支持向量机模型在火山岩储层预测中的应用——以徐家围子断陷徐东斜坡带为例

火山岩储层的发育程度是控制徐家围子断陷火山岩气藏的重要因素,但火山岩储层以岩性复杂、横向变化快、井间可对比性差为特点,火岩储层的准确识别、厚度的精确描述是火山岩气藏勘探开发的难题.针对这一难题,作者提出在专家优化地震属性组合的基础上确定支持向量机模型,进而预测火山岩储层厚度.该技术在实际应用中取得了良好效果,预测的火山...     

基于粒子群优化最小二乘向量机的地震预测模型

为解决地震预测中最小二乘向量机(LSSVM)模型的参数难以确定的问题,利用粒子群算法(PSO)的收敛速度快和全局优化能力,优化LSSVM模型的惩罚因子和核函数参数,建立了PSO-LSSVM地震预测模型.通过对地震实例的预测仿真及其相关分析表明该方法的有效性.该方法优于传统的神经网络和支持向量机的地震预测方法,可以有效提高预测效能.     

半监督最小二乘支持向量机的研究及其在海上油田储层预测中的应用（英文）

勘探开发初期海上油田钻井少、井间距离大,在应用地震多属性分析技术预测储层参数的过程中,直接采用监督最小二乘支持向量机算法预测精度较低。本文将最小二乘支持向量机与半监督学习理论结合,提出基于最小二乘支持向量机协同训练的半监督回归模型,并在模型训练过程中引入矩阵迭代求逆的方法,提高模型训练速度。利用UCI数据集实验研究,对比了半监督与监督最小二乘支持向量机模型,结果表明,半监督学习机制能够有效地提高最小二乘支持向量机的泛化性能,且随着训练样本的减小,效果更加明显;同时对比了半监督最小二乘支持向量机与半监督k-临近算法,结果显示,在小样本建模中,半监督最小二乘支持向量机有着更高的预测精度。最终将半监督最小二乘支持向量机运用于锦州工区,预测该区的砂体及储层孔隙度的分布,获得了较好的地质效果。     

地震前兆综合预测支持向量机模型研究

该文介绍了支持向量机算法的原理与回归方法。 采用支持向量机中的非线性回归算法与理论公式产生的多维样本, 对其进行了数值仿真实验。 利用该方法和地震前兆异常建立了最佳地震综合预测模型, 对获得的最佳模型进行了内符检验, 得出最佳模型的预测结果与实际震例的地震震级基本一致。 综合分析认为, 支持向量机无论在学习或者预测精度方面不但具有很大的优越性和具有较强的外推泛化能力, 而且基于支持向量机回归算法建立的地震前兆综合预测模型是可行的, 其获得的知识可较为准确地实现对主震震级的综合预测。     

基于孔隙结构储层分类的中低孔特低渗储层渗透率确定——以B区块S油层为例

针对B区块S油层含泥含钙中低孔特低渗储层渗透率计算精度低的难题,分析岩性、物性、孔隙结构对储层渗透率的影响,明确了孔隙度、泥质含量、钙质含量、孔隙结构是影响B区块S油层特低渗储层渗透率的主要因素,其中,孔隙结构是影响特低渗储层渗透率的关键因素.综合运用压汞曲线、孔喉半径分布特征以及流动单元指数反映特低渗储层孔隙结构变化,将特低渗储层按不同孔隙结构划分成3种类型,建立了特低渗储层类型的判别标准.利用中子测井、密度测井、声波测井、微球形聚焦测井、深浅侧向电阻率测井差值的绝对值等5个储层类型识别的敏感测井响应及参数,使用决策树法、最邻近结点法、BP神经网络法和支持向量机法建立了4种基于机器学习的储层判别方法,储层类型判别准确率依次提高,其中,基于支持向量机的储层类型判别方法判别准确率最高92.2%,且对3种类储层判别效果均很好.针对3类储层分别建立了渗透率计算公式．实际井解释结果表明,基于机器学习储层分类的渗透率模型计算B区块S油层特低渗储层渗透率精度明显高于储层分类前渗透率计算精度,其中,基于支持向量机储层分类计算的渗透率精度最高．     

