自组织竞争人工神经网络在砂岩型铀矿测井数据解释中的应用

Application of self～organizing competition artificial neural network to logging data explanation of sandstone～hosted uranium deposits

详细介绍了自组织竞争人工神经网络模型结构、原理和钻孔岩性自动识别过程,给出了神经网络模型在钻孔岩性自动识别过程中的有效性实例。自组织竞争人工神经网络具有自组织能力、自适应能力和较高的容错能力;与BP算法相比较,计算量小,收敛速度快,且不需要已知的先验信息而自动确定分类类别。钻孔岩性识别结果与岩心地质编录的对比试验表明,在砂岩型铀矿测井数据的解释中,应用自组织竞争人工方法可较好地完成钻孔岩性自动分类。

The article describes the model construction of self-organizing competition artificial neural network, its principle and automatic recognition process of borehole lithology in detail, and then proves the efficiency of the neural network model for automatically recognizing the borehole lithology with some cases. The self-organizing competition artificial neural network has the ability of self- organization, self-adjustment and high permitting errors. Compared with the BP algorithm, it takes less calculation quantity and more rapidly converges. Furthermore, it can automatically confirm the category without the known sample information. Trial results based on contrasting the identification results of the borehole lithology with geological documentations, indicate that self-organizing artificial neural network can be well applied to automatically performing the category of borehole lithology, during the logging data explanation of sandstone-hosted uranium deposits.