基于量子蚁群优化的油田水淹层识别方法

为提高油田水淹层识别精度及识别效率,论文提出一种基于量子蚁群优化算法的识别方法。首先提出一种基于Bloch球面搜索的量子蚁群算法,然后根据样本数据建立非线性回归模型,最后采用量子蚁群算法优化模型参数。方法简单直观,物理概念清楚。以大庆油田实际水淹层数据进行仿真,结果表明该方法的正确识别率比BP神经网络有25%的提高。     

基于模糊神经网络的水淹层自动识别

针对油田水淹层识别存在的模糊性和多解性,提出了一种基于模糊神经网络的水淹层自动识别方法。该方法将神经网络技术所具有的高度自适应性、容错性及固有的并行处理能力与模糊逻辑所具有的模拟人类思维中的模糊综合判别特点有机地结合,实现了多因素模糊综合判断推理来完成水淹层自动识别。采用该方法,对大庆油田135个地层样本进行处理,符合率达87．6％。结果表明该方法对解决水淹层自动识别问题具有良好的适应性,可提高水淹层自动识别的精度。     

一类正规模糊神经网络及其在复杂水淹层识别中的应用

考虑了一种五层结构的正规化模糊神经网络模型,针对网络结构的优化问题给出了该网络模型的规则层节点的选取方法和相应的反传播学习规则.对于具有较少数输入节点的情况,该网络有较快的训练速度.油藏测井解释中水淹层的识别是石油开发中特别是开发中后期比较突出的一个问题,复杂的地质条件在测井曲线的表现中具有许多模糊性,在各种模糊条件的组合下油藏水淹表现为强水淹、中水淹、弱水淹和无水淹等情形.将正规模糊神经网络用于油藏测井解释中水淹层的识别以提取测井曲线与水淹级别之间的映射关系,从而实现模糊性油藏测井解释中水淹层的识别.实验表明此方法对解决水淹层识别问题具有良好的适应性和实用性.     

支持向量机及其在复杂水淹层识别中的应用

研究了基于结构风险最小化原理的支持向量机方法对模式类的识别能力，构造了可用于多个模式类识别的级连式SVM模型。该模型易于实现，且能够找到模式间的最优分类超平面，泛化能力较高。支持向量机用于模式识别不存在局部极小值问题，且不需网络迭代训练，求解速度明显高于神经网络。该模型采用两种核函数，将SVM用于油藏测井解释中水淹层的识别以提取测井曲线与水淹级别之间的映射关系，从而实现模糊性油藏测井解释中水淹层的识别。实验结果表明，此方法对解决水淹层识别问题具有良好的适应性和实用性。     

基于云变换的混合计算模型在水淹层识别中的应用

目前为止,现有的自动判别方法难以反映定量指标和定性指标相结合的混合信息对水淹层识别的影响.因此,为提高水淹层判别的准确度,本文提出基于云变换的定量与定性混合计算神经网络模型来实现水淹层判别.一方面,利用云模型将提取测井相数据中的定性信息,保证了原始数据的完整性与客观性;另一方面,将输入信息中的定性概念通过正向标准云变换转换为量化的数值信息,保证了数据的科学性;最终将混合信息输入混合计算神经网络模型中进行判别,从而得出结论.实验证明采用基于云变换的混合计算神经网络模型对水淹层进行识别,具有精度高、速度快的特点,是水淹层识别的一种比较实用的方法.     

多资料水淹层识别的模糊神经网络模型研究

该文研究了利用多资料识别水淹层水淹等级的模糊神经元网络自适应模型,模型由若干个规则网络和适用度网络组成,汇合了神经网络与模糊逻辑的优点,具有非线性系统的逼近能力。通过相关性分析和反复测试,最终选择13个参数作为输入参数,水淹层的含水饱和度作为输出参数,实际资料的检验证明该算法明显改进了识别效果。     

基于量子差分进化算法的油田水淹层识别方法

为提高水淹层识别精度及识别效率,本文提出一种基于量子差分进化算法的识别方法。首先根据样本数据建立非线性回归模型,然后采用差分进化算法优化模型参数。方法简单直观,物理概念清楚。以大庆油田实际水淹层数据进行仿真,结果表明该方法的正确识别率比BP神经网络有15%的提高。     

一种加权模糊推理网络模型及其应用

提出了一种加权模糊推理网络的结构模型和学习算法,该网络的基本信息处理单元为模糊推理神经元,融合了模糊逻辑能够较完整地表达领域规则和先验知识,以及神经网络自适应环境的优点。根据模糊推理规则的量化表示形式和微分方程数值解的动力学思想推导出了该网络模型的学习算法。该算法具有稳定、收敛速度快,且能较好地避免网络学习陷入局部极值点。以油田生产复杂水淹层识别问题为例,验证了模型和算法的有效性。     

