摘要
将近年来在统计理论方面的最新研究成果引入到提高采收率潜力分析中,对自组织、改进型BP神经网络、支持向量机3种方法在提高采收率潜力预测中的应用进行了探讨。3种方法的对比研究表明,在所用样本较少的条件下,支持向量机方法能够兼顾模型的通用性和推广性,即由有效的训练集样本得到的小的误差能够保证对独立的测试集的误差仍保持较小,该方法具有较好的应用前景。
The recent results of research in the field of statistical theory were applied to potential analysis of enhanced oil recovery (EOR). The applications of group method of data handling (GMDH), improved error back propagation (BP) artificial neutral network and support vector machine (SVM) to enhanced oil recovery were discussed. The comparison of the three methods indicates that SVM has both the universality and the extendibility of a model when the samples are very limited. A small error from an effective training set can guarantee a small error for the corresponding independent testing set. SVM shows a good prospect of its application.
出处
《石油大学学报（自然科学版）》
CSCD
北大核心
2004年第4期67-70,共4页
Journal of the University of Petroleum,China(Edition of Natural Science)
基金
国家自然科学基金(10302021)
石油大学博士科研基金(Y020229)
