东篱科研大数据发现系统（DRDS）

位置：成果数据库 > 期刊 > 期刊详情页

量子神经网络及其在复杂水淹层识别中的应用

期刊名称：测井技术，2007，（05）
时间：0
分类：TP183[自动化与计算机技术—控制科学与工程;自动化与计算机技术—控制理论与控制工程]
作者机构：[1]清华大学,北京100084, [2]大庆石油学院,黑龙江大庆163318, [3]大庆油田公司第六采油厂,黑龙江大庆163700
相关基金：国家自然科学基金重点项目（50634020）
相关项目：低渗透油层提高驱油效率的机理研究

关键词：测井曲线, 量子神经元模型, BP网络模型, 学习算法, 水淹层识别, 支持向量机, logging curve, quantum neural network, Quantum Back-propagation （QBP） Network, learning algorithm, water flooded layer recognition, quantum computing

中文摘要：

提出一种量子BP网络模型及学习算法。基于量子力学中1位相移门和2位受控非门的通用性,构造出一种量子神经元模型和3层量子BP网络模型,量子神经元模型由输入、相移、聚合、翻转、输出等5部分组成。由量子神经元构造出3层量子BP网络模型,基于梯度下降法构造了该模型学习算法。将该模型及算法用于模拟油藏测井解释中测井曲线与水淹级别之间的映射关系,从而实现油藏测井解释中水淹层自动识别。实验结果表明,该方法对解决水淹层识别问题具有良好的适应性和实用性。

英文摘要：

A quantum BP neural networks model with learning algorithm is proposed. Firstly, based on the universality of single qubit rotation gate and two-qubits controlled NOT gate, a quantum neuron model is constructed, which is composed of input, phase rotation, aggregation, reversal rotation, and output. In this model, both the input and the output are described by qubits. The phase rotation and inversion are performed by the universal quantum gates. Secondly, the quantum BP neural networks model based on quantum neurons is constructed. On the basic of the gradient descent algorithm, a learning algorithm of the model is proposed. The model is ap- plied to simulate the relation between well logging and water-flooded level which can achieve so that water-flooded layer recognition can be achieved with in oil well logging. Testing results indicate that the method is effective.