加权模糊推理网络及在水淹层识别中的应用

提出了一种加权模糊推理网络的结构模型和学习算法，该网络的基本信息处理单元为模糊推理神经元，融合了模糊逻辑能够较完整的表达领域规则和先验知识以及神经网络自适应环境的优点。根据模糊推理规则的量化表示形式和微分方程数值解的动力学思想推导出网络一种新的学习算法。该算法具有稳定，收敛速度快，且能较好避免网络学习陷入局部极值点。以油田生产复杂水淹层识别问题为例，验证了模型和算法的有效性。     

基于GATE的油田信息抽取技术研究

针对目前国内油田信息抽取系统中文信息抽取不准确的现状,提出了更为准确的基于油田的中文信息抽取的解决方案。在GA T E框架下,开发中文信息抽取插件,解决了基于油田的中文分词、中文语料词表和中文命名实体识别,并在企业实际中进行了应用,取得了较好的应用效果,并为后续的油田信息抽取技术研究提供了研究基础。     

Identification of Discrete Linear Objects with a Large Signal-to-Noise Ratio

The convergence and rate of convergence of an estimation algorithm with dead zone for passive identification and identification via test signals in the control loop are investigated.     

电弧炉电极调节系统的参数辨识算法

本文对电弧炉电极调节系统的动态模型提出了两种考虑死区非线性问题的参数辨识算法.仿真实验与现场辨识都证实了所提算法的有效性。     

On the stability of a self-tuning controller in the presence ofbounded disturbances

A proof of bounded-input bounded-output stability of a discrete-time self-tuning control system in the presence of bounded disturbances is given. A recursive least-squares with a dead zone is utilized in the parameter estimation scheme, so that self-tuning takes place only when the identification error exceeds a certain threshold. The controller minimizes a quadratic cost function so that the control signal fluctuations are penalized. The controller can deal with nonminimum-phase systems, which is significant because the nonminimum-phase cases often occur in discrete-time systems. The upper bound of tracking error is also given     

一种非线性系统的参数辨识

本文对带有死区和正反不对称非线性输入的线性系统提出了两种开环参数辨识算法,并 通过仿真验证了算法的有效性.     

Hammerstein Systems Identification in Presence of Hard Nonlinearities of Preload and Dead-Zone Type

Hammerstein system identification is considered in presence of preload and dead zone nonlinearities. The discontinuous feature of these nonlinearities makes it difficult to get a single system parameterization involving linearly all unknown parameters (those of the linear subsystem and those of the nonlinearity). Therefore, system identification has generally been dealt with using multiple stage schemes including different parametrizations and several data acquisition experiences. However, the consistency issue has only been solved under restrictive assumptions regarding the identified system. In this paper, a new identification scheme is designed and shown to be consistent under mild assumptions.     

Exploring the Effect of Obscurants on Safe Landing Zone Identification

Manned rotorcraft are often employed in harsh environments and difficult terrain that are inaccessible to other craft. Conversely, robotic rotorcraft are operated in controlled settings, often at safe, high altitudes. Missions such as cargo delivery, medevac and fire fighting are unachievable because of unpredictable adverse environmental conditions. To enable UAVs to perform these missions, the effects of obscurants on UAV sensor suites and algorithms must be clearly understood. This paper explores the use of a laser range finder to accomplish landing zone identification in unknown, unstructured environments. The ability to detect a landing zone in environments obscured by smoke is investigated. This is accomplished using a design methodology of testing and evaluating in a controlled environment followed by verification and validation in the field. This methodology establishes a concrete understanding of the sensor performance, thereby removing ambiguities in field tests.     

Identification and Reconstruction of a Small Leak Zone in a Pipe by a Spectral Element Method

This paper deals with the identification of a zone permitting fluid to leak out of a drain. Using the analogy with crack identification by boundary measurements, we give uniqueness and stability results and we propose an algorithm for the numerical solution of the problem. Since the forward problem consists of a mixed boundary value problem with a strong anisotropy, we discretize it by a mortar spectral element method.     

Robust adaptive regulation without persistent excitation

A globally convergent adaptive regulator for minimum or nonminimum phase systems subject to bounded disturbances is presented. The control strategy is designed for a particular input-output representation obtained from the state-space representation of the system. The leading coefficient of the novel representation is the product of the observability and controllability matrices of the system. The controller scheme uses a least-squares identification algorithm with a dead zone. The dead zone is chosen to obtain convergence properties on the estimates and on the covariance matrix as well. This allows the definition of modified estimates which secure well-conditioned matrices in the adaptive control law. Explicit bounds on the plant output are given     

Adaptive control for systems with bounded disturbances

The authors present an identification algorithm that can be used to design globally stable indirect adaptive controllers for minimum- and nonminimum-phase systems subject to bounded disturbances. The parameter estimation scheme is a least-squares algorithm with dead zone. The dead zone is such that the estimates converge and make it possible to define projected estimates having the same convergence properties as the original estimates. In the minimum-phase case, the projection facility can be used to ensure that the leading coefficient projected estimate is greater than or equal to the true leading coefficient in absolute value. The projection procedure can also be used to avoid pole-zero cancellations in an adaptive pole-placement algorithm