石油天然气集团公司(CNPC)石油科技中青年创新基金( No.05E7013)

摘　　要：为了进行时序曲线识别,沿着x轴方向,通过均等细分180°,对曲线进行标准编码,以反映曲线的总体变化趋势。在此基础上,进一步确定曲线的修正编码,以表示曲线与标准编码的差异程度。通过两级编码,准确表示了曲线的变化趋势。最后分别定义标准编码和修正编码的近似度函数,实现两条曲线不等长编码的近似度计算。对新疆克拉玛依陆梁地区的测井曲线进行两级编码和近似度计算实现了沉积微相的自动识别,取得很好的识别效果。In order to recognize time-sequence curves,along with the x-axis direction and by means of averagely dividing 0°- 180° into small intervals,standard codes are adopted to express the general tendence of the curves in general.On the basis of standard codes,corresponding revisal codes are also adopted to express the deviation from standard codes.In fact,both codes describe the shapes of curves exactly.A similarity function is defined to compute the similarity between a curve and another one, which in most cases are not of the same length.The method described above is proved effective in the recognition of sediment microfacies by well-logging curves from the Luliang Area of Xinjiang Kelamayi Oil Field.

关 键 词：时序曲线 曲线形态 曲线表示 近似度 模式识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]