基于最小二乘支持向量机的城市桥梁震害预测模型研究

针对地震中城市桥梁震害状态具有较强的非线性、复杂性的特点,采用了具有RBF核函数的最小二乘支持向量机(LS-SVM)算法。在大量收集我国地震中城市桥梁震害资料的基础上,将此算法引入桥梁的震害预测中,选取了地震烈度、上部结构、地基失效程度、支座类型、墩台高度、桥梁跨数和场地类别等因素作为模型的特征输入向量,建立了最小二乘支持向量机的桥梁震害预测模型。通过反复地样本训练及模型参数设置,仿真结果表明,该方法具有一定的准确度和可行性。基于最小二乘支持向量机的桥梁震害预测方法是一种可以用于地震中桥梁震害预测的良好方法。     

基于支持向量机的非线性AVO反演

本文提出了一种新的AVO非线性反演方法,即利用支持向量机来求解AVO非线性反演问题.文中先对支持向量机的原理进行了阐述,然后建立了适合AVO反演的支持向量机模型.最后利用该方法对模型数据和实际资料进行了反演计算,反演结果表明,该方法在没有牺牲反演效果的情况下较好的解决了传统反演方法所具有的局限性,可以直接从合成记录中提取地层的弹性参数,反演速度快、稳定性好.     

基于粗糙集——支持向量机的震害预测模型及应用

结合粗糙集理论的属性约简与支持向量机的分类功能,建立了基于粗糙集与支持向量机的建筑物震害预测模型.该模型首先运用粗糙集理论,建立决策表,进行属性离散、属性重要性排序、属性约简和分类规则的提取,然后用所提取的关键成分训练支持向量机.该模型不但能有效降低建筑物震害影响因子数据维数及支持向量机的复杂程度,提高训练速度和分类精度,而且还能对各因子的影响程度进行排序.最后,通过实例验证了该模型的性能.     

测井岩性识别新方法研究

为了更好地解决测井岩性识别问题,引入了一种基于粒子群优化的支持向量机算法.通过实际测井资料和岩性剖面资料进行学习训练支持向量机,并利用粒子群优化算法对支持向量机参数进行优化,建立了测井岩性识别的支持向量机模型,应用该方法对准噶尔盆地某井的测井岩性进行识别,并将该方法的识别结果与BP神经网络方法的识别结果进行了比较,结果表明该方法优于BP神经网络方法,具有识别正确率高、收敛速度快、推广能力强等优点.     

基于支持向量机回归的宁夏地震前兆综合预测模型研究

将支持向量机方法应用于宁夏及其邻近区域的地震综合预测研究中,通过建立基于多种地震前兆异常的地震综合预测模型,初步探讨了支持向量机方法在宁夏地震综合预测中的应用情况。研究结果表明利用支持向量机形成的地震综合预测模型对宁夏及周边地区可能发生的地震震级具有一定的预测能力。     

Estimation of reservoir flood control operation risks with considering inflow forecasting errors

A method for quantifying inflow forecasting errors and their impact on reservoir flood control operations is proposed. This approach requires the identification of the probability distributions and uncertainty transfer scheme for the inflow forecasting errors. Accordingly, the probability distributions of the errors are inferred through deducing the relationship between its standard deviation and the forecasting accuracy quantified by the Nash–Sutcliffe efficiency coefficient. The traditional deterministic flood routing process is treated as a diffusion stochastic process. The diffusion coefficient is related to the forecasting accuracy, through which the forecasting errors are indirectly related to the sources of reservoir operation risks. The associated risks are derived by solving the stochastic differential equation of reservoir flood routing via the forward Euler method. The Geheyan reservoir in China is selected as a case study. The hydrological forecasting model for this basin is established and verified. The flood control operation risks in the forecast-based pre-release operation mode for different forecasting accuracies are estimated by the proposed approach. Application results show that the proposed method can provide a useful tool for reservoir operation risk estimation and management.     

