神经网络技术在油田地质学领域中的应用——以测井岩性识别为例  

Application of Neural Network Technique to Oilfield Geology——Taking the Identification of Lithology as an Example

作　　者：崔勇[1] 赵澄林[1] 

机构地区：[1]石油大学地球科学系,北京昌平102200

出　　处：《西安石油学院学报（自然科学版）》2002年第4期16-18,23,共4页Journal of Xi'an Petroleum Institute（Natural Science Edition)

摘　　要：论述了神经网络技术的原理、模型及其算法 ,并进一步指出了应用神经网络技术中的局限性和其相应的解决途径 .其中包括有数据的准备、模式的扩展、隐层数目的选择和计算过程中涉及的权值、步长、动量因子、压缩因子的处理 .The principle, model and algorithm of neural network technique are discussed. The problems remaining to be solved in the application of the technique are pointed out, and they include preparation of data, expand of mode, determination of the number of hidden layer elements, and treatment of weight coefficients, step length, momentum factor and expressible factor in the process of computation. The application of neural network to lithologic identification being taken as an example, and the approaches of solving the problems are proposed.

关 键 词：模式识别 神经网络技术 油田地质学 应用 测井 岩性识别 

分 类 号：P618.130.2[天文地球—矿床学] TE319[天文地球—地质学]