基于流体替换技术的地震AVO属性气藏识别(英文)

传统上,油藏地球物理工程师是基于测井数据进行流体替换,计算油藏饱和不同流体时的弹性参数,并通过地震正演模拟分析油藏饱和不同流体时的地震响应,从而进行油气藏识别研究。该研究方案为油藏研究提供了重要的弹性参数和地震响应信息,但这些信息仅限于井眼位置。对于实际油藏条件,地下储层参数都是随位置变化而变化的,如孔隙度、泥质含量和油藏厚度等,因此基于传统流体替换方案得到的流体变化地震响应信息对于油气藏识别具有很大的局限性。研究通过设定联系油藏弹性参数与孔隙度、矿物组分等参数的岩石物理模型,并基于三层地质模型,进行地震正演模拟与AVO属性计算。得到油藏孔隙度、泥质含量和储层厚度变化时地震AVO属性,并建立了饱和水储层和含气储层对应AVO属性(包括梯度与截距)之间的定量关系。建立的AVO属性之间的线性关系可以实现基于地震AVO属性直接进行流体替换。最后,应用建立的流体替换前后AVO属性之间线性方程,对模拟地震数据直接进行流体替换,并通过流体替换前后AVO属性交汇图分析实现了气藏识别。     

Adaptive neuro-fuzzy inference system for prediction of water level in reservoir

Accurate prediction of the water level in a reservoir is crucial to optimizing the management of water resources. A neuro-fuzzy hybrid approach was used to construct a water level forecasting system during flood periods. In particular, we used the adaptive network-based fuzzy inference system (ANFIS) to build a prediction model for reservoir management. To illustrate the applicability and capability of the ANFIS, the Shihmen reservoir, Taiwan, was used as a case study. A large number (132) of typhoon and heavy rainfall events with 8640 hourly data sets collected in past 31 years were used. To investigate whether this neuro-fuzzy model can be cleverer (accurate) if human knowledge, i.e. current reservoir operation outflow, is provided, we developed two ANFIS models: one with human decision as input, another without. The results demonstrate that the ANFIS can be applied successfully and provide high accuracy and reliability for reservoir water level forecasting in the next three hours. Furthermore, the model with human decision as input variable has consistently superior performance with regard to all used indexes than the model without this input.     

叠前反演和地震吸收技术在复杂天然气藏地震预测中的应用

针对某复杂断块天然气目标储层,在岩石物理分析的指导下,综合利用地质、地震、测井等资料,提出了一套面向复杂天然气藏的叠前地震预测技术.首先基于地震岩石物理分析得到的初始横波信息,采用叠前贝叶斯非线性三参数反演得到了井旁控制点处精确纵横波速度和密度信息,然后通过叠前/叠后联合反演技术实现了面向目标的弹性阻抗体反演及含气储层敏感参数直接提取,最后结合小波变换时频谱分析的方法从叠前地震资料中估算地层吸收参数值,提高天然气藏识别精度.实际应用表明,综合各种叠前地震预测技术,可以大大提高对复杂天然气藏的识别精度,降低勘探风险.     

Daily reservoir inflow forecasting using artificial neural networks with stopped training approach

In this paper, an early stopped training approach (STA) is introduced to train multi-layer feed-forward neural networks (FNN) for real-time reservoir inflow forecasting. The proposed method takes advantage of both Levenberg–Marquardt Backpropagation (LMBP) and cross-validation technique to avoid underfitting or overfitting on FNN training and enhances generalization performance. The methodology is assessed using multivariate hydrological time series from Chute-du-Diable hydrosystem in northern Quebec (Canada). The performance of the model is compared to benchmarks from a statistical model and an operational conceptual model. Since the ultimate goal concerns the real-time forecast accuracy, overall the results show that the proposed method is effective for improving prediction accuracy. Moreover it offers an alternative when dynamic adaptive forecasting is desired.     

A reservoir flood forecasting and control system for China / Un système chinois de prévision et de contrôle de crue en barrage

Abstract

Abstract Reservoirs play a vital role in flood prevention and disaster relief in China. The objectives of the project described in this study were to establish a reservoir flood forecasting and control system and to design and develop corresponding application software. This paper introduces the current reservoir flood control and operation practice with this system in China. Using modern integration technologies, an application software for this Reservoir Flood Forecasting and Control System (RFFCS) has been developed and updated since 1995. The structure of the system and its main functions, telemetric data acquisition and processing, the hydrological database, flood forecasting, and reservoir operation components are described in detail. The working environment, key technologies and standardization design are emphasized. Having been successfully applied to 212 reservoirs in China, the software has proved to be reliable and user-friendly. In its latest version, the software supports reservoir flood forecasting and flood dispatch decisions. The future research direction and the extension of the software function are also discussed.     

基于页岩岩石物理等效模型的地应力预测方法研究

地应力的精确预测是对页岩地层进行水平井钻井轨迹设计和压裂的基础.本文在分析页岩构造特征的基础上,提出了适用于页岩地层的岩石物理等效模型的建立流程,并以此为基础实现了最小水平地应力的有效预测.首先,通过分析页岩地层的矿物、孔隙、流体及各向异性特征,将其等效为具有垂直对称轴的横向各向同性介质,进行了页岩岩石物理等效模型的构建;然后建立了页岩地层纵横波速度经验公式,并将该经验公式与岩石物理等效模型均应用于实际页岩工区的横波速度预测中,二者对比表明,本文中建立的页岩气岩石物理等效模型具有更高的横波预测精度,验证了该模型的适用性;最后,利用该模型计算各弹性刚度张量,进而实现了页岩地层最小水平地应力的预测,与各向同性模型估测结果对比表明,该模型预测的最小水平地应力与地层瞬间闭合压力一致性更高,且储层位置更为明显,具有较高的实用性.     

Monthly total sediment forecasting using adaptive neuro fuzzy inference system

Accurate forecasting of sediment is an important issue for reservoir design and water pollution control in rivers and reservoirs. In this study, an adaptive neuro-fuzzy inference system (ANFIS) approach is used to construct monthly sediment forecasting system. To illustrate the applicability of ANFIS method the Great Menderes basin is chosen as the study area. The models with various input structures are constructed for the purpose of identification of the best structure. The performance of the ANFIS models in training and testing sets are compared with the observed data. To get more accurate evaluation of the results ANFIS models, the best fit model structures are also tested by artificial neural networks (ANN) and multiple linear regression (MLR) methods. The results of three methods are compared, and it is observed that the ANFIS is preferable and can be applied successfully because it provides high accuracy and reliability for forecasting of monthly total sediment.     

联合多点地质统计学与序贯高斯模拟的随机反演方法

岩相和储层物性参数是油藏表征的重要参数,地震反演是储层表征和油气藏勘探开发的重要手段.随机地震反演通常基于地质统计学理论,能够对不同类型的信息源进行综合,建立具有较高分辨率的储层模型,因而得到广泛关注.其中,概率扰动方法是一种高效的迭代随机反演策略,它能综合考虑多种约束信息,且只需要较少的迭代次数即可获得反演结果.在概率扰动的优化反演策略中,本文有效的联合多点地质统计学与序贯高斯模拟,并结合统计岩石物理理论实现随机反演.首先,通过多点地质统计学随机模拟,获得一系列等可能的岩相模型,扰动更新初始岩相模型后利用相控序贯高斯模拟建立多个储层物性参数模型;然后通过统计岩石物理理论,计算相应的弹性参数;最后,正演得到合成地震记录并与实际地震数据对比,通过概率扰动方法进行迭代,直到获得满足给定误差要求的反演结果.利用多点地质统计学,能够更好地表征储层空间特征.相控序贯高斯模拟的应用,能够有效反映不同岩相中储层物性参数的分布.提出的方法可在较少的迭代次数内同时获得具有较高分辨率的岩相和物性参数反演结果,模型测试和实际数据应用验证了方法的可行性和有效性.     

Development of a real-time forecasting model for turbidity current arrival time to improve reservoir desilting operation

ABSTRACT

Among various strategies for sediment reduction, venting turbidity currents through dam outlets can be an efficient way to reduce suspended sediment deposition. The accuracy of turbidity current arrival time forecasts is crucial for the operation of reservoir desiltation. A turbidity current arrival time (TCAT) model is proposed. A multi-objective genetic algorithm (MOGA), a support vector machine (SVM) and a two-stage forecasting technique are integrated to obtain more effective long lead-time forecasts of inflow discharge and inflow sediment concentration. The multi-objective genetic algorithm (MOGA) is applied for determining the optimal inputs of the forecasting model, support vector machine (SVM). The two-stage forecasting technique is implemented by adding the forecasted values to candidate inputs for improving the long lead-time forecasting. Then, the turbidity current arrival time from the inflow boundary to the reservoir outlet is calculated. To demonstrate the effectiveness of the TCAT model, it is applied to Shihmen Reservoir in northern Taiwan. The results confirm that the TCAT model forecasts are in good agreement with the observed data. The proposed TCAT model can provide useful information for reservoir sedimentation management during desilting operations.